{"id":"https://openalex.org/W4392305699","doi":"https://doi.org/10.5220/0012453600003654","title":"Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs","display_name":"Integrating Structure and Sequence: Protein Graph Embeddings via GNNs and LLMs","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392305699","doi":"https://doi.org/10.5220/0012453600003654"},"language":"en","primary_location":{"id":"doi:10.5220/0012453600003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012453600003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0012453600003654","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009152630","display_name":"Francesco Ceccarelli","orcid":"https://orcid.org/0000-0001-9574-2899"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Ceccarelli","raw_affiliation_strings":["Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055179380","display_name":"Lorenzo Giusti","orcid":"https://orcid.org/0000-0002-2410-6657"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Giusti","raw_affiliation_strings":["Department of Computer, Control and Management Engineering, Sapienza University, Rome, Italy, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University, Rome, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004572323","display_name":"Sean B. Holden","orcid":"https://orcid.org/0000-0001-7979-1148"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sean Holden","raw_affiliation_strings":["Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056748708","display_name":"P\u00edetro Li\u00f3","orcid":"https://orcid.org/0000-0002-0540-5053"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pietro Li\u00f2","raw_affiliation_strings":["Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , University of Cambridge, Cambridge, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3745,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57938327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9922999739646912,"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":0.9922999739646912,"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":0.9889000058174133,"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":0.9778000116348267,"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/computer-science","display_name":"Computer science","score":0.5842683911323547},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5604269504547119},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5374937653541565},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.397161602973938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36067092418670654},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.346244215965271},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2051773965358734},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2031095325946808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842683911323547},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5604269504547119},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5374937653541565},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.397161602973938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36067092418670654},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.346244215965271},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2051773965358734},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2031095325946808}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.5220/0012453600003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012453600003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/363114","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/363114","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/1f554137-d599-4a2b-aaef-64cdcc1bc408/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Conference Object"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/363114.2","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/363114.2","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/6343c20f-298a-4217-bdba-101a272fd5f2/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Conference Object"},{"id":"pmh:oai:iris.uniroma1.it:11573/1728991","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1728991","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.17863/cam.105355","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.105355","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.5220/0012453600003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012453600003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2112284452","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W3085798047","https://openalex.org/W2951359407","https://openalex.org/W4376623224"],"abstract_inverted_index":{"Proteins":[0],"perform":[1],"much":[2],"of":[3,13,36,104,129,148,155],"the":[4,11,34,40,68,84,102,127,140,163,167],"work":[5],"in":[6,39,57,101,126,133,174],"living":[7],"organisms,":[8],"and":[9,43,79,89,154,185],"consequently":[10],"development":[12],"efficient":[14],"computational":[15],"methods":[16],"for":[17,22,53],"protein":[18,41,55,72,92,106,130],"representation":[19],"is":[20],"essential":[21],"advancing":[23],"large-scale":[24],"biological":[25],"research.":[26],"Most":[27],"current":[28],"approaches":[29,116],"struggle":[30],"to":[31,114,137],"efficiently":[32],"integrate":[33],"wealth":[35],"information":[37],"contained":[38],"sequence":[42],"structure.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"a":[50,110],"novel":[51],"framework":[52,86,122],"embedding":[54],"graphs":[56],"geometric":[58],"vector":[59],"spaces,":[60],"by":[61],"learning":[62],"an":[63,144],"encoder":[64],"function":[65],"that":[66,96],"preserves":[67],"structural":[69,119],"distance":[70],"between":[71],"graphs.":[73],"Utilizing":[74],"Graph":[75],"Neural":[76],"Networks":[77],"(GNNs)":[78],"Large":[80],"Language":[81],"Models":[82],"(LLMs),":[83],"proposed":[85,141],"generates":[87],"structure-":[88],"sequence-":[90],"aware":[91],"representations.":[93],"We":[94],"demonstrate":[95],"our":[97],"embeddings":[98],"are":[99],"successful":[100],"task":[103,128],"comparing":[105],"structures,":[107],"while":[108],"providing":[109],"significant":[111],"speed-up":[112],"compared":[113,136],"traditional":[115],"based":[117],"on":[118,150,159],"alignment.":[120],"Our":[121,170],"achieves":[123],"remarkable":[124],"results":[125],"structure":[131],"classification;":[132],"particular,":[134],"when":[135,157],"other":[138],"work,":[139],"method":[142],"shows":[143],"average":[145],"F1-Score":[146],"improvement":[147],"26%":[149],"out-of-distribution":[151],"(OOD)":[152],"samples":[153,160],"32%":[156],"tested":[158],"coming":[161],"from":[162],"same":[164],"distribution":[165],"as":[166,177],"training":[168],"data.":[169],"approach":[171],"finds":[172],"applications":[173],"areas":[175],"such":[176],"drug":[178,180],"prioritization,":[179],"re-purposing,":[181],"disease":[182],"sub-type":[183],"analysis":[184],"elsewhere.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2025-10-10T00:00:00"}