{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:06:30Z","timestamp":1775325990175,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T00:00:00Z","timestamp":1277942400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1186\/1471-2105-11-364","type":"journal-article","created":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T18:15:26Z","timestamp":1278008126000},"source":"Crossref","is-referenced-by-count":21,"title":["Automatic structure classification of small proteins using random forest"],"prefix":"10.1186","volume":"11","author":[{"given":"Pooja","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan D","family":"Hirst","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,7,1]]},"reference":[{"key":"3821_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","volume":"28","author":"HM Berman","year":"2000","unstructured":"Berman HM, Westbrook J, Feng Z, Gilliland G, Bhat TN, Weissig H, Shindyalov IN, Bourne PE: The protein data bank. Nucleic Acids Res 2000, 28: 235\u2013242. 10.1093\/nar\/28.1.235","journal-title":"Nucleic Acids Res"},{"key":"3821_CR2","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1038\/1334","volume":"5","author":"S Kim","year":"1998","unstructured":"Kim S: Shining a light on structural genomics. Nat Struct Biol 1998, 5: 643\u2013645. 10.1038\/1334","journal-title":"Nat Struct Biol"},{"key":"3821_CR3","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1002\/(SICI)1521-1878(199811)20:11<884::AID-BIES3>3.0.CO;2-H","volume":"20","author":"MB Swindells","year":"1998","unstructured":"Swindells MB, Orengo CA, Jones DT, Hutchinson EG, Thornton JM: Contemporary approaches to protein structure classification. Bioessays 1998, 20: 884\u2013891. 10.1002\/(SICI)1521-1878(199811)20:11<884::AID-BIES3>3.0.CO;2-H","journal-title":"Bioessays"},{"key":"3821_CR4","first-page":"536","volume":"247","author":"AG Murzin","year":"1995","unstructured":"Murzin AG, Brenner SE, Hubbard TJP, Chothia C: SCOP: a structural classification of proteins database for the investigation of sequences and structures. J Mol Biol 1995, 247: 536\u2013540.","journal-title":"J Mol Biol"},{"key":"3821_CR5","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1002\/pro.5560070226","volume":"7","author":"M Gerstein","year":"1998","unstructured":"Gerstein M, Levitt M: Comprehensive assessment of automatic structural alignment against a manual standard, the SCOP classification of proteins. Protein Sci 1998, 7: 445\u2013456. 10.1002\/pro.5560070226","journal-title":"Protein Sci"},{"key":"3821_CR6","doi-asserted-by":"publisher","first-page":"D419","DOI":"10.1093\/nar\/gkm993","volume":"36","author":"A Andreeva","year":"2008","unstructured":"Andreeva A, Howorth D, Chandonia JM, Brenner SE, Hubbard TJP, Chothia C, Murzin AG: Data growth and its impact on the SCOP database: new developments. Nucleic Acids Res 2008, 36: D419-D425. 10.1093\/nar\/gkm993","journal-title":"Nucleic Acids Res"},{"key":"3821_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1471-2105-2-3","volume":"2","author":"Y Cai","year":"2001","unstructured":"Cai Y, Liu X, Xu X, Zhou G: Support Vector Machines for predicting protein structural class. BMC Bioinformatics 2001, 2: 3. 10.1186\/1471-2105-2-3","journal-title":"BMC Bioinformatics"},{"key":"3821_CR8","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1093\/bioinformatics\/17.4.349","volume":"17","author":"CHQ Ding","year":"2001","unstructured":"Ding CHQ, Dubchak I: Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics 2001, 17: 349\u2013358. 10.1093\/bioinformatics\/17.4.349","journal-title":"Bioinformatics"},{"key":"3821_CR9","first-page":"1159","volume-title":"ICANN","author":"I Chung","year":"2003","unstructured":"Chung I, Huang C, Shen Y, Lin C: Recognition of Structure Classification of Protein Folding by NN and SVM Hierarchical Learning Architecture. ICANN 2003, 1159\u20131167."},{"key":"3821_CR10","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1002\/bip.360250909","volume":"25","author":"P Klein","year":"2004","unstructured":"Klein P, Delisi C: Prediction of protein structural class from the amino acid sequence. Biopolymers 2004, 25: 1659\u20131672. 10.1002\/bip.360250909","journal-title":"Biopolymers"},{"key":"3821_CR11","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1093\/bioinformatics\/btg392","volume":"20","author":"S Vinga","year":"2004","unstructured":"Vinga S, Gouveia-Oliveira R, Almeida JS: Comparative evaluation of word composition distances for the recognition of SCOP relationships. Bioinformatics 2004, 20: 206\u2013215. 10.1093\/bioinformatics\/btg392","journal-title":"Bioinformatics"},{"key":"3821_CR12","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1145\/1102351.1102393","volume-title":"proceedings of International Conference On Machine Learning","author":"E Ie","year":"2005","unstructured":"Ie E, Weston J, Noble WS, Leslie C: Multi-class protein fold recognition using adaptive codes. In proceedings of International Conference On Machine Learning. ACM; 2005:329\u2013336."},{"key":"3821_CR13","doi-asserted-by":"publisher","first-page":"2843","DOI":"10.1093\/bioinformatics\/btm475","volume":"23","author":"K Chen","year":"2007","unstructured":"Chen K, Kurgan L: PFRES: protein fold classification by using evolutionary information and predicted secondary structure. Bioinformatics 2007, 23: 2843\u20132850. 10.1093\/bioinformatics\/btm475","journal-title":"Bioinformatics"},{"key":"3821_CR14","doi-asserted-by":"publisher","first-page":"3320","DOI":"10.1093\/bioinformatics\/btm527","volume":"23","author":"MTA Shamim","year":"2007","unstructured":"Shamim MTA, Anwaruddin M, Nagarajaram HA: Support Vector Machine based classification of protein folds using the structural properties of amino acid residues and amino acid residue pairs. Bioinformatics 2007, 23: 3320\u20133327. 10.1093\/bioinformatics\/btm527","journal-title":"Bioinformatics"},{"key":"3821_CR15","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.1186\/1471-2105-8-S4-S2","volume":"8","author":"I Melvin","year":"2007","unstructured":"Melvin I, Ie E, Kuang R, Weston J, Noble WS, Leslie C: SVM-Fold: a tool for discriminative multi-class protein fold and superfamily recognition. BMC Bioinformatics 2007, 8: S2. 10.1186\/1471-2105-8-S4-S2","journal-title":"BMC Bioinformatics"},{"key":"3821_CR16","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/j.bbrc.2007.03.164","volume":"357","author":"L Kurgan","year":"2007","unstructured":"Kurgan L, Chen K: Prediction of protein Structural Class for the Twilight Zone Sequences. Biochem Biophys Res Comm 2007, 357: 453\u2013460. 10.1016\/j.bbrc.2007.03.164","journal-title":"Biochem Biophys Res Comm"},{"key":"3821_CR17","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1093\/bioinformatics\/btm089","volume":"23","author":"JE Gewehr","year":"2007","unstructured":"Gewehr JE, Hintermair V, Zimmer R: AutoSCOP: automated prediction of SCOP classifications using unique pattern-class mappings. Bioinformatics 2007, 23: 1203\u20131210. 10.1093\/bioinformatics\/btm089","journal-title":"Bioinformatics"},{"key":"3821_CR18","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1093\/bioinformatics\/btl170","volume":"22","author":"H Shen","year":"2006","unstructured":"Shen H, Chou K: Ensemble classifier for protein fold pattern recognition. Bioinformatics 2006, 22: 1717\u20131722. 10.1093\/bioinformatics\/btl170","journal-title":"Bioinformatics"},{"key":"3821_CR19","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1002\/prot.1035","volume":"43","author":"KC Chou","year":"2001","unstructured":"Chou KC: Prediction of protein cellular attributes using pseudo-amino acid composition. Proteins: Struc Func Gen 2001, 43: 246\u2013255. 10.1002\/prot.1035","journal-title":"Proteins: Struc Func Gen"},{"key":"3821_CR20","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1002\/prot.21870","volume":"70","author":"XM Zhao","year":"2008","unstructured":"Zhao XM, Li X, Chen L, Aihara K: Protein Classification with Imbalanced Data. Proteins: Struct Func Bioinform 2008, 70: 1125\u20131132. 10.1002\/prot.21870","journal-title":"Proteins: Struct Func Bioinform"},{"key":"3821_CR21","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1093\/bioinformatics\/btl102","volume":"22","author":"J Cheng","year":"2006","unstructured":"Cheng J, Baldi P: A machine learning information retrieval approach to protein fold recognition. Bioinformatics 2006, 22: 1456\u20131463. 10.1093\/bioinformatics\/btl102","journal-title":"Bioinformatics"},{"key":"3821_CR22","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1142\/S0219720005001259","volume":"3","author":"O \u00c7amo\u011flu","year":"2005","unstructured":"\u00c7amo\u011flu O, Can T, Singh AK, Wang Y: Decision tree based information integration for automated protein classification. J Bioinform Comput Biol 2005, 3: 717\u2013742. 10.1142\/S0219720005001259","journal-title":"J Bioinform Comput Biol"},{"key":"3821_CR23","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1186\/1471-2105-9-500","volume":"9","author":"SE Hamby","year":"2008","unstructured":"Hamby SE, Hirst JD: Prediction of glycosylation sites using random forests. BMC Bioinformatics 2008, 9: 500. 10.1186\/1471-2105-9-500","journal-title":"BMC Bioinformatics"},{"key":"3821_CR24","doi-asserted-by":"publisher","first-page":"4394","DOI":"10.1093\/bioinformatics\/bti721","volume":"21","author":"X Chen","year":"2005","unstructured":"Chen X, Liu M: Prediction of protein-protein interactions using random decision forest framework. Bioinformatics 2005, 21: 4394\u20134400. 10.1093\/bioinformatics\/bti721","journal-title":"Bioinformatics"},{"key":"3821_CR25","doi-asserted-by":"publisher","first-page":"e1000278","DOI":"10.1371\/journal.pcbi.1000278","volume":"5","author":"S Mile","year":"2009","unstructured":"Mile S, Tomi\u0107 S, Vlahovi\u010dek K: Prediction of protein-protein interaction sites in sequences and 3 D structures by random forests. PLoS Comput Biol 2009, 5: e1000278. 10.1371\/journal.pcbi.1000278","journal-title":"PLoS Comput Biol"},{"key":"3821_CR26","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1093\/bioinformatics\/btp039","volume":"25","author":"X Chen","year":"2009","unstructured":"Chen X, Jeong JC: Sequence-based prediction of protein interaction sites with an integrative method. Bioinformatics 2009, 25: 585\u2013591. 10.1093\/bioinformatics\/btp039","journal-title":"Bioinformatics"},{"key":"3821_CR27","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/bioinformatics\/btn583","volume":"25","author":"J Wu","year":"2009","unstructured":"Wu J, Liu H, Duan X, Ding Y, Wu H, Bai Y, Sun X: Prediction of DNA-binding residues in proteins from amino acid sequences using a random forest model with a hybrid feature. Bioinformatics 2009, 25: 30\u201335. 10.1093\/bioinformatics\/btn583","journal-title":"Bioinformatics"},{"key":"3821_CR28","first-page":"654","volume":"10","author":"P Han","year":"2009","unstructured":"Han P, Zhang X, Norton RS, Feng Z: Large-scale prediction of long disordered regions in proteins using random forests. BMC Bioinformatics 2009, 10: 654\u2013660.","journal-title":"BMC Bioinformatics"},{"key":"3821_CR29","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/j.procbio.2009.02.007","volume":"44","author":"G Zhanga","year":"2009","unstructured":"Zhanga G, Lia H, Fang B: Discriminating acidic and alkaline enzymes using a random forest model with secondary structure amino acid composition. Process Biochem 2009, 44: 654\u2013660. 10.1016\/j.procbio.2009.02.007","journal-title":"Process Biochem"},{"key":"3821_CR30","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.compbiolchem.2009.04.004","volume":"33","author":"P Jain","year":"2009","unstructured":"Jain P, Garibaldi JM, Hirst JD: Supervised machine learning algorithms for protein structure classification. Comput Biol Chem 2009, 33: 216\u2013223. 10.1016\/j.compbiolchem.2009.04.004","journal-title":"Comput Biol Chem"},{"key":"3821_CR31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L: Random Forests. Mach Learn 2001, 45: 5\u201332. 10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"3821_CR32","volume-title":"C4.5: Programs For Machine Learning","author":"JR Quinlan","year":"1993","unstructured":"Quinlan JR: C4.5: Programs For Machine Learning. Morgan Kaufmann; 1993."},{"key":"3821_CR33","volume-title":"Addison Wesley","author":"AV Levitin","year":"2002","unstructured":"Levitin AV: Introduction to the Design and Analysis of Algorithms. Addison Wesley 2002."},{"key":"3821_CR34","doi-asserted-by":"publisher","first-page":"D226","DOI":"10.1093\/nar\/gkh039","volume":"32","author":"A Andreeva","year":"2004","unstructured":"Andreeva A, Howorth D, Brenner SE, Hubbard TJP, Chothia C, Murzin AG: SCOP database in 2004: refinements integrate structure and sequence family data. Nucleic Acids Res 2004, 32: D226-D229. 10.1093\/nar\/gkh039","journal-title":"Nucleic Acids Res"},{"key":"3821_CR35","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1002\/pro.5560010313","volume":"1","author":"U Hobohm","year":"1992","unstructured":"Hobohm U, M MS, Schneider R, Sander C: Selection of representative protein data sets. Protein Sci 1992, 1: 409\u2013417. 10.1002\/pro.5560010313","journal-title":"Protein Sci"},{"key":"3821_CR36","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1093\/nar\/24.1.206","volume":"24","author":"L Holm","year":"1996","unstructured":"Holm L, Sander C: The FSSP database: fold classification based on structure-structure alignment of proteins. Nucleic Acids Res 1996, 24: 206\u2013209. 10.1093\/nar\/24.1.206","journal-title":"Nucleic Acids Res"},{"key":"3821_CR37","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/S0959-440X(96)80058-3","volume":"6","author":"JF Gibrat","year":"1996","unstructured":"Gibrat JF, Madej T, Bryant SS: Surprising similarities in structure comparison. Curr Opin Struct Biol 1996, 6: 377\u2013385. 10.1016\/S0959-440X(96)80058-3","journal-title":"Curr Opin Struct Biol"},{"key":"3821_CR38","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1016\/S0969-2126(99)80177-4","volume":"7","author":"C Hadley","year":"1999","unstructured":"Hadley C, Jones DT: A systematic comparison of protein structure classifications: SCOP, CATH and FSSP. Structure 1999, 7: 1099\u20131112. 10.1016\/S0969-2126(99)80177-4","journal-title":"Structure"},{"key":"3821_CR39","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1186\/1471-2105-7-206","volume":"7","author":"V Sam","year":"2006","unstructured":"Sam V, Tai CH, Garnier J, Gibrat JF, Lee B, Munson PJ: ROC and confusion analysis of structure comparison methods identify the main causes of divergence from manual. protein classification BMC Bioinformatics 2006, 7: 206.","journal-title":"protein classification BMC Bioinformatics"},{"key":"3821_CR40","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1093\/bioinformatics\/16.5.412","volume":"16","author":"P Baldi","year":"2000","unstructured":"Baldi P, Brunak S, Chauvin Y, Andersen CAF, Nielsen H: Assessing the accuracy of prediction algorithms for classification an overview. Bioinformatics 2000, 16: 412\u2013424. 10.1093\/bioinformatics\/16.5.412","journal-title":"Bioinformatics"},{"key":"3821_CR41","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/978-1-59745-243-4_3","volume":"541","author":"SP Kanaan","year":"2009","unstructured":"Kanaan SP, Huang C, Wuchty S, Chen DZ, Izaguirre JA: Inferring protein-protein interactions from multiple protein domain combinations. Methods Mol Biol 2009, 541: 43\u201359.","journal-title":"Methods Mol Biol"},{"key":"3821_CR42","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1093\/bioinformatics\/bti227","volume":"21","author":"SS Krishna","year":"2005","unstructured":"Krishna SS, Grishin NV: Structural drift: a possible path to protein fold change. Bioinformatics 2005, 21: 1308\u20131310. 10.1093\/bioinformatics\/bti227","journal-title":"Bioinformatics"},{"key":"3821_CR43","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1093\/nar\/28.1.254","volume":"28","author":"SE Brenner","year":"2000","unstructured":"Brenner SE, Koehl P, Levitt M: The ASTRAL compendium for protein structure and sequence analysis. Nucleic Acids Res 2000, 28: 254\u2013256. 10.1093\/nar\/28.1.254","journal-title":"Nucleic Acids Res"},{"key":"3821_CR44","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1002\/bip.360221211","volume":"22","author":"W Kabsch","year":"1983","unstructured":"Kabsch W, Sander C: Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 1983, 22: 2577\u20132637. 10.1002\/bip.360221211","journal-title":"Biopolymers"},{"key":"3821_CR45","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ: Basic local alignment search tool BLAST. J Mol Biol 1990, 215: 403\u2013410.","journal-title":"J Mol Biol"},{"key":"3821_CR46","volume-title":"Data Mining: Practical Machine Learning Tools and Techniques","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann; 2005."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-11-364.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-11-364\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-11-364.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T13:53:49Z","timestamp":1635602029000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-11-364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7,1]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,12]]}},"alternative-id":["3821"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-11-364","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,7,1]]},"article-number":"364"}}