{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T19:16:14Z","timestamp":1791918974230,"version":"4.3.4"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1218201, ABI-1565076"],"award-info":[{"award-number":["IIS-1218201, ABI-1565076"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["G12MD007591"],"award-info":[{"award-number":["G12MD007591"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. While the development of both in vivo and in vitro profiling techniques have significantly enhanced our knowledge of transcription factor (TF)-DNA interactions, computational models of TF-DNA interactions are relatively simple and may not reveal sufficient biological insight. In particular, supervised learning based models for TF-DNA interactions attempt to map sequence-level features (k-mers) to binding event but usually ignore the location of k-mers, which can cause data fragmentation and consequently inferior model performance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we propose a novel algorithm based on the so-called multiple-instance learning (MIL) paradigm. MIL breaks each DNA sequence into multiple overlapping subsequences and models each subsequence separately, therefore implicitly takes into consideration binding site locations, resulting in both higher accuracy and better interpretability of the models. The result from both in vivo and in vitro TF-DNA interaction data show that our approach significantly outperform conventional single-instance learning based algorithms. Importantly, the models learned from in vitro data using our approach can predict in vivo binding with very good accuracy. In addition, the location information obtained by our method provides additional insight for motif finding results from ChIP-Seq data. Finally, our approach can be easily combined with other state-of-the-art TF-DNA interaction modeling methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>http:\/\/www.cs.utsa.edu\/\u223cjruan\/MIL\/<\/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\/btx115","type":"journal-article","created":{"date-parts":[[2017,2,27]],"date-time":"2017-02-27T20:19:21Z","timestamp":1488226761000},"page":"2097-2105","source":"Crossref","is-referenced-by-count":23,"title":["Computational modeling of <i>in vivo<\/i> and <i>in vitro<\/i> protein-DNA interactions by multiple instance learning"],"prefix":"10.1093","volume":"33","author":[{"given":"Zhen","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Texas at San Antonio, San Antonio, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Ruan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Texas at San Antonio, San Antonio, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2017,3,1]]},"reference":[{"key":"2023051601055265600_btx115-B1","first-page":"561","volume-title":"Advances in Neural Information Processing Systems","author":"Andrews","year":"2002"},{"key":"2023051601055265600_btx115-B2","doi-asserted-by":"crossref","first-page":"e20059.","DOI":"10.1371\/journal.pone.0020059","article-title":"A linear model for transcription factor binding affinity prediction in protein binding microarrays","volume":"6","author":"Annala","year":"2011","journal-title":"PloS One"},{"key":"2023051601055265600_btx115-B3","first-page":"21","article-title":"On learning from multi-instance examples: Empirical evaluation of a theoretical approach","volume":"97","author":"Auer","year":"1997","journal-title":"ICML"},{"key":"2023051601055265600_btx115-B4","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1126\/science.1162327","article-title":"Diversity and complexity in DNA recognition by transcription factors","volume":"324","author":"Badis","year":"2009","journal-title":"Science"},{"key":"2023051601055265600_btx115-B5","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1001007","article-title":"Using sequence-specific chemical and structural properties of DNA to predict transcription factor binding sites","volume":"6","author":"Bauer","year":"2010","journal-title":"PLoS Comput. Biol"},{"key":"2023051601055265600_btx115-B6","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1016\/0022-2836(87)90354-8","article-title":"Selection of DNA binding sites by regulatory proteins: Statistical-mechanical theory and application to operators and promoters","volume":"193","author":"Berg","year":"1987","journal-title":"J. Mol. Biol"},{"key":"2023051601055265600_btx115-B7","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1101\/gr.112656.110","article-title":"High-resolution genome-wide in vivo footprinting of diverse transcription factors in human cells","volume":"21","author":"Boyle","year":"2011","journal-title":"Genome Res"},{"key":"2023051601055265600_btx115-B8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"2023051601055265600_btx115-B9","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1038\/84792","article-title":"Regulatory element detection using correlation with expression","volume":"27","author":"Bussemaker","year":"2001","journal-title":"Nat. Genet"},{"key":"2023051601055265600_btx115-B10","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1073\/pnas.0630591100","article-title":"Integrating regulatory motif discovery and genome-wide expression analysis","volume":"100","author":"Conlon","year":"2003","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023051601055265600_btx115-B11","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1093\/bioinformatics\/btr614","article-title":"Epigenetic priors for identifying active transcription factor binding sites","volume":"28","author":"Cuellar-Partida","year":"2012","journal-title":"Bioinformatics"},{"key":"2023051601055265600_btx115-B12","doi-asserted-by":"crossref","first-page":"e141","DOI":"10.1093\/bioinformatics\/btl223","article-title":"Statistical mechanical modeling of genome-wide transcription factor occupancy data by matrixreduce","volume":"22","author":"Foat","year":"2006","journal-title":"Bioinformatics"},{"key":"2023051601055265600_btx115-B13","article-title":"Applying propositional learning algorithms to multi-instance data","author":"Frank","year":"2003"},{"key":"2023051601055265600_btx115-B14","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1186\/1471-2164-16-S4-S3","article-title":"A structure-based multiple-instance learning approach to predicting in vitro transcription factor-DNA interaction","volume":"16","author":"Gao","year":"2015","journal-title":"BMC Genomics"},{"key":"2023051601055265600_btx115-B15","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1016\/j.molcel.2010.05.004","article-title":"Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and b cell identities","volume":"38","author":"Heinz","year":"2010","journal-title":"Mol. Cell"},{"key":"2023051601055265600_btx115-B16","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s11135-007-9077-3","article-title":"Linear versus logistic regression when the dependent variable is a dichotomy","volume":"43","author":"Hellevik","year":"2009","journal-title":"Qual. Quan"},{"key":"2023051601055265600_btx115-B17","article-title":"Integrative annotation of chromatin elements from encode data","author":"Hoffman","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023051601055265600_btx115-B18","first-page":"D117","article-title":"Uniprobe, update 2015: new tools and content for the online database of protein-binding microarray data on protein-DNA interactions","volume":"43","author":"Hume","year":"2015","journal-title":"J. Biol. Chem"},{"key":"2023051601055265600_btx115-B19","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1101\/gr.146399.112","article-title":"Temporal mapping of cebpa and cebpb binding during liver regeneration reveals dynamic occupancy and specific regulatory codes for homeostatic and cell cycle gene batteries","volume":"23","author":"Jakobsen","year":"2013","journal-title":"Genome Res"},{"key":"2023051601055265600_btx115-B20","doi-asserted-by":"crossref","first-page":"e0150715.","DOI":"10.1371\/journal.pone.0150715","article-title":"Comprehensive identification of kruppel-like factor family members contributing to the self-renewal of mouse embryonic stem cells and cellular reprogramming","volume":"11","author":"Jeon","year":"2016","journal-title":"PLoS ONE"},{"key":"2023051601055265600_btx115-B21","doi-asserted-by":"crossref","first-page":"5221","DOI":"10.1093\/nar\/gkn488","article-title":"Genome-wide identification of in vivo protein\u2013DNA binding sites from chip-seq data","volume":"36","author":"Jothi","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023051601055265600_btx115-B22","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1162\/089976601300014493","article-title":"Improvements to platt\u2019s smo algorithm for SVM classifier design","volume":"13","author":"Keerthi","year":"2001","journal-title":"Neural Comput"},{"key":"2023051601055265600_btx115-B23","doi-asserted-by":"crossref","first-page":"191","DOI":"10.2307\/2347628","article-title":"Ridge estimators in logistic regression","volume":"41","author":"Le Cessie","year":"1992","journal-title":"Appl. Stat"},{"key":"2023051601055265600_btx115-B24","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.jgg.2011.05.004","article-title":"c-jun binding site identification in k562 cells","volume":"38","author":"Li","year":"2011","journal-title":"J. Genet. Genomics"},{"key":"2023051601055265600_btx115-B25","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1126\/science.1131007","article-title":"A systems approach to measuring the binding energy landscapes of transcription factors","volume":"315","author":"Maerkl","year":"2007","journal-title":"Science"},{"key":"2023051601055265600_btx115-B26","first-page":"570","article-title":"A framework for multiple-instance learning","author":"Maron","year":"1998","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023051601055265600_btx115-B27","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.1038\/ng1473","article-title":"Rapid analysis of the DNA-binding specificities of transcription factors with DNA microarrays","volume":"36","author":"Mukherjee","year":"2004","journal-title":"Nat. Genet"},{"key":"2023051601055265600_btx115-B28","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1038\/nbt.1882","article-title":"Direct measurement of DNA affinity landscapes on a high-throughput sequencing instrument","volume":"29","author":"Nutiu","year":"2011","journal-title":"Nat. Biotechnol"},{"key":"2023051601055265600_btx115-B29","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1022611825350","article-title":"Boolean feature discovery in empirical learning","volume":"5","author":"Pagallo","year":"1990","journal-title":"Mach. Learn"},{"key":"2023051601055265600_btx115-B30","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1101\/gr.112623.110","article-title":"Accurate inference of transcription factor binding from DNA sequence and chromatin accessibility data","volume":"21","author":"Pique-Regi","year":"2011","journal-title":"Genome Res"},{"key":"2023051601055265600_btx115-B31","first-page":"185","article-title":"12 fast training of support vector machines using sequential minimal optimization","author":"Platt","year":"1999","journal-title":"Adv. Kernel Methods"},{"key":"2023051601055265600_btx115-B32","volume-title":"C4.5: Programs for Machine Learning","author":"Quinlan","year":"1993"},{"key":"2023051601055265600_btx115-B33","doi-asserted-by":"crossref","first-page":"7365","DOI":"10.1074\/jbc.270.13.7365","article-title":"Concerted participation of nf-kappa b and c\/ebp heteromer in lipopolysaccharide induction of serum amyloid a gene expression in liver","volume":"270","author":"Ray","year":"1995","journal-title":"J. Biol. Chem"},{"key":"2023051601055265600_btx115-B34","doi-asserted-by":"crossref","first-page":"3487","DOI":"10.1093\/nar\/gkg630","article-title":"Reduce: an online tool for inferring cis-regulatory elements and transcriptional module activities from microarray data","volume":"31","author":"Roven","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2023051601055265600_btx115-B35","doi-asserted-by":"crossref","first-page":"251.","DOI":"10.1186\/gb-2012-13-10-251","article-title":"The roles of the reprogramming factors oct4, sox2 and klf4 in resetting the somatic cell epigenome during induced pluripotent stem cell generation","volume":"13","author":"Schmidt","year":"2012","journal-title":"Genome Biol"},{"key":"2023051601055265600_btx115-B36","doi-asserted-by":"crossref","first-page":"158.","DOI":"10.12688\/f1000research.7485.1","article-title":"Prediction of fine-tuned promoter activity from DNA sequence","volume":"5","author":"Siwo","year":"2016","journal-title":"F1000Research"},{"key":"2023051601055265600_btx115-B37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1196\/annals.1407.021","article-title":"Dialogue on reverse-engineering assessment and methods","volume":"1115","author":"Stolovitzky","year":"2007","journal-title":"Ann. N. Y. Acad. Sci"},{"key":"2023051601055265600_btx115-B38","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/0076-6879(90)83015-2","article-title":"consensus patterns in DNA","volume":"183","author":"Stormo","year":"1990","journal-title":"Methods Enzymol"},{"key":"2023051601055265600_btx115-B39","article-title":"String v10: protein\u2013protein interaction networks, integrated over the tree of life","author":"Szklarczyk","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023051601055265600_btx115-B40","doi-asserted-by":"crossref","first-page":"40974","DOI":"10.1074\/jbc.M111.290874","article-title":"Binding site specificity and factor redundancy in activator protein-1-driven human papillomavirus chromatin-dependent transcription","volume":"286","author":"Wang","year":"2011","journal-title":"J. Biol. Chem"},{"key":"2023051601055265600_btx115-B41","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/nbt.2486","article-title":"Evaluation of methods for modeling transcription factor sequence specificity","volume":"31","author":"Weirauch","year":"2013","journal-title":"Nat. Biotechnol"},{"key":"2023051601055265600_btx115-B42","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.cell.2014.08.009","article-title":"Determination and inference of eukaryotic transcription factor sequence specificity","volume":"158","author":"Weirauch","year":"2014","journal-title":"Cell"},{"key":"2023051601055265600_btx115-B43","first-page":"1","article-title":"Most+: a de novo motif finding approach combining genomic sequence and heterogeneous genome-wide signatures","volume":"16","author":"Zhang","year":"2015","journal-title":"BMC Genomics"},{"key":"2023051601055265600_btx115-B44","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1089\/cmb.2005.12.894","article-title":"Finding short DNA motifs using permuted Markov models","volume":"12","author":"Zhao","year":"2005","journal-title":"J. Comput. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/2097\/50314715\/bioinformatics_33_14_2097.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/14\/2097\/50314715\/bioinformatics_33_14_2097.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T01:06:40Z","timestamp":1684199200000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/14\/2097\/3059139"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2017,3,1]]},"references-count":44,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2017,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx115","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,7,15]]},"published":{"date-parts":[[2017,3,1]]}}}