{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:38:00Z","timestamp":1740184680227,"version":"3.37.3"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2016,12,5]],"date-time":"2016-12-05T00:00:00Z","timestamp":1480896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["#31670723","#31470033"],"award-info":[{"award-number":["#31670723","#31470033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Innovation Center of Structural Biology"},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["#1059775","#1083450"],"award-info":[{"award-number":["#1059775","#1083450"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The quality of fragment library determines the efficiency of fragment assembly, an approach that is widely used in most de novo protein-structure prediction algorithms. Conventional fragment libraries are constructed mainly based on the identities of amino acids, sometimes facilitated by predicted information including dihedral angles and secondary structures. However, it remains challenging to identify near-native fragment structures with low sequence homology.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce a novel fragment-library-construction algorithm, LRFragLib, to improve the detection of near-native low-homology fragments of 7\u201310 residues, using a multi-stage, flexible selection protocol. Based on logistic regression scoring models, LRFragLib outperforms existing techniques by achieving a significantly higher precision and a comparable coverage on recent CASP protein sets in sampling near-native structures. The method also has a comparable computational efficiency to the fastest existing techniques with substantially reduced memory usage.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>The source code is available for download at http:\/\/166.111.152.91\/Downloads.html<\/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\/btw668","type":"journal-article","created":{"date-parts":[[2016,10,18]],"date-time":"2016-10-18T11:06:59Z","timestamp":1476788819000},"page":"677-684","source":"Crossref","is-referenced-by-count":11,"title":["LRFragLib: an effective algorithm to identify fragments for de novo protein structure prediction"],"prefix":"10.1093","volume":"33","author":[{"given":"Tong","family":"Wang","sequence":"first","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, School of Life Sciences, Tsinghua University, Beijing, China"},{"name":"Beijing Innovation Center of Structural Biology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuedong","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Glycomics and School of Information and Communication Technology, Griffith University, Gold Coast, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute for Glycomics and School of Information and Communication Technology, Griffith University, Gold Coast, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Gong","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, School of Life Sciences, Tsinghua University, Beijing, China"},{"name":"Beijing Innovation Center of Structural Biology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,12,5]]},"reference":[{"key":"2023020204431296800_btw668-B1","doi-asserted-by":"crossref","first-page":"136.","DOI":"10.1186\/s12859-015-0576-2","article-title":"Customised fragments libraries for protein structure prediction based on structural class annotations","volume":"16","author":"Abbass","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023020204431296800_btw668-B2","doi-asserted-by":"crossref","first-page":"17442","DOI":"10.1073\/pnas.1209000109","article-title":"De novo prediction of protein folding pathways and structure using the principle of sequential stabilization","volume":"109","author":"Adhikari","year":"2012","journal-title":"Proc. Natl Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B3","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023020204431296800_btw668-B4","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1042\/bj1280737","article-title":"The formation and stabilization of protein structure","volume":"128","author":"Anfinsen","year":"1972","journal-title":"J. Biochem"},{"key":"2023020204431296800_btw668-B5","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1146\/annurev.biophys.30.1.173","article-title":"Ab initio protein structure prediction: progress and prospects","volume":"30","author":"Bonneau","year":"2001","journal-title":"Annu. Rev. Biophys. Biomol. Struct"},{"key":"2023020204431296800_btw668-B6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0022-2836(02)00698-8","article-title":"De novo prediction of three-dimensional structures for major protein families","volume":"322","author":"Bonneau","year":"2002","journal-title":"J. Mol. Biol"},{"key":"2023020204431296800_btw668-B7","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Bourne","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023020204431296800_btw668-B8","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.1126\/science.1113801","article-title":"Toward high-resolution de novo structure prediction for small proteins","volume":"309","author":"Bradley","year":"2005","journal-title":"Science"},{"key":"2023020204431296800_btw668-B9","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1110\/ps.690101","article-title":"A normalized root-mean-square distance for comparing protein three-dimensional structures","volume":"10","author":"Carugo","year":"2001","journal-title":"Protein Sci"},{"key":"2023020204431296800_btw668-B10","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/S0022-2836(03)00177-3","article-title":"Ab initio folding simulation of the Trp-cage mini-protein approaches NMR resolution","volume":"327","author":"Chowdhury","year":"2003","journal-title":"J. Mol. Biol"},{"key":"2023020204431296800_btw668-B11","doi-asserted-by":"crossref","first-page":"e0123998.","DOI":"10.1371\/journal.pone.0123998","article-title":"Building a better fragment library for de novo protein structure prediction","volume":"10","author":"de Oliveira","year":"2015","journal-title":"PloS One"},{"key":"2023020204431296800_btw668-B12","doi-asserted-by":"crossref","first-page":"3734","DOI":"10.1073\/pnas.0811363106","article-title":"Mimicking the folding pathway to improve homology-free protein structure prediction","volume":"106","author":"DeBartolo","year":"2009","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B13","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1126\/science.282.5389.740","article-title":"Pathways to a protein folding intermediate observed in a 1-microsecond simulation in aqueous solution","volume":"282","author":"Duan","year":"1998","journal-title":"Science"},{"key":"2023020204431296800_btw668-B14","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1016\/j.str.2009.09.006","article-title":"Predicting continuous local structure and the effect of its substitution for secondary structure in fragment-free protein structure prediction","volume":"17","author":"Faraggi","year":"2009","journal-title":"Structure"},{"key":"2023020204431296800_btw668-B15","doi-asserted-by":"crossref","first-page":"e23294.","DOI":"10.1371\/journal.pone.0023294","article-title":"Generalized fragment picking in Rosetta: design, protocols and applications","volume":"6","author":"Gront","year":"2011","journal-title":"PloS One"},{"key":"2023020204431296800_btw668-B16","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1002\/prot.23215","article-title":"The dual role of fragments in fragment-assembly methods for de novo protein structure prediction","volume":"80","author":"Handl","year":"2012","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B17","doi-asserted-by":"crossref","first-page":"5029","DOI":"10.1073\/pnas.1504806112","article-title":"Alternative approach to protein structure prediction based on sequential similarity of physical properties","volume":"112","author":"He","year":"2015","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B18","doi-asserted-by":"crossref","first-page":"11476","DOI":"10.1038\/srep11476","article-title":"Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning","volume":"5","author":"Heffernan","year":"2015","journal-title":"Sci. Rep"},{"key":"2023020204431296800_btw668-B19","doi-asserted-by":"crossref","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B20","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1002\/prot.22499","article-title":"Fast and accurate automatic structure prediction with HHpred","volume":"77","author":"Hildebrand","year":"2009","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B21","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1110\/ps.03494504","article-title":"Some fundamental aspects of building protein structures from fragment libraries","volume":"13","author":"Holmes","year":"2004","journal-title":"Protein Sci"},{"key":"2023020204431296800_btw668-B22","doi-asserted-by":"crossref","first-page":"17747","DOI":"10.1073\/pnas.0605580103","article-title":"Understanding ensemble protein folding at atomic detail","volume":"103","author":"Hubner","year":"2006","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B23","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":"2023020204431296800_btw668-B24","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1002\/bip.360221211","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","author":"Kabsch","year":"1983","journal-title":"Biopolymers"},{"key":"2023020204431296800_btw668-B25","doi-asserted-by":"crossref","first-page":"3110","DOI":"10.1093\/bioinformatics\/btr541","article-title":"HHfrag: HMM-based fragment detection using HHpred","volume":"27","author":"Kalev","year":"2011","journal-title":"Bioinformatics"},{"key":"2023020204431296800_btw668-B26","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1002\/prot.24987","article-title":"Toward a detailed understanding of search trajectories in fragment assembly approaches to protein structure prediction","volume":"84","author":"Kandathil","year":"2016","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B27","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/BF01025494","article-title":"Relation between sequence similarity and structural similarity in proteins. Role of important properties of amino acids","volume":"4","author":"Kidera","year":"1985","journal-title":"J. Protein Chem"},{"key":"2023020204431296800_btw668-B28","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/BF01025492","article-title":"Statistical analysis of the physical properties of the 20 naturally occurring amino acids","volume":"4","author":"Kidera","year":"1985","journal-title":"J. Protein Chem"},{"key":"2023020204431296800_btw668-B29","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/S0022-2836(02)00942-7","article-title":"Small libraries of protein fragments model native protein structures accurately","volume":"323","author":"Kolodny","year":"2002","journal-title":"J. Mol. Biol"},{"key":"2023020204431296800_btw668-B30","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/0022-5193(81)90237-X","article-title":"Homology in protein sequences expressed by correlation coefficients","volume":"91","author":"Kubota","year":"1981","journal-title":"J. Theor. Biol"},{"key":"2023020204431296800_btw668-B31","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1110\/ps.036442.108","article-title":"Fragment-HMM: a new approach to protein structure prediction","volume":"17","author":"Li","year":"2008","journal-title":"Protein Sci"},{"key":"2023020204431296800_btw668-B32","doi-asserted-by":"crossref","first-page":"2383","DOI":"10.1002\/prot.24600","article-title":"Improving the orientation-dependent statistical potential using a reference state","volume":"82","author":"Liu","year":"2014","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/prot.24452","article-title":"Critical assessment of methods of protein structure prediction (CASP)\u2013round X","volume":"82","author":"Moult","year":"2014","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/prot.23200","article-title":"Critical assessment of methods of protein structure prediction (CASP)\u2013round IX","volume":"79","author":"Moult","year":"2011","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B35","doi-asserted-by":"crossref","first-page":"7547","DOI":"10.1073\/pnas.0502655102","article-title":"Physics-based protein-structure prediction using a hierarchical protocol based on the UNRES force field: assessment in two blind tests","volume":"102","author":"O\u0142dziej","year":"2005","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B36","doi-asserted-by":"crossref","first-page":"11987","DOI":"10.1073\/pnas.0703700104","article-title":"Protein folding by zipping and assembly","volume":"104","author":"Ozkan","year":"2007","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B37","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nprot.2010.5","article-title":"I-TASSER: a unified platform for automated protein structure and function prediction","volume":"5","author":"Roy","year":"2010","journal-title":"Nat. Protoc"},{"key":"2023020204431296800_btw668-B38","doi-asserted-by":"crossref","first-page":"e80493.","DOI":"10.1371\/journal.pone.0080493","article-title":"Detecting protein candidate fragments using a structural alphabet profile comparison approach","volume":"8","author":"Shen","year":"2013","journal-title":"PloS One"},{"key":"2023020204431296800_btw668-B39","doi-asserted-by":"crossref","first-page":"11258","DOI":"10.1021\/ja0273851","article-title":"All-atom structure prediction and folding simulations of a stable protein","volume":"124","author":"Simmerling","year":"2002","journal-title":"J. Am. Chem. Soc"},{"key":"2023020204431296800_btw668-B40","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1006\/jmbi.1997.0959","article-title":"Assembly of protein tertiary structures from fragments with similar local sequences using simulated annealing and Bayesian scoring functions","volume":"268","author":"Simons","year":"1997","journal-title":"J. Mol. Biol"},{"key":"2023020204431296800_btw668-B41","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1093\/bioinformatics\/bti125","article-title":"Protein homology detection by HMM-HMM comparison","volume":"21","author":"S\u00f6ding","year":"2005","journal-title":"Bioinformatics"},{"key":"2023020204431296800_btw668-B42","doi-asserted-by":"crossref","first-page":"14258","DOI":"10.1073\/pnas.96.25.14258","article-title":"A physical basis for protein secondary structure","volume":"96","author":"Srinivasan","year":"1999","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020204431296800_btw668-B43","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1002\/prot.10103","article-title":"Ab initio prediction of protein structure using LINUS","volume":"47","author":"Srinivasan","year":"2002","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B44","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1093\/bioinformatics\/btg224","article-title":"PISCES: a protein sequence culling server","volume":"19","author":"Wang","year":"2003","journal-title":"Bioinformatics"},{"key":"2023020204431296800_btw668-B45","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":"2023020204431296800_btw668-B46","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1002\/prot.24179","article-title":"Toward optimal fragment generations for ab initio protein structure assembly","volume":"81","author":"Xu","year":"2013","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B47","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1038\/nmeth.3213","article-title":"The I-TASSER Suite: protein structure and function prediction","volume":"12","author":"Yang","year":"2015","journal-title":"Nat. Methods"},{"key":"2023020204431296800_btw668-B48","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1002\/prot.21968","article-title":"Specific interactions for ab initio folding of protein terminal regions with secondary structures","volume":"72","author":"Yang","year":"2008","journal-title":"Proteins"},{"key":"2023020204431296800_btw668-B49","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"},{"key":"2023020204431296800_btw668-B50","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2023020204431296800_btw668-B51","doi-asserted-by":"crossref","first-page":"2119","DOI":"10.1016\/j.bpj.2008.12.3898","article-title":"Protein structure prediction by pro-Sp3-TASSER","volume":"96","author":"Zhou","year":"2009","journal-title":"Biophys. J"},{"key":"2023020204431296800_btw668-B52","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s00214-010-0799-2","article-title":"Trends in template\/fragment-free protein structure prediction","volume":"128","author":"Zhou","year":"2011","journal-title":"Theor. Chem. Acc"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/5\/677\/49037944\/bioinformatics_33_5_677.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/5\/677\/49037944\/bioinformatics_33_5_677.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T04:48:40Z","timestamp":1675313320000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/5\/677\/2725548"}},"subtitle":[],"editor":[{"given":"Anna","family":"Tramontano","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2016,12,5]]},"references-count":52,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2017,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btw668","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2017,3,1]]},"published":{"date-parts":[[2016,12,5]]}}}