{"id":"https://openalex.org/W2049693862","doi":"https://doi.org/10.1145/2649387.2649446","title":"Community detection-based features for sequence classification","display_name":"Community detection-based features for sequence classification","publication_year":2014,"publication_date":"2014-09-20","ids":{"openalex":"https://openalex.org/W2049693862","doi":"https://doi.org/10.1145/2649387.2649446","mag":"2049693862"},"language":"en","primary_location":{"id":"doi:10.1145/2649387.2649446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2649446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5071868223","display_name":"Karthik Tangirala","orcid":null},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Tangirala","raw_affiliation_strings":["Kansas State University, Manhattan, Kansas","Kansas State University, Manhattan Kansas#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, Kansas","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Kansas State University, Manhattan Kansas#TAB#","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067341711","display_name":"Doina Caragea","orcid":"https://orcid.org/0000-0002-6440-0914"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doina Caragea","raw_affiliation_strings":["Kansas State University, Manhattan, Kansas","Kansas State University, Manhattan Kansas#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, Kansas","institution_ids":["https://openalex.org/I189590672"]},{"raw_affiliation_string":"Kansas State University, Manhattan Kansas#TAB#","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":4.4079,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93729373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"559","last_page":"568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9994000196456909,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9994000196456909,"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":0.9980000257492065,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6691602468490601},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5404731631278992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202513933181763},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42159879207611084},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07268789410591125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691602468490601},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5404731631278992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202513933181763},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42159879207611084},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07268789410591125},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2649387.2649446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2649446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G210295588","display_name":null,"funder_award_id":"CNS-1006860, CNS-1126709, EPS-1006860, EPS-0919443, ACI-1341026, MRI-1126709","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G2241902566","display_name":"Prairie Light: Next Generation Networking for Mid-continent Science","funder_award_id":"1006860","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6235688630","display_name":null,"funder_award_id":"CNS-1006860, CNS-1126709, EPS-1006860, EPS-0919443, ACI-1341026, MRI-1126709","funder_id":"https://openalex.org/F4320338283","funder_display_name":"Office of Experimental Program to Stimulate Competitive Research"},{"id":"https://openalex.org/G8965658532","display_name":null,"funder_award_id":"CNS-1006860, CNS-1126709, EPS-1006860, EPS-0919443, ACI-1341026, MRI-1126709","funder_id":"https://openalex.org/F4320337563","funder_display_name":"Division of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337563","display_name":"Division of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320338283","display_name":"Office of Experimental Program to Stimulate Competitive Research","ror":"https://ror.org/04k9mqs78"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W12829028","https://openalex.org/W1498198371","https://openalex.org/W1969128289","https://openalex.org/W1971421925","https://openalex.org/W1974487050","https://openalex.org/W1982322675","https://openalex.org/W1983078185","https://openalex.org/W1997975869","https://openalex.org/W2006070913","https://openalex.org/W2017987256","https://openalex.org/W2020816856","https://openalex.org/W2037603696","https://openalex.org/W2038920443","https://openalex.org/W2047940964","https://openalex.org/W2048679005","https://openalex.org/W2061548680","https://openalex.org/W2092481996","https://openalex.org/W2095012686","https://openalex.org/W2095293504","https://openalex.org/W2099440252","https://openalex.org/W2100947741","https://openalex.org/W2111642621","https://openalex.org/W2111765516","https://openalex.org/W2115761267","https://openalex.org/W2127048411","https://openalex.org/W2131681506","https://openalex.org/W2132202037","https://openalex.org/W2148014281","https://openalex.org/W2149772057","https://openalex.org/W2157009395","https://openalex.org/W2157963512","https://openalex.org/W2163584430","https://openalex.org/W2164998314","https://openalex.org/W2168171990","https://openalex.org/W2170960297","https://openalex.org/W2885241647","https://openalex.org/W3102641634","https://openalex.org/W3103344744","https://openalex.org/W3196994822","https://openalex.org/W4231476871","https://openalex.org/W6679686813"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W3003836766","https://openalex.org/W2163831990","https://openalex.org/W2378160586","https://openalex.org/W1978450727","https://openalex.org/W4244943737","https://openalex.org/W2996038082","https://openalex.org/W2289108895"],"abstract_inverted_index":{"Machine":[0],"learning":[1,11,73],"algorithms":[2,12,74],"are":[3,37,119,134,148,234],"widely":[4],"used":[5,39,209],"to":[6,15,40,80,84,90,139,210,261],"annotate":[7],"biological":[8,42],"sequences.":[9,43,191,274],"Most":[10],"require":[13],"data":[14],"be":[16],"represented":[17],"using":[18,32,50],"a":[19,66,86,104,175,183,249,268],"vector":[20],"of":[21,26,47,60,71,131,142,177,186,190,194,204,251,254,270,273],"features.":[22],"In":[23],"the":[24,33,45,51,58,61,68,72,114,124,143,170,187,202,226,230,244,263],"absence":[25],"biologically":[27],"informative":[28,92,236],"features,":[29],"k-mers":[30],"generated":[31,49,228],"sliding":[34,52],"window-based":[35,53],"approach":[36,54,89,100,173,233,247,266],"commonly":[38],"represent":[41,211],"However,":[44],"number":[46],"features":[48,93,195,227,258],"increases":[55],"exponentially":[56],"with":[57,229],"length":[59],"k-mer,":[62],"k,":[63],"and":[64,111,201,221],"as":[65,259],"consequence,":[67],"computational":[69],"time":[70],"also":[75],"increases.":[76],"As":[77],"an":[78,164],"alternative":[79],"k-mers,":[81],"we":[82,162,240],"propose":[83,163],"use":[85],"community":[87,98,171,231,245,264],"detection":[88,99,146,172,232,246,265],"identify":[91],"for":[94,152,213],"sequence":[95],"classification.":[96],"The":[97],"is":[101,182,196,208],"run":[102],"on":[103,108,174,248,267],"network":[105],"constructed":[106],"based":[107],"k-mer":[109],"similarity,":[110],"it":[112],"has":[113],"advantage":[115],"that":[116,133,167,225,242],"class":[117],"labels":[118],"not":[120],"needed":[121],"when":[122,137],"constructing":[123],"network.":[125,144],"It":[126],"works":[127],"by":[128],"identifying":[129],"sets":[130,207],"nodes":[132,141],"densely":[135,155],"connected":[136,156],"compared":[138,260],"other":[140],"Community":[145],"approaches":[147],"computationally":[149],"expensive,":[150],"especially":[151],"large":[153,271],"or":[154],"networks.":[157],"To":[158],"address":[159],"this":[160],"challenge,":[161],"efficient":[165],"strategy":[166],"involves":[168],"running":[169,243,262],"set":[176,189,193,250,269],"samples,":[178],"where":[179],"each":[180,199],"sample":[181],"small":[184,252],"subset":[185],"total":[188],"A":[192],"obtained":[197],"from":[198],"sample,":[200],"union":[203],"all":[205],"feature":[206],"sequences":[212,255],"classification":[214],"purposes.":[215],"Experimental":[216],"results":[217],"in":[218],"both":[219],"supervised":[220],"semi-supervised":[222],"settings":[223],"show":[224],"more":[235],"than":[237],"k-mers.":[238],"Furthermore,":[239],"observe":[241],"samples":[253,272],"produces":[256],"better":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}