{"id":"https://openalex.org/W7225275903","doi":"https://doi.org/10.64898/2026.11.01.763467","title":"GOParsimony: parsimonious saltation across the Gene Ontology digraph for efficient functional annotation","display_name":"GOParsimony: parsimonious saltation across the Gene Ontology digraph for efficient functional annotation","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225275903","doi":"https://doi.org/10.64898/2026.11.01.763467"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.01.763467","doi":"https://doi.org/10.64898/2026.11.01.763467","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.01.763467","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.01.763467.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.01.763467.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051233756","display_name":"Paul M. Harrison","orcid":"https://orcid.org/0000-0002-7477-1014","observed_orcids":["https://orcid.org/0000-0002-7477-1014"]},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Paul M Harrison","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051233756"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9897000193595886,"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":0.9897000193595886,"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":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0024999999441206455,"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":0.9890000224113464},{"id":"https://openalex.org/keywords/functional-annotation","display_name":"functional annotation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/parsimony","display_name":"parsimony","score":0.6589999794960022},{"id":"https://openalex.org/keywords/saltation","display_name":"saltation","score":0.7039999961853027},{"id":"https://openalex.org/keywords/semantic-distance","display_name":"semantic distance","score":0.8230000138282776},{"id":"https://openalex.org/keywords/functional-modules","display_name":"functional modules","score":0.6489999890327454},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"hierarchical clustering","score":0.7870000004768372},{"id":"https://openalex.org/keywords/gene-sets","display_name":"gene sets","score":0.41100001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965999960899353},{"id":"https://openalex.org/C2779145032","wikidata":"https://www.wikidata.org/wiki/Q191494","display_name":"Digraph","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43970000743865967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.38839998841285706},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C164953516","wikidata":"https://www.wikidata.org/wiki/Q320357","display_name":"Closed set","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.01.763467","doi":"https://doi.org/10.64898/2026.11.01.763467","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.01.763467","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.01.763467.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.01.763467","doi":"https://doi.org/10.64898/2026.11.01.763467","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.01.763467","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.01.763467.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225275903.pdf","grobid_xml":"https://content.openalex.org/works/W7225275903.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1969353942","https://openalex.org/W2038963685","https://openalex.org/W2120024428","https://openalex.org/W2121343862","https://openalex.org/W2144907278","https://openalex.org/W2997022986","https://openalex.org/W3142564817","https://openalex.org/W4309506674","https://openalex.org/W4403417479","https://openalex.org/W4414334695","https://openalex.org/W6949529390"],"related_works":["https://openalex.org/W2130962401","https://openalex.org/W1969353942","https://openalex.org/W2117673537","https://openalex.org/W2895487334","https://openalex.org/W2271340329","https://openalex.org/W3142564817","https://openalex.org/W2142796008","https://openalex.org/W1548654514","https://openalex.org/W2106419549","https://openalex.org/W2911614256"],"abstract_inverted_index":{"Background.":[0],"The":[1,126],"Gene":[2],"Ontology":[3],"(GO)":[4],"is":[5,81,135],"standardly":[6],"probed":[7],"by":[8,111],"biological":[9],"researchers":[10],"keen":[11],"to":[12,33,36,55,83,88,222],"discern":[13],"the":[14,77,91,100,114,136,214],"functional":[15,101,156,182],"tendencies":[16,102],"of":[17,24,47,103,106,121,128,166,213,216],"their":[18],"gene/protein":[19,58],"data":[20,190],"sets.":[21],"However,":[22],"lists":[23,46,203],"GO":[25,70,115,129,144,159,167,201,218],"terms":[26,48,130,145,168],"are":[27,171],"often":[28],"ontically":[29],"overwhelming,":[30],"and":[31,87,118,163,169,195,208],"need":[32],"be":[34,53,151,179,231],"filtered":[35],"remove":[37],"redundancy.":[38],"Methods":[39],"for":[40,66,99,153,181,187],"such":[41,64,85],"filtering":[42],"either":[43],"employ":[44],"predefined":[45],"that":[49,177,204],"may":[50],"not":[51],"actually":[52],"relevant":[54],"a":[56],"specific":[57],"set,":[59],"or":[60,210],"apply":[61],"arbitrary":[62],"thresholds,":[63],"as":[65],"semantic":[67],"distance":[68],"(i.e.,":[69,94],"term":[71,122,160,202],"dissimilarity).":[72],"Methods.":[73],"Here,":[74],"I":[75],"introduce":[76],"tool":[78],"GOParsimony,":[79],"which":[80],"designed":[82],"avoid":[84],"issues":[86],"pick":[89],"out":[90],"most":[92,96,137],"parsimonious":[93,138],"simplest,":[95],"concise)":[97],"explanation":[98],"any":[104],"set":[105,127],"proteins/genes.":[107],"It":[108],"achieves":[109],"this":[110],"saltating":[112],"across":[113],"digraph,":[116],"assigning":[117],"updating":[119],"cascades":[120],"precedence":[123,132,148,161],"until":[124],"convergence.":[125],"assigned":[131],"=":[133],"1":[134],"set.":[139],"Hierarchical":[140],"clustering":[141],"with":[142,146,174],"other":[143,175,223],"higher":[147],"levels":[149],"can":[150,178,230],"investigated":[152],"clues":[154],"about":[155],"modules.":[157],"Results.":[158],"graphs":[162],"two-dimensional":[164],"heatmaps":[165],"genes/proteins":[170],"output,":[172],"along":[173],"plots":[176],"cross-referenced":[180],"insights.":[183],"In":[184],"test":[185],"analyses":[186],"five":[188],"example":[189],"sets":[191],"from":[192],"budding":[193],"yeast":[194],"human,":[196],"GOParsimony":[197,229],"consistently":[198],"produces":[199],"reduced":[200],"have":[205],"greater":[206],"significance":[207],"low":[209],"intermediate":[211],"coverage":[212],"space":[215],"significant":[217],"terms,":[219],"when":[220],"compared":[221],"distributed":[224],"methods":[225],"in":[226],"default":[227],"mode.":[228],"obtained":[232],"at:":[233],"https://github.com/pmharrison/GOParsimony":[234],".":[235]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}