{"id":"https://openalex.org/W4312214411","doi":"https://doi.org/10.1093/bib/bbac584","title":"SHINE: protein language model-based pathogenicity prediction for short inframe insertion and deletion variants","display_name":"SHINE: protein language model-based pathogenicity prediction for short inframe insertion and deletion variants","publication_year":2022,"publication_date":"2022-12-03","ids":{"openalex":"https://openalex.org/W4312214411","doi":"https://doi.org/10.1093/bib/bbac584","pmid":"https://pubmed.ncbi.nlm.nih.gov/36575831"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac584","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac584","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9851320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067498089","display_name":"Xiao Fan","orcid":"https://orcid.org/0000-0002-8526-6945"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiao Fan","raw_affiliation_strings":["Department of Pediatrics, Columbia University , New York, NY , USA","Department of Systems Biology, Columbia University , New York, NY , USA"],"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Systems Biology, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025018418","display_name":"Hongbing Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongbing Pan","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053151459","display_name":"Alan Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Tian","raw_affiliation_strings":["Lynbrook High School , San Jose, CA , USA"],"affiliations":[{"raw_affiliation_string":"Lynbrook High School , San Jose, CA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018722278","display_name":"Wendy K. Chung","orcid":"https://orcid.org/0000-0003-3438-5685"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wendy K Chung","raw_affiliation_strings":["Department of Medicine, Columbia University , New York, NY , USA","Department of Pediatrics, Columbia University , New York, NY , USA"],"affiliations":[{"raw_affiliation_string":"Department of Medicine, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Pediatrics, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051597447","display_name":"Yufeng Shen","orcid":"https://orcid.org/0000-0002-1299-5979"},"institutions":[{"id":"https://openalex.org/I4210151462","display_name":"New York Genome Center","ror":"https://ror.org/05wf2ga96","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210151462"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufeng Shen","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY , USA","Department of Systems Biology, Columbia University , New York, NY , USA","JP Sulzberger Columbia Genome Center, Columbia University , New York, NY , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Systems Biology, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"JP Sulzberger Columbia Genome Center, Columbia University , New York, NY , USA","institution_ids":["https://openalex.org/I4210151462","https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018722278","https://openalex.org/A5051597447","https://openalex.org/A5067498089"],"corresponding_institution_ids":["https://openalex.org/I4210151462","https://openalex.org/I78577930"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":1.6914,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85555468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"24","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.9987999796867371,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973999857902527,"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":0.9872999787330627,"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/indel","display_name":"Indel","score":0.8364205360412598},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5584986805915833},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5429013967514038},{"id":"https://openalex.org/keywords/frameshift-mutation","display_name":"Frameshift mutation","score":0.5364473462104797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.523521900177002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48206979036331177},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4700169861316681},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.466397225856781},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.45544034242630005},{"id":"https://openalex.org/keywords/pathogenicity","display_name":"Pathogenicity","score":0.43778195977211},{"id":"https://openalex.org/keywords/indel-mutation","display_name":"INDEL Mutation","score":0.4284038841724396},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41167065501213074},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.39669132232666016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34699106216430664},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2770351767539978}],"concepts":[{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.8364205360412598},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5584986805915833},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5429013967514038},{"id":"https://openalex.org/C29906990","wikidata":"https://www.wikidata.org/wiki/Q1440688","display_name":"Frameshift mutation","level":4,"score":0.5364473462104797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.523521900177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48206979036331177},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4700169861316681},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.466397225856781},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.45544034242630005},{"id":"https://openalex.org/C64502627","wikidata":"https://www.wikidata.org/wiki/Q170065","display_name":"Pathogenicity","level":2,"score":0.43778195977211},{"id":"https://openalex.org/C2910714999","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"INDEL Mutation","level":5,"score":0.4284038841724396},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41167065501213074},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.39669132232666016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34699106216430664},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2770351767539978},{"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},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"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/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014774","descriptor_name":"Virulence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbac584","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac584","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36575831","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36575831","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9851320","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9851320","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9851320","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9851320","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6258474117","display_name":null,"funder_award_id":"R01GM120609","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7266119239","display_name":null,"funder_award_id":"K99HG011490","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":29,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1900984040","https://openalex.org/W1986524996","https://openalex.org/W1992880766","https://openalex.org/W1998120162","https://openalex.org/W2101234009","https://openalex.org/W2148152877","https://openalex.org/W2154595610","https://openalex.org/W2519529853","https://openalex.org/W2571852295","https://openalex.org/W2770026599","https://openalex.org/W2773354488","https://openalex.org/W2785900161","https://openalex.org/W2905452503","https://openalex.org/W2951373902","https://openalex.org/W2967865580","https://openalex.org/W2969366465","https://openalex.org/W3080696152","https://openalex.org/W3093292403","https://openalex.org/W3146944767","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W3207912190","https://openalex.org/W3211728297","https://openalex.org/W4282925771","https://openalex.org/W4293068416","https://openalex.org/W4389398607","https://openalex.org/W6648400570","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W1971376828","https://openalex.org/W2046457574","https://openalex.org/W2135846417","https://openalex.org/W4206406917","https://openalex.org/W2080028493","https://openalex.org/W2167094946","https://openalex.org/W3103976079","https://openalex.org/W4387460329","https://openalex.org/W2147536515","https://openalex.org/W2996849075"],"abstract_inverted_index":{"Accurate":[0],"variant":[1,67,207],"pathogenicity":[2,101,147],"predictions":[3],"are":[4],"important":[5],"in":[6,38,71,179,209],"genetic":[7,210],"studies":[8],"of":[9,42,75,87,94,121],"human":[10],"diseases.":[11],"Inframe":[12,30,105],"insertion":[13,177],"and":[14,21,60,62,78,107,124,131,136,155,157,176,198],"deletion":[15,175],"variants":[16,45,178],"(indels)":[17],"alter":[18],"protein":[19,58,76,95,113,126,129,133,189],"sequence":[20,134],"length,":[22],"but":[23],"not":[24],"as":[25,27],"deleterious":[26],"frameshift":[28],"indels.":[29],"indel":[31,123],"Interpretation":[32],"is":[33],"challenging":[34],"due":[35],"to":[36,65,83,116],"limitations":[37],"the":[39,85,138],"available":[40],"number":[41],"known":[43],"pathogenic":[44],"for":[46,103,146,173],"training.":[47],"Existing":[48],"prediction":[49,168],"methods":[50,172,200],"largely":[51],"use":[52],"manually":[53],"encoded":[54],"features":[55,89],"including":[56],"conservation,":[57],"structure":[59],"function,":[61],"allele":[63],"frequency":[64],"infer":[66],"pathogenicity.":[68],"Recent":[69],"advances":[70],"deep":[72],"learning":[73,144],"modeling":[74],"sequences":[77,130],"structures":[79],"provide":[80,193],"an":[81,122],"opportunity":[82],"improve":[84,206],"representation":[86,120,140],"salient":[88],"based":[90,201],"on":[91,202],"large":[92],"numbers":[93],"sequences.":[96],"We":[97,149],"developed":[98],"a":[99,118],"new":[100,199],"predictor":[102],"SHort":[104],"iNsertion":[106],"dEletion":[108],"(SHINE).":[109],"SHINE":[110,165],"uses":[111],"pretrained":[112],"language":[114,190],"models":[115,145,191,204],"construct":[117],"latent":[119,139],"its":[125],"context":[127],"from":[128,153,162],"multiple":[132],"alignments,":[135],"feeds":[137],"into":[141],"supervised":[142],"machine":[143],"prediction.":[148],"curated":[150],"training":[151],"data":[152],"ClinVar":[154],"gnomAD,":[156],"created":[158],"two":[159,181],"test":[160,182],"datasets":[161],"different":[163],"sources.":[164],"achieved":[166],"better":[167],"performance":[169],"than":[170],"existing":[171],"both":[174],"these":[180,203],"datasets.":[183],"Our":[184],"work":[185],"suggests":[186],"that":[187],"unsupervised":[188],"can":[192,205],"valuable":[194],"information":[195],"about":[196],"proteins,":[197],"interpretation":[208],"analyses.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
