{"id":"https://openalex.org/W3101423752","doi":"https://doi.org/10.1145/3388440.3412416","title":"Identifying Evolutionary Origins of Repeat Domains in Protein Families","display_name":"Identifying Evolutionary Origins of Repeat Domains in Protein Families","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3101423752","doi":"https://doi.org/10.1145/3388440.3412416","mag":"3101423752"},"language":"en","primary_location":{"id":"doi:10.1145/3388440.3412416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","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/A5011954582","display_name":"Chaitanya Aluru","orcid":"https://orcid.org/0000-0002-8693-6410"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaitanya Aluru","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085615320","display_name":"Mona Singh","orcid":"https://orcid.org/0000-0001-8271-6026"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Singh","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011954582"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10826461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9879999756813049,"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":0.96670001745224,"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/gene-duplication","display_name":"Gene duplication","score":0.671798825263977},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6293782591819763},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6229188442230225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.585148811340332},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.50567626953125},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.472690612077713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4469899535179138},{"id":"https://openalex.org/keywords/protein-domain","display_name":"Protein domain","score":0.4278068542480469},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.38409626483917236},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34409427642822266},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30440300703048706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25372809171676636},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21971246600151062},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10944315791130066}],"concepts":[{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.671798825263977},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6293782591819763},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6229188442230225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.585148811340332},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.50567626953125},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.472690612077713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4469899535179138},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.4278068542480469},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38409626483917236},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34409427642822266},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30440300703048706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25372809171676636},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21971246600151062},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10944315791130066},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3388440.3412416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2780253554","display_name":null,"funder_award_id":"R01-GM076275","funder_id":"https://openalex.org/F4320337373","funder_display_name":"Center for Information Technology"}],"funders":[{"id":"https://openalex.org/F4320337373","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W598320859","https://openalex.org/W1538981962","https://openalex.org/W1623345578","https://openalex.org/W1867763642","https://openalex.org/W1927128198","https://openalex.org/W1984838744","https://openalex.org/W1990812345","https://openalex.org/W2031776773","https://openalex.org/W2087729294","https://openalex.org/W2112537533","https://openalex.org/W2112792893","https://openalex.org/W2116426890","https://openalex.org/W2129505888","https://openalex.org/W2132318428","https://openalex.org/W2135621733","https://openalex.org/W2141052558","https://openalex.org/W2144345157","https://openalex.org/W2147496016","https://openalex.org/W2159892619","https://openalex.org/W2161303529","https://openalex.org/W2808194443","https://openalex.org/W2875386400","https://openalex.org/W2940808208","https://openalex.org/W4231886136"],"related_works":["https://openalex.org/W4388014327","https://openalex.org/W2115382138","https://openalex.org/W1883409887","https://openalex.org/W2367076742","https://openalex.org/W2349742942","https://openalex.org/W4328050637","https://openalex.org/W2776829638","https://openalex.org/W2064495883","https://openalex.org/W2122664375","https://openalex.org/W1569021382"],"abstract_inverted_index":{"Arrays":[0],"of":[1,10,14,35,111,120,146],"repeat":[2,41,134],"domains":[3],"are":[4,19,25],"critical":[5],"to":[6,27,75,82,101,126],"the":[7,32,51,107,130,144,147],"proper":[8],"function":[9],"a":[11,94],"significant":[12],"fraction":[13],"protein":[15,43],"families.":[16],"These":[17],"repeats":[18],"easily":[20],"identified":[21],"in":[22,58],"sequence,":[23],"and":[24,72,79,105,109,136,151],"thought":[26],"have":[28],"arisen":[29],"primarily":[30],"through":[31],"simultaneous":[33,85,138],"duplication":[34,54,78],"multiple":[36],"domains.":[37],"However,":[38],"for":[39],"most":[40],"domain":[42,53,70,77,86,139],"families,":[44],"very":[45],"little":[46],"is":[47,154],"typically":[48],"known":[49],"about":[50],"specific":[52],"events":[55,81],"that":[56,68,141],"occurred":[57,142],"their":[59],"evolutionary":[60],"histories.":[61],"Here":[62],"we":[63,122],"extend":[64],"existing":[65],"reconciliation":[66,103],"formulations":[67],"use":[69],"trees":[71,74],"sequence":[73],"infer":[76],"loss":[80],"additionally":[83],"consider":[84],"duplications":[87,140],"under":[88],"arbitrary":[89],"cost":[90],"models.":[91],"We":[92],"develop":[93],"novel":[95],"integer":[96],"linear":[97],"programming":[98],"(ILP)":[99],"solution":[100],"this":[102],"problem,":[104],"demonstrate":[106],"accuracy":[108],"robustness":[110],"our":[112,124],"approach":[113,125],"on":[114],"simulated":[115],"datasets.":[116],"Finally,":[117],"as":[118],"proof":[119],"principle,":[121],"apply":[123],"an":[127],"orthogroup":[128],"containing":[129],"C2H2":[131],"zinc":[132],"finger":[133],"domain,":[135],"identify":[137],"at":[143,156],"onset":[145],"primate":[148],"lineage.":[149],"Simulation":[150],"ILP":[152],"code":[153],"available":[155],"https://github.com/Singh-Lab/treeSim.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
