{"id":"https://openalex.org/W4387346494","doi":"https://doi.org/10.1145/3584371.3612953","title":"Leveraging Large Language Models for Predicting Microbial Virulence from Protein Structure and Sequence","display_name":"Leveraging Large Language Models for Predicting Microbial Virulence from Protein Structure and Sequence","publication_year":2023,"publication_date":"2023-09-03","ids":{"openalex":"https://openalex.org/W4387346494","doi":"https://doi.org/10.1145/3584371.3612953"},"language":"en","primary_location":{"id":"doi:10.1145/3584371.3612953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612953","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612953","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089862300","display_name":"Felix Quintana","orcid":"https://orcid.org/0009-0006-4701-2967"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Felix Quintana","raw_affiliation_strings":["Computer Science, Rice University, Houston, Texas, United States"],"raw_orcid":"https://orcid.org/0009-0006-4701-2967","affiliations":[{"raw_affiliation_string":"Computer Science, Rice University, Houston, Texas, United States","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054369332","display_name":"Todd J. Treangen","orcid":"https://orcid.org/0000-0002-3760-564X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd Treangen","raw_affiliation_strings":["Computer Science, Rice University, Houston, Texas, United States"],"raw_orcid":"https://orcid.org/0000-0002-3760-564X","affiliations":[{"raw_affiliation_string":"Computer Science, Rice University, Houston, Texas, United States","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067205988","display_name":"Lydia E. Kavraki","orcid":"https://orcid.org/0000-0003-0699-8038"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lydia Kavraki","raw_affiliation_strings":["Computer Science, Rice University, Houston, Texas, United States"],"raw_orcid":"https://orcid.org/0000-0003-0699-8038","affiliations":[{"raw_affiliation_string":"Computer Science, Rice University, Houston, Texas, United States","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089862300"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.7497,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73085784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9970999956130981,"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":0.9887999892234802,"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/virulence","display_name":"Virulence","score":0.7749803066253662},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5753869414329529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5290162563323975},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4785459637641907},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.44844183325767517},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.43800097703933716},{"id":"https://openalex.org/keywords/virulence-factor","display_name":"Virulence factor","score":0.4286128878593445},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2614380717277527},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24869027733802795},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21694359183311462}],"concepts":[{"id":"https://openalex.org/C60987743","wikidata":"https://www.wikidata.org/wiki/Q1460232","display_name":"Virulence","level":3,"score":0.7749803066253662},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5753869414329529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5290162563323975},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4785459637641907},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44844183325767517},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.43800097703933716},{"id":"https://openalex.org/C2781090273","wikidata":"https://www.wikidata.org/wiki/Q1623405","display_name":"Virulence factor","level":4,"score":0.4286128878593445},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2614380717277527},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24869027733802795},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21694359183311462},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584371.3612953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612953","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3584371.3612953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3584371.3612953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3584371.3612953","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2131653337","display_name":"CAREER: A comprehensive computational platform for detecting yet unseen microbial pathogens","funder_award_id":"2239114","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2328657408","display_name":null,"funder_award_id":"AI152999","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G4433322875","display_name":null,"funder_award_id":"U01CA258512","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4702532634","display_name":null,"funder_award_id":"IIS-2239114","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4815088272","display_name":null,"funder_award_id":"P01-AI152999","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G5918855976","display_name":null,"funder_award_id":"P01-AI152999","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387346494.pdf","grobid_xml":"https://content.openalex.org/works/W4387346494.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2021954541","https://openalex.org/W2103017472","https://openalex.org/W2119497560","https://openalex.org/W2558837609","https://openalex.org/W2559133556","https://openalex.org/W2612690371","https://openalex.org/W2615066396","https://openalex.org/W2963026768","https://openalex.org/W3048038175","https://openalex.org/W3081836708","https://openalex.org/W3105738938","https://openalex.org/W3158986422","https://openalex.org/W3177828909","https://openalex.org/W3208696114","https://openalex.org/W3211795435","https://openalex.org/W4205773061","https://openalex.org/W4213149192","https://openalex.org/W4281790889","https://openalex.org/W4293246520","https://openalex.org/W4310885934","https://openalex.org/W4317802023","https://openalex.org/W4318071656","https://openalex.org/W4327550249","https://openalex.org/W4379882058"],"related_works":["https://openalex.org/W2951035914","https://openalex.org/W2201859025","https://openalex.org/W2124139792","https://openalex.org/W2134930711","https://openalex.org/W3212434704","https://openalex.org/W50609149","https://openalex.org/W2139426682","https://openalex.org/W4238120107","https://openalex.org/W3030861211","https://openalex.org/W2350813442"],"abstract_inverted_index":{"In":[0],"the":[1,30,35,88,123],"aftermath":[2],"of":[3,26,34,67,90,158],"COVID-19,":[4],"screening":[5,17,79],"for":[6,18,77,142,155],"pathogens":[7,19],"has":[8],"never":[9],"been":[10],"a":[11,24,50,64,68,115,131,152],"more":[12,95],"relevant":[13],"problem.":[14],"However,":[15,74],"computational":[16],"is":[20],"challenging":[21],"due":[22],"to":[23,71,109],"variety":[25],"factors,":[27],"including":[28],"(i)":[29],"complexity":[31],"and":[32,41,43,46,58,92,107,127,160],"role":[33],"host,":[36],"(ii)":[37],"virulence":[38,143,156],"factor":[39],"divergence":[40],"dynamics,":[42],"(iii)":[44],"population":[45],"community-level":[47],"dynamics.":[48],"Considering":[49],"potential":[51,65],"pathogen's":[52],"molecular":[53],"interactions,":[54],"specifically":[55],"individual":[56],"proteins":[57,94],"protein":[59,66,105,111,128],"interactions":[60],"can":[61],"help":[62],"pinpoint":[63],"given":[69],"microbe":[70],"cause":[72],"disease.":[73],"existing":[75,82],"tools":[76],"pathogen":[78],"rely":[80],"on":[81],"annotations":[83],"(KEGG,":[84],"GO,":[85],"etc),":[86],"making":[87],"assessment":[89],"novel":[91,159],"unannotated":[93,161],"challenging.":[96],"Here,":[97],"we":[98],"present":[99,114],"an":[100],"LLM-inspired":[101],"approach":[102],"that":[103],"considers":[104],"sequence":[106,140],"structure":[108,129],"predict":[110],"virulence.":[112],"We":[113],"two-stage":[116],"model":[117,126,136],"incorporating":[118],"evolutionary":[119],"features":[120],"captured":[121],"from":[122],"DistilProtBert":[124],"language":[125],"in":[130],"graph":[132],"convolutional":[133],"network.":[134],"Our":[135],"performs":[137],"better":[138],"than":[139],"alone":[141],"function":[144],"when":[145],"high-quality":[146],"structures":[147],"are":[148],"present,":[149],"thus":[150],"representing":[151],"path":[153],"forward":[154],"prediction":[157],"proteins.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}