{"id":"https://openalex.org/W7212065358","doi":"https://doi.org/10.64898/2026.09.06.749687","title":"MutCleaner: Cleaning and Standardizing Biological Mutation Datasets for Variant Effect Prediction","display_name":"MutCleaner: Cleaning and Standardizing Biological Mutation Datasets for Variant Effect Prediction","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212065358","doi":"https://doi.org/10.64898/2026.09.06.749687"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.06.749687","doi":"https://doi.org/10.64898/2026.09.06.749687","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.06.749687","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.06.749687.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.06.749687.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146973418","display_name":"Ziyu Shi","orcid":"https://orcid.org/0009-0002-3748-2536","observed_orcids":["https://orcid.org/0009-0002-3748-2536"]},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Shi","raw_affiliation_strings":["School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China"],"raw_orcid":"https://orcid.org/0009-0002-3748-2536","affiliations":[{"raw_affiliation_string":"School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China","institution_ids":["https://openalex.org/I158934434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101068299","display_name":"Yuxiang Tang","orcid":"https://orcid.org/0009-0009-2967-0140","observed_orcids":["https://orcid.org/0009-0009-2967-0140","https://orcid.org/0009-0001-1449-334X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Tang","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systematic Biology, School of Life Sciences, Tsinghua University, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0009-0001-1449-334X","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systematic Biology, School of Life Sciences, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027788659","display_name":"Mengxin Yang","orcid":"https://orcid.org/0009-0001-4013-8202","observed_orcids":["https://orcid.org/0009-0001-4013-8202","https://orcid.org/0009-0009-3754-8778"]},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxin Yang","raw_affiliation_strings":["School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China"],"raw_orcid":"https://orcid.org/0009-0009-3754-8778","affiliations":[{"raw_affiliation_string":"School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China","institution_ids":["https://openalex.org/I158934434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151087885","display_name":"Shize Yu","orcid":"https://orcid.org/0009-0005-0448-9055","observed_orcids":["https://orcid.org/0009-0005-0448-9055"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shize Yu","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology, Wuhan 430074, China"],"raw_orcid":"https://orcid.org/0009-0005-0448-9055","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151089951","display_name":"Yancheng Shi","orcid":"https://orcid.org/0009-0007-0061-8627","observed_orcids":["https://orcid.org/0009-0007-0061-8627"]},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yancheng Shi","raw_affiliation_strings":["School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China"],"raw_orcid":"https://orcid.org/0009-0007-0061-8627","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China","institution_ids":["https://openalex.org/I158934434"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101495490","display_name":"Yunxin Xu","orcid":"https://orcid.org/0000-0002-9981-2097","observed_orcids":["https://orcid.org/0000-0002-9981-2097"]},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunxin Xu","raw_affiliation_strings":["School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China"],"raw_orcid":"https://orcid.org/0000-0002-9981-2097","affiliations":[{"raw_affiliation_string":"School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China","institution_ids":["https://openalex.org/I158934434"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101495490"],"corresponding_institution_ids":["https://openalex.org/I158934434"],"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":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":0.6747999787330627,"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":0.6747999787330627,"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":0.08959999680519104,"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":0.06620000302791595,"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/variant-effect-prediction","display_name":"variant effect prediction","score":0.8050000071525574},{"id":"https://openalex.org/keywords/data-standardization","display_name":"data standardization","score":0.7570000290870667},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.8479999899864197},{"id":"https://openalex.org/keywords/open-source-python-package","display_name":"open-source Python package","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7720999717712402},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.6672999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.602400004863739},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.5120999813079834},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5063999891281128},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C163565370","wikidata":"https://www.wikidata.org/wiki/Q4308623","display_name":"Mutation testing","level":4,"score":0.44029998779296875},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2815999984741211},{"id":"https://openalex.org/C98638677","wikidata":"https://www.wikidata.org/wiki/Q2067051","display_name":"Mutation rate","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.06.749687","doi":"https://doi.org/10.64898/2026.09.06.749687","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.06.749687","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.06.749687.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.06.749687","doi":"https://doi.org/10.64898/2026.09.06.749687","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.06.749687","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/08/2026.09.06.749687.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212065358.pdf","grobid_xml":"https://content.openalex.org/works/W7212065358.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2060588922","https://openalex.org/W2145317354","https://openalex.org/W2604078450","https://openalex.org/W2987965949","https://openalex.org/W3169651048","https://openalex.org/W3179071715","https://openalex.org/W3179259355","https://openalex.org/W4283646162","https://openalex.org/W4309306331","https://openalex.org/W4384820649","https://openalex.org/W4392041393","https://openalex.org/W4392796941","https://openalex.org/W4401071498","https://openalex.org/W4402132679","https://openalex.org/W4402826776","https://openalex.org/W4403770916","https://openalex.org/W4406167408","https://openalex.org/W4406674953","https://openalex.org/W4409564264","https://openalex.org/W7133185245"],"related_works":["https://openalex.org/W7096142735","https://openalex.org/W2151529283","https://openalex.org/W2760800862","https://openalex.org/W2774216375","https://openalex.org/W2795970199","https://openalex.org/W2132312350","https://openalex.org/W6894198959","https://openalex.org/W2753919414","https://openalex.org/W4389472984","https://openalex.org/W4400358823"],"abstract_inverted_index":{"Abstract":[0],"Summary":[1],"Protein":[2],"mutation":[3,25,64,73,88,95],"datasets":[4,16,65,89],"are":[5],"widely":[6],"used":[7],"in":[8,45],"variant":[9],"effect":[10],"prediction":[11],"and":[12,31,41,48,59,62,72,76,86,98,125],"protein":[13,85],"engineering,":[14],"but":[15],"from":[17],"different":[18],"sources":[19],"often":[20],"lack":[21],"consistent":[22],"conventions":[23],"for":[24],"representation,":[26,28],"sequence":[27,71],"data":[29,74],"organization,":[30],"experimental":[32],"labels,":[33],"making":[34],"these":[35],"resources":[36,82],"difficult":[37],"to":[38],"integrate":[39],"directly":[40],"limiting":[42],"their":[43],"use":[44],"downstream":[46],"analyses":[47],"modeling.":[49],"MutCleaner":[50,100],"is":[51,101,115,121,128],"an":[52,102],"extensible":[53],"Python":[54,104],"framework":[55],"that":[56],"cleans,":[57],"validates,":[58],"standardizes":[60],"protein-":[61],"codon-level":[63],"through":[66,123],"composable":[67],"cleaning":[68],"pipelines,":[69],"unified":[70],"structures,":[75],"dataset-specific":[77],"cleaners.":[78],"It":[79],"provides":[80],"standardized":[81],"covering":[83],"16":[84],"codon":[87],"with":[90],"more":[91],"than":[92],"12.14":[93],"million":[94],"records":[96],"Availability":[97],"implementation":[99],"open-source":[103],"package":[105,120],"released":[106],"under":[107],"the":[108,119,126],"Apache":[109],"License":[110],"2.0.":[111],"The":[112],"source":[113],"code":[114],"available":[116,129],"on":[117],"GitHub,":[118],"distributed":[122],"PyPI,":[124],"documentation":[127],"online.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-10T00:00:00"}
