{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T12:36:20Z","timestamp":1767962180578,"version":"3.49.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2008,12,1]],"date-time":"2008-12-01T00:00:00Z","timestamp":1228089600000},"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":[[2008,12]]},"DOI":"10.1186\/1471-2105-9-510","type":"journal-article","created":{"date-parts":[[2008,12,2]],"date-time":"2008-12-02T09:27:38Z","timestamp":1228210058000},"source":"Crossref","is-referenced-by-count":119,"title":["A discriminative method for protein remote homology detection and fold recognition combining Top-n-grams and latent semantic analysis"],"prefix":"10.1186","volume":"9","author":[{"given":"Bin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiwen","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,12,1]]},"reference":[{"issue":"1","key":"2495_CR1","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"TF Smith","year":"1981","unstructured":"Smith TF, Waterman MS: Identification of Common Molecular Subsequences. J Mol Biol 1981, 147(1):195\u2013197.","journal-title":"J Mol Biol"},{"issue":"20","key":"2495_CR2","doi-asserted-by":"publisher","first-page":"5119","DOI":"10.1111\/j.1742-4658.2005.04947.x","volume":"272","author":"WS Noble","year":"2005","unstructured":"Noble WS, Kuang R, Leslie C, Weston J: Identifying remote protein homologs by network propagation. The FEBS journal 2005, 272(20):5119\u20135128.","journal-title":"The FEBS journal"},{"issue":"3","key":"2495_CR3","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. J Mol Biol 1990, 215(3):403\u2013410.","journal-title":"J Mol Biol"},{"key":"2495_CR4","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/0076-6879(90)83007-V","volume":"183","author":"WR Pearson","year":"1990","unstructured":"Pearson WR: Rapid and Sensitive Sequence Comparison with Fastp and Fasta. Methods Enzymol 1990, 183: 63\u201398.","journal-title":"Methods Enzymol"},{"issue":"2","key":"2495_CR5","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1093\/protein\/12.2.85","volume":"12","author":"B Rost","year":"1999","unstructured":"Rost B: Twilight zone of protein sequence alignments. Protein Eng 1999, 12(2):85\u201394.","journal-title":"Protein Eng"},{"issue":"18","key":"2495_CR6","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1093\/bioinformatics\/btl376","volume":"22","author":"T Lingner","year":"2006","unstructured":"Lingner T, Meinicke P: Remote homology detection based on oligomer distances. Bioinformatics 2006, 22(18):2224\u20132231.","journal-title":"Bioinformatics"},{"issue":"10","key":"2495_CR7","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1093\/bioinformatics\/14.10.846","volume":"14","author":"K Karplus","year":"1998","unstructured":"Karplus K, Barrett C, Hughey R: Hidden Markov Models for Detecting Remote Protein Homologies. Bioinformatics 1998, 14(10):846\u2013856.","journal-title":"Bioinformatics"},{"issue":"14","key":"2495_CR8","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1093\/bioinformatics\/bth181","volume":"20","author":"B Qian","year":"2004","unstructured":"Qian B, Goldstein RA: Performance of an Iterated T-Hmm for Homology Detection. Bioinformatics 2004, 20(14):2175\u20132180.","journal-title":"Bioinformatics"},{"key":"2495_CR9","volume-title":"New York","author":"VN Vapnik","year":"1998","unstructured":"Vapnik VN: Statistical Learning Theory. New York 1998."},{"issue":"23","key":"2495_CR10","doi-asserted-by":"publisher","first-page":"4239","DOI":"10.1093\/bioinformatics\/bti687","volume":"21","author":"H Rangwala","year":"2005","unstructured":"Rangwala H, Karypis G: Profile-based direct kernels for remote homology detection and fold recognition. Bioinformatics 2005, 21(23):4239\u20134247.","journal-title":"Bioinformatics"},{"issue":"11","key":"2495_CR11","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1093\/bioinformatics\/bth141","volume":"20","author":"H Saigo","year":"2004","unstructured":"Saigo H, Vert JP, Ueda N, Akutsu T: Protein Homology Detection Using String Alignment Kernels. Bioinformatics 2004, 20(11):1682\u20131689.","journal-title":"Bioinformatics"},{"issue":"1\u20132","key":"2495_CR12","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1089\/10665270050081405","volume":"7","author":"T Jaakkola","year":"2000","unstructured":"Jaakkola T, Diekhans M, Haussler D: A Discriminative Framework for Detecting Remote Protein Homologies. J Comput Biol 2000, 7(1\u20132):95\u2013114.","journal-title":"J Comput Biol"},{"issue":"6","key":"2495_CR13","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1089\/106652703322756113","volume":"10","author":"L Liao","year":"2003","unstructured":"Liao L, Noble WS: Combining Pairwise Sequence Similarity and Support Vector Machines for Detecting Remote Protein Evolutionary and Structural Relationships. J Comput Biol 2003, 10(6):857\u2013868.","journal-title":"J Comput Biol"},{"issue":"17","key":"2495_CR14","doi-asserted-by":"publisher","first-page":"2294","DOI":"10.1093\/bioinformatics\/btg317","volume":"19","author":"Y Hou","year":"2003","unstructured":"Hou Y, Hsu W, Lee ML, Bystroff C: Efficient Remote Homology Detection Using Local Structure. Bioinformatics 2003, 19(17):2294\u20132301.","journal-title":"Bioinformatics"},{"key":"2495_CR15","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1002\/prot.20221","volume":"57","author":"Y Hou","year":"2004","unstructured":"Hou Y, Hsu W, Lee L, Bystroff C: Remote homolog detection using local sequence-structure correlations. Proteins 2004, 57: 518\u2013530.","journal-title":"Proteins"},{"issue":"6","key":"2495_CR16","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1016\/j.compbiolchem.2005.09.006","volume":"29","author":"B-J Webb-Robertson","year":"2005","unstructured":"Webb-Robertson B-J, Oehmen C, Matzke M: SVM-BALSA: Remote homology detection based on Bayesian sequence alignment. Comput Biol Chem 2005, 29(6):440\u2013443.","journal-title":"Comput Biol Chem"},{"key":"2495_CR17","first-page":"564","volume-title":"Pac Symp Biocomput","author":"C Leslie","year":"2002","unstructured":"Leslie C, Eskin E, Noble WS: The Spectrum Kernel: A String Kernel for svm Protein Classification. Pac Symp Biocomput 2002, 564\u2013575."},{"issue":"1","key":"2495_CR18","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.biosystems.2006.03.006","volume":"87","author":"H Ogul","year":"2007","unstructured":"Ogul H, Mumcuoglu EU: A discriminative method for remote homology detection based on n-peptide compositions with reduced amino acid alphabets. BioSystems 2007, 87(1):75\u201381.","journal-title":"BioSystems"},{"issue":"4","key":"2495_CR19","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1093\/bioinformatics\/btg431","volume":"20","author":"CS Leslie","year":"2004","unstructured":"Leslie CS, Eskin E, Cohen A, Weston J, Noble WS: Mismatch String Kernels for Discriminative Protein Classification. Bioinformatics 2004, 20(4):467\u2013476.","journal-title":"Bioinformatics"},{"key":"2495_CR20","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1142\/S021972000500120X","volume":"3","author":"R Kuang","year":"2005","unstructured":"Kuang R, Ie E, Wang K, Wang K, Siddiqi M, Freund Y, Leslie C: Profile-based string kernels for remote homology detection and motif extraction. J Bioinform Comput Biol 2005, 3: 527\u2013550.","journal-title":"J Bioinform Comput Biol"},{"issue":"Suppl 1","key":"2495_CR21","doi-asserted-by":"publisher","first-page":"i26","DOI":"10.1093\/bioinformatics\/btg1002","volume":"19","author":"A Ben-Hur","year":"2003","unstructured":"Ben-Hur A, Brutlag D: Remote homology detection: A motif based approach. Bioinformatics 2003, 19(Suppl 1):i26-i33.","journal-title":"Bioinformatics"},{"issue":"11","key":"2495_CR22","doi-asserted-by":"publisher","first-page":"5865","DOI":"10.1073\/pnas.95.11.5865","volume":"95","author":"CG Nevill-Manning","year":"1998","unstructured":"Nevill-Manning CG, Wu TD, Brutlag DL: Highly Specific Protein Sequence Motifs for Genome Analysis. Proc Natl Acad Sci USA 1998, 95(11):5865\u20135871.","journal-title":"Proc Natl Acad Sci USA"},{"key":"2495_CR23","doi-asserted-by":"publisher","first-page":"D178","DOI":"10.1093\/nar\/gki060","volume":"33","author":"QJ Su","year":"2005","unstructured":"Su QJ, Lu L, Saxonov S, Brutlag DL: eBLOCKS: enumerating conserved protein blocks to achieve maximal sensitivity and specificity. Nucleic Acids Res 2005, 33: D178-D182.","journal-title":"Nucleic Acids Res"},{"key":"2495_CR24","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/1471-2105-8-23","volume":"8","author":"T H\u00e5ndstad","year":"2007","unstructured":"H\u00e5ndstad T, Hestnes AJ, S\u00e6trom P: Motif kernel generated by genetic programming improves remote homology and fold detection. BMC Bioinformatics 2007, 8: 23.","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"2495_CR25","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1093\/bioinformatics\/btn028","volume":"24","author":"AR Shah","year":"2008","unstructured":"Shah AR, Oehmen CS, Webb-Robertson B-J: SVM-HUSTLE \u2013 an iterative semi-supervised machine learning approach for pairwise protein remote homology detection. Bioinformatics 2008, 24(6):783\u2013790.","journal-title":"Bioinformatics"},{"issue":"17","key":"2495_CR26","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul SF, Madden TL, Schaffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ: Gapped Blast and Psi-Blast: A New Generation of Protein Database Search Programs. Nucleic Acids Res 1997, 25(17):3389\u20133402.","journal-title":"Nucleic Acids Res"},{"key":"2495_CR27","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1186\/1471-2105-6-93","volume":"6","author":"SE Dowd","year":"2005","unstructured":"Dowd SE, Zaragoza J, Rodriguez JR, Oliver MJ, Payton PR: Windows.Net Network Distributed Basic Local Alignment Search Toolkit (W.Nd-Blast). BMC Bioinformatics 2005, 6: 93.","journal-title":"BMC Bioinformatics"},{"key":"2495_CR28","first-page":"212","volume-title":"Proc 1st International Conference on Bioinformatics Research and Development (BIRD) Germany","author":"Q Dong","year":"2007","unstructured":"Dong Q, Lin L, Wang XL: Protein Remote Homology Detection Based on Binary Profiles. Proc 1st International Conference on Bioinformatics Research and Development (BIRD) Germany 2007, 212\u2013223."},{"issue":"2","key":"2495_CR29","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.compbiolchem.2006.01.001","volume":"30","author":"Q Dong","year":"2006","unstructured":"Dong Q, Wang X, Lin L, Xu Z: Domain boundary prediction based on profile domain linker propensity index. Comput Biol Chem 2006, 30(2):127\u2013133.","journal-title":"Comput Biol Chem"},{"key":"2495_CR30","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1186\/1471-2105-7-324","volume":"7","author":"Q Dong","year":"2006","unstructured":"Dong Q, Wang X, Lin L: Novel knowledge-based mean force potential at the profile level. BMC Bioinformatics 2006, 7: 324.","journal-title":"BMC Bioinformatics"},{"key":"2495_CR31","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1186\/1471-2105-8-147","volume":"8","author":"Q Dong","year":"2007","unstructured":"Dong Q, Wang X, Lin L, Guan Y: Exploiting residue-level and profile-level interface propensities for usage in binding sites prediction of proteins. BMC Bioinformatics 2007, 8: 147.","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"2495_CR32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/bioinformatics\/bti801","volume":"22","author":"QW Dong","year":"2006","unstructured":"Dong QW, Wang XL, Lin L: Application of Latent Semantic Analysis to Protein Remote Homology Detection. Bioinformatics 2006, 22(3):285\u2013290.","journal-title":"Bioinformatics"},{"issue":"8","key":"2495_CR33","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1109\/5.880084","volume":"88","author":"J Bellegarda","year":"2000","unstructured":"Bellegarda J: Exploiting Latent Semantic Information in Statistical Language Modeling. Proc IEEE 2000, 88(8):1279\u20131296.","journal-title":"Proc IEEE"},{"key":"2495_CR34","first-page":"3363","volume-title":"4th international conference on machine learning and cybernetics. GuangZhou, China","author":"Q Dong","year":"2005","unstructured":"Dong Q, Lin L, Wang XL, Li MH: A Pattern-Based svm for Protein Remote Homology Detection. 4th international conference on machine learning and cybernetics. GuangZhou, China 2005, 3363\u20133368."},{"issue":"10","key":"2495_CR35","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1093\/bioinformatics\/btn112","volume":"24","author":"T Damoulas","year":"2008","unstructured":"Damoulas T, Girolami MA: Probabilistic multi-class multi-kernel learning: on protein fold recognition and remote homology detection. Bioinformatics 2008, 24(10):1264\u20131270.","journal-title":"Bioinformatics"},{"key":"2495_CR36","unstructured":"Supplementary data for \"Profile-based direct kernels for remote homology detection and fold recognition\"[\n                    http:\/\/bioinfo.cs.umn.edu\/supplements\/remote-homology\/\n                    \n                  ]"},{"key":"2495_CR37","volume-title":"Support Vector Machines and other kernel-based learning methods","author":"J Shawe-Taylor","year":"2000","unstructured":"Shawe-Taylor J, Cristianini N: Support Vector Machines and other kernel-based learning methods. Cambridge University Press; 2000."},{"key":"2495_CR38","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1093\/bioinformatics\/14.1.55","volume":"14","author":"I Rigoutsos","year":"1998","unstructured":"Rigoutsos I, Floratos A: Combinatorial pattern discovery in biological sequences: the TEIRESIAS algorithm. Bioinformatics 1998, 14: 55\u201367.","journal-title":"Bioinformatics"},{"key":"2495_CR39","volume-title":"98A000290","author":"A Floratos","year":"1998","unstructured":"Floratos A, Rigoutsos I: Research Report On the Time Complexity of the TEIRESIAS Algorithm. 98A000290 1998."},{"key":"2495_CR40","first-page":"28","volume":"2","author":"TL Bailey","year":"1994","unstructured":"Bailey TL, Elkan C: Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proc Int Conf Intell Syst Mol Biol 1994, 2: 28\u201336.","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"2495_CR41","unstructured":"Bailey TL, Elkan C: Fitting a Mixture Model by Expectation Maximization to Discover Motifs in Biopolymers. UCSD Technical Report CS94\u2013351"},{"key":"2495_CR42","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","volume":"25","author":"TK Landauer","year":"1998","unstructured":"Landauer TK, Foltz PW, Laham D: Introduction to Latent Semantic Analysis. Discourse Processes 1998, 25: 259\u2013284.","journal-title":"Discourse Processes"},{"key":"2495_CR43","first-page":"412","volume-title":"14th international conference on machine learning","author":"Y Yang","year":"1997","unstructured":"Yang Y, Pedersen JA: A comparative study on feature selection in text categorization. In 14th international conference on machine learning. San Francisco, USA; 1997:412\u2013420."},{"issue":"1","key":"2495_CR44","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 sequence and structure analysis. Nucleic Acids Res 2000, 28(1):254\u2013256.","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"2495_CR45","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1093\/bioinformatics\/14.5.423","volume":"14","author":"L Holm","year":"1998","unstructured":"Holm L, Sander C: Removing near-neighbour redundancy from large protein sequence collections. Bioinformatics 1998, 14(5):423\u2013429.","journal-title":"Bioinformatics"},{"issue":"4","key":"2495_CR46","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/0022-2836(94)90032-9","volume":"243","author":"S Henikoff","year":"1994","unstructured":"Henikoff S, Henikoff JG: Position-Based Sequence Weights. J Mol Biol 1994, 243(4):574\u2013578.","journal-title":"J Mol Biol"},{"key":"2495_CR47","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MSP.2004.1296545","volume":"21","author":"M Ganapathiraju","year":"2004","unstructured":"Ganapathiraju M, Klein-Seetharaman J, Balakrishnan N, Reddy R: Characterization of protein secondary structure, Application of latent semantic analysis using different vocabularies. IEEE Signal Processing Magazine 2004, 21: 78\u201387.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"1","key":"2495_CR48","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/S0097-8485(96)80004-0","volume":"20","author":"M Gribskov","year":"1996","unstructured":"Gribskov M, Robinson NL: Use of Receiver Operating Characteristic (Roc) Analysis to Evaluate Sequence Matching. Comput Chem 1996, 20(1):25\u201333.","journal-title":"Comput Chem"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-9-510.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-9-510\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-9-510.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T10:11:12Z","timestamp":1548151872000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-9-510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,12]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2008,12]]}},"alternative-id":["2495"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-9-510","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,12]]},"article-number":"510"}}