{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T23:30:54Z","timestamp":1790206254491,"version":"4.1.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T00:00:00Z","timestamp":1562544000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["1DP2GM123485"],"award-info":[{"award-number":["1DP2GM123485"]}]},{"name":"National Institute of Health","award":["1U01HG009431"],"award-info":[{"award-number":["1U01HG009431"]}]},{"name":"National Institute of Health","award":["1R01HG00967401"],"award-info":[{"award-number":["1R01HG00967401"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Support Vector Machines with gapped k-mer kernels (gkm-SVMs) have been used to learn predictive models of regulatory DNA sequence. However, interpreting predictive sequence patterns learned by gkm-SVMs can be challenging. Existing interpretation methods such as deltaSVM, in-silico mutagenesis (ISM) or SHAP either do not scale well or make limiting assumptions about the model that can produce misleading results when the gkm kernel is combined with nonlinear kernels. Here, we propose GkmExplain: a computationally efficient feature attribution method for interpreting predictive sequence patterns from gkm-SVM models that has theoretical connections to the method of Integrated Gradients. Using simulated regulatory DNA sequences, we show that GkmExplain identifies predictive patterns with high accuracy while avoiding pitfalls of deltaSVM and ISM and being orders of magnitude more computationally efficient than SHAP. By applying GkmExplain and a recently developed motif discovery method called TF-MoDISco to gkm-SVM models trained on in vivo transcription factor (TF) binding data, we recover consolidated, non-redundant TF motifs. Mutation impact scores derived using GkmExplain consistently outperform deltaSVM and ISM at identifying regulatory genetic variants from gkm-SVM models of chromatin accessibility in lymphoblastoid cell-lines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Code and example notebooks to reproduce results are at https:\/\/github.com\/kundajelab\/gkmexplain.<\/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\/btz322","type":"journal-article","created":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T23:20:10Z","timestamp":1557444010000},"page":"i173-i182","source":"Crossref","is-referenced-by-count":64,"title":["GkmExplain: fast and accurate interpretation of nonlinear gapped\n                    <i>k<\/i>\n                    -mer SVMs"],"prefix":"10.1093","volume":"35","author":[{"given":"Avanti","family":"Shrikumar","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"Prakash","sequence":"additional","affiliation":[{"name":"Computer Science, BASIS Independent Silicon Valley, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3084-2287","authenticated-orcid":false,"given":"Anshul","family":"Kundaje","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA, USA"},{"name":"Department of Genetics, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"2023062712345226600_btz322-B1","doi-asserted-by":"crossref","first-page":"W202","DOI":"10.1093\/nar\/gkp335","article-title":"MEME SUITE: tools for motif discovery and searching","volume":"37","author":"Bailey","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023062712345226600_btz322-B2","doi-asserted-by":"crossref","first-page":"i207","DOI":"10.1093\/bioinformatics\/btn268","article-title":"Comprehensive in silico mutagenesis highlights functionally important residues in proteins","volume":"24","author":"Bromberg","year":"2008","journal-title":"Bioinformatics"},{"key":"2023062712345226600_btz322-B3","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/nature10808","article-title":"DNase I sensitivity QTLs are a major determinant of human expression variation","volume":"482","author":"Degner","year":"2012","journal-title":"Nature"},{"key":"2023062712345226600_btz322-B4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","year":"2012","journal-title":"Nature"},{"key":"2023062712345226600_btz322-B5","doi-asserted-by":"crossref","first-page":"e1003711.","DOI":"10.1371\/journal.pcbi.1003711","article-title":"Enhanced regulatory sequence prediction using gapped k-mer features","volume":"10","author":"Ghandi","year":"2014","journal-title":"PLoS Comput. Biol"},{"key":"2023062712345226600_btz322-B6","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":"2023062712345226600_btz322-B7","doi-asserted-by":"crossref","first-page":"2976","DOI":"10.1093\/nar\/gkt1249","article-title":"Systematic discovery and characterization of regulatory motifs in ENCODE TF binding experiments","volume":"42","author":"Kheradpour","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023062712345226600_btz322-B8","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1093\/bioinformatics\/btw142","article-title":"LS-GKM: a new gkm-SVM for large-scale datasets","volume":"32","author":"Lee","year":"2016","journal-title":"Bioinformatics"},{"key":"2023062712345226600_btz322-B9","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1038\/ng.3331","article-title":"A method to predict the impact of regulatory variants from DNA sequence","volume":"47","author":"Lee","year":"2015","journal-title":"Nat. Genet"},{"key":"2023062712345226600_btz322-B10","first-page":"1435","article-title":"Fast String Kernels using inexact matching for protein sequences","volume":"5","author":"Leslie","year":"2004","journal-title":"J. Mach. Learn. Res"},{"key":"2023062712345226600_btz322-B11","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"2023062712345226600_btz322-B12","author":"Shrikumar","year":"2017"},{"key":"2023062712345226600_btz322-B13","author":"Shrikumar","year":"2018"},{"key":"2023062712345226600_btz322-B14","author":"Sundararajan","year":"2017"},{"key":"2023062712345226600_btz322-B16"},{"key":"2023062712345226600_btz322-B17","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning\u2013based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat. Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i173\/50720979\/bioinformatics_35_14_i173.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i173\/50720979\/bioinformatics_35_14_i173.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T08:35:28Z","timestamp":1687854928000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/14\/i173\/5529147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":16,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2019,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz322","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/457606","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,7]]},"published":{"date-parts":[[2019,7]]}}}