{"id":"https://openalex.org/W4288421358","doi":"https://doi.org/10.1145/3535508.3545550","title":"Deep sequence representation learning for predicting human proteins with liquid-liquid phase separation propensity and synaptic functions","display_name":"Deep sequence representation learning for predicting human proteins with liquid-liquid phase separation propensity and synaptic functions","publication_year":2022,"publication_date":"2022-07-28","ids":{"openalex":"https://openalex.org/W4288421358","doi":"https://doi.org/10.1145/3535508.3545550"},"language":"en","primary_location":{"id":"doi:10.1145/3535508.3545550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535508.3545550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024210777","display_name":"Anqi Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anqi Wei","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080695941","display_name":"Liangjiang Wang","orcid":"https://orcid.org/0000-0002-6316-7962"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangjiang Wang","raw_affiliation_strings":["Clemson University"],"affiliations":[{"raw_affiliation_string":"Clemson University","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024210777"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":0.1716,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47377174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9995999932289124,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9987000226974487,"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":0.6529354453086853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426756381988525},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5572145581245422},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5270001292228699},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5157466530799866},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5059015154838562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4571440517902374},{"id":"https://openalex.org/keywords/repertoire","display_name":"Repertoire","score":0.41730695962905884},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4158073663711548},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3037346303462982},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17182466387748718},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10509631037712097},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08095437288284302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6529354453086853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426756381988525},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5572145581245422},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5270001292228699},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5157466530799866},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5059015154838562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4571440517902374},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.41730695962905884},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4158073663711548},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3037346303462982},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17182466387748718},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10509631037712097},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08095437288284302},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3535508.3545550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535508.3545550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G7684218412","display_name":null,"funder_award_id":"P20GM139769","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W19619244","https://openalex.org/W1501531009","https://openalex.org/W1663984431","https://openalex.org/W2064675550","https://openalex.org/W2095294411","https://openalex.org/W2097606916","https://openalex.org/W2101234009","https://openalex.org/W2163922914","https://openalex.org/W2252523470","https://openalex.org/W2339629769","https://openalex.org/W2736638974","https://openalex.org/W2756067497","https://openalex.org/W2791796577","https://openalex.org/W2794191332","https://openalex.org/W2810866092","https://openalex.org/W2909727437","https://openalex.org/W2912459817","https://openalex.org/W2939777553","https://openalex.org/W2948949781","https://openalex.org/W2950379219","https://openalex.org/W2951765074","https://openalex.org/W2955829592","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2971594646","https://openalex.org/W2977849281","https://openalex.org/W2991067665","https://openalex.org/W2995514860","https://openalex.org/W2999481648","https://openalex.org/W3004042481","https://openalex.org/W3040052015","https://openalex.org/W3046158099","https://openalex.org/W3049692992","https://openalex.org/W3083303726","https://openalex.org/W3085173862","https://openalex.org/W3097876879","https://openalex.org/W3111467036","https://openalex.org/W3112376646","https://openalex.org/W3127087732","https://openalex.org/W3128708278","https://openalex.org/W3143253488","https://openalex.org/W3144701084","https://openalex.org/W3164264961","https://openalex.org/W4212848381","https://openalex.org/W4292358656","https://openalex.org/W4299838440"],"related_works":["https://openalex.org/W2053028024","https://openalex.org/W2011602722","https://openalex.org/W2024383575","https://openalex.org/W1965617697","https://openalex.org/W2072002764","https://openalex.org/W2012033675","https://openalex.org/W4237340100","https://openalex.org/W2073512219","https://openalex.org/W2033162017","https://openalex.org/W1986026327"],"abstract_inverted_index":{"With":[0],"advancements":[1],"in":[2,53,135],"next-generation":[3],"sequencing":[4],"techniques,":[5],"the":[6,18,25,66,77,119,144,153],"whole":[7],"protein":[8,44,70,88,117,145,161],"sequence":[9,79],"repertoire":[10],"has":[11,48],"increased":[12],"to":[13,30,83,142,148,159],"a":[14,50],"great":[15],"extent.":[16],"In":[17,72],"meantime,":[19],"deep":[20,78],"learning":[21,68,150],"techniques":[22,64],"have":[23,57,106],"promoted":[24],"development":[26],"of":[27,39,69],"computational":[28],"methods":[29],"interpret":[31],"large-scale":[32],"proteomic":[33],"data":[34],"and":[35,85,99,113,127,152],"facilitate":[36],"functional":[37],"studies":[38,56],"proteins.":[40,103],"Inferring":[41],"properties":[42],"from":[43],"amino":[45],"acid":[46],"sequences":[47],"been":[49],"long-standing":[51],"problem":[52],"Bioinformatics.":[54],"Extensive":[55],"successfully":[58],"applied":[59,76],"natural":[60],"language":[61,121,146],"processing":[62],"(NLP)":[63],"for":[65,163],"representation":[67],"sequences.":[71],"this":[73],"paper,":[74],"we":[75],"model":[80,147],"-":[81],"UDSMProt,":[82],"fine-tune":[84],"evaluate":[86],"two":[87],"prediction":[89],"tasks:":[90],"(1)":[91],"predict":[92,101,160],"proteins":[93],"with":[94],"liquid-liquid":[95],"phase":[96],"separation":[97],"propensity":[98],"(2)":[100],"synaptic":[102],"Our":[104],"results":[105],"shown":[107],"that,":[108],"without":[109],"prior":[110],"domain":[111],"knowledge":[112],"only":[114],"based":[115],"on":[116],"sequences,":[118],"fine-tuned":[120,154],"models":[122,130,155],"achieved":[123],"high":[124],"classification":[125],"accuracies":[126],"outperformed":[128],"baseline":[129],"using":[131],"compositional":[132],"k-mer":[133],"features":[134],"both":[136],"tasks.":[137],"Hence,":[138],"it":[139],"is":[140],"promising":[141],"apply":[143],"some":[149],"tasks":[151],"can":[156],"be":[157],"used":[158],"candidates":[162],"biological":[164],"studies.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}