{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:21:05Z","timestamp":1781882465766,"version":"3.54.5"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2017,12,8]],"date-time":"2017-12-08T00:00:00Z","timestamp":1512691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01GM093123"],"award-info":[{"award-number":["R01GM093123"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Significant improvements in the prediction of protein residue\u2013residue contacts are observed in the recent years. These contacts, predicted using a variety of coevolution-based and machine learning methods, are the key contributors to the recent progress in ab initio protein structure prediction, as demonstrated in the recent CASP experiments. Continuing the development of new methods to reliably predict contact maps is essential to further improve ab initio structure prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In this paper we discuss DNCON2, an improved protein contact map predictor based on two-level deep convolutional neural networks. It consists of six convolutional neural networks\u2014the first five predict contacts at 6, 7.5, 8, 8.5 and 10\u2009\u00c5 distance thresholds, and the last one uses these five predictions as additional features to predict final contact maps. On the free-modeling datasets in CASP10, 11 and 12 experiments, DNCON2 achieves mean precisions of 35, 50 and 53.4%, respectively, higher than 30.6% by MetaPSICOV on CASP10 dataset, 34% by MetaPSICOV on CASP11 dataset and 46.3% by Raptor-X on CASP12 dataset, when top L\/5 long-range contacts are evaluated. We attribute the improved performance of DNCON2 to the inclusion of short- and medium-range contacts into training, two-level approach to prediction, use of the state-of-the-art optimization and activation functions, and a novel deep learning architecture that allows each filter in a convolutional layer to access all the input features of a protein of arbitrary length.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The web server of DNCON2 is at http:\/\/sysbio.rnet.missouri.edu\/dncon2\/ where training and testing datasets as well as the predictions for CASP10, 11 and 12 free-modeling datasets can also be downloaded. Its source code is available at https:\/\/github.com\/multicom-toolbox\/DNCON2\/.<\/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\/btx781","type":"journal-article","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T15:13:50Z","timestamp":1512659630000},"page":"1466-1472","source":"Crossref","is-referenced-by-count":152,"title":["DNCON2: improved protein contact prediction using two-level deep convolutional neural networks"],"prefix":"10.1093","volume":"34","author":[{"given":"Badri","family":"Adhikari","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, MO, USA"},{"name":"Informatics Institute, University of Missouri, Columbia, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2017,12,8]]},"reference":[{"key":"2023012713023475500_btx781-B1","doi-asserted-by":"crossref","first-page":"517.","DOI":"10.1186\/s12859-016-1404-z","article-title":"ConEVA: a toolbox for comprehensive assessment of protein contacts","volume":"17","author":"Adhikari","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2023012713023475500_btx781-B2","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1002\/prot.24829","article-title":"CONFOLD: residue\u2013residue contact-guided ab initio protein folding","volume":"83","author":"Adhikari","year":"2015","journal-title":"Proteins"},{"key":"2023012713023475500_btx781-B3","doi-asserted-by":"crossref","first-page":"W72","DOI":"10.1093\/nar\/gki396","article-title":"SCRATCH: a protein structure and structural feature prediction server","volume":"33","author":"Cheng","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2023012713023475500_btx781-B4","doi-asserted-by":"crossref","first-page":"S12.","DOI":"10.1186\/1471-2105-14-S14-S12","article-title":"A study and benchmark of DNcon: a method for protein residue\u2013residue contact prediction using deep networks","volume":"14","author":"Eickholt","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023012713023475500_btx781-B5","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1093\/bioinformatics\/bts598","article-title":"Predicting protein residue\u2013residue contacts using deep networks and boosting","volume":"28","author":"Eickholt","year":"2012","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B6","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","volume":"37","author":"Ioffe","year":"2015","journal-title":"Proc. 32nd Int. Conf. Mach. Learn"},{"key":"2023012713023475500_btx781-B7","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1186\/1471-2105-11-431","article-title":"Hidden Markov model speed heuristic and iterative HMM search procedure","volume":"11","author":"Johnson","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012713023475500_btx781-B8","first-page":"btu791","article-title":"MetaPSICOV: Combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins","volume":"31","author":"Jones","year":"2014","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B9","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1002\/prot.1171","article-title":"Predicting novel protein folds by using FRAGFOLD","volume":"45","author":"Jones","year":"2001","journal-title":"Proteins Struct. Funct. Genet"},{"key":"2023012713023475500_btx781-B10","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1006\/jmbi.1999.3091","article-title":"Protein secondary structure prediction based on position-specific scoring matrices","volume":"292","author":"Jones","year":"1999","journal-title":"J. Mol. Biol"},{"key":"2023012713023475500_btx781-B11","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1093\/bioinformatics\/btr638","article-title":"PSICOV: Precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments","volume":"28","author":"Jones","year":"2012","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B12","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/1471-2105-15-85","article-title":"FreeContact: fast and free software for protein contact prediction from residue co-evolution","volume":"15","author":"Kaj\u00e1n","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023012713023475500_btx781-B13","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1002\/prot.24982","article-title":"CASP 11 target classification","volume":"84","author":"Kinch","year":"2016","journal-title":"Proteins Struct. Funct. Bioinform"},{"key":"2023012713023475500_btx781-B14","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1002\/prot.24863","article-title":"Accurate contact predictions using covariation techniques and machine learning","volume":"84","author":"Kosciolek","year":"2015","journal-title":"Proteins Struct. Funct. Bioinform"},{"key":"2023012713023475500_btx781-B15","doi-asserted-by":"crossref","first-page":"e92197.","DOI":"10.1371\/journal.pone.0092197","article-title":"De novo structure prediction of globular proteins aided by sequence variation-derived contacts","volume":"9","author":"Kosciolek","year":"2014","journal-title":"PLoS One"},{"key":"2023012713023475500_btx781-B16","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1002\/prot.24950","article-title":"Analysis of free modeling predictions by RBO aleph in CASP11","volume":"84","author":"Mabrouk","year":"2016","journal-title":"Proteins"},{"key":"2023012713023475500_btx781-B17","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1038\/nbt.2419","article-title":"Protein structure prediction from sequence variation","volume":"30","author":"Marks","year":"2012","journal-title":"Nat. Biotechnol"},{"key":"2023012713023475500_btx781-B18","doi-asserted-by":"crossref","first-page":"i482","DOI":"10.1093\/bioinformatics\/btu458","article-title":"PconsFold: improved contact predictions improve protein models","volume":"30","author":"Michel","year":"2014","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B19","doi-asserted-by":"crossref","first-page":"i23","DOI":"10.1093\/bioinformatics\/btx239","article-title":"Large-scale structure prediction by improved contact predictions and model quality assessment","volume":"33","author":"Michel","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B20","doi-asserted-by":"crossref","first-page":"2859","DOI":"10.1093\/bioinformatics\/btx332","article-title":"Predicting accurate contacts in thousands of Pfam domain families using PconsC3","volume":"33","author":"Michel","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B21","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1002\/prot.24340","article-title":"Evaluation of residue\u2013residue contact prediction in CASP10","volume":"82","author":"Monastyrskyy","year":"2014","journal-title":"Proteins Struct. Funct. Bioinform"},{"key":"2023012713023475500_btx781-B22","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1002\/prot.23160","article-title":"Evaluation of residue\u2013residue contact predictions in CASP9","volume":"79","author":"Monastyrskyy","year":"2011","journal-title":"Proteins"},{"key":"2023012713023475500_btx781-B23","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1002\/prot.24943","article-title":"New encouraging developments in contact prediction: Assessment of the CASP11 results","volume":"84","author":"Monastyrskyy","year":"2016","journal-title":"Proteins Struct. Funct. Bioinform"},{"key":"2023012713023475500_btx781-B24","first-page":"807","author":"Nair","year":"2010"},{"key":"2023012713023475500_btx781-B25","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1002\/prot.24974","article-title":"Improved de novo structure prediction in CASP11 by incorporating coevolution information into Rosetta","volume":"84","author":"Ovchinnikov","year":"2016","journal-title":"Proteins Struct. Funct. Bioinform"},{"key":"2023012713023475500_btx781-B26","doi-asserted-by":"crossref","first-page":"3499","DOI":"10.1093\/bioinformatics\/btv390","article-title":"GDFuzz3D: a method for protein 3D structure reconstruction from contact maps, based on a non-Euclidean distance function","volume":"31","author":"Pietal","year":"2015","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B27","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nmeth.1818","article-title":"HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment","volume":"9","author":"Remmert","year":"2011","journal-title":"Nat. Methods"},{"key":"2023012713023475500_btx781-B28","doi-asserted-by":"crossref","first-page":"3128","DOI":"10.1093\/bioinformatics\/btu500","article-title":"CCMpred \u2013 Fast and precise prediction of protein residue\u2013residue contacts from correlated mutations","volume":"30","author":"Seemayer","year":"2014","journal-title":"Bioinformatics"},{"key":"2023012713023475500_btx781-B29","doi-asserted-by":"crossref","first-page":"e1003889","DOI":"10.1371\/journal.pcbi.1003889","article-title":"Improved contact predictions using the recognition of protein like contact patterns","volume":"10","author":"Skwark","year":"2014","journal-title":"PLoS Comput. Biol"},{"key":"2023012713023475500_btx781-B30","author":"Sutskever","year":"2013"},{"key":"2023012713023475500_btx781-B31","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":"2023012713023475500_btx781-B32","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1002\/prot.24065","article-title":"Ab initio protein structure assembly using continuous structure fragments and optimized knowledge-based force field","volume":"80","author":"Xu","year":"2012","journal-title":"Proteins"},{"key":"2023012713023475500_btx781-B33","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1002\/prot.24930","article-title":"Integration of QUARK and I-TASSER for ab initio protein structure prediction in CASP11","volume":"84","author":"Zhang","year":"2016","journal-title":"Proteins Struct. Funct. Bioinform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/9\/1466\/48916255\/bioinformatics_34_9_1466.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/9\/1466\/48916255\/bioinformatics_34_9_1466.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T08:55:53Z","timestamp":1674809753000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/9\/1466\/4708303"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2017,12,8]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx781","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/222893","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,5,1]]},"published":{"date-parts":[[2017,12,8]]}}}