<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Yang, Mi</style></author><author><style face="normal" font="default" size="100%">Petralia, Francesca</style></author><author><style face="normal" font="default" size="100%">Li, Zhi</style></author><author><style face="normal" font="default" size="100%">Li, Hongyang</style></author><author><style face="normal" font="default" size="100%">Ma, Weiping</style></author><author><style face="normal" font="default" size="100%">Song, Xiaoyu</style></author><author><style face="normal" font="default" size="100%">Kim, Sunkyu</style></author><author><style face="normal" font="default" size="100%">Lee, Heewon</style></author><author><style face="normal" font="default" size="100%">Yu, Han</style></author><author><style face="normal" font="default" size="100%">Lee, Bora</style></author><author><style face="normal" font="default" size="100%">Bae, Seohui</style></author><author><style face="normal" font="default" size="100%">Heo, Eunji</style></author><author><style face="normal" font="default" size="100%">Kaczmarczyk, Jan</style></author><author><style face="normal" font="default" size="100%">Stępniak, Piotr</style></author><author><style face="normal" font="default" size="100%">Warchoł, Michał</style></author><author><style face="normal" font="default" size="100%">Yu, Thomas</style></author><author><style face="normal" font="default" size="100%">Calinawan, Anna P</style></author><author><style face="normal" font="default" size="100%">Boutros, Paul C</style></author><author><style face="normal" font="default" size="100%">Payne, Samuel H</style></author><author><style face="normal" font="default" size="100%">Reva, Boris</style></author><author><style face="normal" font="default" size="100%">Boja, Emily</style></author><author><style face="normal" font="default" size="100%">Rodriguez, Henry</style></author><author><style face="normal" font="default" size="100%">Stolovitzky, Gustavo</style></author><author><style face="normal" font="default" size="100%">Guan, Yuanfang</style></author><author><style face="normal" font="default" size="100%">Kang, Jaewoo</style></author><author><style face="normal" font="default" size="100%">Wang, Pei</style></author><author><style face="normal" font="default" size="100%">Fenyö, David</style></author><author><style face="normal" font="default" size="100%">Saez-Rodriguez, Julio</style></author></authors><translated-authors><author><style face="normal" font="default" size="100%">NCI-CPTAC-DREAM Consortium</style></author></translated-authors></contributors><titles><title><style face="normal" font="default" size="100%">Community Assessment of the Predictability of Cancer Protein and Phosphoprotein Levels from Genomics and Transcriptomics.</style></title><secondary-title><style face="normal" font="default" size="100%">Cell Syst</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Cell Syst</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Crowdsourcing</style></keyword><keyword><style  face="normal" font="default" size="100%">Female</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Male</style></keyword><keyword><style  face="normal" font="default" size="100%">Neoplasms</style></keyword><keyword><style  face="normal" font="default" size="100%">Phosphoproteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcriptome</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2020 08 26</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">11</style></volume><pages><style face="normal" font="default" size="100%">186-195.e9</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Cancer is driven by genomic alterations, but the processes causing this disease are largely performed by proteins. However, proteins are harder and more expensive to measure than genes and transcripts. To catalyze developments of methods to infer protein levels from other omics measurements, we leveraged crowdsourcing via the NCI-CPTAC DREAM proteogenomic challenge. We asked for methods to predict protein and phosphorylation levels from genomic and transcriptomic data in cancer patients. The best performance was achieved by an ensemble of models, including as predictors transcript level of the corresponding genes, interaction between genes, conservation across tumor types, and phosphosite proximity for phosphorylation prediction. Proteins from metabolic pathways and complexes were the best and worst predicted, respectively. The performance of even the best-performing model was modest, suggesting that many proteins are strongly regulated through translational control and degradation. Our results set a reference for the limitations of computational inference in proteogenomics. A record of this paper's transparent peer review process is included in the Supplemental Information.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">2</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/32710834?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Loucera, Carlos</style></author><author><style face="normal" font="default" size="100%">Esteban-Medina, Marina</style></author><author><style face="normal" font="default" size="100%">Rian, Kinza</style></author><author><style face="normal" font="default" size="100%">Falco, Matias M</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Peña-Chilet, Maria</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Drug repurposing for COVID-19 using machine learning and mechanistic models of signal transduction circuits related to SARS-CoV-2 infection.</style></title><secondary-title><style face="normal" font="default" size="100%">Signal Transduct Target Ther</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Signal Transduct Target Ther</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Computational Chemistry</style></keyword><keyword><style  face="normal" font="default" size="100%">COVID-19</style></keyword><keyword><style  face="normal" font="default" size="100%">drug repositioning</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Molecular Docking Simulation</style></keyword><keyword><style  face="normal" font="default" size="100%">Molecular Targeted Therapy</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">SARS-CoV-2</style></keyword><keyword><style  face="normal" font="default" size="100%">Signal Transduction</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2020 12 11</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">5</style></volume><pages><style face="normal" font="default" size="100%">290</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><issue><style face="normal" font="default" size="100%">1</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/33311438?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Esteban-Medina, Marina</style></author><author><style face="normal" font="default" size="100%">Peña-Chilet, Maria</style></author><author><style face="normal" font="default" size="100%">Loucera, Carlos</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Exploring the druggable space around the Fanconi anemia pathway using machine learning and mechanistic models.</style></title><secondary-title><style face="normal" font="default" size="100%">BMC Bioinformatics</style></secondary-title><alt-title><style face="normal" font="default" size="100%">BMC Bioinformatics</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Databases, Factual</style></keyword><keyword><style  face="normal" font="default" size="100%">Fanconi Anemia</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Phenotype</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Signal Transduction</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2019 Jul 02</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">20</style></volume><pages><style face="normal" font="default" size="100%">370</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;BACKGROUND: &lt;/b&gt;In spite of the abundance of genomic data, predictive models that describe phenotypes as a function of gene expression or mutations are difficult to obtain because they are affected by the curse of dimensionality, given the disbalance between samples and candidate genes. And this is especially dramatic in scenarios in which the availability of samples is difficult, such as the case of rare diseases.&lt;/p&gt;&lt;p&gt;&lt;b&gt;RESULTS: &lt;/b&gt;The application of multi-output regression machine learning methodologies to predict the potential effect of external proteins over the signaling circuits that trigger Fanconi anemia related cell functionalities, inferred with a mechanistic model, allowed us to detect over 20 potential therapeutic targets.&lt;/p&gt;&lt;p&gt;&lt;b&gt;CONCLUSIONS: &lt;/b&gt;The use of artificial intelligence methods for the prediction of potentially causal relationships between proteins of interest and cell activities related with disease-related phenotypes opens promising avenues for the systematic search of new targets in rare diseases.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">1</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/31266445?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Amadoz, Alicia</style></author><author><style face="normal" font="default" size="100%">Sebastián-Leon, Patricia</style></author><author><style face="normal" font="default" size="100%">Vidal, Enrique</style></author><author><style face="normal" font="default" size="100%">Salavert, Francisco</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Using activation status of signaling pathways as mechanism-based biomarkers to predict drug sensitivity.</style></title><secondary-title><style face="normal" font="default" size="100%">Sci Rep</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Sci Rep</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Antineoplastic Agents</style></keyword><keyword><style  face="normal" font="default" size="100%">biomarkers</style></keyword><keyword><style  face="normal" font="default" size="100%">Cell Line, Tumor</style></keyword><keyword><style  face="normal" font="default" size="100%">Cell Survival</style></keyword><keyword><style  face="normal" font="default" size="100%">gene expression</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Lethal Dose 50</style></keyword><keyword><style  face="normal" font="default" size="100%">Neoplasms</style></keyword><keyword><style  face="normal" font="default" size="100%">Phosphorylation</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Signal Transduction</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2015</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2015 Dec 18</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">5</style></volume><pages><style face="normal" font="default" size="100%">18494</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Many complex traits, as drug response, are associated with changes in biological pathways rather than being caused by single gene alterations. Here, a predictive framework is presented in which gene expression data are recoded into activity statuses of signal transduction circuits (sub-pathways within signaling pathways that connect receptor proteins to final effector proteins that trigger cell actions). Such activity values are used as features by a prediction algorithm which can efficiently predict a continuous variable such as the IC50 value. The main advantage of this prediction method is that the features selected by the predictor, the signaling circuits, are themselves rich-informative, mechanism-based biomarkers which provide insight into or drug molecular mechanisms of action (MoA). &lt;/p&gt;</style></abstract><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/26678097?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">De Baets, Greet</style></author><author><style face="normal" font="default" size="100%">Van Durme, Joost</style></author><author><style face="normal" font="default" size="100%">Reumers, Joke</style></author><author><style face="normal" font="default" size="100%">Maurer-Stroh, Sebastian</style></author><author><style face="normal" font="default" size="100%">Vanhee, Peter</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Schymkowitz, Joost</style></author><author><style face="normal" font="default" size="100%">Rousseau, Frederic</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">SNPeffect 4.0: on-line prediction of molecular and structural effects of protein-coding variants.</style></title><secondary-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Databases, Protein</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Internet</style></keyword><keyword><style  face="normal" font="default" size="100%">Meta-Analysis as Topic</style></keyword><keyword><style  face="normal" font="default" size="100%">Phenotype</style></keyword><keyword><style  face="normal" font="default" size="100%">Polymorphism, Single Nucleotide</style></keyword><keyword><style  face="normal" font="default" size="100%">Protein Conformation</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2012</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2012 Jan</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">40</style></volume><pages><style face="normal" font="default" size="100%">D935-9</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Single nucleotide variants (SNVs) are, together with copy number variation, the primary source of variation in the human genome and are associated with phenotypic variation such as altered response to drug treatment and susceptibility to disease. Linking structural effects of non-synonymous SNVs to functional outcomes is a major issue in structural bioinformatics. The SNPeffect database (http://snpeffect.switchlab.org) uses sequence- and structure-based bioinformatics tools to predict the effect of protein-coding SNVs on the structural phenotype of proteins. It integrates aggregation prediction (TANGO), amyloid prediction (WALTZ), chaperone-binding prediction (LIMBO) and protein stability analysis (FoldX) for structural phenotyping. Additionally, SNPeffect holds information on affected catalytic sites and a number of post-translational modifications. The database contains all known human protein variants from UniProt, but users can now also submit custom protein variants for a SNPeffect analysis, including automated structure modeling. The new meta-analysis application allows plotting correlations between phenotypic features for a user-selected set of variants.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">Database issue</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/22075996?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Shi, W</style></author><author><style face="normal" font="default" size="100%">Bessarabova, M</style></author><author><style face="normal" font="default" size="100%">Dosymbekov, D</style></author><author><style face="normal" font="default" size="100%">Dezso, Z</style></author><author><style face="normal" font="default" size="100%">Nikolskaya, T</style></author><author><style face="normal" font="default" size="100%">Dudoladova, M</style></author><author><style face="normal" font="default" size="100%">Serebryiskaya, T</style></author><author><style face="normal" font="default" size="100%">Bugrim, A</style></author><author><style face="normal" font="default" size="100%">Guryanov, A</style></author><author><style face="normal" font="default" size="100%">Brennan, R J</style></author><author><style face="normal" font="default" size="100%">Shah, R</style></author><author><style face="normal" font="default" size="100%">Dopazo, J</style></author><author><style face="normal" font="default" size="100%">Chen, M</style></author><author><style face="normal" font="default" size="100%">Deng, Y</style></author><author><style face="normal" font="default" size="100%">Shi, T</style></author><author><style face="normal" font="default" size="100%">Jurman, G</style></author><author><style face="normal" font="default" size="100%">Furlanello, C</style></author><author><style face="normal" font="default" size="100%">Thomas, R S</style></author><author><style face="normal" font="default" size="100%">Corton, J C</style></author><author><style face="normal" font="default" size="100%">Tong, W</style></author><author><style face="normal" font="default" size="100%">Shi, L</style></author><author><style face="normal" font="default" size="100%">Nikolsky, Y</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Functional analysis of multiple genomic signatures demonstrates that classification algorithms choose phenotype-related genes.</style></title><secondary-title><style face="normal" font="default" size="100%">Pharmacogenomics J</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Pharmacogenomics J</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Genetic</style></keyword><keyword><style  face="normal" font="default" size="100%">Endpoint Determination</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Expression Profiling</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Neural Networks, Computer</style></keyword><keyword><style  face="normal" font="default" size="100%">Oligonucleotide Array Sequence Analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Phenotype</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive Value of Tests</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Quality Control</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2010 Aug</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">10</style></volume><pages><style face="normal" font="default" size="100%">310-23</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Gene expression signatures of toxicity and clinical response benefit both safety assessment and clinical practice; however, difficulties in connecting signature genes with the predicted end points have limited their application. The Microarray Quality Control Consortium II (MAQCII) project generated 262 signatures for ten clinical and three toxicological end points from six gene expression data sets, an unprecedented collection of diverse signatures that has permitted a wide-ranging analysis on the nature of such predictive models. A comprehensive analysis of the genes of these signatures and their nonredundant unions using ontology enrichment, biological network building and interactome connectivity analyses demonstrated the link between gene signatures and the biological basis of their predictive power. Different signatures for a given end point were more similar at the level of biological properties and transcriptional control than at the gene level. Signatures tended to be enriched in function and pathway in an end point and model-specific manner, and showed a topological bias for incoming interactions. Importantly, the level of biological similarity between different signatures for a given end point correlated positively with the accuracy of the signature predictions. These findings will aid the understanding, and application of predictive genomic signatures, and support their broader application in predictive medicine.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">4</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/20676069?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Minguez, Pablo</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Functional genomics and networks: new approaches in the extraction of complex gene modules.</style></title><secondary-title><style face="normal" font="default" size="100%">Expert Rev Proteomics</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Expert Rev Proteomics</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Gene Expression Regulation</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Regulatory Networks</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Protein Binding</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Systems biology</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2010 Feb</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">7</style></volume><pages><style face="normal" font="default" size="100%">55-63</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;The engine that makes the cell work is made of an intricate network of molecular interactions. Nowadays, the elements and relationships of this complex network can be studied with several types of high-throughput techniques. The dream of having a global picture of the cell from different perspectives that can jointly explain cell behavior is, at least technically, feasible. However, this task can only be accomplished by filling the gap between data and information. The availability of methods capable of accurately managing, integrating and analyzing the results from these experiments is crucial for this purpose. Here, we review the new challenges raised by the availability of different genomic data, as well as the new proposals presented to cope with the increasing data complexity. Special emphasis is given to approaches that explore the transcriptome trying to describe the modules of genes that account for the traits studied.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">1</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/20121476?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Reumers, Joke</style></author><author><style face="normal" font="default" size="100%">Conde, Lucia</style></author><author><style face="normal" font="default" size="100%">Medina, Ignacio</style></author><author><style face="normal" font="default" size="100%">Maurer-Stroh, Sebastian</style></author><author><style face="normal" font="default" size="100%">Van Durme, Joost</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Rousseau, Frederic</style></author><author><style face="normal" font="default" size="100%">Schymkowitz, Joost</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Joint annotation of coding and non-coding single nucleotide polymorphisms and mutations in the SNPeffect and PupaSuite databases.</style></title><secondary-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Amino Acid Substitution</style></keyword><keyword><style  face="normal" font="default" size="100%">Animals</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Genetic</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic Diseases, Inborn</style></keyword><keyword><style  face="normal" font="default" size="100%">HSP70 Heat-Shock Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Internet</style></keyword><keyword><style  face="normal" font="default" size="100%">Mice</style></keyword><keyword><style  face="normal" font="default" size="100%">MicroRNAs</style></keyword><keyword><style  face="normal" font="default" size="100%">mutation</style></keyword><keyword><style  face="normal" font="default" size="100%">Polymorphism, Single Nucleotide</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Rats</style></keyword><keyword><style  face="normal" font="default" size="100%">RNA Splice Sites</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Factors</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2008 Jan</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">36</style></volume><pages><style face="normal" font="default" size="100%">D825-9</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Single nucleotide polymorphisms (SNPs) are, together with copy number variation, the primary source of variation in the human genome. SNPs are associated with altered response to drug treatment, susceptibility to disease and other phenotypic variation. Furthermore, during genetic screens for disease-associated mutations in groups of patients and control individuals, the distinction between disease causing mutation and polymorphism is often unclear. Annotation of the functional and structural implications of single nucleotide changes thus provides valuable information to interpret and guide experiments. The SNPeffect and PupaSuite databases are now synchronized to deliver annotations for both non-coding and coding SNP, as well as annotations for the SwissProt set of human disease mutations. In addition, SNPeffect now contains predictions of Tango2: an improved aggregation detector, and Waltz: a novel predictor of amyloid-forming sequences, as well as improved predictors for regions that are recognized by the Hsp70 family of chaperones. The new PupaSuite version incorporates predictions for SNPs in silencers and miRNAs including their targets, as well as additional methods for predicting SNPs in TFBSs and splice sites. Also predictions for mouse and rat genomes have been added. In addition, a PupaSuite web service has been developed to enable data access, programmatically. The combined database holds annotations for 4,965,073 regulatory as well as 133,505 coding human SNPs and 14,935 disease mutations, and phenotypic descriptions of 43,797 human proteins and is accessible via http://snpeffect.vib.be and http://pupasuite.bioinfo.cipf.es/.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">Database issue</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/18086700?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Huerta-Cepas, Jaime</style></author><author><style face="normal" font="default" size="100%">Bueno, Anibal</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Gabaldón, Toni</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">PhylomeDB: a database for genome-wide collections of gene phylogenies.</style></title><secondary-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Base Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Escherichia coli</style></keyword><keyword><style  face="normal" font="default" size="100%">Genes</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">History, Ancient</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Phylogeny</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Saccharomyces cerevisiae</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Alignment</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2008 Jan</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">36</style></volume><pages><style face="normal" font="default" size="100%">D491-6</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;The complete collection of evolutionary histories of all genes in a genome, also known as phylome, constitutes a valuable source of information. The reconstruction of phylomes has been previously prevented by large demands of time and computer power, but is now feasible thanks to recent developments in computers and algorithms. To provide a publicly available repository of complete phylomes that allows researchers to access and store large-scale phylogenomic analyses, we have developed PhylomeDB. PhylomeDB is a database of complete phylomes derived for different genomes within a specific taxonomic range. All phylomes in the database are built using a high-quality phylogenetic pipeline that includes evolutionary model testing and alignment trimming phases. For each genome, PhylomeDB provides the alignments, phylogentic trees and tree-based orthology predictions for every single encoded protein. The current version of PhylomeDB includes the phylomes of Human, the yeast Saccharomyces cerevisiae and the bacterium Escherichia coli, comprising a total of 32 289 seed sequences with their corresponding alignments and 172 324 phylogenetic trees. PhylomeDB can be publicly accessed at http://phylomedb.bioinfo.cipf.es.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">Database issue</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/17962297?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Capriotti, Emidio</style></author><author><style face="normal" font="default" size="100%">Arbiza, Leonardo</style></author><author><style face="normal" font="default" size="100%">Casadio, Rita</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Dopazo, Hernán</style></author><author><style face="normal" font="default" size="100%">Marti-Renom, Marc A</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Use of estimated evolutionary strength at the codon level improves the prediction of disease-related protein mutations in humans.</style></title><secondary-title><style face="normal" font="default" size="100%">Hum Mutat</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Hum Mutat</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Codon</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Protein</style></keyword><keyword><style  face="normal" font="default" size="100%">DNA Mutational Analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Evolution, Molecular</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic Predisposition to Disease</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic Variation</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome, Human</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Iduronic Acid</style></keyword><keyword><style  face="normal" font="default" size="100%">Point Mutation</style></keyword><keyword><style  face="normal" font="default" size="100%">Polymorphism, Single Nucleotide</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Tumor Suppressor Protein p53</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2008 Jan</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">29</style></volume><pages><style face="normal" font="default" size="100%">198-204</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Predicting the functional impact of protein variation is one of the most challenging problems in bioinformatics. A rapidly growing number of genome-scale studies provide large amounts of experimental data, allowing the application of rigorous statistical approaches for predicting whether a given single point mutation has an impact on human health. Up until now, existing methods have limited their source data to either protein or gene information. Novel in this work, we take advantage of both and focus on protein evolutionary information by using estimated selective pressures at the codon level. Here we introduce a new method (SeqProfCod) to predict the likelihood that a given protein variant is associated with human disease or not. Our method relies on a support vector machine (SVM) classifier trained using three sources of information: protein sequence, multiple protein sequence alignments, and the estimation of selective pressure at the codon level. SeqProfCod has been benchmarked with a large dataset of 8,987 single point mutations from 1,434 human proteins from SWISS-PROT. It achieves 82% overall accuracy and a correlation coefficient of 0.59, indicating that the estimation of the selective pressure helps in predicting the functional impact of single-point mutations. Moreover, this study demonstrates the synergic effect of combining two sources of information for predicting the functional effects of protein variants: protein sequence/profile-based information and the evolutionary estimation of the selective pressures at the codon level. The results of large-scale application of SeqProfCod over all annotated point mutations in SWISS-PROT (available for download at http://sgu.bioinfo.cipf.es/services/Omidios/; last accessed: 24 August 2007), could be used to support clinical studies.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">1</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/17935148?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Marti-Renom, Marc A</style></author><author><style face="normal" font="default" size="100%">Pieper, Ursula</style></author><author><style face="normal" font="default" size="100%">Madhusudhan, M S</style></author><author><style face="normal" font="default" size="100%">Rossi, Andrea</style></author><author><style face="normal" font="default" size="100%">Eswar, Narayanan</style></author><author><style face="normal" font="default" size="100%">Davis, Fred P</style></author><author><style face="normal" font="default" size="100%">Al-Shahrour, Fátima</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author><author><style face="normal" font="default" size="100%">Sali, Andrej</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">DBAli tools: mining the protein structure space.</style></title><secondary-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Amino Acid Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Data Interpretation, Statistical</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Protein</style></keyword><keyword><style  face="normal" font="default" size="100%">Internet</style></keyword><keyword><style  face="normal" font="default" size="100%">Molecular Sequence Data</style></keyword><keyword><style  face="normal" font="default" size="100%">Protein Conformation</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Pseudomonas aeruginosa</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Alignment</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Analysis, Protein</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Homology, Amino Acid</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Structure-Activity Relationship</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2007</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2007 Jul</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">35</style></volume><pages><style face="normal" font="default" size="100%">W393-7</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;The DBAli tools use a comprehensive set of structural alignments in the DBAli database to leverage the structural information deposited in the Protein Data Bank (PDB). These tools include (i) the DBAlit program that allows users to input the 3D coordinates of a protein structure for comparison by MAMMOTH against all chains in the PDB; (ii) the AnnoLite and AnnoLyze programs that annotate a target structure based on its stored relationships to other structures; (iii) the ModClus program that clusters structures by sequence and structure similarities; (iv) the ModDom program that identifies domains as recurrent structural fragments and (v) an implementation of the COMPARER method in the SALIGN command in MODELLER that creates a multiple structure alignment for a set of related protein structures. Thus, the DBAli tools, which are freely accessible via the World Wide Web at http://salilab.org/DBAli/, allow users to mine the protein structure space by establishing relationships between protein structures and their functions.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">Web Server issue</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/17478513?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Minguez, Pablo</style></author><author><style face="normal" font="default" size="100%">Al-Shahrour, Fátima</style></author><author><style face="normal" font="default" size="100%">Montaner, David</style></author><author><style face="normal" font="default" size="100%">Dopazo, Joaquin</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Functional profiling of microarray experiments using text-mining derived bioentities.</style></title><secondary-title><style face="normal" font="default" size="100%">Bioinformatics</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Bioinformatics</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Artificial Intelligence</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Protein</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Expression Profiling</style></keyword><keyword><style  face="normal" font="default" size="100%">Information Storage and Retrieval</style></keyword><keyword><style  face="normal" font="default" size="100%">Natural Language Processing</style></keyword><keyword><style  face="normal" font="default" size="100%">Proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Research Design</style></keyword><keyword><style  face="normal" font="default" size="100%">Systems Integration</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2007</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2007 Nov 15</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">23</style></volume><pages><style face="normal" font="default" size="100%">3098-9</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;MOTIVATION: &lt;/b&gt;The increasing use of microarray technologies brought about a parallel demand in methods for the functional interpretation of the results. Beyond the conventional functional annotations for genes, such as gene ontology, pathways, etc. other sources of information are still to be exploited. Text-mining methods allow extracting informative terms (bioentities) with different functional, chemical, clinical, etc. meanings, that can be associated to genes. We show how to use these associations within an appropriate statistical framework and how to apply them through easy-to-use, web-based environments to the functional interpretation of microarray experiments. Functional enrichment and gene set enrichment tests using bioentities are presented.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">22</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/17855415?dopt=Abstract</style></custom1></record></records></xml>