{"id":"https://openalex.org/W3207127885","doi":"https://doi.org/10.1371/journal.pcbi.1009542","title":"A data-driven approach for constructing mutation categories for mutational signature analysis","display_name":"A data-driven approach for constructing mutation categories for mutational signature analysis","publication_year":2021,"publication_date":"2021-10-19","ids":{"openalex":"https://openalex.org/W3207127885","doi":"https://doi.org/10.1371/journal.pcbi.1009542","mag":"3207127885","pmid":"https://pubmed.ncbi.nlm.nih.gov/34665813"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009542","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009542","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1009542","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081666168","display_name":"Gal Gilad","orcid":"https://orcid.org/0000-0003-1913-8918"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gal Gilad","raw_affiliation_strings":["School of Computer Science, Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0003-1913-8918","affiliations":[{"raw_affiliation_string":"School of Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089144841","display_name":"Mark D.M. Leiserson","orcid":"https://orcid.org/0000-0002-1034-4363"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark D. M. Leiserson","raw_affiliation_strings":["Department of Computer Science and Center for Bioinformatics and Computational Biology, University of Maryland, College Park, Maryland, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1034-4363","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Center for Bioinformatics and Computational Biology, University of Maryland, College Park, Maryland, United States of America","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046958549","display_name":"Roded Sharan","orcid":"https://orcid.org/0000-0001-8363-4882"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Roded Sharan","raw_affiliation_strings":["School of Computer Science, Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-8363-4882","affiliations":[{"raw_affiliation_string":"School of Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046958549"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.2652,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48703478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":"10","first_page":"e1009542","last_page":"e1009542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.9955999851226807,"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/T11369","display_name":"Genetic factors in colorectal cancer","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2734","display_name":"Pathology and Forensic Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.798373818397522},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7127596139907837},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.6827763915061951},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6441929936408997},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.49306079745292664},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4889437258243561},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4789334237575531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4500093162059784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4456355571746826},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3781830072402954},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36198127269744873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25809383392333984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10091981291770935}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.798373818397522},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7127596139907837},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.6827763915061951},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6441929936408997},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.49306079745292664},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4889437258243561},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4789334237575531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4500093162059784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4456355571746826},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3781830072402954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36198127269744873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25809383392333984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10091981291770935},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004249","descriptor_name":"DNA Damage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004249","descriptor_name":"DNA Damage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004249","descriptor_name":"DNA Damage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1009542","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009542","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:34665813","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34665813","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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1009542","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009542","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:2e2db682464b4c72ad2e2f5eb12868df","is_oa":true,"landing_page_url":"https://doaj.org/article/2e2db682464b4c72ad2e2f5eb12868df","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 17, Iss 10, p e1009542 (2021)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:7444316","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8555780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8555780","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8555780","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1009542","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009542","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308960","display_name":"United States - Israel Binational Science Foundation","ror":"https://ror.org/00j8z2m73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1545005363","https://openalex.org/W1659842140","https://openalex.org/W2012071848","https://openalex.org/W2025341678","https://openalex.org/W2075665712","https://openalex.org/W2121906867","https://openalex.org/W2129136620","https://openalex.org/W2135029798","https://openalex.org/W2152061559","https://openalex.org/W2158485828","https://openalex.org/W2181632153","https://openalex.org/W2303680209","https://openalex.org/W2609876203","https://openalex.org/W2617540636","https://openalex.org/W2795993993","https://openalex.org/W2799563655","https://openalex.org/W2804661515","https://openalex.org/W2884378660","https://openalex.org/W2885111416","https://openalex.org/W2898789672","https://openalex.org/W2899765160","https://openalex.org/W2951429562","https://openalex.org/W2952020316","https://openalex.org/W2953163445","https://openalex.org/W2963488396","https://openalex.org/W3003990879","https://openalex.org/W3004480399","https://openalex.org/W3022650955","https://openalex.org/W3029777085","https://openalex.org/W3097041219","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Mutational":[0],"processes":[1,22],"shape":[2],"the":[3,57,60,95,130,143,154,173],"genomes":[4],"of":[5,20,36,52,111],"cancer":[6,164],"patients":[7],"and":[8,16,134,138],"their":[9,25],"understanding":[10],"has":[11],"important":[12],"applications":[13],"in":[14,32,59,72,119],"diagnosis":[15],"treatment.":[17],"Current":[18],"modeling":[19],"mutational":[21,87,105],"by":[23],"identifying":[24],"characteristic":[26],"signatures":[27],"views":[28],"each":[29,42],"base":[30,40],"substitution":[31],"a":[33,37,78,83,126],"limited":[34],"context":[35,45,169],"single":[38],"flanking":[39,175],"on":[41,94],"side.":[43],"This":[44],"definition":[46],"gives":[47],"rise":[48],"to":[49,69,103,124,159],"96":[50],"categories":[51],"mutations":[53],"that":[54,97,100,116,128,140,153,167],"have":[55,66],"become":[56],"standard":[58,144],"field,":[61],"even":[62],"though":[63],"wider":[64],"contexts":[65],"been":[67],"shown":[68],"be":[70],"informative":[71],"specific":[73],"cases.":[74],"Here":[75],"we":[76,151,156],"propose":[77],"data-driven":[79],"approach":[80,91],"for":[81,86],"constructing":[82],"mutation":[84,133,168],"categorization":[85,127,145,155],"signature":[88],"analysis.":[89],"Our":[90],"is":[92],"based":[93],"assumption":[96],"tumor":[98],"cells":[99],"are":[101,117],"exposed":[102],"similar":[104,108],"processes,":[106],"show":[107,139,152],"expression":[109,136],"levels":[110],"DNA":[112],"damage":[113],"repair":[114],"genes":[115],"involved":[118],"these":[120],"processes.":[121],"We":[122],"attempt":[123],"find":[125],"maximizes":[129],"agreement":[131],"between":[132],"gene":[135],"data,":[137],"it":[141],"outperforms":[142],"over":[146],"multiple":[147],"quality":[148],"measures.":[149],"Moreover,":[150],"identify":[157],"generalizes":[158],"unseen":[160],"data":[161],"from":[162],"different":[163],"types,":[165],"suggesting":[166],"patterns":[170],"extend":[171],"beyond":[172],"immediate":[174],"bases.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
