{"id":"https://openalex.org/W7213738775","doi":null,"title":"Protein Function Prediction: Capabilities and Limitations of Alignment-based Approaches","display_name":"Protein Function Prediction: Capabilities and Limitations of Alignment-based Approaches","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7213738775"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05747418v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05747418v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"info:eu-repo/semantics/preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05747418v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093407630","display_name":"Antoine Toffano","orcid":"https://orcid.org/0009-0008-0575-8490","observed_orcids":["https://orcid.org/0009-0008-0575-8490"]},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Toffano, Antoine","raw_affiliation_strings":["LIRMM | ADVANSE - ADVanced Analytics for data SciencE (LIRMM, 161 rue Ada, 34000 Montpellier - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIRMM | ADVANSE - ADVanced Analytics for data SciencE (LIRMM, 161 rue Ada, 34000 Montpellier - France)","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061826905","display_name":"J\u00e9r\u00f4me Az\u00e9","orcid":"https://orcid.org/0000-0002-7372-729X","observed_orcids":["https://orcid.org/0000-0002-7372-729X"]},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Az\u00e9, J\u00e9r\u00f4me","raw_affiliation_strings":["LIRMM | ADVANSE - ADVanced Analytics for data SciencE (LIRMM, 161 rue Ada, 34000 Montpellier - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIRMM | ADVANSE - ADVanced Analytics for data SciencE (LIRMM, 161 rue Ada, 34000 Montpellier - France)","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063266192","display_name":"Pierre Larmande","orcid":"https://orcid.org/0000-0002-2923-9790","observed_orcids":["https://orcid.org/0000-0002-2923-9790"]},"institutions":[{"id":"https://openalex.org/I4210117822","display_name":"Diversit\u00e9, adaptation et d\u00e9veloppement des plantes","ror":"https://ror.org/02banhz78","country_code":"FR","type":"facility","lineage":["https://openalex.org/I131077856","https://openalex.org/I19894307","https://openalex.org/I2802818602","https://openalex.org/I4210090127","https://openalex.org/I4210117822","https://openalex.org/I4210131494","https://openalex.org/I4210166444"]},{"id":"https://openalex.org/I4210166444","display_name":"Institut de Recherche pour le D\u00e9veloppement","ror":"https://ror.org/05q3vnk25","country_code":"FR","type":"government","lineage":["https://openalex.org/I2802818602","https://openalex.org/I4210090127","https://openalex.org/I4210131494","https://openalex.org/I4210166444"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Larmande, Pierre","raw_affiliation_strings":["IRD - Institut de Recherche pour le D\u00e9veloppement (Si\u00e8geLe Sextant 44, bd de DunkerqueCS 9000913572 Marseille cedex 02 - France)","UMR DIADE - Diversit\u00e9, adaptation, d\u00e9veloppement des plantes (Centre IRD de Montpellier 911 av Agropolis BP 604501 34394 Montpellier cedex 5 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRD - Institut de Recherche pour le D\u00e9veloppement (Si\u00e8geLe Sextant 44, bd de DunkerqueCS 9000913572 Marseille cedex 02 - France)","institution_ids":["https://openalex.org/I4210166444"]},{"raw_affiliation_string":"UMR DIADE - Diversit\u00e9, adaptation, d\u00e9veloppement des plantes (Centre IRD de Montpellier 911 av Agropolis BP 604501 34394 Montpellier cedex 5 - France)","institution_ids":["https://openalex.org/I4210117822","https://openalex.org/I4210166444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5404999852180481,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5404999852180481,"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":0.2964000105857849,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.12439999729394913,"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/protein-function-prediction","display_name":"protein function prediction","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"sequence alignment","score":0.5860000252723694},{"id":"https://openalex.org/keywords/annotation-transfer","display_name":"annotation transfer","score":0.7919999957084656},{"id":"https://openalex.org/keywords/protein-protein-interaction-network","display_name":"protein-protein interaction network","score":0.8730000257492065},{"id":"https://openalex.org/keywords/deep-learning-model-comparison","display_name":"deep learning model comparison","score":0.722000002861023},{"id":"https://openalex.org/keywords/benchmark-evaluation","display_name":"benchmark evaluation","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934999823570251},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.5807999968528748},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.27410000562667847},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.26089999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-05747418v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05747418v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05747418v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05747418v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4213112325","https://openalex.org/W3117408946","https://openalex.org/W2807818025","https://openalex.org/W4416358185","https://openalex.org/W2970416468","https://openalex.org/W4406799358","https://openalex.org/W2923652344","https://openalex.org/W2952710849","https://openalex.org/W4384282985","https://openalex.org/W4394857429"],"abstract_inverted_index":{"Computational":[0],"prediction":[1],"of":[2,35,66,76,105,126],"protein":[3],"function":[4],"is":[5],"increasingly":[6],"dominated":[7],"by":[8,149],"deep":[9,46],"learning":[10,47],"architectures,":[11],"often":[12],"premised":[13],"on":[14,24],"the":[15,33,103],"assumption":[16],"that":[17,40,57,86,130,155],"alignment-based":[18,58,138,156],"methods":[19,59],"leveraging":[20],"sequence":[21],"homology":[22],"fail":[23,60],"highly":[25,159],"divergent":[26],"sequences.":[27],"In":[28],"this":[29],"study,":[30],"we":[31,82],"reassess":[32],"capacity":[34],"alignmentbased":[36],"annotation":[37,170],"transfer,":[38,69],"demonstrating":[39],"these":[41],"approaches":[42,157],"can":[43],"surpass":[44],"state-of-the-art":[45],"models":[48],"when":[49],"provided":[50],"with":[51],"appropriate":[52],"contextual":[53],"data.":[54],"We":[55],"identify":[56],"primarily":[61],"due":[62],"to":[63,68,74],"a":[64,84,118,123,163],"lack":[65],"annotations":[67],"an":[70],"issue":[71],"affecting":[72],"up":[73],"73%":[75],"low-homology":[77,120],"proteins.":[78],"To":[79],"resolve":[80],"this,":[81],"introduce":[83],"framework":[85],"integrates":[87],"multi-template":[88],"alignment,":[89],"manually":[90],"curated":[91],"non-experimental":[92],"labels,":[93],"and":[94,109,161],"STRING":[95],"protein-protein":[96],"interaction":[97],"networks.":[98],"This":[99],"methodology":[100],"largely":[101],"reduces":[102],"fraction":[104],"proteins":[106],"left":[107],"unannotated":[108],"achieves":[110],"superior":[111],"performance":[112],"across":[113],"three":[114],"benchmark":[115],"datasets,":[116],"including":[117],"custom":[119],"dataset.":[121],"Furthermore,":[122],"longitudinal":[124],"analysis":[125],"database":[127],"updates":[128],"reveals":[129],"static":[131],"benchmarks":[132],"systematically":[133],"underestimate":[134],"predictive":[135],"value;":[136],"many":[137],"\"false":[139],"positives\"":[140],"are,":[141],"in":[142],"fact,":[143],"early":[144],"accurate":[145],"predictions":[146],"later":[147],"confirmed":[148],"experimental":[150],"updates.":[151],"Our":[152],"findings":[153],"indicate":[154],"remain":[158],"competitive":[160],"offer":[162],"robust,":[164],"explainable":[165],"baseline":[166],"for":[167],"future":[168],"functional":[169],"developments.":[171]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-09-20T00:00:00"}