{"id":"https://openalex.org/W2987617421","doi":"https://doi.org/10.1093/bib/bbz101","title":"Flexible k-mers with variable-length indels for identifying binding sequences of protein dimers","display_name":"Flexible k-mers with variable-length indels for identifying binding sequences of protein dimers","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2987617421","doi":"https://doi.org/10.1093/bib/bbz101","mag":"2987617421"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbz101","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz101","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010503703","display_name":"Chenyang Hong","orcid":"https://orcid.org/0000-0001-8965-3961"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Hong","raw_affiliation_strings":["Department of Computer Science and Engineering at The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering at The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066417693","display_name":"Kevin Y. Yip","orcid":"https://orcid.org/0000-0001-5516-9944"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kevin Y Yip","raw_affiliation_strings":["Department of Computer Science and Engineering at The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering at The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066417693"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.2587,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57148774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"21","issue":"5","first_page":"1787","last_page":"1797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/systematic-evolution-of-ligands-by-exponential-enrichment","display_name":"Systematic evolution of ligands by exponential enrichment","score":0.6416217088699341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5833795070648193},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.526367723941803},{"id":"https://openalex.org/keywords/indel","display_name":"Indel","score":0.5101311802864075},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.48558610677719116},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.46557778120040894},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45857009291648865},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4556678831577301},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.44911256432533264},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.43523120880126953},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.3727627396583557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35336458683013916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3514895439147949},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3452182412147522},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2541946470737457},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22156083583831787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19187819957733154},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1413741111755371}],"concepts":[{"id":"https://openalex.org/C122682173","wikidata":"https://www.wikidata.org/wiki/Q907101","display_name":"Systematic evolution of ligands by exponential enrichment","level":4,"score":0.6416217088699341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5833795070648193},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.526367723941803},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.5101311802864075},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.48558610677719116},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.46557778120040894},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45857009291648865},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4556678831577301},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.44911256432533264},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.43523120880126953},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3727627396583557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35336458683013916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3514895439147949},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3452182412147522},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2541946470737457},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22156083583831787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19187819957733154},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1413741111755371},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/bib/bbz101","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz101","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1900337607","https://openalex.org/W1928213240","https://openalex.org/W1963778673","https://openalex.org/W1964719993","https://openalex.org/W1972792790","https://openalex.org/W1973714307","https://openalex.org/W1974258454","https://openalex.org/W1976209715","https://openalex.org/W1976917060","https://openalex.org/W1986929921","https://openalex.org/W1987122345","https://openalex.org/W1988536808","https://openalex.org/W1988581590","https://openalex.org/W2012114217","https://openalex.org/W2014677321","https://openalex.org/W2018924988","https://openalex.org/W2020816856","https://openalex.org/W2023825247","https://openalex.org/W2046842005","https://openalex.org/W2050284387","https://openalex.org/W2057000344","https://openalex.org/W2087064593","https://openalex.org/W2100558818","https://openalex.org/W2100847260","https://openalex.org/W2101234009","https://openalex.org/W2109897790","https://openalex.org/W2116318902","https://openalex.org/W2119290215","https://openalex.org/W2125125731","https://openalex.org/W2131000278","https://openalex.org/W2132955708","https://openalex.org/W2154855927","https://openalex.org/W2160626228","https://openalex.org/W2165405907","https://openalex.org/W2168390758","https://openalex.org/W2170960297","https://openalex.org/W2259938310","https://openalex.org/W2287365612","https://openalex.org/W2330303612","https://openalex.org/W2338148720","https://openalex.org/W2511791445","https://openalex.org/W3006651541","https://openalex.org/W4246359243","https://openalex.org/W6655478935","https://openalex.org/W6675354045","https://openalex.org/W6677949267","https://openalex.org/W6679579819","https://openalex.org/W6684425192"],"related_works":["https://openalex.org/W2033001683","https://openalex.org/W2187256985","https://openalex.org/W2898349292","https://openalex.org/W2167094946","https://openalex.org/W2894284492","https://openalex.org/W4387460329","https://openalex.org/W2046457574","https://openalex.org/W4313237059","https://openalex.org/W1949458596","https://openalex.org/W3144677376"],"abstract_inverted_index":{"Abstract":[0],"Many":[1],"DNA-binding":[2],"proteins":[3],"interact":[4],"with":[5,34],"partner":[6],"proteins.":[7],"Recently,":[8],"based":[9],"on":[10,103],"the":[11,67,70,127],"high-throughput":[12],"consecutive":[13],"affinity-purification":[14],"systematic":[15],"evolution":[16],"of":[17,69,83,142,153],"ligands":[18],"by":[19],"exponential":[20],"enrichment":[21],"(CAP-SELEX)":[22],"method,":[23],"many":[24],"such":[25,51,89],"protein":[26],"pairs":[27],"have":[28],"been":[29],"found":[30],"to":[31,49,57,116],"bind":[32],"DNA":[33],"flexible":[35],"spacing":[36],"between":[37],"their":[38],"individual":[39],"binding":[40],"motifs.":[41],"Most":[42],"existing":[43],"motif":[44],"representations":[45],"were":[46],"not":[47,124],"designed":[48],"capture":[50],"flexibly":[52,87],"spaced":[53],"regions.":[54,129],"In":[55],"order":[56],"computationally":[58],"discover":[59,147],"more":[60],"co-binding":[61,71],"events":[62,149],"without":[63],"prior":[64],"knowledge":[65],"about":[66],"identities":[68],"proteins,":[72],"a":[73,80,151],"new":[74,81,140],"representation":[75],"is":[76,162],"needed.":[77],"We":[78,130],"propose":[79],"class":[82,141],"sequence":[84,113,143],"patterns":[85,114,121,144],"that":[86,95,122,133],"model":[88,126],"variable":[90,128],"regions":[91],"and":[92,106],"corresponding":[93],"algorithms":[94],"identify":[96],"co-bound":[97,148],"sequences":[98,154],"using":[99],"these":[100],"patterns.":[101],"Based":[102],"both":[104],"simulated":[105],"CAP-SELEX":[107],"data,":[108,138],"features":[109],"derived":[110],"from":[111],"our":[112],"lead":[115],"better":[117],"classification":[118],"performance":[119],"than":[120],"do":[123],"explicitly":[125],"also":[131],"show":[132],"even":[134],"for":[135],"standard":[136],"ChIP-seq":[137],"this":[139],"can":[145],"help":[146],"in":[150,155],"subset":[152],"an":[156],"unsupervised":[157],"manner.":[158],"The":[159],"open-source":[160],"software":[161],"available":[163],"at":[164],"https://github.com/kevingroup/glk-SVM.":[165]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}