<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.science.org/doi/10.1126/science.adv7924"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.05003"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.06786"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.04087"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/10.1101/393835v1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.03145"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.07800"/>
	<rdf:li rdf:resource="https://www.sciencedirect.com/science/article/pii/S2452310019300022"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.08477"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.02045"/>
	<rdf:li rdf:resource="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/"/>
	<rdf:li rdf:resource="https://gcbias.org/2018/03/14/polygenic-scores-and-tea-drinking/"/>
	<rdf:li rdf:resource="https://kappalanguage.org/"/>
	<rdf:li rdf:resource="http://www.mdpi.com/2073-4425/9/2/61/htm"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/early/2017/11/25/225003?rss=1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1404.6520"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.03144"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/early/2017/09/25/193599?rss=1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.05701"/>
	<rdf:li rdf:resource="https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.08085"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.02293"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.01780"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1306.5667"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.06530"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1606.09370"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2017/04/13/125542?rss=1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.04048"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.04823"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/24/055020?rss=1%2522"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1511.02393"/>
	<rdf:li rdf:resource="http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.00318"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.06971"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.02948"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1605.01639"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.07151"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/06/21/060111?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/26/055624"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.03043"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.01941"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/28/050732?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/26/050187?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/23/049999?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/28/050757?rss=1%2522"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1604.08354"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/25/049627?rss=1%2522"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/04/25/050146?rss=1%2522"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1510.02356"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1501.03971"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1512.00268"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1508.05990"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1512.05055"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1512.03094"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1512.02786"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1509.03434"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1510.08513"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1511.07662"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1509.00896"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1501.04648"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2015/10/22/029710"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.05815"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1407.2812"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1509.02975"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.4967"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1303.3692"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2015/08/21/025262"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1508.04174"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.1074"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.science.org/doi/10.1126/science.adv7924">
    <title>DefensePredictor: A machine learning model to discover prokaryotic immune systems | Science</title>
    <dc:date>2026-04-26T12:32:02+00:00</dc:date>
    <link>https://www.science.org/doi/10.1126/science.adv7924</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Bacteria have diverse immune systems that protect them from viral infection, yet the full extent of this diversity remains unknown. Two groups of researchers have now independently developed machine learning and deep learning models that leverage protein sequences and genomic context to predict antiphage defense systems at scale. DeWeirdt et al. developed a model called DefensePredictor and applied it to Escherichia coli, experimentally validating dozens of previously uncharacterized defense systems. Mordret et al. developed several different models and applied them to over 120 million proteins from bacterial genomes, identifying hundreds of thousands of candidate antiphage families, many lacking any prior annotation. Together, these studies reveal that bacterial immunity is far more extensive than previously thought and highlight how such discoveries can inspire powerful biotechnologies. —Di Jiang
]]></description>
<dc:subject>structural-biology machine-learning bioinformatics indistinguishable-from-magic learning-from-data to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d94701a9a214/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indistinguishable-from-magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.05003">
    <title>[1804.05003] Higher order molecular organisation as a source of biological function</title>
    <dc:date>2022-02-05T13:33:25+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.05003</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Molecular interactions have widely been modelled as networks. The local wiring patterns around molecules in molecular networks are linked with their biological functions. However, networks model only pairwise interactions between molecules and cannot explicitly and directly capture the higher order molecular organisation, such as protein complexes and pathways. Hence, we ask if hypergraphs (hypernetworks), that directly capture entire complexes and pathways along with protein-protein interactions (PPIs), carry additional functional information beyond what can be uncovered from networks of pairwise molecular interactions. The mathematical formalism of a hypergraph has long been known, but not often used in studying molecular networks due to the lack of sophisticated algorithms for mining the underlying biological information hidden in the wiring patterns of molecular systems modelled as hypernetworks. 
We propose a new, multi-scale, protein interaction hypernetwork model that utilizes hypergraphs to capture different scales of protein organization, including PPIs, protein complexes and pathways. In analogy to graphlets, we introduce hypergraphlets, small, connected, non-isomorphic, induced sub-hypergraphs of a hypergraph, to quantify the local wiring patterns of these multi-scale molecular hypergraphs and to mine them for new biological information. We apply them to model the multi-scale protein networks of baker yeast and human and show that the higher order molecular organisation captured by these hypergraphs is strongly related to the underlying biology. Importantly, we demonstrate that our new models and data mining tools reveal different, but complementary biological information compared to classical PPI networks. We apply our hypergraphlets to successfully predict biological functions of uncharacterised proteins.
]]></description>
<dc:subject>structural-biology systems-biology rather-interesting hypergraphs interaction-graphs bioinformatics structure-function-relations consider:components-in-Push to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:06c5ffeda0b0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interaction-graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structure-function-relations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:components-in-Push"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.06786">
    <title>[2002.06786] DAWGs for parameterized matching: online construction and related indexing structures</title>
    <dc:date>2021-01-21T21:00:34+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.06786</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Two strings x and y over Σ∪Π of equal length are said to parameterized match (p-match) if there is a renaming bijection f:Σ∪Π→Σ∪Π that is identity on Σ and transforms x to y (or vice versa). The p-matching problem is to look for substrings in a text that p-match a given pattern. In this paper, we propose parameterized suffix automata (p-suffix automata) and parameterized directed acyclic word graphs (PDAWGs) which are the p-matching versions of suffix automata and DAWGs. While suffix automata and DAWGs are equivalent for standard strings, we show that p-suffix automata can have Θ(n2) nodes and edges but PDAWGs have only O(n) nodes and edges, where n is the length of an input string. We also give O(n|Π|log(|Π|+|Σ|))-time O(n)-space algorithm that builds the PDAWG in a left-to-right online manner. As a byproduct, it is shown that the parameterized suffix tree for the reversed string can also be built in the same time and space, in a right-to-left online manner. We also discuss parameterized compact DAWGs.
]]></description>
<dc:subject>strings bioinformatics algorithms rather-interesting hard-problems pattern-matching to-write-about to-simulate consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9a95cb8f1ca9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:strings"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hard-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-matching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.04087">
    <title>[1801.04087] Gene regulatory network inference: an introductory survey</title>
    <dc:date>2020-05-23T13:23:17+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.04087</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Gene regulatory networks are powerful abstractions of biological systems. Since the advent of high-throughput measurement technologies in biology in the late 90s, reconstructing the structure of such networks has been a central computational problem in systems biology. While the problem is certainly not solved in its entirety, considerable progress has been made in the last two decades, with mature tools now available. This chapter aims to provide an introduction to the basic concepts underpinning network inference tools, attempting a categorisation which highlights commonalities and relative strengths. While the chapter is meant to be self-contained, the material presented should provide a useful background to the later, more specialised chapters of this book.
]]></description>
<dc:subject>gene-regulatory-networks inverse-problems bioinformatics systems-biology rather-interesting modeling to-write-about to-simulate consider:data-quality consider:representation consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3c46f24714c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:data-quality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/10.1101/393835v1">
    <title>Regularization Improves the Robustness of Learned Sequence-to-Expression Models | bioRxiv</title>
    <dc:date>2020-02-18T22:52:54+00:00</dc:date>
    <link>https://www.biorxiv.org/content/10.1101/393835v1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding of the gene regulatory activity of enhancers is a major problem in regulatory biology. The nascent field of sequence-to-expression modelling seeks to create quantitative models of gene expression based on regulatory DNA (cis) and cellular environmental (trans) contexts. All quantitative models are defined partially by numerical parameters, and it is common to fit these parameters to data provided by existing experimental results. However, the relative paucity of experimental data appropriate for this task, and lacunae in our knowledge of all components of the systems, results in problems often being under-specified, which in turn may lead to a situation where wildly different model parameterizations perform similarly well on training data. It may also lead to models being fit to the idiosyncrasies of the training data, without representing the more general process (overfitting).

In other contexts where parameter-fitting is performed, it is common to apply regularization to reduce overfitting. We systematically evaluated the efficacy of three types of regularization in improving the generalizability of trained sequence-to-expression models. The evaluation was performed in two types of cross-validation experiments: one training on D. melanogaster data and predicting on orthologous enhancers from related species, and the other cross-validating between four D. melanogaster neurogenic ectoderm enhancers, which are thought to be under control of the same transcription factors. We show that training with a combination of noise-injection, L1, and L2 regularization can drastically reduce overfitting and improve the generalizability of learned sequence-to-expression models. These results suggest that it may be possible to mitigate the tendency of sequence-to-expression models to overfit available data, thus improving predictive power and potentially resulting in models that provide better insight into underlying biological processes.

]]></description>
<dc:subject>bioinformatics systems-biology nonlinear-dynamics machine-learning regularization statistics numerical-methods heuristics to-write-about to-simulate consider:symbolic-regression consider:robustness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f08dfb1849d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:regularization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.03145">
    <title>[1608.03145] Physical model of the genotype-to-phenotype map of proteins</title>
    <dc:date>2019-04-24T15:24:51+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.03145</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[How DNA is mapped to functional proteins is a basic question of living matter. We introduce and study a physical model of protein evolution which suggests a mechanical basis for this map. Many proteins rely on large-scale motion to function. We therefore treat protein as learning amorphous matter that evolves towards such a mechanical function: Genes are binary sequences that encode the connectivity of the amino acid network that makes a protein. The gene is evolved until the network forms a shear band across the protein, which allows for long-range, soft modes required for protein function. The evolution reduces the high-dimensional sequence space to a low-dimensional space of mechanical modes, in accord with the observed dimensional reduction between genotype and phenotype of proteins. Spectral analysis of the space of 106 solutions shows a strong correspondence between localization around the shear band of both mechanical modes and the sequence structure. Specifically, our model shows how mutations of the gene and their correlations occur at amino acids whose interactions determine the functional mode.
]]></description>
<dc:subject>complexology rather-interesting theoretical-biology abstract-models combinatorics bioinformatics structural-biology structure-function-cartoons to-write-about to-simulate lattice-polymers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:63c4d1b88c21/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complexology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:abstract-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structure-function-cartoons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lattice-polymers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.07800">
    <title>[1810.07800] Alignments as Compositional Structures</title>
    <dc:date>2019-04-17T10:49:17+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.07800</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Alignments, i.e., position-wise comparisons of two or more strings or ordered lists are of utmost practical importance in computational biology and a host of other fields, including historical linguistics and emerging areas of research in the Digital Humanities. The problem is well-known to be computationally hard as soon as the number of input strings is not bounded. Due to its prac- tical importance, a huge number of heuristics have been devised, which have proved very successful in a wide range of applications. Alignments nevertheless have received hardly any attention as formal, mathematical structures. Here, we focus on the compositional aspects of alignments, which underlie most algo- rithmic approaches to computing alignments. We also show that the concepts naturally generalize to finite partially ordered sets and partial maps between them that in some sense preserve the partial orders.
]]></description>
<dc:subject>discrete-mathematics optimization alignments combinatorics hey-I-know-this-guy bioinformatics rather-interesting formalization to-write-about consider:multiobjective-optimization consider:fitness-landscapes question:transitivity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cdd8a5b8e59e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrete-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:alignments"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:question:transitivity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.sciencedirect.com/science/article/pii/S2452310019300022">
    <title>Learning from protein fitness landscapes: a review of mutability, epistasis, and evolution - ScienceDirect</title>
    <dc:date>2019-03-17T12:28:35+00:00</dc:date>
    <link>https://www.sciencedirect.com/science/article/pii/S2452310019300022</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Proteins carry out many diverse functions in nature and are increasingly used in non-native contexts, such as in medical or industrial applications. A wide array of synthetic biology techniques can be used both to study proteins in their native context and to identify new variants with useful properties for non-native functions. High-resolution protein fitness landscapes, generated via deep scanning mutagenesis, are an emerging technology that can be used to model evolution and identify useful variants. Interestingly, many differences exist between mutability quantified by evolutionary studies and deep scanning mutagenesis. Here, we review several contributing factors to this difference, highlighting epistasis, binding partners, and selection conditions as key contributors. Through this lens, we describe what can be learned, both about evolution and protein function more broadly, from fitness landscape studies.

]]></description>
<dc:subject>cannot-access dammit fitness-landscapes scanning-mutagenesis bioinformatics theoretical-biology looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ec4a0e226b25/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cannot-access"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dammit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:scanning-mutagenesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.08477">
    <title>[1711.08477] Benchmarking Relief-Based Feature Selection Methods for Bioinformatics Data Mining</title>
    <dc:date>2019-02-24T15:29:46+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.08477</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Modern biomedical data mining requires feature selection methods that can (1) be applied to large scale feature spaces (e.g. `omics' data), (2) function in noisy problems, (3) detect complex patterns of association (e.g. gene-gene interactions), (4) be flexibly adapted to various problem domains and data types (e.g. genetic variants, gene expression, and clinical data) and (5) are computationally tractable. To that end, this work examines a set of filter-style feature selection algorithms inspired by the `Relief' algorithm, i.e. Relief-Based algorithms (RBAs). We implement and expand these RBAs in an open source framework called ReBATE (Relief-Based Algorithm Training Environment). We apply a comprehensive genetic simulation study comparing existing RBAs, a proposed RBA called MultiSURF, and other established feature selection methods, over a variety of problems. The results of this study (1) support the assertion that RBAs are particularly flexible, efficient, and powerful feature selection methods that differentiate relevant features having univariate, multivariate, epistatic, or heterogeneous associations, (2) confirm the efficacy of expansions for classification vs. regression, discrete vs. continuous features, missing data, multiple classes, or class imbalance, (3) identify previously unknown limitations of specific RBAs, and (4) suggest that while MultiSURF* performs best for explicitly identifying pure 2-way interactions, MultiSURF yields the most reliable feature selection performance across a wide range of problem types.
]]></description>
<dc:subject>machine-learning bioinformatics hey-I-know-this-guy feature-selection benchmarking epistasis algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2c11820a8280/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:epistasis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.02045">
    <title>[1804.02045] Approximating Functions on Boxes</title>
    <dc:date>2019-02-22T23:08:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.02045</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The vector space of all polynomial functions of degree k on a box of dimension n is of dimension (nk). A consequence of this fact is that a function can be approximated on vertices of the box using other vertices to higher degrees than expected. This approximation is useful for various biological applications such as predicting the effect of a treatment with drug combinations and computing values of fitness landscape.]]></description>
<dc:subject>approximation fitness-landscapes dimension-reduction rather-interesting statistics modeling bioinformatics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:319a7d7a9e80/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fitness-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/">
    <title>Genome graphs and the evolution of genome inference</title>
    <dc:date>2019-02-13T10:43:47+00:00</dc:date>
    <link>https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The human reference genome is part of the foundation of modern human biology and a monumental scientific achievement. However, because it excludes a great deal of common human variation, it introduces a pervasive reference bias into the field of human genomics. To reduce this bias, it makes sense to draw on representative collections of human genomes, brought together into reference cohorts. There are a number of techniques to represent and organize data gleaned from these cohorts, many using ideas implicitly or explicitly borrowed from graph-based models. Here, we survey various projects underway to build and apply these graph-based structures—which we collectively refer to as genome graphs—and discuss the improvements in read mapping, variant calling, and haplotype determination that genome graphs are expected to produce.

]]></description>
<dc:subject>via:arthegall bioinformatics clustering visualization data-analysis rather-interesting consider:nonbiological-genomes review</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8e2e925902f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonbiological-genomes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://gcbias.org/2018/03/14/polygenic-scores-and-tea-drinking/">
    <title>Polygenic scores and tea drinking | gcbias</title>
    <dc:date>2018-12-28T11:42:59+00:00</dc:date>
    <link>https://gcbias.org/2018/03/14/polygenic-scores-and-tea-drinking/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Some of these complications are perhaps best illustrated with a toy example. Say we perform a GWAS of the amount of tea that individuals in the UK drink (e.g. in the UK Biobank). On the basis of this tea GWAS, someone (let’s call him Bob) could claim that we could learn about France-UK differences in tea consumption by just counting up the average number of alleles for tea preference that individuals in the UK and France carry. If the British, overall, are more likely to have alleles that increase tea consumption than French people, then Bob might say that we have demonstrated that the difference between French and UK people’s preference for tea is in part genetic. Bob would assure us that these alleles are polymorphic in both countries, and that both environment and culture plays a role. He would further reassure us that there’ll be an overlapping distribution of tea drinking preferences in both countries, so he’s not saying that all British people drink more tea for genetic reasons. He’ll tell us he’s simply interested in showing that the average difference in tea consumption is partly genetic.

]]></description>
<dc:subject>genetics bioinformatics GWAS good-example nature-and-nurture-sittin-in-a-tree population-biology cultural-norms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:906b1be19f45/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:GWAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:good-example"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nature-and-nurture-sittin-in-a-tree"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:population-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cultural-norms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://kappalanguage.org/">
    <title>Home | Kappa Language</title>
    <dc:date>2018-05-28T12:03:17+00:00</dc:date>
    <link>https://kappalanguage.org/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[By separating a rule from a patch on which it acts we gain a much clearer approach to mechanistic causality. If causal analysis were to proceed at the level of patches, it would obfuscate the causal structure of a system by dragging along context irrelevant to an event. In addition to simulation and static analysis, the Kappa platform also extracts the causal structure of a rule system from its simulation traces.

]]></description>
<dc:subject>bioinformatics representation hey-I-know-this-guy complexology pattern-discovery rather-interesting to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2f4be5227079/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complexology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mdpi.com/2073-4425/9/2/61/htm">
    <title>Genes | Free Full-Text | Another Round of “Clue” to Uncover the Mystery of Complex Traits | HTML</title>
    <dc:date>2018-02-27T12:43:44+00:00</dc:date>
    <link>http://www.mdpi.com/2073-4425/9/2/61/htm</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Abstract: A plethora of genetic association analyses have identified several genetic risk loci. Technological and statistical advancements have now led to the identification of not only common genetic variants, but also low-frequency variants, structural variants, and environmental factors, as well as multi-omics variations that affect the phenotypic variance of complex traits in a population, thus referred to as complex trait architecture. The concept of heritability, or the proportion of phenotypic variance due to genetic inheritance, has been studied for several decades, but its application is mainly in addressing the narrow sense heritability (or additive genetic component) from Genome-Wide Association Studies (GWAS). In this commentary, we reflect on our perspective on the complexity of understanding heritability for human traits in comparison to model organisms, highlighting another round of clues beyond GWAS and an alternative approach, investigating these clues comprehensively to help in elucidating the genetic architecture of complex traits.]]></description>
<dc:subject>GWAS bioinformatics medicine machine-learning epistasis it's-more-complicated-than-you-think</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d478a0f637e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:GWAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medicine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:epistasis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:it's-more-complicated-than-you-think"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/early/2017/11/25/225003?rss=1">
    <title>The standard genetic code facilitates exploration of the space of functional nucleotide sequences | bioRxiv</title>
    <dc:date>2018-02-25T12:50:22+00:00</dc:date>
    <link>https://www.biorxiv.org/content/early/2017/11/25/225003?rss=1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The standard genetic code is well known to be optimized for minimizing the phenotypic effects of single nucleotide substitutions, a property that was likely selected for during the emergence of a universal code. Given the fitness advantage afforded by high standing genetic diversity in a population in a dynamic environment, it is possible that selection to explore a large fraction of the space of functional proteins also occurred. To determine whether selection for such a property played a role during the emergence of the nearly universal genetic code, we investigated the number of functional variants of the Escherichia coli PhoQ protein explored at different time scales under translation using different genetic codes. We found that the standard genetic code is highly optimal for exploring a large fraction of the space of functional PhoQ variants at intermediate time scales as compared to random codes. Environmental changes, in response to which genetic diversity in a population provides a fitness advantage, are likely to have occurred at these intermediate time scales. Our results indicate that the ability of the standard code to explore a large fraction of the space of functional sequence variants arises from a balance between robustness and flexibility and is largely independent of the property of the standard code to minimize the phenotypic effects of mutations. We propose that selection to explore a large fraction of the functional sequence space while minimizing the phenotypic effects of mutations contributed towards the emergence of the standard code as the universal genetic code.

]]></description>
<dc:subject>origin-of-life bioinformatics exploration exploitation robustness evolutionary-biology self-organization rather-interesting to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:09b654789fc6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:origin-of-life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploitation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-organization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1404.6520">
    <title>[1404.6520] How to partition diversity</title>
    <dc:date>2018-02-04T13:44:32+00:00</dc:date>
    <link>https://arxiv.org/abs/1404.6520</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Diversity measurement underpins the study of biological systems, but measures used vary across disciplines. Despite their common use and broad utility, no unified framework has emerged for measuring, comparing and partitioning diversity. The introduction of information theory into diversity measurement has laid the foundations, but the framework is incomplete without the ability to partition diversity, which is central to fundamental questions across the life sciences: How do we prioritise communities for conservation? How do we identify reservoirs and sources of pathogenic organisms? How do we measure ecological disturbance arising from climate change? 
The lack of a common framework means that diversity measures from different fields have conflicting fundamental properties, allowing conclusions reached to depend on the measure chosen. This conflict is unnecessary and unhelpful. A mathematically consistent framework would transform disparate fields by delivering scientific insights in a common language. It would also allow the transfer of theoretical and practical developments between fields. 
We meet this need, providing a versatile unified framework for partitioning biological diversity. It encompasses any kind of similarity between individuals, from functional to genetic, allowing comparisons between qualitatively different kinds of diversity. Where existing partitioning measures aggregate information across the whole population, our approach permits the direct comparison of subcommunities, allowing us to pinpoint distinct, diverse or representative subcommunities and investigate population substructure. The framework is provided as a ready-to-use R package to easily test our approach.
]]></description>
<dc:subject>diversity population-biology bioinformatics philosophy-of-science algorithms statistics rather-interesting to-write-about to-understand consider:genetic-programming define-your-terms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c21c80ffcd46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:diversity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:population-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.03144">
    <title>[1611.03144] Therapeutic target discovery using Boolean network attractors: improvements of kali</title>
    <dc:date>2018-02-02T16:46:54+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.03144</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In a previous article, an algorithm for identifying therapeutic targets in Boolean networks modeling pathological mechanisms was introduced. In the present article, the improvements made on this algorithm, named kali, are described. These improvements are i) the possibility to work on asynchronous Boolean networks, ii) a finer assessment of therapeutic targets and iii) the possibility to use multivalued logic. kali assumes that the attractors of a dynamical system, such as a Boolean network, are associated with the phenotypes of the modeled biological system. Given a logic-based model of pathological mechanisms, kali searches for therapeutic targets able to reduce the reachability of the attractors associated with pathological phenotypes, thus reducing their likeliness. kali is illustrated on an example network and used on a biological case study. The case study is a published logic-based model of bladder tumorigenesis from which kali returns consistent results. However, like any computational tool, kali can predict but can not replace human expertise: it is a supporting tool for coping with the complexity of biological systems in the field of drug discovery.
]]></description>
<dc:subject>reaction-networks boolean-networks Kauffmania bioinformatics systems-biology rather-interesting nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:828e912cdc36/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reaction-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:boolean-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Kauffmania"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/early/2017/09/25/193599?rss=1">
    <title>Reprogramming, oscillations and transdifferentiation in epigenetic landscapes | bioRxiv</title>
    <dc:date>2017-11-12T12:35:05+00:00</dc:date>
    <link>https://www.biorxiv.org/content/early/2017/09/25/193599?rss=1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Waddington's epigenetic landscape provides a phenomenological understanding of the cell differentiation pathways from the pluripotent to mature lineage-committed cell lines. In light of recent successes in the reverse programming process there has been significant interest in quantifying the underlying landscape picture through the mathematics of gene regulatory networks. We investigate the role of time delays arising from multistep chemical reactions and epigenetic rearrangement on the cell differentiation landscape for a realistic two-gene regulatory network, consisting of self-promoting and mutually inhibiting genes. Our work provides the first theoretical basis of the transdifferentiation process in the presence of delays, where one differentiated cell type can transition to another directly without passing through the undifferentiated state. Additionally, the interplay of time-delayed feedback and a time dependent chemical drive leads to long-lived oscillatory states in appropriate parameter regimes. This work emphasizes the important role played by time-delayed feedback loops in gene regulatory circuits and provides a framework for the characterization of epigenetic landscapes.

]]></description>
<dc:subject>epigenetics gene-regulatory-networks bioinformatics theoretical-biology simulation biological-engineering rather-interesting to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0666921dd3d3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:epigenetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biological-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.05701">
    <title>[1709.05701] Transkingdom Networks: A Systems Biology Approach to Identify Causal Members of Host-Microbiota Interactions</title>
    <dc:date>2017-10-09T11:33:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.05701</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Improvements in sequencing technologies and reduced experimental costs have resulted in a vast number of studies generating high-throughput data. Although the number of methods to analyze these "omics" data has also increased, computational complexity and lack of documentation hinder researchers from analyzing their high-throughput data to its true potential. In this chapter we detail our data-driven, transkingdom network (TransNet) analysis protocol to integrate and interrogate multi-omics data. This systems biology approach has allowed us to successfully identify important causal relationships between different taxonomic kingdoms (e.g. mammals and microbes) using diverse types of data.
]]></description>
<dc:subject>rather-interesting bioinformatics community-detection symbiosis machine-learning to-write-about consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f0b72c056f4a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:community-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbiosis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522">
    <title>Tracing co-regulatory network dynamics in noisy, single-cell transcriptome trajectories | bioRxiv</title>
    <dc:date>2017-10-03T11:01:27+00:00</dc:date>
    <link>https://www.biorxiv.org/content/early/2016/08/18/070151?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The availability of gene expression data at the single cell level makes it possible to probe the molecular underpinnings of complex biological processes such as differentiation and oncogenesis. Promising new methods have emerged for reconstructing a progression 'trajectory' from static single-cell transcriptome measurements. However, it remains unclear how to adequately model the appreciable level of noise in these data to elucidate gene regulatory network rewiring. Here, we present a framework called Single Cell Inference of MorphIng Trajectoiries and their Associated Regulation (SCIMITAR) that infers progressions from static single-cell transcriptomes by employing a continuous parametrization of Gaussian mixtures in high-dimensional curves. SCIMITAR yields rich models from the data that highlight genes with expression and coexpression patterns that are associated with the inferred progression. Further, SCIMITAR extracts regulatory states from the implicated trajectory-evolving co-expression networks. We benchmark the method on simulated data to show that it yields accurate cell ordering and gene network inferences. Applied to the interpretation of a single-cell human fetal neuron dataset, SCIMITAR finds progression-associated genes in cornerstone neural differentiation pathways missed by standard differential expression tests. Finally, by leveraging the rewiring of gene-gene co-expression relations across the progression, the method reveals the rise and fall of co-regulatory states and trajectory-dependent gene modules. These analyses implicate new transcription factors in neural differentiation including putative co-factors for the multi-functional NFAT pathway.

]]></description>
<dc:subject>gene-regulatory-networks bioinformatics systems-biology rather-interesting modeling experiment nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2f149bc59c46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1701.08085">
    <title>[1701.08085] The Biological Consequences of the Computational World: Mathematical Reflections on Cancer Biology</title>
    <dc:date>2017-09-26T11:54:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.08085</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The role of continua has been clear since antiquity in the mathematical approaches to physics, while discrete manifolds were brought to the limelight mostly by Quantum and Information Theories, in the XX century. We first recall how theorizing and measuring radically change in physics when using discrete vs. continuous mathematical manifolds. It will follow that the reference to discrete structures and digital information is far from neutral in knowledge construction. In biology, in particular, the introduction of information as a new observable on discrete data types has been promoting a dramatic reorganization of the tools for knowledge. We briefly analyze the origin and the nature, then some consequences of the bias thus induced in life sciences, with particular emphasis on research on cancer. We finally summarize new theoretical frames that propose different directions as for the organizing principles for biological thinking and experimenting, including in cancer research. Cancer is now viewed as an organismal, tissue based issue, according to the perspective proposed in (Sonnenschein, Soto, 1999; Baker, 2015).]]></description>
<dc:subject>representation philosophy-of-science theoretical-biology bioinformatics systems-biology modeling to-write-about define-your-terms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:591b903d92f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.02293">
    <title>[1709.02293] Analyzing huge pathology images with open source software</title>
    <dc:date>2017-09-19T11:46:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.02293</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Backgr: Digital pathology images are increasingly used both for diagnosis and research, because slide scanners are nowadays broadly available and because the quantitative study of these images yields new insights in systems biology. However, such virtual slides build up a technical challenge since the images occupy often several gigabytes and cannot be fully opened in a computer's memory. Moreover, there is no standard format. Therefore, most common open source tools such as ImageJ fail at treating them, and the others require expensive hardware while still being prohibitively slow. 
Res: We have developed several cross-platform open source software tools to overcome these limitations. The NDPITools provide a way to transform microscopy images initially in the loosely supported NDPI format into one or several standard TIFF files, and to create mosaics (division of huge images into small ones, with or without overlap) in various TIFF and JPEG formats. They can be driven through ImageJ plugins. The LargeTIFFTools achieve similar functionality for huge TIFF images which do not fit into RAM. We test the performance of these tools on several digital slides and compare them, when applicable, to standard software. A statistical study of the cells in a tissue sample from an oligodendroglioma was performed on an average laptop computer to demonstrate the efficiency of the tools. 
Concl: Our open source software enables dealing with huge images with standard software on average computers. Our tools are cross-platform, independent of proprietary libraries, and very modular, allowing them to be used in other open source projects. They have excellent performance in terms of execution speed and RAM requirements. They open promising perspectives both to the clinician who wants to study a single slide and to the research team or data centre who do image analysis of many slides on a computer cluster.
]]></description>
<dc:subject>image-processing software-development-is-not-programming rather-interesting bioinformatics medinformatics user-experience scaling to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:133bf8473bc9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-development-is-not-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:user-experience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.01780">
    <title>[1702.01780] Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming</title>
    <dc:date>2017-04-30T12:44:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.01780</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning has been gaining traction in recent years to meet the demand for tools that can efficiently analyze and make sense of the ever-growing databases of biomedical data in health care systems around the world. However, effectively using machine learning methods requires considerable domain expertise, which can be a barrier of entry for bioinformaticians new to computational data science methods. Therefore, off-the-shelf tools that make machine learning more accessible can prove invaluable for bioinformaticians. To this end, we have developed an open source pipeline optimization tool (TPOT-MDR) that uses genetic programming to automatically design machine learning pipelines for bioinformatics studies. In TPOT-MDR, we implement Multifactor Dimensionality Reduction (MDR) as a feature construction method for modeling higher-order feature interactions, and combine it with a new expert knowledge-guided feature selector for large biomedical data sets. We demonstrate TPOT-MDR's capabilities using a combination of simulated and real world data sets from human genetics and find that TPOT-MDR significantly outperforms modern machine learning methods such as logistic regression and eXtreme Gradient Boosting (XGBoost). We further analyze the best pipeline discovered by TPOT-MDR for a real world problem and highlight TPOT-MDR's ability to produce a high-accuracy solution that is also easily interpretable.
]]></description>
<dc:subject>hey-I-know-this-guy bioinformatics machine-learning meta-optimization workflows framework</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f1ddc6939c05/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meta-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:workflows"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:framework"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1306.5667">
    <title>[1306.5667] Using Genetic Programming to Model Software</title>
    <dc:date>2017-04-30T12:40:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1306.5667</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study a generic program to investigate the scope for automatically customising it for a vital current task, which was not considered when it was first written. In detail, we show genetic programming (GP) can evolve models of aspects of BLAST's output when it is used to map Solexa Next-Gen DNA sequences to the human genome.
]]></description>
<dc:subject>bioinformatics software-synthesis algorithms genetic-programming hey-I-know-this-guy nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5ff9a0ec790f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.06530">
    <title>[1704.06530] Taming Asynchrony for Attractor Detection in Large Boolean Networks (Technical Report)</title>
    <dc:date>2017-04-26T11:37:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.06530</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Boolean networks is a well-established formalism for modelling biological systems. A vital challenge for analysing a Boolean network is to identify all the attractors. This becomes more challenging for large asynchronous Boolean networks, due to the asynchronous updating scheme. Existing methods are prohibited due to the well-known state-space explosion problem in large Boolean networks. In this paper, we tackle this challenge by proposing a SCC-based decomposition method. We prove the correctness of our proposed method and demonstrate its efficiency with two real-life biological networks.
]]></description>
<dc:subject>boolean-networks Kauffmania rather-interesting heuristics algorithms bioinformatics systems-biology nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a806a8f6fa56/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:boolean-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Kauffmania"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1606.09370">
    <title>[1606.09370] Relation extraction from clinical texts using domain invariant convolutional neural network</title>
    <dc:date>2017-04-26T10:18:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1606.09370</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In recent years extracting relevant information from biomedical and clinical texts such as research articles, discharge summaries, or electronic health records have been a subject of many research efforts and shared challenges. Relation extraction is the process of detecting and classifying the semantic relation among entities in a given piece of texts. Existing models for this task in biomedical domain use either manually engineered features or kernel methods to create feature vector. These features are then fed to classifier for the prediction of the correct class. It turns out that the results of these methods are highly dependent on quality of user designed features and also suffer from curse of dimensionality. In this work we focus on extracting relations from clinical discharge summaries. Our main objective is to exploit the power of convolution neural network (CNN) to learn features automatically and thus reduce the dependency on manual feature engineering. We evaluate performance of the proposed model on i2b2-2010 clinical relation extraction challenge dataset. Our results indicate that convolution neural network can be a good model for relation exaction in clinical text without being dependent on expert's knowledge on defining quality features.]]></description>
<dc:subject>text-mining bioinformatics salience-detection algorithms neural-networks nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:acffcca1b7cc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:salience-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2017/04/13/125542?rss=1">
    <title>Describing the Local Structure of Sequence Graphs | bioRxiv</title>
    <dc:date>2017-04-25T10:11:50+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2017/04/13/125542?rss=1</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Analysis of genetic variation using graph structures is an emerging paradigm of genomics. However, defining genetic sites on sequence graphs remains an open problem. Paten's invention of the ultrabubble and snarl, special subgraphs of sequence graphs which can identified with efficient algorithms, represents important first step to segregating graphs into genetic sites. We extend the theory of ultrabubbles to a special subclass where every detail of the ultrabubble can be described in a series and parallel arrangement of genetic sites. We furthermore introduce the concept of bundle structures, which allows us to recognize the graph motifs created by additional combinations of variation in the graph, including but not limited to runs of abutting single nucleotide variants. We demonstrate linear-time identification of bundles in a bidirected graph. These two advances build on initial work on ultrabubbles in bidirected graphs, and define a more granular concept of genetic site.

]]></description>
<dc:subject>bioinformatics visualization representation rather-odd to-understand ultrabubbles</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:157d64c026ca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-odd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ultrabubbles"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.04048">
    <title>[1608.04048] Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data</title>
    <dc:date>2017-04-17T10:35:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.04048</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximally predictive features with minimal redundancy, yielding higher predictive power and improved interpretability. Its effectiveness is demonstrated through applications to classify phenotypes based on module expression in human prostate cancer patients and to detect enzymes among protein structures. We achieve high accuracy with as few as 20 out of one million features --- a dimensionality reduction of 99.998%. Our algorithm can be implemented on commodity cloud computing platforms. The dramatic reduction of features may lead to the ubiquitous deployment of sophisticated prediction models in mobile health care applications.
]]></description>
<dc:subject>feature-selection data-analysis big-data bioinformatics statistics algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ef2072225004/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:big-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.04823">
    <title>[1703.04823] Classification in biological networks with hypergraphlet kernels</title>
    <dc:date>2017-04-17T10:30:55+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.04823</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins, drugs) and edges represent relational ties among these objects (binds-to, interacts-with, regulates). This approach has been highly successful owing to the theory, methodology and software that support analysis and learning on graphs. Graphs, however, often suffer from information loss when modeling physical systems due to their inability to accurately represent multiobject relationships. Hypergraphs, a generalization of graphs, provide a framework to mitigate information loss and unify disparate graph-based methodologies. In this paper, we present a hypergraph-based approach for modeling physical systems and formulate vertex classification, edge classification and link prediction problems on (hyper)graphs as instances of vertex classification on (extended, dual) hypergraphs in a semi-supervised setting. We introduce a novel kernel method on vertex- and edge-labeled (colored) hypergraphs for analysis and learning. The method is based on exact and inexact (via hypergraph edit distances) enumeration of small simple hypergraphs, referred to as hypergraphlets, rooted at a vertex of interest. We extensively evaluate this method and show its potential use in a positive-unlabeled setting to estimate the number of missing and false positive links in protein-protein interaction networks.
]]></description>
<dc:subject>machine-learning representation rather-interesting hypergraphs to-write-about nudge-targets consider:representation consider:looking-to-see bioinformatics clustering metrics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d6f591f5708d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/24/055020?rss=1%2522">
    <title>Reference-free comparison of microbial communities via de Bruijn graphs | bioRxiv</title>
    <dc:date>2017-03-24T22:32:49+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/24/055020?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Microbial communities inhabiting the human body exhibit significant variability across different individuals and tissues, and are suggested to play an important role in health and disease. High-throughput sequencing offers unprecedented possibilities to profile microbial community composition, but limitations of existing taxonomic classification methods (including incompleteness of existing microbial reference databases) limits the ability to accurately compare microbial communities across different samples. In this paper, we present a method able to overcome these limitations by circumventing the classification step and directly using the sequencing data to compare microbial communities. The proposed method provides a powerful reference-free way to assess differences in microbial abundances across samples. This method, called EMDeBruijn, condenses the sequencing data into a de Bruijn graph. The Earth Mover's Distance (EMD) is then used to measure similarities and differences of the microbial communities associated with the individual graphs. We apply this method to RNA-Seq data sets from a coronary artery calcification (CAC) study and shown that EMDeBruijn is able to differentiate between case and control CAC samples while utilizing all the candidate microbial reads. We compare these results to current reference-based methods, which are shown to have a limited capacity to discriminate between case and control samples. We conclude that this reference-free approach is a viable choice in comparative metatranscriptomic studies.

]]></description>
<dc:subject>microbiology bioinformatics microbial-ecology wow indistinguishable-from-magic algorithms to-understand to-learn</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6949e50e44e0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:microbiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:microbial-ecology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wow"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indistinguishable-from-magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-learn"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1511.02393">
    <title>[1511.02393] On Stabbing Queries for Generalized Longest Repeat</title>
    <dc:date>2017-03-22T11:53:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1511.02393</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A longest repeat query on a string, motivated by its applications in many subfields including computational biology, asks for the longest repetitive substring(s) covering a particular string position (point query). In this paper, we extend the longest repeat query from point query to \emph{interval query}, allowing the search for longest repeat(s) covering any position interval, and thus significantly improve the usability of the solution. Our method for interval query takes a different approach using the insight from a recent work on \emph{shortest unique substrings} [1], as the prior work's approach for point query becomes infeasible in the setting of interval query. Using the critical insight from [1], we propose an indexing structure, which can be constructed in the optimal O(n) time and space for a string of size n, such that any future interval query can be answered in O(1) time. Further, our solution can find \emph{all} longest repeats covering any given interval using optimal O(occ) time, where occ is the number of longest repeats covering that given interval, whereas the prior O(n)-time and space work can find only one candidate for each point query. Experiments with real-world biological data show that our proposal is competitive with prior works, both time and space wise, while providing with the new functionality of interval queries as opposed to point queries provided by prior works.
]]></description>
<dc:subject>strings bioinformatics search-algorithms algorithms computational-complexity nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e4f8cfc93713/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:strings"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:search-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html">
    <title>Inferring biological tasks using Pareto analysis of high-dimensional data : Nature Methods : Nature Research</title>
    <dc:date>2017-02-27T14:57:21+00:00</dc:date>
    <link>http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present the Pareto task inference method (ParTI; http://www.weizmann.ac.il/mcb/UriAlon/download/ParTI) for inferring biological tasks from high-dimensional biological data. Data are described as a polytope, and features maximally enriched closest to the vertices (or archetypes) allow identification of the tasks the vertices represent. We demonstrate that human breast tumors and mouse tissues are well described by tetrahedrons in gene expression space, with specific tumor types and biological functions enriched at each of the vertices, suggesting four key tasks.

]]></description>
<dc:subject>archetypal-analysis clustering bioinformatics systems-biology machine-learning algorithms rather-interesting to-write-about nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cdfd7e23fcd5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.00318">
    <title>[1702.00318] A Hybrid Evolutionary Algorithm Based on Solution Merging for the Longest Arc-Preserving Common Subsequence Problem</title>
    <dc:date>2017-02-11T15:31:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.00318</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The longest arc-preserving common subsequence problem is an NP-hard combinatorial optimization problem from the field of computational biology. This problem finds applications, in particular, in the comparison of arc-annotated Ribonucleic acid (RNA) sequences. In this work we propose a simple, hybrid evolutionary algorithm to tackle this problem. The most important feature of this algorithm concerns a crossover operator based on solution merging. In solution merging, two or more solutions to the problem are merged, and an exact technique is used to find the best solution within this union. It is experimentally shown that the proposed algorithm outperforms a heuristic from the literature.
]]></description>
<dc:subject>combinatorics bioinformatics metaheuristics strings rather-interesting nudge-targets consider:looking-to-see consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:62e2723cdce4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:strings"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.06971">
    <title>[1608.06971] Protein Collapse is Encoded in the Folded State Architecture</title>
    <dc:date>2016-12-31T11:50:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.06971</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Natural protein sequences that self-assemble to form globular structures are compact with high packing densities in the folded states. It is known that proteins unfold upon addition of denaturants, adopting random coil structures. The dependence of the radii of gyration on protein size in the folded and unfolded states obeys the same scaling laws as synthetic polymers. Thus, one might surmise that the mechanism of collapse in proteins and polymers ought to be similar. However, because the number of amino acids in single domain proteins is not significantly greater than about two hundred, it has not been resolved if the unfolded states of proteins are compact under conditions that favor the folded states - a problem at the heart of how proteins fold. By adopting a theory used to derive polymer-scaling laws, we find that the propensity for the unfolded state of a protein to be compact is universal and is encoded in the contact map of the folded state. Remarkably, analysis of over 2000 proteins shows that proteins rich in β-sheets have greater tendency to be compact than α-helical proteins. The theory provides insights into the reasons for the small size of single domain proteins and the physical basis for the origin of multi-domain proteins. Application to non-coding RNA molecules show that they have evolved to collapse sharing similarities to β-sheet proteins. An implication of our theory is that the evolution of natural foldable sequences is guided by the requirement that for efficient folding they should populate minimum energy compact states under folding conditions. This concept also supports the compaction selection hypothesis used to rationalize the unusually condensed states of viral RNA molecules.
]]></description>
<dc:subject>structural-biology protein-folding rather-interesting bioinformatics theoretical-biology self-organization engineering-design dynamical-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:81ce4c9f7934/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-organization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1605.02948">
    <title>[1605.02948] A Bayesian Approach to Biomedical Text Summarization</title>
    <dc:date>2016-12-25T22:11:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.02948</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Automatic text summarization tools help biomedical researchers and clinicians to acquire intended information from various textual resources in shorter time and with less effort. Some of the biomedical text summarization systems put the basis of their sentence selection approach on the frequency of concepts extracted from the input text. However, it seems that exploring other measures rather than the frequency for identifying the valuable content of the input document, and considering the correlations existing between concepts can be more useful for this type of summarization. In this paper, we propose a biomedical text summarization method based on the na\"ive Bayes classifier. The input text is mapped to the Unified Medical Language System (UMLS) concepts, and the important ones are selected to be used as the classification features. We introduce different feature selection approaches to identify the most important concepts of the text and select the most informative content according to the distribution of these concepts. We show that with the use of an appropriate feature selection approach, our Bayesian biomedical summarizer can improve the performance of summarization. An extensive evaluation was performed on a collection of scientific papers in biomedical domain. The results show that our proposed method outperforms the biomedical summarizers that rely on the frequency of concepts, the domain-independent and baseline methods based on the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics. Moreover, the results suggest that using the meaningfulness measure and considering the correlations of concepts in the feature selection step yield a desirable summarization performance.
]]></description>
<dc:subject>natural-language-processing bioinformatics topic-modeling machine-learning algorithms nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:07802c3a0242/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:topic-modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1605.01639">
    <title>[1605.01639] Context-dependent metabolic networks</title>
    <dc:date>2016-10-31T13:08:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1605.01639</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Cells adapt their metabolism to survive changes in their environment. We present a framework for the construction and analysis of metabolic reaction networks that can be tailored to reflect different environmental conditions. Using context-dependent flux distributions from Flux Balance Analysis (FBA), we produce directed networks with weighted links representing the amount of metabolite flowing from a source reaction to a target reaction per unit time. Such networks are analyzed with tools from network theory to reveal salient features of metabolite flows in each biological context. We illustrate our approach with the directed network of the central carbon metabolism of Escherichia coli, and study its properties in four relevant biological scenarios. Our results show that both flow and network structure depend drastically on the environment: networks produced from the same metabolic model in different contexts have different edges, components, and flow communities, capturing the biological re-routing of metabolic flows inside the cell. By integrating FBA-based analysis with tools from network science, our results provide a framework to interrogate cellular metabolism beyond standard pathway descriptions that are blind to the environmental context.
]]></description>
<dc:subject>systems-biology reaction-networks bioinformatics simulation theoretical-biology control-theory nonlinear-dynamics rather-interesting nudge-targets consider:feature-discovery consider:simulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8930897a6abf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reaction-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:control-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:simulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.07151">
    <title>[1605.07151] Shotgun edge assembly of random jigsaw puzzles</title>
    <dc:date>2016-08-06T13:29:35+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.07151</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In recent work by Mossel and Ross, it was asked how large q has to be for a random jigsaw puzzle with q different shapes of "jigs" to have exactly one solution. The jigs are assumed symmetric in the sense that two jigs of the same type always fit together. They showed that for q=o(n2/3) there are a.a.s. multiple solutions, and for q=ω(n2) there is a.a.s. exactly one. The latter bound has since been improved to q≥n1+ε independently by Nenadov, Pfister and Steger, and by Bordernave, Feige and Mossel. Both groups further remark that for q=o(n) there are a.a.s. duplicate pieces in the puzzle. In this paper, we show that such puzzle a.a.s. has multiple solutions whenever q≤2e√n−ω(log2n), even if permuting identical pieces is not considered changing the solution. We further give some remarks about the number of solutions, and the probability of a unique solution in this regime.]]></description>
<dc:subject>bioinformatics combinatorics rather-interesting puzzles algorithms uniqueness nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:93925600eef6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:puzzles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:uniqueness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/06/21/060111?rss=1%2522">
    <title>Tradict enables high fidelity reconstruction of the eukaryotic transcriptome from 100 marker genes | bioRxiv</title>
    <dc:date>2016-07-04T18:04:22+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/06/21/060111?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Transcript levels are a critical determinant of the proteome and hence cellular function. Because the transcriptome is an outcome of the interactions between genes and their products, we reasoned it might be accurately represented by a subset of transcript abundances. We develop a method, Tradict (transcriptome predict), capable of learning and using the expression measurements of a small subset of 100 marker genes to reconstruct entire transcriptomes. By analyzing over 23,000 publicly available RNA-Seq datasets, we show that Tradict is robust to noise and accurate, especially for predicting the expression of a comprehensive, but interpretable list of transcriptional programs that represent the major biological processes and cellular pathways. Coupled with targeted RNA sequencing, Tradict may therefore enable simultaneous transcriptome-wide screening and mechanistic investigation at large scales. Thus, whether for performing forward genetic, chemogenomic, or agricultural screens or for profiling single-cells, Tradict promises to help accelerate genetic dissection and drug discovery.

]]></description>
<dc:subject>bioinformatics algorithms statistics models rather-interesting systems-biology nudge-targets approximation consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ff270eb6af8f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522">
    <title>Accurate prediction of single-cell DNA methylation states using deep learning | bioRxiv</title>
    <dc:date>2016-06-06T10:55:29+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent technological advances have enabled assaying DNA methylation in single cells. Current protocols are limited by incomplete CpG coverage and hence methods to predict missing methylation states are critical to enable genome-wide analyses. We here report DeepCpG, a computational approach based on deep neural networks to predict DNA methylation states from DNA sequence and incomplete methylation profiles in single cells. We validate DeepCpG on mouse embryonic stem cells, where we report substantially more accurate predictions than previous methods. Additionally, we show that DeepCpG provides new insights for interpreting the sources of epigenetic diversity. Our model can be used to estimate the effect of single nucleotide changes and we uncover sequence motifs that are associated with DNA methylation level and epigenetic heterogeneity.

]]></description>
<dc:subject>bioinformatics deep-learning neural-networks machine-learning prediction nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6d5a8c061369/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/26/055624">
    <title>Could a neuroscientist understand a microprocessor? | bioRxiv</title>
    <dc:date>2016-05-28T21:04:34+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/26/055624</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[There is a popular belief in neuroscience that we are primarily data limited, that producing large, multimodal, and complex datasets will, enabled by data analysis algorithms, lead to fundamental insights into the way the brain processes information. Microprocessors are among those artificial information processing systems that are both complex and that we understand at all levels, from the overall logical flow, via logical gates, to the dynamics of transistors. Here we take a simulated classical microprocessor as a model organism, and use our ability to perform arbitrary experiments on it to see if popular data analysis methods from neuroscience can elucidate the way it processes information. We show that the approaches reveal interesting structure in the data but do not meaningfully describe the hierarchy of information processing in the processor. This suggests that current approaches in neuroscience may fall short of producing meaningful models of the brain.

]]></description>
<dc:subject>via:numerous neural-networks inference modeling experiment rather-interesting big-data bioinformatics looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cd7d452bf53f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:numerous"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:big-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.03043">
    <title>[1605.03043] Unique reconstruction threshold for random jigsaw puzzles</title>
    <dc:date>2016-05-16T12:25:04+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.03043</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A random jigsaw puzzle is constructed by arranging n2 square pieces into an n×n grid and assigning to each edge of a piece one of q available colours uniformly at random, with the restriction that touching edges receive the same colour. We show that if q=o(n) then with high probability such a puzzle does not have a unique solution, while if q≥n1+ε for any constant ε>0 then the solution is unique. This solves a conjecture of Mossel and Ross (Shotgun assembly of labeled graphs, arXiv:1504.07682).
]]></description>
<dc:subject>probability-theory proof combinatorics graph-theory bioinformatics rather-interesting nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e85c734bda20/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:proof"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.01941">
    <title>[1605.01941] Partial DNA Assembly: A Rate-Distortion Perspective</title>
    <dc:date>2016-05-13T23:44:27+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.01941</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Earlier formulations of the DNA assembly problem were all in the context of perfect assembly; i.e., given a set of reads from a long genome sequence, is it possible to perfectly reconstruct the original sequence? In practice, however, it is very often the case that the read data is not sufficiently rich to permit unambiguous reconstruction of the original sequence. While a natural generalization of the perfect assembly formulation to these cases would be to consider a rate-distortion framework, partial assemblies are usually represented in terms of an assembly graph, making the definition of a distortion measure challenging. In this work, we introduce a distortion function for assembly graphs that can be understood as the logarithm of the number of Eulerian cycles in the assembly graph, each of which correspond to a candidate assembly that could have generated the observed reads. We also introduce an algorithm for the construction of an assembly graph and analyze its performance on real genomes.
]]></description>
<dc:subject>bioinformatics algorithms DNA-assembly molecular-biology statistics inference nudge-targets consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cec42b767669/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:DNA-assembly"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/28/050732?rss=1%2522">
    <title>Inferring interaction partners from protein sequences | bioRxiv</title>
    <dc:date>2016-05-08T13:53:08+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/28/050732?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Specific protein-protein interactions are crucial in the cell, both to ensure the formation and stability of multi-protein complexes, and to enable signal transduction in various pathways. Functional interactions between proteins result in coevolution between the interaction partners. Hence, the sequences of interacting partners are correlated. Here we exploit these correlations to accurately identify which proteins are specific interaction partners from sequence data alone. Our general approach, which employs a pairwise maximum entropy model to infer direct couplings between residues, has been successfully used to predict the three-dimensional structures of proteins from sequences. Building on this approach, we introduce an iterative algorithm to predict specific interaction partners from among the members of two protein families. We assess the algorithm's performance on histidine kinases and response regulators from bacterial two-component signaling systems. The algorithm proves successful without any a priori knowledge of interaction partners, yielding a striking 0.93 true positive fraction on our complete dataset, and we uncover the origin of this surprising success. Finally, we discuss how our method could be used to predict novel protein-protein interactions.

]]></description>
<dc:subject>protein-structure biophysics systems-biology machine-learning algorithms rather-interesting bioinformatics nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:44fa91e27326/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-structure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biophysics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/26/050187?rss=1%2522">
    <title>Pan-cancer analysis of the metabolic reaction network | bioRxiv</title>
    <dc:date>2016-05-03T13:08:00+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/26/050187?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Metabolic reprogramming is considered a hallmark of malignant transformation. However, it is not clear whether the network of metabolic reactions expressed by cancers of different origin differ from each other nor from normal human tissues. In this study, we reconstructed functional and connected genome-scale metabolic models for 917 primary tumors based on the probability of expression for 3,765 reference metabolic genes in the sample. This network-centric approach revealed that tumor metabolic networks are largely similar in terms of accounted reactions, despite diversity in the expression of the associated genes. On average, each network contained 4,721 reactions, of which 74% were core reactions (present in >95% of all models). Whilst 99.3% of the core reactions were classified as housekeeping also in normal tissues, we identified reactions catalyzed by ARG2, RHAG, SLC6 and SLC16 family gene members, and PTGS1 and PTGS2 as core exclusively in cancer. The remaining 26% of the reactions were contextual reactions. Their inclusion was dependent in one case (GLS2) on the absence of TP53 mutations and in 94.6% of cases on differences in cancer types. This dependency largely resembled differences in expression patterns in the corresponding normal tissues, with some exceptions like the presence of the NANP-encoded reaction in tumors not from the female reproductive system or of the SLC5A9-encoded reaction in kidney-pancreatic-colorectal tumors. In conclusion, tumors expressed a metabolic network virtually overlapping the matched normal tissues, raising the possibility that metabolic reprogramming simply reflects cancer cell plasticity to adapt to varying conditions thanks to redundancy and complexity of the underlying metabolic networks. At the same time, the here uncovered exceptions represent a resource to identify selective liabilities of tumor metabolism.

]]></description>
<dc:subject>systems-biology network-theory bioinformatics medical-technology machine-learning feature-extraction nudge-targets consider:feature-discovery classification</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3dcc3f3401d0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medical-technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/23/049999?rss=1%2522">
    <title>Olfactory perception of chemically diverse molecules | bioRxiv</title>
    <dc:date>2016-05-02T10:06:52+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/23/049999?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Background Understanding the relationship between a stimulus and how it is perceived reveals fundamental principles about the mechanisms of sensory perception. While this stimulus-percept problem is mostly understood for color vision and tone perception, it is not currently possible to predict how a given molecule smells. While there has been some progress in predicting the pleasantness and intensity of an odor, perceptual data for a larger number of diverse molecules are needed to improve current predictions. Towards this goal, we tested the olfactory perception of 480 structurally and perceptually diverse molecules at two concentrations using a panel of 55 healthy human subjects. Results For each stimulus, we collected data on perceived intensity, pleasantness, and familiarity. In addition, subjects were asked to apply 20 semantic odor quality descriptors to these stimuli, and were offered the option to describe the smell in their own words. Using this dataset, we replicated several previous correlations between molecular features of the stimulus and olfactory perception. The number of sulfur atoms in a molecule was highly correlated with the descriptors garlic, fish, decayed, and large and structurally complex molecules were perceived to be more pleasant. We discovered a number of strong correlations in intensity perception between molecules, which suggests a shared mechanism for perceiving these molecules. We show that familiarity had a strong effect on the ability of subjects to describe a smell. Many subjects used commercial products to describe familiar odors, highlighting the role of prior experience in biasing verbal report of perceived smells. Nonspecific descriptors like chemical were applied frequently to unfamiliar smells, and unfamiliar odors were generally rated as neither pleasant nor unpleasant. Conclusions We present a very large psychophysical dataset and use this to correlate molecular features of a stimulus to olfactory percept. Our work reveals robust correlations between molecular features and perceptual qualities, and highlights the dominant role of familiarity and experience in assigning verbal descriptors to smells.

]]></description>
<dc:subject>rather-interesting physiology bioinformatics statistics machine-learning also-not-machine-learning feature-extraction feature-construction nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:55ac7c01d000/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:also-not-machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/28/050757?rss=1%2522">
    <title>Accurate classification of protein subcellular localization from high throughput microscopy images using deep learning | bioRxiv</title>
    <dc:date>2016-05-02T10:00:07+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/28/050757?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[High throughput microscopy of many single cells generates high-dimensional data that are far from straightforward to analyze. One important problem is automatically detecting the cellular compartment where a fluorescently tagged protein resides, a task relatively simple for an experienced human, but difficult to automate on a computer. Here, we train an 11-layer neural network on data from mapping thousands of yeast proteins, achieving per cell localization classification accuracy of 91%, and per protein accuracy of 99% on held out images. We confirm that low-level network features correspond to basic image characteristics, while deeper layers separate localization classes. Using this network as a feature calculator, we train standard classifiers that assign proteins to previously unseen compartments after observing only a small number of training examples. Our results are the most accurate subcellular localization classifications to date, and demonstrate the usefulness of deep learning for high throughput microscopy.

]]></description>
<dc:subject>cell-biology image-processing image-analysis deep-learning bioinformatics rather-interesting nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7fbb74767e1e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cell-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1604.08354">
    <title>[1604.08354] Inferring interaction partners from protein sequences</title>
    <dc:date>2016-05-01T12:50:48+00:00</dc:date>
    <link>http://arxiv.org/abs/1604.08354</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Specific protein-protein interactions are crucial in the cell, both to ensure the formation and stability of multi-protein complexes, and to enable signal transduction in various pathways. Functional interactions between proteins result in coevolution between the interaction partners. Hence, the sequences of interacting partners are correlated. Here we exploit these correlations to accurately identify which proteins are specific interaction partners from sequence data alone. Our general approach, which employs a pairwise maximum entropy model to infer direct couplings between residues, has been successfully used to predict the three-dimensional structures of proteins from sequences. Building on this approach, we introduce an iterative algorithm to predict specific interaction partners from among the members of two protein families. We assess the algorithm's performance on histidine kinases and response regulators from bacterial two-component signaling systems. The algorithm proves successful without any a priori knowledge of interaction partners, yielding a striking 0.93 true positive fraction on our complete dataset, and we uncover the origin of this surprising success. Finally, we discuss how our method could be used to predict novel protein-protein interactions.
]]></description>
<dc:subject>bioinformatics machine-learning systems-biology algorithms prediction nudge-targets consider:feature-discovery consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f945fc799b7b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/25/049627?rss=1%2522">
    <title>Predictability of Genetic Interactions from Functional Gene Modules | bioRxiv</title>
    <dc:date>2016-05-01T12:14:42+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/25/049627?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Characterizing genetic interactions is crucial to understanding cellular and organismal response to gene-level perturbations. Such knowledge can inform the selection of candidate disease therapy targets. Yet experimentally determining whether genes interact is technically non-trivial and time-consuming. High-fidelity prediction of different classes of genetic interactions in multiple organisms would substantially alleviate this experimental burden. Under the hypothesis that functionally-related genes tend to share common genetic interaction partners, we evaluate a computational approach to predict genetic interactions in Homo sapiens, Drosophila melanogaster, and Saccharomyces cerevisiae. By leveraging knowledge of functional relationships between genes, we cross-validate predictions on known genetic interactions and observe high-predictive power of multiple classes of genetic interactions in all three organisms. Additionally, our method suggests high-confidence candidate interaction pairs that can be directly experimentally tested. A web application is provided for users to query genes for predicted novel genetic interaction partners. Finally, by subsampling the known yeast genetic interaction network, we found that novel genetic interactions are predictable even when knowledge of currently known interactions is minimal

]]></description>
<dc:subject>bioinformatics machine-learning gene-regulatory-networks systems-biology engineering-design rather-interesting nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:297d50ef9c6f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/04/25/050146?rss=1%2522">
    <title>Chromatin structure shapes the search process of transcription factors | bioRxiv</title>
    <dc:date>2016-05-01T11:57:47+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/04/25/050146?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The diffusion of regulatory proteins within the nucleus plays a crucial role in the dynamics of transcriptional regulation. The standard model assumes a 3D plus 1D diffusion process: regulatory proteins either move freely in solution or slide on DNA. This model however does not considered the 3D structure of chromatin. Here we proposed a multi-scale stochastic model that integrates, for the first time, high-resolution information on chromatin structure as well as DNA-protein interactions. The dynamics of transcription factors was modeled as a slide plus jump diffusion process on a chromatin network based on pair-wise contact maps obtained from high-resolution Hi-C experiments. Our model allowed us to uncover the effects of chromatin structure on transcription factor occupancy profiles and target search times. Finally, we showed that binding sites clustered on few topological associated domains leading to a higher local concentration of transcription factors which could reflect an optimal strategy to efficiently use limited transcriptional resources.

]]></description>
<dc:subject>structural-biology molecular-design molecular-biology systems-biology bioinformatics it's-more-complicated-than-you-think</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f151d98280fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:it's-more-complicated-than-you-think"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1510.02356">
    <title>[1510.02356] Clustering genes of common evolutionary history</title>
    <dc:date>2016-03-20T16:40:19+00:00</dc:date>
    <link>http://arxiv.org/abs/1510.02356</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Phylogenetic inference can potentially result in a more accurate tree using data from multiple loci. However, if the loci are incongruent--due to events such as incomplete lineage sorting or horizontal gene transfer--it can be misleading to infer a single tree. To address this, many previous contributions have taken a mechanistic approach, by modelling specific processes. Alternatively, one can cluster loci without assuming how these incongruencies might arise. Such "process-agnostic" approaches typically infer a tree for each locus and cluster these. There are, however, many possible combinations of tree distance and clustering methods; their comparative performance in the context of tree incongruence is largely unknown. Furthermore, because standard model selection criteria such as AIC cannot be applied to problems with a variable number of topologies, the issue of inferring the optimal number of clusters is poorly understood. Here, we perform a large-scale simulation study of phylogenetic distances and clustering methods to infer loci of common evolutionary history. We observe that the best-performing combinations are distances accounting for branch lengths followed by spectral clustering or Ward's method. We also introduce two statistical tests to infer the optimal number of clusters and show that they strongly outperform the silhouette criterion, a general-purpose heuristic. We illustrate the usefulness of the approach by (i) identifying errors in a previous phylogenetic analysis of yeast species and (ii) identifying topological incongruence among newly sequenced loci of the globeflower fly genus Chiastocheta. We release treeCl, a new program to cluster genes of common evolutionary history (this http URL).
]]></description>
<dc:subject>bioinformatics cladistics classification statistics algorithms theoretical-biology nudge-targets consider:alternatives</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:19c5dbb24aae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cladistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:alternatives"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1501.03971">
    <title>[1501.03971] Bayesian protein structure alignment</title>
    <dc:date>2016-02-27T21:43:28+00:00</dc:date>
    <link>http://arxiv.org/abs/1501.03971</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The analysis of the three-dimensional structure of proteins is an important topic in molecular biochemistry. Structure plays a critical role in defining the function of proteins and is more strongly conserved than amino acid sequence over evolutionary timescales. A key challenge is the identification and evaluation of structural similarity between proteins; such analysis can aid in understanding the role of newly discovered proteins and help elucidate evolutionary relationships between organisms. Computational biologists have developed many clever algorithmic techniques for comparing protein structures, however, all are based on heuristic optimization criteria, making statistical interpretation somewhat difficult. Here we present a fully probabilistic framework for pairwise structural alignment of proteins. Our approach has several advantages, including the ability to capture alignment uncertainty and to estimate key "gap" parameters which critically affect the quality of the alignment. We show that several existing alignment methods arise as maximum a posteriori estimates under specific choices of prior distributions and error models. Our probabilistic framework is also easily extended to incorporate additional information, which we demonstrate by including primary sequence information to generate simultaneous sequence-structure alignments that can resolve ambiguities obtained using structure alone. This combined model also provides a natural approach for the difficult task of estimating evolutionary distance based on structural alignments. The model is illustrated by comparison with well-established methods on several challenging protein alignment examples.
]]></description>
<dc:subject>biochemistry structural-biology protein-folding bioinformatics algorithms machine-learning statistics metrics nudge-targets consider:distance-measure</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:eefeff02cf1a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biochemistry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:distance-measure"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1512.00268">
    <title>[1512.00268] Chromatin assortativity: integrating epigenomic data and 3D genomic structure</title>
    <dc:date>2016-02-25T11:23:58+00:00</dc:date>
    <link>http://arxiv.org/abs/1512.00268</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Background: The field of 3D chromatin interaction mapping is changing our point of view on the genome, paving the way for new insights into its organization. Network analysis is a natural and powerful way of modelling chromatin interactions. Assortativity is a network property that has been widely used in the social sciences to measure the probability of nodes with similar values of a specific feature to interact preferentially. We propose a new approach, using Chromatin feature Assortativity (ChAs), to integrate the epigenomic landscape of a specific cell type with its chromatin interaction network. Results: We use high-resolution Promoter Capture Hi-C and Hi-Cap data as well as ChIA-PET data from embryonic stem cells to generate promoter-centered interaction networks. We calculate the presence of a collection of 78 chromatin features in the chromatin fragments constituting the nodes of the network. Based on the ChAs of these epigenomic features calculated in 4 different interaction networks, we find Polycomb Group proteins and associated histone marks to play a prominent role. Remarkably, in promoter-centered networks, we observe higher ChAs of the actively elongating form of RNA Polymerase 2 compared to inactive forms in interactions between promoters and other elements. Conclusions: Contacts amongst promoters and between promoters and other elements have different characteristic epigenomic features. Using ChAs we identify a possible role of the elongating form of RNAPII in enhancer activity. Our approach facilitates the study of multiple genome-wide epigenomic profiles, considering network topology and allowing for the comparison of any number of chromatin interaction networks.
]]></description>
<dc:subject>bioinformatics structural-biology it's-more-complicated-than-you-think supramolecular-complex cell-biology molecular-machinery experiment</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d7eadedfcdd2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:it's-more-complicated-than-you-think"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:supramolecular-complex"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cell-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-machinery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1508.05990">
    <title>[1508.05990] A Multi-Time-Scale Analysis of Chemical Reaction Networks : II. Stochastic Systems</title>
    <dc:date>2016-02-09T17:48:33+00:00</dc:date>
    <link>http://arxiv.org/abs/1508.05990</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider stochastic descriptions of chemical reaction networks in which there are both fast and slow reactions, and for which the time scales are widely separated. We develop a computational algorithm that produces the generator of the full chemical master equation for arbitrary systems, and show how to obtain a reduced equation that governs the evolution on the slow time scale. This is done by applying a state space decomposition to the full equation that leads to the reduced dynamics in terms of certain projections and the invariant distributions of the fast system. The rates or propensities of the reduced system are shown to be the rates of the slow reactions conditioned on the expectations of fast steps. We also show that the generator of the reduced system is a Markov generator, and we present an efficient stochastic simulation algorithm for the slow time scale dynamics. We illustrate the numerical accuracy of the approximation by simulating several examples. Graph-theoretic techniques are used throughout to describe the structure of the reaction network and the state-space transitions accessible under the dynamics.
]]></description>
<dc:subject>reaction-networks dynamical-systems simulation models-and-modes modeling-is-not-mathematics theoretical-biology bioinformatics nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:854bafa52318/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reaction-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1512.05055">
    <title>[1512.05055] Inferring Gene Regulatory Network Using An Evolutionary Multi-Objective Method</title>
    <dc:date>2015-12-27T21:48:14+00:00</dc:date>
    <link>http://arxiv.org/abs/1512.05055</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Inference of gene regulatory networks (GRNs) based on experimental data is a challenging task in bioinformatics. In this paper, we present a bi-objective minimization model (BoMM) for inference of GRNs, where one objective is the fitting error of derivatives, and the other is the number of connections in the network. To solve the BoMM efficiently, we propose a multi-objective evolutionary algorithm (MOEA), and utilize the separable parameter estimation method (SPEM) decoupling the ordinary differential equation (ODE) system. Then, the Akaike Information Criterion (AIC) is employed to select one inference result from the obtained Pareto set. Taking the S-system as the investigated GRN model, our method can properly identify the topologies and parameter values of benchmark systems. There is no need to preset problem-dependent parameter values to obtain appropriate results, and thus, our method could be applicable to inference of various GRNs models.
]]></description>
<dc:subject>gene-regulatory-networks boolean-networks Kauffmania inference bioinformatics models nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:60795608658c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:boolean-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Kauffmania"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1512.03094">
    <title>[1512.03094] Theoretical knock-outs on biological networks</title>
    <dc:date>2015-12-27T13:46:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1512.03094</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this work we formalize a method to compute the degree of importance of biological agents that participates on the dynamics of a biological phenomenon build upon a complex network. We call this new procedure by theoretical knock-out (KO). To devise this method, we make two approaches: algebraically and algorithmically. In both cases we compute a vector on an asymptotic state, called flux vector. The flux is given by a random walk on a directed graph that represents a biological phenomenon. This vector gives us the information about the relative flux of walkers on a vertex which represents a biological agent. With two vector of this kind, we can calculate the relative mean error between them by averaging over its coefficients. This quantity allows us to assess the degree of importance of each vertex of a complex network that evolves in time and has experimental background. We find out that this procedure can be applied in any sort of biological phenomena in which we can know the role and interrelationships of its agents. These results also provide experimental biologists to predict the order of importance of biological agents on a mounted complex network.
]]></description>
<dc:subject>systems-biology gene-regulatory-networks bioinformatics inference nudge-targets representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dfc186d58fa7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1512.02786">
    <title>[1512.02786] A weighted pair graph representation for reconstructibility of Boolean control networks</title>
    <dc:date>2015-12-27T13:34:27+00:00</dc:date>
    <link>http://arxiv.org/abs/1512.02786</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A new concept of weighted pair graphs (WPGs) is proposed to represent a new reconstructibility of Boolean control networks (BCNs), which is a generalization of the reconstructibility shown in [Fornasini & Valcher, TAC2013, Def. 4]. Based on the representation of WPGs, an effective algorithm for determining the new reconstructibility of BCNs is designed with the help of the theories of finite automata and formal languages. Actually, we prove that a BCN is not reconstructible iff one of the weakly connected components of its WPG has a complete subgraph. One can execute the new algorithm concurrently on all these components. Hence usually the more weakly connected components a WPG has, the more efficient the new algorithm is. Besides, we prove that a BCN is reconstructible in the sense of [Fornasini & Valcher, TAC2013, Def. 4], iff the WPG of the BCN has no cycles, which is simpler to be checked than [Fornasini & Valcher, TAC2013, Thm. 4].
]]></description>
<dc:subject>boolean-networks theoretical-biology bioinformatics systems-biology engineering-design representation nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:395589621b21/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:boolean-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1509.03434">
    <title>[1509.03434] Improving protein threading accuracy via combining local and global potential using TreeCRF model</title>
    <dc:date>2015-12-25T17:11:31+00:00</dc:date>
    <link>http://arxiv.org/abs/1509.03434</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Protein structure prediction remains to be an open problem in bioinformatics. There are two main categories of methods for protein structure prediction: Free Modeling (FM) and Template Based Modeling (TBM). Protein threading, belonging to the category of template based modeling, identifies the most likely fold with the target by making a sequence-structure alignment between target protein and template protein. Though protein threading has been shown to more be successful for protein structure prediction, it performs poorly for remote homology detection.
]]></description>
<dc:subject>structural-biology biophysics protein-folding models optimization algorithms representation nudge-targets bioinformatics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ad99a83404f6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structural-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biophysics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1510.08513">
    <title>[1510.08513] Time-delayed models of gene regulatory networks</title>
    <dc:date>2015-12-25T16:37:08+00:00</dc:date>
    <link>http://arxiv.org/abs/1510.08513</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this review we discuss different mathematical models of gene regulatory networks as relevant to the onset and development of cancer. After discussion of alternative modelling approaches, we use a paradigmatic two-gene network to focus on the role played by time delays in the dynamics of gene regulatory networks. We contrast the dynamics of the reduced model arising in the limit of fast mRNA dynamics with that of the full model. The review concludes with the discussion of some open problems.
]]></description>
<dc:subject>gene-regulatory-networks systems-biology models bioinformatics inference network-theory inverse-problems nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:261731ed3d67/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1511.07662">
    <title>[1511.07662] A Paradigmatic Regression Algorithm for Gene Selection Problems</title>
    <dc:date>2015-12-10T12:32:37+00:00</dc:date>
    <link>http://arxiv.org/abs/1511.07662</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Motivation: Gene selection has become a common task in most gene expression studies. The objective of such research is often to identify the smallest possible set of genes that can still achieve good predictive performance. The problem of assigning tumours to a known class is a particularly important example that has received considerable attention in the last ten years. Many of the classification methods proposed recently require some form of dimension-reduction of the problem. These methods provide a single model as an output and, in most cases, rely on the likelihood function in order to achieve variable selection. 
Results: We propose a prediction-based objective function that can be tailored to the requirements of practitioners and can be used to assess and interpret a given problem. The direct optimization of such a function can be very difficult because the problem is potentially discontinuous and nonconvex. We therefore propose a general procedure for variable selection that resembles importance sampling to explore the feature space. Our proposal compares favorably with competing alternatives when applied to two cancer data sets in that smaller models are obtained for better or at least comparable classification errors. Furthermore by providing a set of selected models instead of a single one, we construct a network of possible models for a target prediction accuracy level.
]]></description>
<dc:subject>bioinformatics network-theory interaction-models systems-biology inference statistics nudge-targets consider:stress-testing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:434056c61fa2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interaction-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stress-testing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1509.00896">
    <title>[1509.00896] Visualizing Regulation in Rule-based Models</title>
    <dc:date>2015-11-13T22:20:59+00:00</dc:date>
    <link>http://arxiv.org/abs/1509.00896</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Rule-based modeling is a powerful way to model kinetic interactions in biochemical systems. Rules enable a precise encoding of biochemical interactions at the resolution of sites within molecules, but obtaining an integrated global view from sets of rules remains challenging. Current automated approaches to rule visualization fail to address the complexity of interactions between rules, limiting either the types of rules that are allowed or the set of interactions that can be visualized simultaneously. There is a need for scalable visualization approaches that present the information encoded in rules in an intuitive and useful manner at different levels of detail. We have developed new automated approaches for visualizing both individual rules and complete rule-based models. We find that a more compact representation of an individual rule promotes promotes understanding the model assumptions underlying each rule. For global visualization of rule interactions, we have developed a method to synthesize a network of interactions between sites and processes from a rule-based model and then use a combination of user-defined and automated approaches to compress this network into a readable form. The resulting diagrams enable modelers to identify signaling motifs such as cascades, feedback loops, and feed-forward loops in complex models, as we demonstrate using several large-scale models. These capabilities are implemented within the BioNetGen framework but the approach is equally applicable to rule-based models specified in other formats.
]]></description>
<dc:subject>bioinformatics reaction-networks inference statistics rather-interesting community-detection network-theory nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:944048fd76da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reaction-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:community-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1501.04648">
    <title>[1501.04648] Fast, approximate kinetics of RNA folding</title>
    <dc:date>2015-11-05T02:05:42+00:00</dc:date>
    <link>http://arxiv.org/abs/1501.04648</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we introduce the software suite, Hermes, which provides fast, novel algorithms for RNA secondary structure kinetics. Using the fast Fourier transform to e?ciently compute the Boltzmann probability that a secondary structure S of a given RNA sequence has base pair distance x [resp. y] from reference structure A [resp. B], Hermes computes the exact kinetics of folding from A to B in this coarse-grained model. In particular, Hermes computes the mean ?rst passage time from the transition probability matrix by using matrix inversion, and also computes the equilibrium time from the rate matrix by using spectral decomposition. Due to the model granularity and the speed of Hermes, it is capable of determining secondary structure refolding kinetics for large RNA sequences, beyond the range of other methods. Comparative benchmarking of Hermes with other methods indicates that Hermes provides refolding kinetics of accuracy suitable for use in computational design of RNA, an important area of synthetic biology. Source code and documentation for Hermes are available at this http URL bc.edu/clotelab/Hermes/.
]]></description>
<dc:subject>RNA molecular-biology biophysics bioinformatics optimization simulation approximation algorithms nudge-targets consider:representation rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fe8151cde260/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:RNA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biophysics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2015/10/22/029710">
    <title>Flowr: Robust and efficient pipelines using a simple language-agnostic approach | bioRxiv</title>
    <dc:date>2015-11-03T20:57:49+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2015/10/22/029710</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Motivation: Bioinformatics analyses have become increasingly intensive computing processes, with lowering costs and increasing numbers of samples. Each laboratory spends time creating and maintaining a set of pipelines, which may not be robust, scalable, or efficient. Further, the existence of different computing environments across institutions hinders both collabo-ration and the portability of analysis pipelines. Results: Flowr is a robust and scalable framework for designing and deploying computing pipelines in an easy-to-use fashion. It implements a scatter-gather approach using computing clusters, simplifying the concept to the use of five simple terms (in submission and dependency types). Most importantly, it is flexible, such that customizing existing pipelines is easy, and since it works across several computing environments (LSF, SGE, Torque, and SLURM), it is portable. Availability: http://docs.flowr.space

]]></description>
<dc:subject>workflow framework representation software-development design-patterns bioinformatics distributed-processing rather-interesting consider:for-GP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3b3bf92b0890/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:workflow"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:framework"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:design-patterns"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distributed-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:for-GP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.05815">
    <title>[1505.05815] Inference of Ancestral Recombination Graphs through Topological Data Analysis</title>
    <dc:date>2015-10-16T12:54:23+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.05815</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The recent explosion of genomic data has underscored the need for interpretable and comprehensive analyses that can capture complex phylogenetic relations within and across species. Recombination, reassortment, horizontal gene transfer, and species hybridization constitute examples of pervasive biological phenomena that cannot be captured by tree-like representations. Starting from tens or hundreds of genomes, we are interested in the reconstruction of potential evolutionary histories leading to the observed data. Ancestral recombination graphs (ARGs) represent potential histories that explicitly accommodate recombination and mutation events across orthologous genomes. However, ARGs are computationally costly to reconstruct and usually become infeasible for more than few tens of genomes. Recently, Topological Data Analysis (TDA) methods have been proposed as robust and scalable methods that can capture the genetic scale and frequency of recombination. We build on previous TDA developments for detecting and quantifying recombination, and present a novel framework that can be applied to hundreds of genomes and can be interpreted in terms of minimal histories of mutation and recombination events, quantifying the scales and identifying the genomic locations of recombinations. For that aim, we extend the notion of barcodes in persistent homology, largely increasing their sensitivity to recombination, and present a new type of summary graph (topological ARG, or tARG), analogous to ARGs, that capture ensembles of minimal recombination histories. We implement this framework in a software package, called TARGet, and apply it to several examples, including small migration between different populations and horizontal evolution in finches inhabiting the Gal\'apagos Islands.
]]></description>
<dc:subject>bioinformatics cladistics taxonomy inference algorithms topology rather-interesting representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d55ab49e29ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cladistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:taxonomy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:topology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1407.2812">
    <title>[1407.2812] Rate-Optimal Detection of Very Short Signal Segments</title>
    <dc:date>2015-09-30T11:57:30+00:00</dc:date>
    <link>http://arxiv.org/abs/1407.2812</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Motivated by a range of applications in engineering and genomics, we consider in this paper detection of very short signal segments in three settings: signals with known shape, arbitrary signals, and smooth signals. Optimal rates of detection are established for the three cases and rate-optimal detectors are constructed. The detectors are easily implementable and are based on scanning with linear and quadratic statistics. Our analysis reveals both similarities and differences in the strategy and fundamental difficulty of detection among these three settings.
]]></description>
<dc:subject>machine-learning bioinformatics probability-theory nudge-targets signal-processing information-theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dd6ee046718b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1509.02975">
    <title>[1509.02975] De Bruijn entropy and string similarity</title>
    <dc:date>2015-09-20T11:25:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1509.02975</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce the notion of de Bruijn entropy of an Eulerian quiver and show how the corresponding relative entropy can be applied to practical string similarity problems. This approach explicitly links the combinatorial and information-theoretical properties of words and its performance is superior to edit distances in many respects and competitive in most others. The computational complexity of our current implementation is parametrically tunable between linear and cubic, and we outline how an optimized linear algebra subroutine can reduce the cubic complexity to approximately linear. Numerous examples are provided, including a realistic application to molecular phylogenetics.
]]></description>
<dc:subject>strings metrics clustering similarity feature-construction information-theory bioinformatics algorithms rather-interesting nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4ddbd2e129b9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:strings"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:similarity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.4967">
    <title>[1412.4967] Sparse, guided feature connections in an Abstract Deep Network</title>
    <dc:date>2015-09-13T21:56:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.4967</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present a technique for developing a network of re-used features, where the topology is formed using a coarse learning method, that allows gradient-descent fine tuning, known as an Abstract Deep Network (ADN). New features are built based on observed co-occurrences, and the network is maintained using a selection process related to evolutionary algorithms. This allows coarse ex- ploration of the problem space, effective for irregular domains, while gradient descent allows pre- cise solutions. Accuracy on standard UCI and Protein-Structure Prediction problems is comparable with benchmark SVM and optimized GBML approaches, and shows scalability for addressing large problems. The discrete implementation is symbolic, allowing interpretability, while the continuous method using fine-tuning shows improved accuracy. The binary multiplexer problem is explored, as an irregular domain that does not support gradient descent learning, showing solution to the bench- mark 135-bit problem. A convolutional implementation is demonstrated on image classification, showing an error-rate of 0.79% on the MNIST problem, without a pre-defined topology. The ADN system provides a method for developing a very sparse, deep feature topology, based on observed relationships between features, that is able to find solutions in irregular domains, and initialize a network prior to gradient descent learning.
]]></description>
<dc:subject>feature-extraction deep-learning bioinformatics rather-interesting horse-races algorithms machine-learning nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5846b66126f2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1303.3692">
    <title>[1303.3692] Ultra-fast Multiple Genome Sequence Matching Using GPU</title>
    <dc:date>2015-09-06T14:34:02+00:00</dc:date>
    <link>http://arxiv.org/abs/1303.3692</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, a contrastive evaluation of massively parallel implementations of suffix tree and suffix array to accelerate genome sequence matching are proposed based on Intel Core i7 3770K quad-core and NVIDIA GeForce GTX680 GPU. Besides suffix array only held approximately 20%~30% of the space relative to suffix tree, the coalesced binary search and tile optimization make suffix array clearly outperform suffix tree using GPU. Consequently, the experimental results show that multiple genome sequence matching based on suffix array is more than 99 times speedup than that of CPU serial implementation. There is no doubt that massively parallel matching algorithm based on suffix array is an efficient approach to high-performance bioinformatics applications.
]]></description>
<dc:subject>GPU bioinformatics algorithms to-learn</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:467cff5c87f7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:GPU"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-learn"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2015/08/21/025262">
    <title>A Graph Theoretical Approach to Data Fusion | bioRxiv</title>
    <dc:date>2015-08-28T23:29:43+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2015/08/21/025262</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The rapid development of high throughput experimental techniques has resulted in a growing diversity of genomic datasets being produced and requiring analysis. A variety of computational techniques allow us to analyse such data and to model the biological processes behind them. However, it is increasingly being recognised that we can gain deeper understanding by combining the insights obtained from multiple, diverse datasets. We therefore require scalable computational approaches for data fusion. We propose a novel methodology for scalable unsupervised data fusion. Our technique exploits network representations of the data in order to identify (and quantify) similarities among the datasets. We may work within the Bayesian formalism, using Bayesian nonparametric approaches to model each dataset; or (for fast, approximate, and massive scale data fusion) can naturally switch to more heuristic modelling techniques. An advantage of the proposed approach is that each dataset can initially be modelled independently (and therefore in parallel), before applying a fast post-processing step in order to perform data fusion. This allows us to incorporate new experimental data in an online fashion, without having to rerun all of the analysis. The methodology can be applied to genomic scale datasets and we demonstrate its applicability on examples from the literature, using a broad range of genomic datasets, and also on a recent gene expression dataset from Sporadic inclusion body myositis.

]]></description>
<dc:subject>data-fusion bioinformatics medinformatics statistics algorithms rather-interesting nudge-targets consider:feature-discovery consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f6d2ae6a30b7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-fusion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:medinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1508.04174">
    <title>[1508.04174] New Scaling Relation for Information Transfer in Biological Networks</title>
    <dc:date>2015-08-22T12:32:38+00:00</dc:date>
    <link>http://arxiv.org/abs/1508.04174</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Living systems are often described utilizing informational analogies. An important open question is whether information is merely a useful conceptual metaphor, or intrinsic to the operation of biological systems. To address this question, we provide a rigorous case study of the informational architecture of two representative biological networks: the Boolean network model for the cell-cycle regulatory network of the fission yeast S. pombe and that of the budding yeast S. cerevisiae. We compare our results for these biological networks to the same analysis performed on ensembles of two different types of random networks. We show that both biological networks share features in common that are not shared by either ensemble. In particular, the biological networks in our study, on average, process more information than the random networks. They also exhibit a scaling relation in information transferred between nodes that distinguishes them from either ensemble: even when compared to the ensemble of random networks that shares important topological properties, such as a scale-free structure. We show that the most biologically distinct regime of this scaling relation is associated with the dynamics and function of the biological networks. Information processing in biological networks is therefore interpreted as an emergent property of topology (causal structure) and dynamics (function). These results demonstrate quantitatively how the informational architecture of biologically evolved networks can distinguish them from other classes of network architecture that do not share the same informational properties.
]]></description>
<dc:subject>network-theory complexology information-theory bioinformatics nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:adf398c3dc4a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complexology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.1074">
    <title>[1412.1074] Learning interpretable models of phenotypes from whole genome sequences with the Set Covering Machine</title>
    <dc:date>2015-08-09T14:51:25+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.1074</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The increased affordability of whole genome sequencing has motivated its use for phenotypic studies. We address the problem of learning interpretable models for discrete phenotypes from whole genomes. We propose a general approach that relies on the Set Covering Machine and a k-mer representation of the genomes. We show results for the problem of predicting the resistance of Pseudomonas Aeruginosa, an important human pathogen, against 4 antibiotics. Our results demonstrate that extremely sparse models which are biologically relevant can be learnt using this approach.
]]></description>
<dc:subject>bioinformatics genomics modeling modeling-is-not-mathematics representation interpretability performance-measure nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3301527c1269/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genomics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>