{"id":"https://openalex.org/W4417062523","doi":"https://doi.org/10.1145/3768322.3769097","title":"Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN","display_name":"Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN","publication_year":2025,"publication_date":"2025-10-11","ids":{"openalex":"https://openalex.org/W4417062523","doi":"https://doi.org/10.1145/3768322.3769097"},"language":null,"primary_location":{"id":"doi:10.1145/3768322.3769097","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769097","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769097","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769097","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113301319","display_name":"Mohammadsaleh Refahi","orcid":"https://orcid.org/0009-0000-9581-5883"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammadsaleh Refahi","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0000-9581-5883","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098975021","display_name":"Gavin Hearne","orcid":"https://orcid.org/0009-0006-9193-4264"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gavin Hearne","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0006-9193-4264","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109330099","display_name":"Hannes M\u00fcller","orcid":"https://orcid.org/0009-0006-9567-0964"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harrison Muller","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0006-9567-0964","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073377257","display_name":"Kieran James Lynch","orcid":"https://orcid.org/0009-0007-8446-8186"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kieran Lynch","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0007-8446-8186","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038775063","display_name":"Bahrad A. Sokhansanj","orcid":"https://orcid.org/0000-0002-5050-5926"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahrad A. Sokhansanj","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5050-5926","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089794666","display_name":"James R. Brown","orcid":"https://orcid.org/0000-0002-9368-627X"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Brown","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9368-627X","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Rosen","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1763-5750","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7106000185012817,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7106000185012817,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.07199999690055847,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.050700001418590546,"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/scalability","display_name":"Scalability","score":0.6298999786376953},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49639999866485596},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.459199994802475},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42100000381469727},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.3659999966621399},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.36309999227523804},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.36000001430511475},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377999782562256},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.36000001430511475},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.34139999747276306},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.30809998512268066},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2687999904155731},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C92087593","wikidata":"https://www.wikidata.org/wiki/Q427389","display_name":"Vector (molecular biology)","level":4,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768322.3769097","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769097","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769097","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3768322.3769097","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769097","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769097","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1484936278","display_name":"MRI: Proteus++: Enabling Data-Intensive Computing at Drexel University","funder_award_id":"1919691","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2256477278","display_name":"Collaborative Research: IIBR Informatics: Keeping up with the genomes - Continual Learning of Metagenomic Data","funder_award_id":"1936791","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417062523.pdf","grobid_xml":"https://content.openalex.org/works/W4417062523.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,83],"exponential":[1],"growth":[2],"of":[3,10,46],"DNA":[4],"sequencing":[5],"has":[6],"produced":[7],"vast":[8],"amounts":[9],"genetic":[11],"data,":[12],"yet":[13],"alignment-based":[14],"similarity":[15],"search":[16,34,64],"tools":[17],"such":[18],"as":[19],"BLAST":[20],"and":[21,38,48,68,97,100,108],"MMseqs2":[22],"struggle":[23],"to":[24,26,86,90,101],"scale":[25],"these":[27],"large,":[28],"noisy":[29],"datasets.":[30],"Embedding-based":[31],"approximate":[32],"nearest-neighbor":[33],"promises":[35],"both":[36],"efficiency":[37],"biological":[39],"fidelity":[40],"by":[41],"learning":[42],"dense":[43],"vector":[44,51,63],"representations":[45],"genes":[47],"employing":[49],"high-performance":[50],"indices.":[52],"This":[53],"highlight":[54],"summarizes":[55],"recent":[56],"work":[57],"that":[58],"systematically":[59],"benchmarks":[60],"two":[61],"state-of-the-art":[62],"libraries":[65],"Facebook's":[66],"FAISS":[67],"Google's":[69],"ScaNN":[70],"on":[71],"biologically":[72],"meaningful":[73],"gene":[74,95],"embeddings":[75],"derived":[76],"from":[77],"a":[78],"transformer":[79],"based":[80],"language":[81],"model.":[82],"goal":[84],"is":[85],"assess":[87],"their":[88],"ability":[89],"detect":[91],"novel":[92],"sequences,":[93],"support":[94],"annotation":[96],"taxonomic":[98],"classification,":[99],"illuminate":[102],"the":[103],"trade-offs":[104],"between":[105],"accuracy,":[106],"runtime":[107],"memory":[109],"usage":[110],"for":[111],"metagenomic":[112],"retrieval.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-05T00:00:00"}