{"id":"https://openalex.org/W7203477847","doi":"https://doi.org/10.64898/2026.08.12.744371","title":"CodonBench: separating gene context, exon position, and variant-specific component in synonymous-variant classification","display_name":"CodonBench: separating gene context, exon position, and variant-specific component in synonymous-variant classification","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203477847","doi":"https://doi.org/10.64898/2026.08.12.744371"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.12.744371","doi":"https://doi.org/10.64898/2026.08.12.744371","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.12.744371","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.12.744371.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.12.744371.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147159691","display_name":"Yuanqing Liang","orcid":"https://orcid.org/0009-0004-4761-2706","observed_orcids":["https://orcid.org/0009-0004-4761-2706"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqing Liang","raw_affiliation_strings":["School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":"https://orcid.org/0009-0004-4761-2706","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042267085","display_name":"Weimin Zhu","orcid":"https://orcid.org/0000-0002-2420-0731","observed_orcids":["https://orcid.org/0000-0002-2420-0731","https://orcid.org/0000-0001-8347-5754","https://orcid.org/0000-0002-9200-2438"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zhu","raw_affiliation_strings":["Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China"],"raw_orcid":"https://orcid.org/0000-0002-9200-2438","affiliations":[{"raw_affiliation_string":"Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091365447","display_name":"Xiaoyong Pan","orcid":"https://orcid.org/0000-0001-5010-464X","observed_orcids":["https://orcid.org/0000-0001-5010-464X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Pan","raw_affiliation_strings":["Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China"],"raw_orcid":"https://orcid.org/0000-0001-5010-464X","affiliations":[{"raw_affiliation_string":"Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633592","display_name":"Huixian Li","orcid":"https://orcid.org/0000-0001-5722-8602","observed_orcids":["https://orcid.org/0000-0001-5722-8602"]},"institutions":[{"id":"https://openalex.org/I4210145693","display_name":"Guangdong Academy of Medical Sciences","ror":"https://ror.org/0432p8t34","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210145693"]},{"id":"https://openalex.org/I4210153930","display_name":"Guangdong Provincial People's Hospital","ror":"https://ror.org/045kpgw45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210153930"]},{"id":"https://openalex.org/I58200834","display_name":"Southern Medical University","ror":"https://ror.org/01vjw4z39","country_code":"CN","type":"education","lineage":["https://openalex.org/I58200834"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huixian Li","raw_affiliation_strings":["Medical Big Data Center, Guangdong Provincial People\u2019s Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, Guangdong Province, 510080, China"],"raw_orcid":"https://orcid.org/0000-0001-5722-8602","affiliations":[{"raw_affiliation_string":"Medical Big Data Center, Guangdong Provincial People\u2019s Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, Guangdong Province, 510080, China","institution_ids":["https://openalex.org/I4210145693","https://openalex.org/I4210153930","https://openalex.org/I58200834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9984999895095825,"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":0.9984999895095825,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.00019999999494757503,"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/T13702","display_name":"Machine Learning in Healthcare","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/synonymous-mutations","display_name":"synonymous mutations","score":0.9269999861717224},{"id":"https://openalex.org/keywords/variant-pathogenicity-classification","display_name":"variant pathogenicity classification","score":0.7950000166893005},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.9390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5963000059127808},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496000051498413},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C87253356","wikidata":"https://www.wikidata.org/wiki/Q1106472","display_name":"Codon usage bias","level":4,"score":0.3804999887943268},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.12.744371","doi":"https://doi.org/10.64898/2026.08.12.744371","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.12.744371","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.12.744371.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.12.744371","doi":"https://doi.org/10.64898/2026.08.12.744371","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.12.744371","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.12.744371.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203477847.pdf","grobid_xml":"https://content.openalex.org/works/W7203477847.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161579030","https://openalex.org/W4390656830","https://openalex.org/W2666856234","https://openalex.org/W7124466396","https://openalex.org/W7169836198","https://openalex.org/W7125954661","https://openalex.org/W4290714496","https://openalex.org/W7128001783","https://openalex.org/W4417442018","https://openalex.org/W6889460051"],"abstract_inverted_index":{"Background":[0],"A":[1,122],"synonymous":[2,46],"variant":[3,133,211],"leaves":[4],"the":[5,23,109,119,129,132,135,142,154,165,172,175,178,210,219],"protein":[6,152],"unchanged,":[7],"so":[8,82],"a":[9,30,35,42,70,104,151,206],"classifier":[10],"that":[11,124,217],"still":[12],"separates":[13],"pathogenic":[14],"from":[15,131,199,203],"benign":[16],"examples":[17],"must":[18],"be":[19],"reading":[20],"something":[21],"beyond":[22],"protein.":[24],"Such":[25],"variants":[26],"test":[27],"cleanly":[28],"what":[29,229],"codon-level":[31],"model":[32,66,153],"adds":[33],"to":[34,134],"protein-level":[36],"one.":[37],"Methods":[38],"We":[39],"assembled":[40],"SynPath,":[41],"benchmark":[43],"of":[44],"ClinVar":[45],"variants,":[47],"and":[48,63,113,180,188,202,213],"scored":[49],"frozen":[50],"representations":[51],"under":[52,141],"two":[53],"splitting":[54,91],"protocols.":[55],"Under":[56],"gene-held-out":[57],"folds":[58],"whole":[59,96],"genes":[60,97,187],"are":[61,98],"withheld,":[62],"each":[64],"coding-sequence":[65,169],"is":[67,157,196],"compared":[68],"against":[69],"position-matched":[71,191],"control.":[72,192],"Results":[73],"The":[74],"models":[75,170,216,231],"were":[76],"not":[77,87,117],"trained":[78],"for":[79],"this":[80],"task,":[81],"these":[83,230],"numbers":[84],"describe":[85],"transfer,":[86],"designed":[88],"performance.":[89],"Random":[90],"flatters":[92],"every":[93,146],"representation.":[94],"Once":[95],"held":[99],"out,":[100],"they":[101],"fall":[102],"into":[103],"narrow":[105],"band":[106],"near":[107],"chance,":[108],"best":[110],"at":[111],"0.58,":[112],"low-rank":[114],"fine-tuning":[115],"does":[116],"restore":[118],"random-split":[120],"level.":[121],"feature":[123],"reads":[125],"no":[126],"sequence,":[127],"only":[128,171,214],"distance":[130],"nearest":[136],"exon":[137],"junction,":[138],"reaches":[139],"0.84":[140],"same":[143,166],"folds,":[144],"above":[145],"neural":[147],"representation":[148],"tested.":[149],"In":[150,168],"variant-specific":[155],"component":[156],"zero":[158],"by":[159],"construction,":[160],"because":[161],"both":[162],"alleles":[163],"present":[164],"input.":[167],"response":[173],"vector,":[174],"difference":[176],"between":[177],"alternate":[179],"reference":[181],"embeddings,":[182],"keeps":[183],"signal":[184],"on":[185,224],"unseen":[186],"beats":[189],"its":[190],"Conclusions":[193],"Synonymous-variant":[194],"pathogenicity":[195],"predictable":[197],"mainly":[198],"gene":[200],"identity":[201],"position.":[204],"Only":[205],"small":[207],"part":[208],"reflects":[209],"itself,":[212],"in":[215],"read":[218],"coding":[220],"sequence.":[221],"Benchmarks":[222],"judged":[223],"random":[225],"splits":[226],"will":[227],"overstate":[228],"have":[232],"learned.":[233]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-15T00:00:00"}