{"id":"https://openalex.org/W4393158238","doi":"https://doi.org/10.1609/aaai.v38i1.27753","title":"Neural Embeddings for kNN Search in Biological Sequence","display_name":"Neural Embeddings for kNN Search in Biological Sequence","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393158238","doi":"https://doi.org/10.1609/aaai.v38i1.27753"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i1.27753","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/27753/27549","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/27753/27549","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078622553","display_name":"Zhihao Chang","orcid":"https://orcid.org/0000-0003-4627-7331"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Chang","raw_affiliation_strings":["The State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085979284","display_name":"Linzhu Yu","orcid":"https://orcid.org/0000-0002-1063-3990"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhu Yu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600463","display_name":"Yanchao Xu","orcid":"https://orcid.org/0000-0003-3500-3079"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanchao Xu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101464722","display_name":"Wentao Hu","orcid":"https://orcid.org/0009-0000-9881-2207"},"institutions":[{"id":"https://openalex.org/I4210108177","display_name":"Zhejiang Police College","ror":"https://ror.org/01rxaf991","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210108177"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Hu","raw_affiliation_strings":["Zhejiang Police college"],"affiliations":[{"raw_affiliation_string":"Zhejiang Police college","institution_ids":["https://openalex.org/I4210108177"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.884,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.999574,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":84,"max":92},"biblio":{"volume":"38","issue":"1","first_page":"38","last_page":"45"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9745,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9745,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9585,"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/sequence","display_name":"Sequence (biology)","score":0.6391432}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6391432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51796687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46055922},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42898336},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3735957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3729719},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.35464412},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29147026},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16141602}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i1.27753","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/27753/27549","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i1.27753","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/27753/27549","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.47,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":23,"referenced_works":["https://openalex.org/W1489608363","https://openalex.org/W1508885706","https://openalex.org/W1965555277","https://openalex.org/W1968570655","https://openalex.org/W1971239653","https://openalex.org/W1975775747","https://openalex.org/W2074231493","https://openalex.org/W2095071222","https://openalex.org/W2099254366","https://openalex.org/W2105767494","https://openalex.org/W2106053110","https://openalex.org/W2132914434","https://openalex.org/W2140211206","https://openalex.org/W2150774511","https://openalex.org/W2156125289","https://openalex.org/W2158703410","https://openalex.org/W2598634450","https://openalex.org/W2903674301","https://openalex.org/W2953008890","https://openalex.org/W3003533349","https://openalex.org/W3027211216","https://openalex.org/W4286970725","https://openalex.org/W4307054535"],"related_works":["https://openalex.org/W4390653028","https://openalex.org/W2391251536","https://openalex.org/W2375008505","https://openalex.org/W2362198218","https://openalex.org/W2350679292","https://openalex.org/W2113077220","https://openalex.org/W2086348228","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W1982750869"],"abstract_inverted_index":{"Biological":[0],"sequence":[1],"nearest":[2],"neighbor":[3],"search":[4,116],"plays":[5],"a":[6,35,57,64,80,114,123,129,146,192,201,216,229],"fundamental":[7],"role":[8],"in":[9,180,240],"bioinformatics.":[10],"To":[11,38],"alleviate":[12],"the":[13,40,96,133,181,186,257,266],"pain":[14],"of":[15,59,82,135,178],"quadratic":[16],"complexity":[17],"for":[18,61,93,118,220,246],"conventional":[19],"distance":[20,23,41,83,137],"computation,":[21],"neural":[22,203],"embeddings,":[24],"which":[25,237],"project":[26],"sequences":[27],"into":[28,153,243],"geometric":[29],"space,":[30],"have":[31],"been":[32],"recognized":[33],"as":[34,228],"promising":[36],"paradigm.":[37],"maintain":[39],"order":[42],"between":[43],"sequences,":[44],"these":[45,164],"models":[46,76,242],"all":[47,136,151,211],"deploy":[48],"triplet":[49,125],"loss":[50],"and":[51,128,159,213],"use":[52],"intuitive":[53],"methods":[54,259],"to":[55,77,149,195,205],"select":[56,161],"subset":[58],"triplets":[60,92,152,162,179],"training":[62,73,94,141,175,267],"from":[63,163],"vast":[65],"selection":[66,126],"space.":[67],"However,":[68],"we":[69,111,144,171,190,225],"observed":[70],"that":[71,173,252],"such":[72],"often":[74],"enables":[75],"distinguish":[78],"only":[79,100],"fraction":[81],"orders,":[84],"leaving":[85],"others":[86],"unrecognized.":[87],"Moreover,":[88],"naively":[89],"selecting":[90],"more":[91],"under":[95],"state-of-the-art":[97,258],"network":[98,183,194,199],"not":[99],"adds":[101],"costs":[102],"but":[103],"also":[104],"hampers":[105],"model":[106,245],"performance.":[107],"In":[108],"this":[109],"paper,":[110],"introduce":[112],"Bio-kNN:":[113],"kNN":[115],"framework":[117],"biological":[119],"sequences.":[120],"It":[121],"includes":[122],"systematic":[124],"method":[127],"multi-head":[130,193],"network,":[131],"enhancing":[132],"discernment":[134],"orders":[138],"without":[139,264],"increasing":[140,265],"expenses.":[142],"Initially,":[143],"propose":[145,191],"clustering-based":[147],"approach":[148],"partition":[150],"several":[154],"clusters":[155,165],"with":[156],"similar":[157],"properties,":[158],"then":[160,214],"using":[166],"an":[167],"innovative":[168],"strategy.":[169],"Meanwhile,":[170],"noticed":[172],"simultaneously":[174],"different":[176],"types":[177],"same":[182],"cannot":[184],"achieve":[185],"expected":[187],"performance,":[188],"thus":[189],"tackle":[196],"this.":[197],"Our":[198],"employs":[200],"convolutional":[202],"network(CNN)":[204],"extract":[206],"local":[207,235],"features":[208,236],"shared":[209],"by":[210],"clusters,":[212],"learns":[215],"multi-layer":[217],"perception(MLP)":[218],"head":[219],"each":[221],"cluster":[222],"separately.":[223],"Besides,":[224],"treat":[226],"CNN":[227],"special":[230],"head,":[231],"thereby":[232],"integrating":[233],"crucial":[234],"are":[238],"neglected":[239],"previous":[241],"our":[244,253],"similarity":[247],"recognition.":[248],"Extensive":[249],"experiments":[250],"show":[251],"Bio-kNN":[254],"significantly":[255],"outperforms":[256],"on":[260],"two":[261],"large-scale":[262],"datasets":[263],"cost.":[268]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4393158238","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-06T04:51:51.545393","created_date":"2024-03-26"}