{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Yang X"],"funding":["NIMH NIH HHS","U.S. Department of Health & Human Services | NIH | National Institute of Mental Health","NIH HHS"],"pagination":["870-877"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10314968"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["41(6)"],"pubmed_abstract":["Mosaic variants (MVs) reflect mutagenic processes during embryonic development and environmental exposure, accumulate with aging and underlie diseases such as cancer and autism. The detection of noncancer MVs has been computationally challenging due to the sparse representation of nonclonally expanded MVs. Here we present DeepMosaic, combining an image-based visualization module for single nucleotide MVs and a convolutional neural network-based classification module for control-independent MV detection. DeepMosaic was trained on 180,000 simulated or experimentally assessed MVs, and was benchmarked on 619,740 simulated MVs and 530 independent biologically tested MVs from 16 genomes and 181 exomes. DeepMosaic achieved higher accuracy compared with existing methods on biological data, with a "],"journal":["Nature biotechnology"],"pubmed_title":["Control-independent mosaic single nucleotide variant detection with DeepMosaic."],"pmcid":["PMC10314968"],"funding_grant_id":["R01 MH124890","U01 MH108898","S10 OD026929","1U01MH108898","1R01MH124890"],"pubmed_authors":["Maury E","Shen J","Dias C","Emery S","Povolotskaya I","Akbarian S","Erwin J","Dou Y","Kwan K","Walsh CA","Scuderi S","Juan D","Viswanadham V","Pochareddy S","Park PJ","Perez RG","Rosenbluh C","Ball LL","Marques-Bonet T","Chess AJ","Paquola A","Xu X","Kopera H","Lee S","Ganz J","Miller M","Gleeson JG","D'Gama A","Ratan A","Molitor C","Lee J","Sestan N","Jones A","Cheng Y","Reed P","Zhao X","Sherman M","Weinberger D","Chu C","Lee A","Bae T","Mathern G","Zhou B","Roy S","Jang Y","Flasch D","Wei L","Urban A","Alexandrov LB","Frisbie T","Kwon M","Coulter M","Zhou W","Zhou Z","Jaffe A","Galor A","Kim S","Langmead B","Chung C","Zhu X","Averbuj D","Moldovan J","Sebat JL","Hill R","Straub R","Shin J","Moran JV","Wang M","Lodato M","Thorpe J","Wang Y","Peters M","Khoshkhoo S","Li C","Yang L","Soriano E","Moruno MS","Li P","Linker S","NIMH Brain Somatic Mosaicism Network","Yang X","Gage FH","Borges-Monroy R","Courchesne E","Mills R","Breuss MW","Lobon I","Bohrson C","Jourdon A","Gulhan D","Barton A","Narurkar R","Kidd J","Cho S","Abyzov A","Vaccarino FM","Rodin R","Antaki D","McConnell M","Bizzotto S","Melloni G","Luquette J","George RD","Lim E","Fasching L","Cortes I","Huang AY","Amero AS"],"additional_accession":[]},"is_claimable":false,"name":"Control-independent mosaic single nucleotide variant detection with DeepMosaic.","description":"Mosaic variants (MVs) reflect mutagenic processes during embryonic development and environmental exposure, accumulate with aging and underlie diseases such as cancer and autism. The detection of noncancer MVs has been computationally challenging due to the sparse representation of nonclonally expanded MVs. Here we present DeepMosaic, combining an image-based visualization module for single nucleotide MVs and a convolutional neural network-based classification module for control-independent MV detection. DeepMosaic was trained on 180,000 simulated or experimentally assessed MVs, and was benchmarked on 619,740 simulated MVs and 530 independent biologically tested MVs from 16 genomes and 181 exomes. DeepMosaic achieved higher accuracy compared with existing methods on biological data, with a ","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Jun","modification":"2025-04-22T09:54:31.505Z","creation":"2025-02-19T01:18:24.358Z"},"accession":"S-EPMC10314968","cross_references":{"pubmed":["36593400"],"doi":["10.1038/s41587-022-01559-w"]}}