{"id":"https://openalex.org/W7225622907","doi":"https://doi.org/10.64898/2026.11.05.764556","title":"Choice of annotation data significantly impacts automated reconstruction of genome-scale metabolic networks","display_name":"Choice of annotation data significantly impacts automated reconstruction of genome-scale metabolic networks","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225622907","doi":"https://doi.org/10.64898/2026.11.05.764556"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.05.764556","doi":"https://doi.org/10.64898/2026.11.05.764556","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764556","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764556.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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/2026/11/09/2026.11.05.764556.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140558572","display_name":"B Adam Bates","orcid":"https://orcid.org/0009-0000-7607-6237","observed_orcids":["https://orcid.org/0009-0000-7607-6237"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blaine Adam Bates","raw_affiliation_strings":["University of Virginia"],"raw_orcid":"https://orcid.org/0009-0000-7607-6237","affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000119406","display_name":"Jason A. Papin","orcid":"https://orcid.org/0000-0002-2769-5805","observed_orcids":["https://orcid.org/0000-0002-2769-5805"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason A Papin","raw_affiliation_strings":["University of Virginia"],"raw_orcid":"https://orcid.org/0000-0002-2769-5805","affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000119406"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9990000128746033,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9990000128746033,"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":0.0005000000237487257,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.00039999998989515007,"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/genome-scale-metabolic-models","display_name":"genome-scale metabolic models","score":0.8629999756813049},{"id":"https://openalex.org/keywords/genome-annotation","display_name":"genome annotation","score":0.6489999890327454},{"id":"https://openalex.org/keywords/functional-annotation","display_name":"functional annotation","score":0.796999990940094},{"id":"https://openalex.org/keywords/gene-function-prediction","display_name":"gene function prediction","score":0.5450000166893005},{"id":"https://openalex.org/keywords/model-accuracy","display_name":"model accuracy","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7491000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235000133514404},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5188999772071838},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C137858568","wikidata":"https://www.wikidata.org/wiki/Q7239","display_name":"Organism","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.05.764556","doi":"https://doi.org/10.64898/2026.11.05.764556","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764556","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764556.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.05.764556","doi":"https://doi.org/10.64898/2026.11.05.764556","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764556","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764556.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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/W7225622907.pdf","grobid_xml":"https://content.openalex.org/works/W7225622907.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1994750157","https://openalex.org/W1997037290","https://openalex.org/W2010068400","https://openalex.org/W2025207333","https://openalex.org/W2038304602","https://openalex.org/W2044935306","https://openalex.org/W2048464962","https://openalex.org/W2060797027","https://openalex.org/W2075919068","https://openalex.org/W2079531107","https://openalex.org/W2084503127","https://openalex.org/W2085993965","https://openalex.org/W2086016524","https://openalex.org/W2100084634","https://openalex.org/W2120167281","https://openalex.org/W2140470365","https://openalex.org/W2161827792","https://openalex.org/W2169059428","https://openalex.org/W2170427655","https://openalex.org/W2182101717","https://openalex.org/W2202347610","https://openalex.org/W2559588208","https://openalex.org/W2764202526","https://openalex.org/W2775873384","https://openalex.org/W2796889218","https://openalex.org/W2902705770","https://openalex.org/W2910511306","https://openalex.org/W2949418748","https://openalex.org/W2952015518","https://openalex.org/W2952117162","https://openalex.org/W2966440819","https://openalex.org/W2977870980","https://openalex.org/W2982500515","https://openalex.org/W3009070426","https://openalex.org/W3087744872","https://openalex.org/W3090689814","https://openalex.org/W3094560666","https://openalex.org/W3129727011","https://openalex.org/W3134142139","https://openalex.org/W4294990920","https://openalex.org/W4306918328","https://openalex.org/W4362471278","https://openalex.org/W4366986540","https://openalex.org/W4379599517","https://openalex.org/W4398475265","https://openalex.org/W4400353742","https://openalex.org/W4404458588","https://openalex.org/W4410596734","https://openalex.org/W4416572963","https://openalex.org/W4416704627","https://openalex.org/W7119770694","https://openalex.org/W7147007913"],"related_works":["https://openalex.org/W2401483360","https://openalex.org/W1985669994","https://openalex.org/W150916034","https://openalex.org/W2790993665","https://openalex.org/W2137787974","https://openalex.org/W315903372","https://openalex.org/W2887194058","https://openalex.org/W4294990920","https://openalex.org/W3166024157","https://openalex.org/W6980669281"],"abstract_inverted_index":{"Genome-scale":[0],"metabolic":[1,14],"models":[2,22,35,57,68],"are":[3,23],"valuable":[4],"tools":[5,49],"for":[6,25,36,93,202,227],"studying":[7],"metabolism":[8],"in":[9,58,96,178],"many":[10],"applications,":[11],"such":[12,100,116],"as":[13,101,117],"engineering":[15],"or":[16],"understanding":[17],"human":[18],"disease.":[19],"However,":[20],"curated":[21,72],"available":[24],"only":[26],"a":[27,40,78,135,154,204],"limited":[28],"number":[29],"of":[30,65,131,143,150,160,175,187,214],"organisms,":[31],"and":[32,104,123,141,217],"generating":[33],"high-quality":[34],"additional":[37],"organisms":[38],"remains":[39],"challenge.":[41],"To":[42],"help":[43],"address":[44],"this":[45],"challenge,":[46],"several":[47],"software":[48],"have":[50,153],"been":[51],"developed":[52],"that":[53,112,127,166,195,220],"can":[54,152],"produce":[55],"draft":[56,67],"an":[59,193],"automated":[60],"fashion,":[61],"but":[62],"the":[63,97,110,129,139,148,158,167,173,179,185,200,212],"quality":[64],"these":[66,82,114],"lags":[69],"behind":[70],"manually":[71],"ones.":[73],"Thus,":[74],"there":[75],"is":[76,170,196,206],"still":[77],"need":[79],"to":[80,172,199],"improve":[81],"tools.":[83,229],"Previous":[84],"work":[85],"has":[86,134],"focused":[87],"primarily":[88],"on":[89,109,138],"developing":[90],"better":[91],"methods":[92],"each":[94],"step":[95],"reconstruction":[98,132,161,168,180,215,228],"process,":[99],"gene":[102,176],"annotation":[103,190],"gap-filling.":[105],"Here,":[106],"we":[107,164,183],"focus":[108],"data":[111,133,151,191,216,226],"underlies":[113],"methods,":[115],"known":[118],"connections":[119],"between":[120],"protein":[121],"sequence":[122],"function.":[124],"We":[125],"find":[126],"changing":[128],"source":[130,149],"substantial":[136],"impact":[137,156],"contents":[140],"predictions":[142],"generated":[144],"models.":[145],"In":[146],"fact,":[147],"bigger":[155],"than":[157],"choice":[159],"method.":[162],"Additionally,":[163],"show":[165],"process":[169],"sensitive":[171],"accuracy":[174],"annotations":[177],"data.":[181],"Finally,":[182],"demonstrate":[184],"importance":[186,213],"having":[188],"functional":[189],"from":[192],"organism":[194],"closely":[197],"related":[198],"one":[201],"which":[203],"model":[205],"being":[207],"built.":[208],"These":[209],"observations":[210],"highlight":[211],"identify":[218],"principles":[219],"should":[221],"be":[222],"considered":[223],"when":[224],"selecting":[225]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
