{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:52:17Z","timestamp":1781286737955,"version":"3.54.1"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2020,8,11]],"date-time":"2020-08-11T00:00:00Z","timestamp":1597104000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Swedish E-science Research Council"},{"name":"Swedish National Infrastructure for Computing"},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2017-04609"],"award-info":[{"award-number":["2017-04609"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2016-03798"],"award-info":[{"award-number":["2016-03798"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Proteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure. Experimental identification of a protein\u2019s structure can be time-consuming, prohibitively expensive and not always possible. Alternatively, protein folding can be modeled using computational methods, which however are not guaranteed to always produce optimal results. GraphQA is a graph-based method to estimate the quality of protein models, that possesses favorable properties such as representation learning, explicit modeling of both sequential and 3D structure, geometric invariance and computational efficiency.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>GraphQA performs similarly to state-of-the-art methods despite using a relatively low number of input features. In addition, the graph network structure provides an improvement over the architecture used in ProQ4 operating on the same input features. Finally, the individual contributions of GraphQA components are carefully evaluated.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>PyTorch implementation, datasets, experiments and link to an evaluation server are available through this GitHub repository: github.com\/baldassarreFe\/graphqa.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa714","type":"journal-article","created":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T11:40:00Z","timestamp":1596627600000},"page":"360-366","source":"Crossref","is-referenced-by-count":105,"title":["GraphQA: protein model quality assessment using graph convolutional networks"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8152-767X","authenticated-orcid":false,"given":"Federico","family":"Baldassarre","sequence":"first","affiliation":[{"name":"Division of Robotics, Perception and Learning (RPL), KTH \u2013 Royal Institute of Technology , 10044 Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Men\u00e9ndez Hurtado","sequence":"additional","affiliation":[{"name":"Department of Intelligent Systems, Science for Life Laboratory, Stockholm University , Box 1031, 17121 Solna, Sweden"},{"name":"Department of Biochemistry and Biophysics, school of Electrical Engineering and Computer Science (EECS), Stockholm University , 10691 Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[{"name":"Department of Intelligent Systems, Science for Life Laboratory, Stockholm University , Box 1031, 17121 Solna, Sweden"},{"name":"Department of Biochemistry and Biophysics, school of Electrical Engineering and Computer Science (EECS), Stockholm University , 10691 Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hossein","family":"Azizpour","sequence":"additional","affiliation":[{"name":"Division of Robotics, Perception and Learning (RPL), KTH \u2013 Royal Institute of Technology , 10044 Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,8,11]]},"reference":[{"key":"2023051604091220600_btaa714-B1","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.cels.2019.03.006","article-title":"End-to-end differentiable learning of protein structure","volume":"8","author":"AlQuraishi","year":"2019","journal-title":"Cell Syst"},{"key":"2023051604091220600_btaa714-B2","author":"Anand","year":"2018"},{"key":"2023051604091220600_btaa714-B3","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1093\/bioinformatics\/bti770","article-title":"The SWISS-MODEL workspace: a web-based environment for protein structure homology modelling","volume":"22","author":"Arnold","year":"2006","journal-title":"Bioinformatics"},{"key":"2023051604091220600_btaa714-B4","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"Baehrens","year":"2010","journal-title":"J. Mach. Learn. Res"},{"key":"2023051604091220600_btaa714-B5","author":"Battaglia","year":"2018"},{"key":"2023051604091220600_btaa714-B6","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1002\/prot.25767","article-title":"Estimation of model accuracy in CASP13","volume":"87","author":"Cheng","year":"2019","journal-title":"Proteins"},{"key":"2023051604091220600_btaa714-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1515\/cmb-2019-0001","article-title":"AngularQA: protein model quality assessment with LSTM networks","volume":"7","author":"Conover","year":"2019","journal-title":"Comput. Math. Biophys"},{"key":"2023051604091220600_btaa714-B8","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1002\/prot.21669","article-title":"Assessment of predictions in the model quality assessment category","volume":"69","author":"Cozzetto","year":"2007","journal-title":"Proteins"},{"key":"2023051604091220600_btaa714-B9","first-page":"4046","article-title":"Deep convolutional networks for quality assessment of protein folds","volume":"34","author":"Derevyanko","year":"2018","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023051604091220600_btaa714-B10","first-page":"2224","author":"Duvenaud","year":"2015"},{"key":"2023051604091220600_btaa714-B11","first-page":"6","article-title":"De novo structure prediction with deeplearning based scoring","volume":"77","author":"Evans","year":"2018","journal-title":"Annu. Rev. Biochem"},{"key":"2023051604091220600_btaa714-B12","first-page":"6530","author":"Fout","year":"2017"},{"key":"2023051604091220600_btaa714-B13","first-page":"3371","author":"Gao","year":"2018"},{"key":"2023051604091220600_btaa714-B14","author":"Gilmer","year":"2017"},{"key":"2023051604091220600_btaa714-B15","author":"Gonzalez","year":"2018"},{"key":"2023051604091220600_btaa714-B16","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1002\/prot.25697","article-title":"Protein tertiary structure modeling driven by deep learning and contact distance prediction in casp13","volume":"87","author":"Hou","year":"2019","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023051604091220600_btaa714-B17","author":"Hurtado","year":"2018"},{"key":"2023051604091220600_btaa714-B18","author":"Ingraham","year":"2019"},{"key":"2023051604091220600_btaa714-B19","author":"Ingraham","year":"2019"},{"key":"2023051604091220600_btaa714-B20","author":"Jin","year":"2019"},{"key":"2023051604091220600_btaa714-B21","doi-asserted-by":"crossref","first-page":"3308","DOI":"10.1093\/bioinformatics\/bty341","article-title":"High precision in protein contact prediction using fully convolutional neural networks and minimal sequence features","volume":"34","author":"Jones","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051604091220600_btaa714-B22","first-page":"2577","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","author":"Kabsch","year":"1983","journal-title":"Biopolym. Orig. Res. Biomol"},{"key":"2023051604091220600_btaa714-B23","doi-asserted-by":"crossref","first-page":"2801","DOI":"10.1093\/bioinformatics\/bty1037","article-title":"Smooth orientation-dependent scoring function for coarse-grained protein quality assessment","volume":"35","author":"Karasikov","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051604091220600_btaa714-B24","author":"Kingma","year":"2014"},{"key":"2023051604091220600_btaa714-B25","author":"Kipf","year":"2017"},{"key":"2023051604091220600_btaa714-B26","author":"Li","year":"2018"},{"key":"2023051604091220600_btaa714-B27","author":"Li","year":"2018"},{"key":"2023051604091220600_btaa714-B28","first-page":"7795","author":"Liu","year":"2018"},{"key":"2023051604091220600_btaa714-B29","article-title":"Pcons: a neural-network-based consensus predictor that improves fold recognition","volume":"10, 2354\u20132362","author":"Lundstrom","year":"2001","journal-title":"Protein Sci"},{"key":"2023051604091220600_btaa714-B30","doi-asserted-by":"crossref","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"LDDT: a local superposition-free score for comparing protein structures and models using distance difference tests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"},{"key":"2023051604091220600_btaa714-B31","doi-asserted-by":"crossref","first-page":"W408","DOI":"10.1093\/nar\/gkz322","article-title":"IntFOLD: an integrated web resource for high performance protein structure and function prediction","volume":"47","author":"McGuffin","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023051604091220600_btaa714-B32","doi-asserted-by":"crossref","first-page":"W408","DOI":"10.1093\/nar\/gkz322","article-title":"IntFOLD: an integrated web resource for high performance protein structure and function prediction","volume":"47","author":"McGuffin","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023051604091220600_btaa714-B33","doi-asserted-by":"crossref","first-page":"ii","DOI":"10.1002\/prot.340230303","article-title":"A large-scale experiment to assess protein structure prediction methods","volume":"23","author":"Moult","year":"1995","journal-title":"Proteins"},{"key":"2023051604091220600_btaa714-B34","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1002\/(SICI)1097-0134(1999)37:3+<2::AID-PROT2>3.0.CO;2-2","article-title":"Critical assessment of methods of protein structure predictions (CASP): round III","volume":"3","author":"Moult","year":"1999","journal-title":"Proteins"},{"key":"2023051604091220600_btaa714-B35","author":"Narasimhan","year":"2018"},{"key":"2023051604091220600_btaa714-B36","author":"Niepert","year":"2016"},{"key":"2023051604091220600_btaa714-B37","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1002\/prot.24172","article-title":"CAD-score: a new contact area difference-based function for evaluation of protein structural models","volume":"81","author":"Olechnovi\u010d","year":"2013","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023051604091220600_btaa714-B38","author":"Pag\u00e8s","year":"2018"},{"key":"2023051604091220600_btaa714-B39","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1186\/1471-2105-13-224","article-title":"Improved model quality assessment using ProQ2","volume":"13","author":"Ray","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2023051604091220600_btaa714-B40","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/S0022-2836(05)80007-5","article-title":"Redefining the goals of protein secondary structure prediction","volume":"235","author":"Rost","year":"1994","journal-title":"J. Mol. Biol"},{"key":"2023051604091220600_btaa714-B41","author":"Simonovsky","year":"2018"},{"key":"2023051604091220600_btaa714-B42","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1093\/bioinformatics\/btz828","article-title":"Qmeandisco-distance constraints applied on model quality estimation","volume":"36","author":"Studer","year":"2020","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023051604091220600_btaa714-B43","doi-asserted-by":"crossref","first-page":"33509","DOI":"10.1038\/srep33509","article-title":"ProQ3: improved model quality assessments using Rosetta energy terms","volume":"6","author":"Uziela","year":"2016","journal-title":"Sci. Rep"},{"key":"2023051604091220600_btaa714-B44","first-page":"1578","article-title":"ProQ3D: improved model quality assessments using deep learning","volume":"33","author":"Uziela","year":"2017","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023051604091220600_btaa714-B45","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1002\/prot.25492","article-title":"Improved protein model quality assessments by changing the target function","volume":"86","author":"Uziela","year":"2018","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023051604091220600_btaa714-B46","article-title":"Can correct protein models be identified?","volume":"12, 1073--1086","author":"Wallner","year":"2003","journal-title":"Protein Sci"},{"key":"2023051604091220600_btaa714-B47","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1110\/ps.051799606","article-title":"Can correct regions in protein models be identified","volume":"15","author":"Wallner","year":"2006","journal-title":"Protein Sci"},{"key":"2023051604091220600_btaa714-B48","doi-asserted-by":"crossref","first-page":"e1005324","DOI":"10.1371\/journal.pcbi.1005324","article-title":"Accurate de novo prediction of protein contact map by ultra-deep learning model","volume":"13","author":"Wang","year":"2017","journal-title":"PLoS Comput. Biol"},{"key":"2023051604091220600_btaa714-B49","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1002\/prot.25804","article-title":"Assessment of protein model structure accuracy estimation in casp13: challenges in the era of deep learning","volume":"87","author":"Won","year":"2019","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023051604091220600_btaa714-B50","doi-asserted-by":"crossref","first-page":"16856","DOI":"10.1073\/pnas.1821309116","article-title":"Distance-based protein folding powered by deep learning","volume":"116","author":"Xu","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051604091220600_btaa714-B51","author":"You","year":"2018"},{"key":"2023051604091220600_btaa714-B52","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1093\/nar\/gkg571","article-title":"LGA: a method for finding 3D similarities in protein structures","volume":"31","author":"Zemla","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2023051604091220600_btaa714-B53","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1002\/prot.20264","article-title":"Scoring function for automated assessment of protein structure template quality","volume":"57","author":"Zhang","year":"2004","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023051604091220600_btaa714-B54","doi-asserted-by":"crossref","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa714\/34192500\/btaa714.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/3\/360\/50326072\/btaa714.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/3\/360\/50326072\/btaa714.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T04:10:37Z","timestamp":1684210237000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/3\/360\/5891171"}},"subtitle":[],"editor":[{"given":"Yann","family":"Ponty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,8,11]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,4,20]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa714","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,2,1]]},"published":{"date-parts":[[2020,8,11]]}}}