{"id":"https://openalex.org/W2802867082","doi":"https://doi.org/10.1109/tcbb.2018.2828313","title":"Efficient Mining Multi-Mers in a Variety of Biological Sequences","display_name":"Efficient Mining Multi-Mers in a Variety of Biological Sequences","publication_year":2018,"publication_date":"2018-04-19","ids":{"openalex":"https://openalex.org/W2802867082","doi":"https://doi.org/10.1109/tcbb.2018.2828313","mag":"2802867082","pmid":"https://pubmed.ncbi.nlm.nih.gov/29993642"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2828313","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"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/A5101732656","display_name":"Jingsong Zhang","orcid":"https://orcid.org/0000-0002-9023-9933"},"institutions":[{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]},{"id":"https://openalex.org/I4210106477","display_name":"Shanghai Institutes for Biological Sciences","ror":"https://ror.org/011rf9d86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106477"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingsong Zhang","raw_affiliation_strings":["Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210121447","https://openalex.org/I4210106477","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008649715","display_name":"Jianmei Guo","orcid":"https://orcid.org/0000-0001-5787-6781"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmei Guo","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447313","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0003-0794-2546"},"institutions":[{"id":"https://openalex.org/I177933477","display_name":"Second Military Medical University","ror":"https://ror.org/04tavpn47","country_code":"CN","type":"education","lineage":["https://openalex.org/I177933477"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":["Second Military Medical University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Second Military Medical University, Shanghai, China","institution_ids":["https://openalex.org/I177933477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016501386","display_name":"Xiangtian Yu","orcid":"https://orcid.org/0000-0002-9571-3446"},"institutions":[{"id":"https://openalex.org/I4210106477","display_name":"Shanghai Institutes for Biological Sciences","ror":"https://ror.org/011rf9d86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106477"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangtian Yu","raw_affiliation_strings":["Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210106477","https://openalex.org/I19820366","https://openalex.org/I4210121447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101821823","display_name":"Xiaoqing Yu","orcid":"https://orcid.org/0000-0003-3572-5821"},"institutions":[{"id":"https://openalex.org/I67001856","display_name":"Shanghai Institute of Technology","ror":"https://ror.org/00fjzqj15","country_code":"CN","type":"education","lineage":["https://openalex.org/I67001856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Yu","raw_affiliation_strings":["Department of Applied Mathematics, Shanghai Institute of Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Shanghai Institute of Technology, Shanghai, China","institution_ids":["https://openalex.org/I67001856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038446460","display_name":"Wei-Feng Guo","orcid":"https://orcid.org/0000-0003-0565-177X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Guo","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026321844","display_name":"Tao Zeng","orcid":"https://orcid.org/0000-0002-0295-3994"},"institutions":[{"id":"https://openalex.org/I4210106477","display_name":"Shanghai Institutes for Biological Sciences","ror":"https://ror.org/011rf9d86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106477"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zeng","raw_affiliation_strings":["Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210106477","https://openalex.org/I19820366","https://openalex.org/I4210121447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012283696","display_name":"Luonan Chen","orcid":"https://orcid.org/0000-0002-3960-0068"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210106477","display_name":"Shanghai Institutes for Biological Sciences","ror":"https://ror.org/011rf9d86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106477"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Luonan Chen","raw_affiliation_strings":["Center for Excellence in Animal Evolution and Genetics, Chinese Academy of Sciences, Kunming, China","Center for Excellence in Molecular Cell Science, Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China","Collaborative Research Center for Innovative Mathematical Modelling, Institute of Industrial Science, University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Excellence in Animal Evolution and Genetics, Chinese Academy of Sciences, Kunming, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Center for Excellence in Molecular Cell Science, Institute of Biochemistry and Cell Biology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210106477","https://openalex.org/I4210121447","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Collaborative Research Center for Innovative Mathematical Modelling, Institute of Industrial Science, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.35,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.514283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":83},"biblio":{"volume":"17","issue":"3","first_page":"949","last_page":"958"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9982,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9982,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9979,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9967,"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/sequence","display_name":"Sequence (biology)","score":0.58418083},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.49596676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6032039},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.58418083},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5296383},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.49596676},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48438343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47421077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44667196},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4118573},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.29142496},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26263827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21995261},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17035913}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2828313","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29993642","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai","award_id":"17ZR1406900"},{"funder":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai","award_id":"17ZR1446100"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"91529303"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"31771476"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61602460"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"11701379"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61772200"},{"funder":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation","award_id":"2016M601660"},{"funder":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation","award_id":"2016M600338"}],"datasets":[],"versions":[],"referenced_works_count":54,"referenced_works":["https://openalex.org/W1572096077","https://openalex.org/W1892363833","https://openalex.org/W1989245611","https://openalex.org/W1998031633","https://openalex.org/W2003347102","https://openalex.org/W2015536647","https://openalex.org/W2016661940","https://openalex.org/W2027667941","https://openalex.org/W2035471593","https://openalex.org/W2037444377","https://openalex.org/W2051486134","https://openalex.org/W2053229585","https://openalex.org/W2057253402","https://openalex.org/W2058009774","https://openalex.org/W2096128575","https://openalex.org/W2101849110","https://openalex.org/W2105191441","https://openalex.org/W2111384508","https://openalex.org/W2114392707","https://openalex.org/W2116412478","https://openalex.org/W2122555405","https://openalex.org/W2124626190","https://openalex.org/W2125266506","https://openalex.org/W2126419817","https://openalex.org/W2142428670","https://openalex.org/W2159954944","https://openalex.org/W2161546116","https://openalex.org/W2161922860","https://openalex.org/W2163584430","https://openalex.org/W2171003081","https://openalex.org/W2198606573","https://openalex.org/W2268029186","https://openalex.org/W2305104349","https://openalex.org/W2322633195","https://openalex.org/W2335527355","https://openalex.org/W2337686908","https://openalex.org/W2337819340","https://openalex.org/W2343816076","https://openalex.org/W2344493264","https://openalex.org/W2411730464","https://openalex.org/W2498761000","https://openalex.org/W2508622936","https://openalex.org/W2514175126","https://openalex.org/W2518058967","https://openalex.org/W2571952481","https://openalex.org/W2617103607","https://openalex.org/W2631063318","https://openalex.org/W2733397209","https://openalex.org/W2754346778","https://openalex.org/W2800948866","https://openalex.org/W2951160681","https://openalex.org/W3122121132","https://openalex.org/W758607154","https://openalex.org/W952339689"],"related_works":["https://openalex.org/W54497855","https://openalex.org/W4243495532","https://openalex.org/W3125814499","https://openalex.org/W3121970507","https://openalex.org/W217960748","https://openalex.org/W2110028391","https://openalex.org/W2092772380","https://openalex.org/W2090827041","https://openalex.org/W2053421025","https://openalex.org/W2032233321"],"abstract_inverted_index":{"Counting":[0],"the":[1,62,109,115,122],"occurrence":[2],"frequency":[3],"of":[4,64,94,105,117,131],"each":[5],"-mer":[6,23,46],"in":[7,17,66,74,128],"a":[8,12,28,129],"biological":[9,72],"sequence":[10,39],"is":[11,36,89,103,121],"preliminary":[13],"yet":[14],"important":[15],"step":[16],"many":[18],"bioinformatics":[19],"applications.":[20],"However,":[21],"most":[22],"counting":[24],"algorithms":[25],"rely":[26],"on":[27,50,57],"given":[29],"k":[30],"to":[31,91,114,125],"produce":[32],"single-length":[33],"-mers,":[34],"which":[35,102],"inefficient":[37],"for":[38,41],"analysis":[40,63],"different":[42],"k.":[43],"Moreover,":[44,113],"existing":[45],"counters":[47],"focus":[48],"more":[49],"DNA":[51],"and":[52,55,77,135],"RNA":[53],"sequences":[54,68],"less":[56],"protein":[58,67,136],"ones.":[59],"In":[60],"practice,":[61],"-mers":[65,93],"can":[69],"provide":[70],"substantial":[71],"insights":[73],"structure,":[75],"function":[76],"evolution.":[78],"To":[79],"this":[80],"end,":[81],"an":[82],"efficient":[83],"algorithm,":[84],"called":[85],"MulMer":[86,120],"(Multiple-Mer":[87],"mining),":[88],"proposed":[90],"mine":[92,126],"various":[95],"lengths":[96],"termed":[97],"multi-mers":[98,127],"via":[99],"inverted-index":[100],"technique,":[101],"orders":[104],"magnitude":[106],"faster":[107],"than":[108],"conventional":[110],"forward-index":[111],"methods.":[112],"best":[116],"our":[118],"knowledge,":[119],"first":[123],"able":[124],"variety":[130],"sequences,":[132],"including":[133],"DNARNA":[134],"sequences.":[137]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2802867082","counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-01-02T06:50:07.532960","created_date":"2018-05-17"}