{"id":"https://openalex.org/W4398200498","doi":"https://doi.org/10.1093/bioinformatics/btae328","title":"SAFPred: synteny-aware gene function prediction for bacteria using protein embeddings","display_name":"SAFPred: synteny-aware gene function prediction for bacteria using protein embeddings","publication_year":2024,"publication_date":"2024-05-22","ids":{"openalex":"https://openalex.org/W4398200498","doi":"https://doi.org/10.1093/bioinformatics/btae328","pmid":"https://pubmed.ncbi.nlm.nih.gov/38775729"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae328","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae328","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae328/57826417/btae328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae328/57826417/btae328.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006732412","display_name":"Aysun Urhan","orcid":"https://orcid.org/0000-0001-8584-4736"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Aysun Urhan","raw_affiliation_strings":["Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8584-4736","affiliations":[{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070970429","display_name":"Bianca-Maria Cosma","orcid":"https://orcid.org/0009-0000-1447-2701"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bianca-Maria Cosma","raw_affiliation_strings":["Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0000-1447-2701","affiliations":[{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079515502","display_name":"Ashlee M. Earl","orcid":"https://orcid.org/0000-0001-7857-9145"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashlee M Earl","raw_affiliation_strings":["Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088129247","display_name":"Abigail L. Manson","orcid":"https://orcid.org/0000-0002-3800-0714"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abigail L Manson","raw_affiliation_strings":["Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002088014","display_name":"Thomas Abeel","orcid":"https://orcid.org/0000-0002-7205-7431"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Thomas Abeel","raw_affiliation_strings":["Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-7205-7431","affiliations":[{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik , Delft XE 2628, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, United States","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, 415 Main Street, Cambridge, MA, 02142, US","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Delft Bioinformatics Lab, Delft University of Technology Van Mourik, Broekmanweg 6, 2628 XE, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002088014"],"corresponding_institution_ids":["https://openalex.org/I107606265","https://openalex.org/I98358874"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.2095,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77863179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"6","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":0.7311999797821045,"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":0.7311999797821045,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.04969999939203262,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.0333000011742115,"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/synteny","display_name":"Synteny","score":0.94566410779953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6061622500419617},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5654630064964294},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5516416430473328},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.513286292552948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41160574555397034},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32509398460388184},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.32437795400619507},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.23602494597434998}],"concepts":[{"id":"https://openalex.org/C53702515","wikidata":"https://www.wikidata.org/wiki/Q971246","display_name":"Synteny","level":4,"score":0.94566410779953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061622500419617},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5654630064964294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5516416430473328},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.513286292552948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41160574555397034},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32509398460388184},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.32437795400619507},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.23602494597434998}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D026801","descriptor_name":"Synteny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae328","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae328","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae328/57826417/btae328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38775729","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38775729","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11147799","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11147799","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11147799/pdf/btae328.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:tudelft.nl:uuid:d0d955b2-4940-4a98-b50e-8c0447ee98fa","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:d0d955b2-4940-4a98-b50e-8c0447ee98fa","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"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":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae328","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae328","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae328/57826417/btae328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2089557771","display_name":null,"funder_award_id":"U19AI110818","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3708211351","display_name":null,"funder_award_id":"U19AI110818","funder_id":"https://openalex.org/F4320314070","funder_display_name":"Broad Institute"},{"id":"https://openalex.org/G4015378213","display_name":null,"funder_award_id":"U19AI110818","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G7149703821","display_name":null,"funder_award_id":"U19AI110818","funder_id":"https://openalex.org/F4320306085","funder_display_name":"U.S. Department of Health and Human Services"}],"funders":[{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320314070","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142"},{"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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4398200498.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1977922844","https://openalex.org/W2055043387","https://openalex.org/W2096093282","https://openalex.org/W2103017472","https://openalex.org/W2117486996","https://openalex.org/W2138122982","https://openalex.org/W2156125289","https://openalex.org/W2156735102","https://openalex.org/W2160794724","https://openalex.org/W2164461702","https://openalex.org/W2166637863","https://openalex.org/W2171042267","https://openalex.org/W2613825882","https://openalex.org/W2785353872","https://openalex.org/W2808291890","https://openalex.org/W2900629010","https://openalex.org/W2951731136","https://openalex.org/W2966590054","https://openalex.org/W2989608901","https://openalex.org/W2995514860","https://openalex.org/W3095583226","https://openalex.org/W3107041591","https://openalex.org/W3118936575","https://openalex.org/W3136918052","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3165795318","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3200103613","https://openalex.org/W4221078486","https://openalex.org/W4236358448","https://openalex.org/W4280524269","https://openalex.org/W4282984452","https://openalex.org/W4308616064","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4386947433","https://openalex.org/W4392231323","https://openalex.org/W6684606845","https://openalex.org/W6684816851"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1969010119","https://openalex.org/W4395463268","https://openalex.org/W2626545547","https://openalex.org/W2167155214","https://openalex.org/W2124599625","https://openalex.org/W2952105401","https://openalex.org/W2347154653","https://openalex.org/W2733127495","https://openalex.org/W2464653720"],"abstract_inverted_index":{"MOTIVATION:":[0],"Today,":[1],"we":[2,87,152,235],"know":[3],"the":[4,12,31,50,67,102,174,203,207,210],"function":[5,54,91,159],"of":[6,11,30,43,69,113,133,178,227],"only":[7,139],"a":[8,155],"small":[9],"fraction":[10],"protein":[13,125,164,168],"sequences":[14,71,81],"predicted":[15],"from":[16,101,166],"genomic":[17],"data.":[18],"This":[19,40],"problem":[20],"is":[21,47],"even":[22],"more":[23],"salient":[24],"for":[25,82,95,130,198],"bacteria,":[26,151],"which":[27,228],"represent":[28],"some":[29,229],"most":[32,53],"phylogenetically":[33],"and":[34,61,190,248],"metabolically":[35],"diverse":[36,225],"taxa":[37],"on":[38,59,66,142,163,193],"Earth.":[39],"low":[41,215],"rate":[42],"bacterial":[44,84,143,195],"gene":[45,90,148,158,222],"annotation":[46,63,132,188],"compounded":[48],"by":[49],"fact":[51],"that":[52],"prediction":[55,92,160],"algorithms":[56],"have":[57,127,137],"focused":[58],"eukaryotes,":[60,134],"conventional":[62,186],"approaches":[64],"rely":[65],"presence":[68],"similar":[70],"in":[72,150,209],"existing":[73],"databases.":[74],"However,":[75],"often":[76],"there":[77,136],"are":[78,231],"no":[79],"such":[80],"novel":[83,156,241],"proteins.":[85],"Thus,":[86],"need":[88],"improved":[89],"methods":[93,189,192],"tailored":[94],"bacteria.":[96],"Recently,":[97],"transformer-based":[98],"language":[99,104,169],"models-adopted":[100],"natural":[103],"processing":[105],"field-have":[106],"been":[107,138],"used":[108],"to":[109,115,123,206,220,246],"obtain":[110],"new":[111],"representations":[112],"proteins,":[114],"replace":[116],"amino":[117],"acid":[118],"sequences.":[119],"These":[120],"representations,":[121],"referred":[122],"as":[124,214,216],"embeddings,":[126],"shown":[128],"promise":[129],"improving":[131],"but":[135],"limited":[140],"applications":[141],"genomes.":[144],"RESULTS:":[145],"To":[146],"predict":[147],"functions":[149,223],"developed":[153],"SAFPred,":[154],"synteny-aware":[157],"tool":[161],"based":[162],"embeddings":[165],"state-of-the-art":[167,191],"models.":[170],"SAFpred":[171],"also":[172],"leverages":[173],"unique":[175],"operon":[176],"structure":[177],"bacteria":[179],"through":[180],"conserved":[181],"synteny.":[182],"SAFPred":[183,219],"outperformed":[184],"both":[185],"sequence-based":[187],"multiple":[194],"species,":[196],"including":[197],"distant":[199],"homolog":[200],"detection,":[201],"where":[202],"sequence":[204],"similarity":[205],"proteins":[208],"training":[211],"set":[212],"was":[213],"40%.":[217],"Using":[218],"identify":[221],"across":[224],"enterococci,":[226],"species":[230],"major":[232],"clinical":[233],"threats,":[234],"identified":[236],"11":[237],"previously":[238],"unrecognized":[239],"putative":[240],"toxins,":[242],"with":[243],"potential":[244],"significance":[245],"human":[247],"animal":[249],"health.":[250],"AVAILABILITY":[251],"AND":[252],"IMPLEMENTATION:":[253],"https://github.com/AbeelLab/safpred.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
