{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:04:56Z","timestamp":1775041496217,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T00:00:00Z","timestamp":1707436800000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Impuls- und Vernetzungfond of the Helmholtz Association"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The accurate prediction of how mutations change biophysical properties of proteins or RNA is a major goal in computational biology with tremendous impacts on protein design and genetic variant interpretation. Evolutionary approaches such as coevolution can help solving this issue.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present pycofitness, a standalone Python-based software package for the in silico mutagenesis of protein and RNA sequences. It is based on coevolution and, more specifically, on a popular inverse statistical approach, namely direct coupling analysis by pseudo-likelihood maximization. Its efficient implementation and user-friendly command line interface make it an easy-to-use tool even for researchers with no bioinformatics background. To illustrate its strengths, we present three applications in which pycofitness efficiently predicts the deleteriousness of genetic variants and the effect of mutations on protein fitness and thermodynamic stability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/KIT-MBS\/pycofitness.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae074","type":"journal-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T23:09:33Z","timestamp":1707520173000},"source":"Crossref","is-referenced-by-count":9,"title":["pycofitness\u2014Evaluating the fitness landscape of RNA and protein sequences"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2916-022X","authenticated-orcid":false,"given":"Fabrizio","family":"Pucci","sequence":"first","affiliation":[{"name":"Computational Biology and Bioinformatics, Universit\u00e9 Libre de Bruxelles , 1050 Brussels, Belgium"},{"name":"Interuniversity Institute of Bioinformatics in Brussels , 1050 Brussels, Belgium"}]},{"given":"Mehari B","family":"Zerihun","sequence":"additional","affiliation":[{"name":"John von Neumann Institute for Computing, J\u00fclich Supercomputer Centre , 52428 J\u00fclich, Germany"}]},{"given":"Marianne","family":"Rooman","sequence":"additional","affiliation":[{"name":"Computational Biology and Bioinformatics, Universit\u00e9 Libre de Bruxelles , 1050 Brussels, Belgium"},{"name":"Interuniversity Institute of Bioinformatics in Brussels , 1050 Brussels, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0534-502X","authenticated-orcid":false,"given":"Alexander","family":"Schug","sequence":"additional","affiliation":[{"name":"John von Neumann Institute for Computing, J\u00fclich Supercomputer Centre , 52428 J\u00fclich, Germany"},{"name":"Department of Biology, University of Duisburg-Essen , D-45141 Essen, Germany"}]}],"member":"286","published-online":{"date-parts":[[2024,2,9]]},"reference":[{"key":"2024022120061138400_btae074-B1","doi-asserted-by":"crossref","first-page":"158","DOI":"10.3389\/fgene.2014.00158","article-title":"Transfer RNA and human disease","volume":"5","author":"Abbott","year":"2014","journal-title":"Front Genet"},{"key":"2024022120061138400_btae074-B2","doi-asserted-by":"crossref","first-page":"e92721","DOI":"10.1371\/journal.pone.0092721","article-title":"Fast and accurate multivariate gaussian modeling of protein families: predicting residue contacts and protein-interaction partners","volume":"9","author":"Baldassi","year":"2014","journal-title":"PLoS One"},{"key":"2024022120061138400_btae074-B3","doi-asserted-by":"crossref","first-page":"3054","DOI":"10.1093\/molbev\/msw188","article-title":"Connecting the sequence-space of bacterial signaling proteins to phenotypes using coevolutionary landscapes","volume":"33","author":"Cheng","year":"2016","journal-title":"Mol Biol Evol"},{"key":"2024022120061138400_btae074-B4","doi-asserted-by":"crossref","first-page":"032601","DOI":"10.1088\/1361-6633\/aa9965","article-title":"Inverse statistical physics of protein sequences: a key issues review","volume":"81","author":"Cocco","year":"2018","journal-title":"Rep Prog Phys"},{"key":"2024022120061138400_btae074-B5","doi-asserted-by":"crossref","first-page":"143001","DOI":"10.1088\/1361-648X\/aa5c76","article-title":"Computational protein design: a review","volume":"29","author":"Coluzza","year":"2017","journal-title":"J Phys Condensed Matter"},{"key":"2024022120061138400_btae074-B6","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1261\/rna.074179.119","article-title":"Assessing the accuracy of direct-coupling analysis for RNA contact prediction","volume":"26","author":"Cuturello","year":"2020","journal-title":"RNA"},{"key":"2024022120061138400_btae074-B7","doi-asserted-by":"crossref","first-page":"E1733","DOI":"10.1073\/pnas.1201301109","article-title":"Structural basis of histidine kinase autophosphorylation deduced by integrating genomics, molecular dynamics, and mutagenesis","volume":"109","author":"Dago","year":"2012","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B8","first-page":"10444","article-title":"Direct-coupling analysis of nucleotide coevolution facilitates RNA secondary and tertiary structure prediction","volume":"43","author":"De Leonardis","year":"2015","journal-title":"Nucl. Acids Res"},{"key":"2024022120061138400_btae074-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1103\/PhysRevE.87.012707","article-title":"Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models","volume":"87","author":"Ekeberg","year":"2013","journal-title":"Phys Rev E"},{"key":"2024022120061138400_btae074-B10","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.sbi.2017.09.006","article-title":"Frustration, function and folding","volume":"48","author":"Ferreiro","year":"2018","journal-title":"Curr Opin Struct Biol"},{"key":"2024022120061138400_btae074-B11","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1093\/molbev\/msv211","article-title":"Coevolutionary landscape inference and the context-dependence of mutations in beta-lactamase TEM-1","volume":"33","author":"Figliuzzi","year":"2016","journal-title":"Mol Biol Evol"},{"key":"2024022120061138400_btae074-B12","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1093\/molbev\/msx095","article-title":"Inference of epistatic effects leading to entrenchment and drug resistance in HIV-1 protease","volume":"34","author":"Flynn","year":"2017","journal-title":"Mol Biol Evol"},{"key":"2024022120061138400_btae074-B13","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/s41586-021-04043-8","article-title":"Disease variant prediction with deep generative models of evolutionary data","volume":"599","author":"Frazer","year":"2021","journal-title":"Nature"},{"key":"2024022120061138400_btae074-B14","doi-asserted-by":"crossref","first-page":"15387","DOI":"10.1038\/s41598-020-72404-w","article-title":"Identification of pathogenic missense mutations using protein stability predictors","volume":"10","author":"Gerasimavicius","year":"2020","journal-title":"Sci Rep"},{"key":"2024022120061138400_btae074-B15","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1016\/j.cell.2012.04.012","article-title":"Three-dimensional structures of membrane proteins from genomic sequencing","volume":"149","author":"Hopf","year":"2012","journal-title":"Cell"},{"key":"2024022120061138400_btae074-B16","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1038\/nbt.3769","article-title":"Mutation effects predicted from sequence co-variation","volume":"35","author":"Hopf","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2024022120061138400_btae074-B17","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1093\/bioinformatics\/bty862","article-title":"The EVcouplings Python framework for coevolutionary sequence analysis","volume":"35","author":"Hopf","year":"2018","journal-title":"Bioinformatics"},{"key":"2024022120061138400_btae074-B18","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.1093\/bioinformatics\/btab034","article-title":"SWOTein: a structure-based approach to predict stability strengths and weaknesses of proteins","volume":"37","author":"Hou","year":"2021","journal-title":"Bioinformatics"},{"key":"2024022120061138400_btae074-B19","doi-asserted-by":"crossref","first-page":"28201","DOI":"10.1073\/pnas.2002660117","article-title":"Comprehensive characterization of amino acid positions in protein structures reveals molecular effect of missense variants","volume":"117","author":"Iqbal","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B20","doi-asserted-by":"crossref","first-page":"D192","DOI":"10.1093\/nar\/gkaa1047","article-title":"Rfam 14: expanded coverage of metagenomic, viral and microRNA families","volume":"49","author":"Kalvari","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024022120061138400_btae074-B21","doi-asserted-by":"crossref","first-page":"D1062","DOI":"10.1093\/nar\/gkx1153","article-title":"ClinVar: improving access to variant interpretations and supporting evidence","volume":"46","author":"Landrum","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2024022120061138400_btae074-B22","doi-asserted-by":"crossref","first-page":"e28766","DOI":"10.1371\/journal.pone.0028766","article-title":"Protein 3D structure computed from evolutionary sequence variation","volume":"6","author":"Marks","year":"2011","journal-title":"PLoS One"},{"key":"2024022120061138400_btae074-B23","doi-asserted-by":"crossref","first-page":"6302","DOI":"10.1038\/s41467-021-26529-9","article-title":"The generative capacity of probabilistic protein sequence models","volume":"12","author":"McGee","year":"2021","journal-title":"Nat Commun"},{"key":"2024022120061138400_btae074-B24","doi-asserted-by":"crossref","first-page":"E1293","DOI":"10.1073\/pnas.1111471108","article-title":"Direct-coupling analysis of residue coevolution captures native contacts across many protein families","volume":"108","author":"Morcos","year":"2011","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B25","doi-asserted-by":"crossref","first-page":"20533","DOI":"10.1073\/pnas.1315625110","article-title":"Coevolutionary signals across protein lineages help capture multiple protein conformations","volume":"110","author":"Morcos","year":"2013","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B26","doi-asserted-by":"crossref","first-page":"2933","DOI":"10.1093\/bioinformatics\/btt509","article-title":"Infernal 1.1: 100-fold faster RNA homology searches","volume":"29","author":"Nawrocki","year":"2013","journal-title":"Bioinformatics"},{"key":"2024022120061138400_btae074-B27","doi-asserted-by":"crossref","first-page":"16367","DOI":"10.1073\/pnas.1903888116","article-title":"Protein stability engineering insights revealed by domain-wide comprehensive mutagenesis","volume":"116","author":"Nisthal","year":"2019","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B28","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1515\/hsz-2019-0156","article-title":"Direct coupling analysis improves the identification of beneficial amino acid mutations for the functional thermostabilization of a delicate decarboxylase","volume":"400","author":"Peng","year":"2019","journal-title":"Biol Chem"},{"key":"2024022120061138400_btae074-B29","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.ymeth.2019.04.012","article-title":"Shedding light on the dark matter of the biomolecular structural universe: progress in RNA 3D structure prediction","volume":"162-163","author":"Pucci","year":"2019","journal-title":"Methods"},{"key":"2024022120061138400_btae074-B30","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.sbi.2021.11.001","article-title":"Artificial intelligence challenges for predicting the impact of mutations on protein stability","volume":"72","author":"Pucci","year":"2022","journal-title":"Curr Opin Struct Biol"},{"key":"2024022120061138400_btae074-B31","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1126\/science.aba3304","article-title":"An evolution-based model for designing chorismate mutase enzymes","volume":"369","author":"Russ","year":"2020","journal-title":"Science"},{"key":"2024022120061138400_btae074-B32","doi-asserted-by":"crossref","first-page":"22124","DOI":"10.1073\/pnas.0912100106","article-title":"High-resolution protein complexes from integrating genomic information with molecular simulation","volume":"106","author":"Schug","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B33","doi-asserted-by":"crossref","first-page":"5800","DOI":"10.1038\/s41467-021-25756-4","article-title":"Efficient generative modeling of protein sequences using simple autoregressive models","volume":"12","author":"Trinquier","year":"2021","journal-title":"Nat Commun"},{"key":"2024022120061138400_btae074-B34","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1073\/pnas.0805923106","article-title":"Identification of direct residue contacts in protein\u2013protein interaction by message passing","volume":"106","author":"Weigt","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024022120061138400_btae074-B35","doi-asserted-by":"crossref","first-page":"957","DOI":"10.15252\/msb.20177908","article-title":"A framework for exhaustively mapping functional missense variants","volume":"13","author":"Weile","year":"2017","journal-title":"Mol Syst Biol"},{"key":"2024022120061138400_btae074-B36","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1016\/j.cell.2016.03.030","article-title":"3D RNA and functional interactions from evolutionary couplings","volume":"165","author":"Weinreb","year":"2016","journal-title":"Cell"},{"key":"2024022120061138400_btae074-B37","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1111\/j.1469-0691.2006.01492.x","article-title":"The emergence of antibiotic resistance by mutation","volume":"13","author":"Woodford","year":"2007","journal-title":"Clin Microbiol Infect"},{"key":"2024022120061138400_btae074-B38","doi-asserted-by":"crossref","first-page":"2264","DOI":"10.1093\/bioinformatics\/btz892","article-title":"pydca v1.0: a comprehensive software for direct coupling analysis of RNA and protein sequences","volume":"36","author":"Zerihun","year":"2020","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae074\/56644241\/btae074.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/2\/btae074\/56731888\/btae074.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/2\/btae074\/56731888\/btae074.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T20:06:41Z","timestamp":1708546001000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae074\/7604531"}},"subtitle":[],"editor":[{"given":"Yann","family":"Ponty","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae074","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2,1]]},"published":{"date-parts":[[2024,2,1]]},"article-number":"btae074"}}