{"id":"https://openalex.org/W2789127487","doi":"https://doi.org/10.48550/arxiv.1802.07204","title":"Automation of gene function prediction through modeling human curators' decisions in GO phylogenetic annotation project","display_name":"Automation of gene function prediction through modeling human curators' decisions in GO phylogenetic annotation project","publication_year":2018,"publication_date":"2018-02-20","ids":{"openalex":"https://openalex.org/W2789127487","doi":"https://doi.org/10.48550/arxiv.1802.07204","mag":"2789127487"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1802.07204","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.07204","pdf_url":"https://arxiv.org/pdf/1802.07204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.07204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016534135","display_name":"Haiming Tang","orcid":"https://orcid.org/0000-0001-7058-349X","observed_orcids":["https://orcid.org/0000-0001-7058-349X"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Haiming","raw_affiliation_strings":[". Department of Preventive Medicine , University of Southern California , Los Angeles , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Preventive Medicine , University of Southern California , Los Angeles , CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016853551","display_name":"Paul D. Thomas","orcid":"https://orcid.org/0000-0002-9074-3507","observed_orcids":["https://orcid.org/0000-0002-9074-3507"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas, Paul D","raw_affiliation_strings":[". Department of Biological Sciences , University of Southern California , Los Angeles , CA",". Department of Preventive Medicine , University of Southern California , Los Angeles , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Biological Sciences , University of Southern California , Los Angeles , CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":". Department of Preventive Medicine , University of Southern California , Los Angeles , CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060575386","display_name":"Huaiyu Mi","orcid":"https://orcid.org/0000-0001-8721-202X","observed_orcids":["https://orcid.org/0000-0001-8721-202X"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mi, Huaiyu","raw_affiliation_strings":[". Department of Preventive Medicine , University of Southern California , Los Angeles , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Preventive Medicine , University of Southern California , Los Angeles , CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5249000191688538,"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":0.5249000191688538,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.24609999358654022,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.21719999611377716,"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-ontology","display_name":"Gene Ontology","score":0.9580000042915344},{"id":"https://openalex.org/keywords/gene-function-prediction","display_name":"gene function prediction","score":0.7919999957084656},{"id":"https://openalex.org/keywords/homology-based-annotation","display_name":"homology-based annotation","score":0.7279999852180481},{"id":"https://openalex.org/keywords/automated-annotation-pipeline","display_name":"automated annotation pipeline","score":0.7960000038146973},{"id":"https://openalex.org/keywords/molecular-function","display_name":"molecular function","score":0.6190000176429749},{"id":"https://openalex.org/keywords/cell-components","display_name":"cellular component","score":0.9039999842643738},{"id":"https://openalex.org/keywords/biological-processes","display_name":"biological processes","score":1.0}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8648730516433716},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.65907222032547},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6340323090553284},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6095883846282959},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5583817958831787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5191511511802673},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4712448716163635},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43772655725479126},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.4221493601799011},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4215657711029053},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.42118653655052185},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4196981191635132},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.345731258392334},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34134769439697266},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32617565989494324},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2646557688713074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25327616930007935},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.23514887690544128},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.165623277425766},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15191581845283508},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1213814914226532},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1802.07204","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.07204","pdf_url":"https://arxiv.org/pdf/1802.07204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.1802.07204","doi":"https://doi.org/10.48550/arxiv.1802.07204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.07204","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.07204","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.07204","pdf_url":"https://arxiv.org/pdf/1802.07204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2789127487.pdf","grobid_xml":"https://content.openalex.org/works/W2789127487.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W791550880","https://openalex.org/W1990157150","https://openalex.org/W2001338440","https://openalex.org/W2016205873","https://openalex.org/W2025273505","https://openalex.org/W2057268591","https://openalex.org/W2076637325","https://openalex.org/W2103017472","https://openalex.org/W2114075279","https://openalex.org/W2146341019","https://openalex.org/W2153544371","https://openalex.org/W2472351724","https://openalex.org/W2520894026","https://openalex.org/W2786956758","https://openalex.org/W3189492453"],"related_works":["https://openalex.org/W2171815113","https://openalex.org/W2561761403","https://openalex.org/W4400592908","https://openalex.org/W2284058076","https://openalex.org/W3131602060","https://openalex.org/W2141465955","https://openalex.org/W7100711551","https://openalex.org/W1922686488","https://openalex.org/W2124915144","https://openalex.org/W2117223578"],"abstract_inverted_index":{"The":[0,138,153],"Gene":[1],"Ontology":[2],"Consortium":[3],"launched":[4],"the":[5,22,74,103,122,130,134,144],"GO-PAINT":[6,75],"project":[7,76],"(Phylogenetic":[8],"Annotation":[9,26],"and":[10,16,39,68,99,118,128,157],"INference":[11],"Tool)":[12],"9":[13],"years":[14],"ago":[15],"is":[17],"currently":[18],"being":[19],"used":[20],"in":[21],"GO":[23,32],"Reference":[24],"Genome":[25],"Project":[27],"to":[28,49],"support":[29],"inference":[30],"of":[31,61,66,102,126,147],"function":[33,52],"terms":[34],"(molecular":[35],"function,":[36],"cellular":[37],"component":[38],"biological":[40],"process)":[41],"by":[42,53],"homology.":[43],"PAINT":[44,148],"uses":[45],"a":[46,55],"phylogenetic":[47,83,107,116],"model":[48],"infer":[50],"gene":[51],"homology,":[54],"process":[56],"that":[57],"requires":[58],"manual":[59,135],"curation":[60,136],"experienced":[62],"biocurators.":[63],"Tremendous":[64],"amount":[65],"time":[67],"efforts":[69],"have":[70,93],"been":[71,141],"spent":[72],"on":[73],"yielding":[77],"more":[78,86],"than":[79,87],"4000":[80],"fully":[81],"annotated":[82],"families":[84],"with":[85],"170,000":[88],"annotations.":[89],"These":[90],"preliminary":[91],"data":[92],"thus":[94],"enabled":[95],"potential":[96],"algorithmic":[97],"representation":[98],"automatic":[100],"solvation":[101],"additional":[104],"9000":[105],"unannoated":[106],"families.":[108],"Here":[109],"we":[110],"present":[111],"an":[112],"automated":[113],"pipeline":[114,139,156],"for":[115],"annotation":[117,124],"inference,":[119],"which":[120],"simulates":[121],"standard":[123],"procedures":[125],"curators":[127],"models":[129],"curators'":[131],"decisions":[132],"during":[133],"process.":[137],"has":[140],"built":[142],"into":[143],"newest":[145],"version":[146],"software":[149],"available":[150,160],"at":[151,161],"http://www.pantherdb.org/downloads/index.jsp.":[152],"standalone":[154],"automation":[155],"datasets":[158],"are":[159],"https://github.com/haimingt/GO-PAINT-automation":[162]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-03-06T00:00:00"}
