{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T04:03:54Z","timestamp":1751774634137,"version":"3.41.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,7,16]],"date-time":"2018-07-16T00:00:00Z","timestamp":1531699200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1186\/s12859-018-2240-0","type":"journal-article","created":{"date-parts":[[2018,7,16]],"date-time":"2018-07-16T14:21:10Z","timestamp":1531750870000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Discovering themes in biomedical literature using a projection-based algorithm"],"prefix":"10.1186","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9527-0764","authenticated-orcid":false,"given":"Lana","family":"Yeganova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigory","family":"Balasanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. John","family":"Wilbur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,16]]},"reference":[{"key":"2240_CR1","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei D, Ng A, Jordan M. Latent Dirichlet allocation. J Mach Learn Res. 2003; 3:993\u20131022.","journal-title":"J Mach Learn Res"},{"key":"2240_CR2","volume-title":"A Survey of Text Clustering Algorithms. Mining Text Data, vol 4","author":"C Aggarwal","year":"2012","unstructured":"Aggarwal C, Zhai C. A Survey of Text Clustering Algorithms. Mining Text Data, vol 4. New York: Springer; 2012."},{"key":"2240_CR3","volume-title":"Document Clustering: The Next Frontier. Data Clustering: Algorithms and Applications","author":"D Anastasiu","year":"2013","unstructured":"Anastasiu D, Tagarelli A, Karypis G. Document Clustering: The Next Frontier. Data Clustering: Algorithms and Applications. Boca Raton: CRC Press; 2013."},{"issue":"3","key":"2240_CR4","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"A Jain","year":"1999","unstructured":"Jain A, Murty M, Flynn P. Data clustering: A review. ACM Comput Surv. 1999; 31(3):264\u2013323.","journal-title":"ACM Comput Surv"},{"key":"2240_CR5","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu R, Wunsch D. Survey of clustering algorithms. IEEE Trans Neural Netw. 2005; 16:645\u201378.","journal-title":"IEEE Trans Neural Netw"},{"key":"2240_CR6","doi-asserted-by":"crossref","unstructured":"Shatkay H, Wilbur WJ. Finding themes in MEDLINE documents: Probabilistic similarity search. In: Proceedings of the IEEE Conference on Advanced Digital Libraries: 2000. p. 183\u201392.","DOI":"10.1109\/ADL.2000.848381"},{"key":"2240_CR7","doi-asserted-by":"crossref","unstructured":"Dhillon IS. Co-clustering documents and words using bipartite spectral graph partitioning. In: Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: 2001. p. 269\u201374.","DOI":"10.1145\/502512.502550"},{"key":"2240_CR8","doi-asserted-by":"publisher","first-page":"2964","DOI":"10.1016\/j.cor.2007.01.005","volume":"35","author":"S Busygin","year":"2008","unstructured":"Busygin S, Prokopyev O, Pardalos P. Biclustering in data mining. Comput Oper Res. 2008; 35:2964\u201387.","journal-title":"Comput Oper Res"},{"key":"2240_CR9","doi-asserted-by":"crossref","unstructured":"Frigui H, Nasraoui O. Simultaneous clustering and attribute discrimination. In: Proceedings of the IEEE International Conference on Fuzzy Systems: 2000. p. 158\u201363.","DOI":"10.1109\/FUZZY.2000.838651"},{"key":"2240_CR10","unstructured":"Shatkay H, Edwards S, Wilbur WJ, Boguski M. Genes, themes and microarrays: using information retrieval for large-scale gene analysis. In: Proceedings of the International Conference on Intelligent Systems for Molecular Biology: 2000. p. 317\u201328."},{"key":"2240_CR11","doi-asserted-by":"crossref","unstructured":"Wilbur WJ. A thematic analysis of the AIDS literature. In: Proceedings of the Pacific Symposium on Biocomputing: 2002. p. 386\u201397.","DOI":"10.1142\/9789812799623_0036"},{"key":"2240_CR12","unstructured":"Shatkay H, Edwards S, Wilbur WJ, Boguski M. Applying probabilistic thematic clustering for classification in the TREC 2005 Genomics Track. In: Proceedings of the Text Retrieval Conference: 2005."},{"issue":"Suppl 3","key":"2240_CR13","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/2041-1480-3-S3-S6","volume":"3","author":"S Kim","year":"2012","unstructured":"Kim S, Wilbur WJ. Thematic clustering of text documents using an EM-based approach. J Biomed Semant. 2012; 3(Suppl 3):6.","journal-title":"J Biomed Semant"},{"issue":"2","key":"2240_CR14","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/s10791-010-9141-9","volume":"14","author":"Y Lu","year":"2011","unstructured":"Lu Y, Mei Q, Zhai C. Investigating task performance of probabilistic topic models: an empirical study of PLSA and LDA. Inf Retr. 2011; 14(2):178\u2013203.","journal-title":"Inf Retr"},{"key":"2240_CR15","unstructured":"Xie P, Xing E. Integrating document clustering and topic modeling. In: Proceedings of Conference on Uncertainty in Artificial Intelligence: 2013. p. 694\u2013703."},{"key":"2240_CR16","doi-asserted-by":"crossref","unstructured":"Xu W, Gong Y. Document clustering by concept factorization. In: Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval: 2004. p. 202\u20139.","DOI":"10.1145\/1008992.1009029"},{"key":"2240_CR17","unstructured":"Ng AY, Jordan MI, Weiss Y. On spectral clustering: Analysis and an algorithm. In: Advances in Neural Information Processing Systems: 2001. p. 849\u201356."},{"key":"2240_CR18","doi-asserted-by":"crossref","unstructured":"Xu W, Liu X, Gong Y. Document clustering based on non-negative matrix factorization. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201903): 2003. p. 267\u201373.","DOI":"10.1145\/860484.860485"},{"key":"2240_CR19","doi-asserted-by":"crossref","unstructured":"Deerwester S, Dumais S, Landauer T, Furnas G, Harshman R. Indexing by latent semantic analysis. J Am Soc Inf Sci. 1990;41(6).","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"2240_CR20","unstructured":"Wallach H. Structured topic models for language. PhD thesis. 2008."},{"key":"2240_CR21","volume-title":"Matrix Computations","author":"G Golub","year":"2012","unstructured":"Golub G, Van Loan C. Matrix Computations, 4th edn. Baltimore and London: Johns Hopkins University Press; 2012."},{"key":"2240_CR22","volume-title":"Introduction to Linear Algebra","author":"G Strang","year":"2009","unstructured":"Strang G. Introduction to Linear Algebra, 4th edn. Wellesley: Wellesley - Cambridge Press; 2009."},{"key":"2240_CR23","unstructured":"Kim W, Aronson AR, Wilbur WJ. Automatic MeSH term assignment and quality assessment. In: Proceedings of the AMIA Annual Symposium: 2001. p. 319\u201323."},{"key":"2240_CR24","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1186\/1471-2105-8-423","volume":"8","author":"J Lin","year":"2007","unstructured":"Lin J, Wilbur WJ. PubMed related articles: a probabilistic topic-based model for content similarity. BMC Bioinformatics. 2007; 8:423.","journal-title":"BMC Bioinformatics"},{"key":"2240_CR25","unstructured":"Aletras N, Stevenson M. Evaluating topic coherence using distributional semantics. In: Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013): 2013."},{"key":"2240_CR26","doi-asserted-by":"crossref","unstructured":"R\u00f6der M, Both A, Hinneburg A. Exploring the space of topic coherence measures. In: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining: 2015. p. 399\u2013408.","DOI":"10.1145\/2684822.2685324"},{"key":"2240_CR27","doi-asserted-by":"crossref","unstructured":"Newman D, Noh Y, Talley E, Karimi S, Baldwin T. Evaluating topic models for digital libraries. In: Proceedings of the 10th Annual Joint Conference on Digital Libraries (JDCL \u201910): 2010. p. 215\u201324.","DOI":"10.1145\/1816123.1816156"},{"key":"2240_CR28","unstructured":"Mimno D, Wallach H, Talley E, Leenders M, McCallum A. Optimizing semantic coherence in topic models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing: 2011. p. 262\u201372."},{"key":"2240_CR29","unstructured":"McCallum A. MALLET: A Machine Learning for Language Toolkit. 2002. http:\/\/mallet.cs.umass.edu ."},{"issue":"14","key":"2240_CR30","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1001\/jama.1994.03510380059038","volume":"271","author":"HJ Lowe","year":"1994","unstructured":"Lowe HJ, Barnett GO. Understanding and using the medical subject headings (MeSH) vocabulary to perform literature searches. J Am Med Assoc. 1994; 271(14):1103\u20138.","journal-title":"J Am Med Assoc"},{"issue":"3","key":"2240_CR31","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1002\/1097-4571(2000)9999:9999<::AID-ASI1588>3.0.CO;2-7","volume":"52","author":"W Kim","year":"2001","unstructured":"Kim W, Wilbur WJ. Corpus-based statistical screening for content-bearing terms. J Am Soc Inf Sci Technol. 2001; 52(3):247\u201359.","journal-title":"J Am Soc Inf Sci Technol"},{"issue":"22","key":"2240_CR32","doi-asserted-by":"publisher","first-page":"3240","DOI":"10.1093\/bioinformatics\/btu514","volume":"30","author":"L Yeganova","year":"2014","unstructured":"Yeganova L, Kim S, Wilbur WJ. Retro: concept-based clustering of biomedical topical sets. Bioinformatics. 2014; 30(22):3240\u20138.","journal-title":"Bioinformatics"},{"issue":"6","key":"2240_CR33","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1109\/TKDE.2010.165","volume":"23","author":"D Cai","year":"2011","unstructured":"Cai D, He X, Han J. Locally consistent concept factorization for document clustering. IEEE Trans Knowl Eng. 2011; 23(6):902\u201313.","journal-title":"IEEE Trans Knowl Eng"},{"key":"2240_CR34","volume-title":"Managing Gigabytes (2nd Ed.): Compressing and Indexing Documents and Images","author":"IH Witten","year":"1999","unstructured":"Witten IH, Moffat A, Bell TC. Managing Gigabytes (2nd Ed.): Compressing and Indexing Documents and Images. San Francisco: Morgan Kaufmann Publishers Inc.; 1999."},{"issue":"4","key":"2240_CR35","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson S, Zaragoza H. The probabilistic relevance framework: BM25 and beyond. Found Trends Inf Retr. 2009; 3(4):333\u201389.","journal-title":"Found Trends Inf Retr"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-018-2240-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-018-2240-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-018-2240-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T20:54:38Z","timestamp":1751748878000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-018-2240-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,16]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["2240"],"URL":"https:\/\/doi.org\/10.1186\/s12859-018-2240-0","relation":{},"ISSN":["1471-2105"],"issn-type":[{"type":"electronic","value":"1471-2105"}],"subject":[],"published":{"date-parts":[[2018,7,16]]},"assertion":[{"value":"20 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"269"}}