{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T13:06:20Z","timestamp":1775221580565,"version":"3.50.1"},"reference-count":11,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T00:00:00Z","timestamp":1664496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM130376"],"award-info":[{"award-number":["R35GM130376"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004412","name":"Human Frontier Science Program","doi-asserted-by":"publisher","award":["RGP0021\/2018"],"award-info":[{"award-number":["RGP0021\/2018"]}],"id":[{"id":"10.13039\/100004412","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Several high-throughput protein\u2013DNA binding methods currently available produce highly reproducible measurements of binding affinity at the level of the k-mer. However, understanding where a k-mer is positioned along a binding site sequence depends on alignment. Here, we present Top-Down Crawl (TDC), an ultra-rapid tool designed for the alignment of k-mer level data in a rank-dependent and position weight matrix (PWM)-independent manner. As the framework only depends on the rank of the input, the method can accept input from many types of experiments (protein binding microarray, SELEX-seq, SMiLE-seq, etc.) without the need for specialized parameterization. Measuring the performance of the alignment using multiple linear regression with 5-fold cross-validation, we find TDC to perform as well as or better than computationally expensive PWM-based methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>TDC can be run online at https:\/\/topdowncrawl.usc.edu or locally as a python package available through pip at https:\/\/pypi.org\/project\/TopDownCrawl.<\/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\/btac653","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T20:48:17Z","timestamp":1664484497000},"page":"5121-5123","source":"Crossref","is-referenced-by-count":6,"title":["Top-Down Crawl: a method for the ultra-rapid and motif-free alignment of sequences with associated binding metrics"],"prefix":"10.1093","volume":"38","author":[{"given":"Brendon H","family":"Cooper","sequence":"first","affiliation":[{"name":"Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089, USA"}]},{"given":"Tsu-Pei","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1752-1884","authenticated-orcid":false,"given":"Remo","family":"Rohs","sequence":"additional","affiliation":[{"name":"Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089, USA"},{"name":"Departments of Chemistry, Physics & Astronomy, and Computer Science, University of Southern California, Los Angeles, CA 90089, USA"}]}],"member":"286","published-online":{"date-parts":[[2022,9,30]]},"reference":[{"key":"2022112014194924000_btac653-B1","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.cell.2015.02.008","article-title":"Deconvolving the recognition of DNA shape from sequence","volume":"161","author":"Abe","year":"2015","journal-title":"Cell"},{"key":"2022112014194924000_btac653-B2","first-page":"28","article-title":"Fitting a mixture model by expectation maximization to discover motifs in biopolymers","volume":"2","author":"Bailey","year":"1994","journal-title":"Proc. Int. Conf. Intell. Syst. Mol. Biol"},{"key":"2022112014194924000_btac653-B3","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1038\/nbt1246","article-title":"Compact, universal DNA microarrays to comprehensively determine transcription-factor binding site specificities","volume":"24","author":"Berger","year":"2006","journal-title":"Nat. Biotechnol"},{"key":"2022112014194924000_btac653-B4","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1093\/bioinformatics\/btv735","article-title":"DNAshapeR: an R\/bioconductor package for DNA shape prediction and feature encoding","volume":"32","author":"Chiu","year":"2016","journal-title":"Bioinformatics"},{"key":"2022112014194924000_btac653-B5","doi-asserted-by":"crossref","first-page":"8529","DOI":"10.1093\/nar\/gkaa642","article-title":"Landscape of DNA binding signatures of myocyte enhancer factor-2B reveals a unique interplay of base and shape readout","volume":"48","author":"Dantas Machado","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2022112014194924000_btac653-B6","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nmeth.4143","article-title":"SMiLE-seq identifies binding motifs of single and dimeric transcription factors","volume":"14","author":"Isakova","year":"2017","journal-title":"Nat. Methods"},{"key":"2022112014194924000_btac653-B7","first-page":"255","author":"Riley","year":"2014"},{"key":"2022112014194924000_btac653-B8","doi-asserted-by":"crossref","first-page":"2288","DOI":"10.1093\/bioinformatics\/btx191","article-title":"BEESEM: estimation of binding energy models using HT-SELEX data","volume":"33","author":"Ruan","year":"2017","journal-title":"Bioinformatics"},{"key":"2022112014194924000_btac653-B9","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1016\/j.cell.2011.10.053","article-title":"Cofactor binding evokes latent differences in DNA binding specificity between Hox proteins","volume":"147","author":"Slattery","year":"2011","journal-title":"Cell"},{"key":"2022112014194924000_btac653-B10","doi-asserted-by":"crossref","first-page":"910","DOI":"10.15252\/msb.20167238","article-title":"Transcription factor family-specific DNA shape readout revealed by quantitative specificity models","volume":"13","author":"Yang","year":"2017","journal-title":"Mol. Syst. Biol"},{"key":"2022112014194924000_btac653-B11","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1101\/gr.222844.117","article-title":"SelexGLM differentiates androgen and glucocorticoid receptor DNA-binding preference over an extended binding site","volume":"28","author":"Zhang","year":"2018","journal-title":"Genome Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac653\/46500103\/btac653.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/22\/5121\/47153861\/btac653.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/22\/5121\/47153861\/btac653.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T14:20:03Z","timestamp":1668954003000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/22\/5121\/6731921"}},"subtitle":[],"editor":[{"given":"Can","family":"Alkan","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,9,30]]},"references-count":11,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,9,30]]},"published-print":{"date-parts":[[2022,11,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac653","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,11,15]]},"published":{"date-parts":[[2022,9,30]]}}}