{"id":"https://openalex.org/W4220657176","doi":"https://doi.org/10.1093/bioinformatics/btac188","title":"TransPPMP: predicting pathogenicity of frameshift and non-sense mutations by a Transformer based on protein features","display_name":"TransPPMP: predicting pathogenicity of frameshift and non-sense mutations by a Transformer based on protein features","publication_year":2022,"publication_date":"2022-03-26","ids":{"openalex":"https://openalex.org/W4220657176","doi":"https://doi.org/10.1093/bioinformatics/btac188","pmid":"https://pubmed.ncbi.nlm.nih.gov/35561183"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac188","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac188","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"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/A5073740698","display_name":"Liangpeng Nie","orcid":"https://orcid.org/0000-0003-4210-8039"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangpeng Nie","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University , Suzhou 215006, China"],"raw_orcid":"https://orcid.org/0000-0003-4210-8039","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102768562","display_name":"Lijun Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Quan","raw_affiliation_strings":["Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","School of Computer Science and Technology, Soochow University , Suzhou 215006, China"],"raw_orcid":"https://orcid.org/0000-0002-8103-555X","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","institution_ids":[]},{"raw_affiliation_string":"Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064852381","display_name":"Tingfang Wu","orcid":"https://orcid.org/0000-0001-8137-2436"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingfang Wu","raw_affiliation_strings":["Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","School of Computer Science and Technology, Soochow University , Suzhou 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","institution_ids":[]},{"raw_affiliation_string":"Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061966798","display_name":"Ruji He","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruji He","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University , Suzhou 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061252858","display_name":"Qiang Lyu","orcid":"https://orcid.org/0000-0003-2371-835X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiang Lyu","raw_affiliation_strings":["Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","School of Computer Science and Technology, Soochow University , Suzhou 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing 210000, China","institution_ids":[]},{"raw_affiliation_string":"Province Key Lab for Information Processing Technologies, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University , Suzhou 215006, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061252858"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.1623,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87600958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"38","issue":"10","first_page":"2705","last_page":"2711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.8730999827384949,"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":0.8730999827384949,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0786999985575676,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.007699999958276749,"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/frameshift-mutation","display_name":"Frameshift mutation","score":0.9685980081558228},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5211508274078369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5170974731445312},{"id":"https://openalex.org/keywords/indel","display_name":"Indel","score":0.4867975413799286},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.472102552652359},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4585364758968353},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3731800317764282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3504602611064911},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34130996465682983},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3260958194732666},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07966634631156921}],"concepts":[{"id":"https://openalex.org/C29906990","wikidata":"https://www.wikidata.org/wiki/Q1440688","display_name":"Frameshift mutation","level":4,"score":0.9685980081558228},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5211508274078369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5170974731445312},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.4867975413799286},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.472102552652359},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4585364758968353},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3731800317764282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3504602611064911},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34130996465682983},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3260958194732666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07966634631156921},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":"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":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btac188","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac188","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35561183","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35561183","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}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[{"id":"https://openalex.org/G4447477790","display_name":null,"funder_award_id":"31801108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G739727963","display_name":null,"funder_award_id":"62002251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W255996521","https://openalex.org/W1543773936","https://openalex.org/W1900984040","https://openalex.org/W1912672559","https://openalex.org/W1979315776","https://openalex.org/W1987754412","https://openalex.org/W1990862775","https://openalex.org/W1992014969","https://openalex.org/W1992880766","https://openalex.org/W2004854771","https://openalex.org/W2006770045","https://openalex.org/W2007089471","https://openalex.org/W2051978340","https://openalex.org/W2059145105","https://openalex.org/W2096777589","https://openalex.org/W2097606916","https://openalex.org/W2116836989","https://openalex.org/W2123960992","https://openalex.org/W2139814263","https://openalex.org/W2158714788","https://openalex.org/W2160995259","https://openalex.org/W2187089797","https://openalex.org/W2208335363","https://openalex.org/W2212703438","https://openalex.org/W2276848127","https://openalex.org/W2474991972","https://openalex.org/W2779236324","https://openalex.org/W2802948002","https://openalex.org/W2884561390","https://openalex.org/W2936956377","https://openalex.org/W3119010522","https://openalex.org/W3121000782","https://openalex.org/W3132630320","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W4385245566","https://openalex.org/W6609701964","https://openalex.org/W6688167117","https://openalex.org/W6739901393","https://openalex.org/W6787714344"],"related_works":["https://openalex.org/W4207058155","https://openalex.org/W2404943785","https://openalex.org/W2125459609","https://openalex.org/W1989496903","https://openalex.org/W2001105869","https://openalex.org/W4281651212","https://openalex.org/W1999676762","https://openalex.org/W2072457809","https://openalex.org/W2366621628","https://openalex.org/W2032169129"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein":[1],"structure":[2,147],"can":[3,24,224,245],"be":[4,26,246],"severely":[5],"disrupted":[6],"by":[7,133,248],"frameshift":[8,39,96,115],"and":[9,20,36,40,46,68,80,93,97,116,122,142,148,156,175,185,202,230],"non-sense":[10,21,41,98,117],"mutations":[11,42,99,118],"at":[12,279,287],"specific":[13],"positions":[14],"in":[15,28,188,215],"the":[16,57,112,134,143,157,165,170,208,211,219,242,258],"protein":[17,120],"sequence.":[18],"Frameshift":[19],"mutation":[22,140],"cases":[23],"also":[25,234],"found":[27],"healthy":[29],"individuals.":[30],"A":[31],"method":[32],"to":[33,53,76,83,89,110,163,217,256],"distinguish":[34,90],"neutral":[35,92],"potentially":[37,58,94],"disease-associated":[38,95],"is":[43,161,277],"of":[44,65,87,114,129,139,210,221,261],"practical":[45],"fundamental":[47],"importance.":[48],"It":[49],"would":[50],"allow":[51],"researchers":[52],"rapidly":[54],"screen":[55],"out":[56],"pathogenic":[59],"sites":[60,72,236],"from":[61],"a":[62,105,238],"large":[63,239],"number":[64],"mutated":[66,243],"genes":[67],"then":[69],"use":[70],"these":[71],"as":[73,153],"drug":[74],"targets":[75],"speed":[77],"up":[78],"diagnosis":[79],"improve":[81],"access":[82],"treatment.":[84],"The":[85,126],"problem":[86,168],"how":[88],"between":[91],"remains":[100],"under-researched.":[101],"RESULTS:":[102],"We":[103],"built":[104],"Transformer-based":[106],"neural":[107],"network":[108],"model":[109],"predict":[111,218],"pathogenicity":[113,220,259],"on":[119,241],"features":[121],"named":[123],"it":[124],"TransPPMP.":[125],"feature":[127],"matrix":[128],"contextual":[130],"sequences":[131],"computed":[132],"ESM":[135],"pre-training":[136],"model,":[137],"type":[138],"residue":[141,244],"auxiliary":[144],"features,":[145,155],"including":[146],"function":[149,160],"information,":[150],"are":[151,285],"combined":[152],"input":[154],"focal":[158],"loss":[159],"designed":[162],"solve":[164],"sample":[166],"imbalance":[167],"during":[169],"training.":[171],"In":[172,204],"10-fold":[173],"cross-validation":[174],"independent":[176],"blind":[177],"test":[178],"set,":[179],"TransPPMP":[180,276],"showed":[181],"good":[182],"robust":[183],"performance":[184],"absolute":[186],"advantages":[187],"all":[189],"evaluation":[190],"metrics":[191],"compared":[192],"with":[193,237],"four":[194],"other":[195],"advanced":[196],"methods,":[197],"namely,":[198],"ENTPRISE-X,":[199],"VEST-indel,":[200],"DDIG-in":[201],"CADD.":[203],"addition,":[205],"we":[206],"demonstrate":[207],"usefulness":[209],"multi-head":[212],"attention":[213,249],"mechanism":[214,260],"Transformer":[216],"mutations-not":[222],"only":[223],"multiple":[225],"self-attention":[226],"heads":[227],"learn":[228],"local":[229],"global":[231],"interactions":[232],"but":[233],"functional":[235],"influence":[240],"captured":[247],"focus.":[250],"These":[251],"could":[252],"offer":[253],"useful":[254],"clues":[255],"study":[257],"human":[262],"complex":[263],"diseases":[264],"for":[265],"which":[266],"traditional":[267],"machine":[268],"learning":[269],"methods":[270],"fall":[271],"short.":[272],"AVAILABILITY":[273],"AND":[274],"IMPLEMENTATION:":[275],"available":[278,286],"https://github.com/lennylv/TransPPMP.":[280],"SUPPLEMENTARY":[281],"INFORMATION:":[282],"Supplementary":[283],"data":[284],"Bioinformatics":[288],"online.":[289]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
