{"id":"https://openalex.org/W3026661711","doi":"https://doi.org/10.1145/3386052.3386067","title":"Comparing Dissimilarity Metrics for Clustering Gene into Functional Modules using Machine Learning","display_name":"Comparing Dissimilarity Metrics for Clustering Gene into Functional Modules using Machine Learning","publication_year":2020,"publication_date":"2020-01-19","ids":{"openalex":"https://openalex.org/W3026661711","doi":"https://doi.org/10.1145/3386052.3386067","mag":"3026661711"},"language":"en","primary_location":{"id":"doi:10.1145/3386052.3386067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","raw_type":"proceedings-article"},"type":"article","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/A5101539993","display_name":"Xin Yan","orcid":"https://orcid.org/0000-0002-5053-5447"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Yan","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032324362","display_name":"Dantong Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dantong Lyu","raw_affiliation_strings":["Northwest A&F University, Xianyang, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Northwest A&F University, Xianyang, Shaanxi, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101539993"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04445908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","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"}},"topics":[{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","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/T10885","display_name":"Gene expression and cancer classification","score":0.998199999332428,"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/T10497","display_name":"Fungal and yeast genetics research","score":0.9968000054359436,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8753945827484131},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.6977561712265015},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.636223554611206},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.610433042049408},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.569136917591095},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5673975944519043},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5445331931114197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5308785438537598},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5068731904029846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4868687689304352},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4607990086078644},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.4570661783218384},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4150266647338867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41489723324775696},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.29056745767593384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2627474069595337},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18634411692619324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09102898836135864}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8753945827484131},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.6977561712265015},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.636223554611206},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.610433042049408},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.569136917591095},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5673975944519043},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5445331931114197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5308785438537598},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5068731904029846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4868687689304352},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4607990086078644},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.4570661783218384},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4150266647338867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41489723324775696},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.29056745767593384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2627474069595337},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18634411692619324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09102898836135864},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3386052.3386067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2102221598","https://openalex.org/W2137683543","https://openalex.org/W2270192120","https://openalex.org/W2339766289","https://openalex.org/W2470722034","https://openalex.org/W2610618308","https://openalex.org/W2612976808","https://openalex.org/W2677742661","https://openalex.org/W2762638728","https://openalex.org/W2801395517"],"related_works":["https://openalex.org/W2199594781","https://openalex.org/W3035964814","https://openalex.org/W2311450085","https://openalex.org/W3124860551","https://openalex.org/W2965089876","https://openalex.org/W2953854373","https://openalex.org/W3020292803","https://openalex.org/W4232587025","https://openalex.org/W4238952262","https://openalex.org/W2038937869"],"abstract_inverted_index":{"Clustering":[0],"is":[1,43],"widely":[2],"used":[3,29,46,124],"in":[4,59,94,102,156],"biological":[5],"analyses":[6],"for":[7,23,47,61,81,98,125],"clustering":[8,15,63,111,129,153],"genes":[9,100,131],"into":[10],"functional":[11],"modules.":[12],"For":[13],"any":[14],"mechanism,":[16],"we":[17,51],"need":[18],"to":[19],"define":[20],"some":[21],"measurements":[22],"dissimilarity.":[24],"The":[25],"two":[26,76,95],"most":[27],"commonly":[28,45],"dissimilarity":[30,72,121],"metrics":[31,77],"are":[32],"the":[33,40,53,66,92,115],"Manhattan":[34],"distance":[35],"and":[36,64,83,105,108,154],"Euclidean":[37],"distance.":[38],"Moreover,":[39],"1-correlation":[41],"coefficient":[42],"also":[44],"defining":[48],"similarity.":[49],"Here,":[50],"use":[52,79],"transcriptomic":[54,143],"data":[55],"across":[56,145],"multiple":[57],"environments":[58],"yeast":[60],"gene":[62,152],"evaluate":[65],"performance":[67],"of":[68,128,130,142,151],"using":[69],"these":[70],"four":[71],"metrics.":[73],"We":[74,86,117],"designed":[75],"that":[78,88,119],"1-abs(correlation)":[80],"Pearson":[82],"Spearman":[84],"correlation.":[85],"found":[87],"1-abs(Pearson":[89],"correlation)":[90],"works":[91],"best":[93],"test":[96],"cases":[97],"identifying":[99],"involved":[101],"ethanol":[103],"metabolism":[104,107],"galactose":[106],"build":[109],"a":[110],"model":[112],"based":[113,132],"on":[114,133],"metric.":[116],"propose":[118],"this":[120],"metric":[122],"be":[123],"future":[126],"studies":[127],"expression":[134],"level.":[135],"Such":[136],"information,":[137],"combined":[138],"with":[139],"more":[140],"gathering":[141],"information":[144],"environments,":[146],"will":[147],"boost":[148],"our":[149],"understanding":[150],"modularity":[155],"exploring":[157],"unknown":[158],"species.":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}