Jiyun Zhou, Chongyuan Luo, Hanqing Liu, Matthew G Heffel, Richard E Straub, Joel E Kleinman, Thomas M Hyde, Joseph R Ecker, Daniel R Weinberger, Shizhong Han
{"title":"深度学习估算单细胞DNA甲基化状态,增强对精神分裂症表观遗传改变的检测。","authors":"Jiyun Zhou, Chongyuan Luo, Hanqing Liu, Matthew G Heffel, Richard E Straub, Joel E Kleinman, Thomas M Hyde, Joseph R Ecker, Daniel R Weinberger, Shizhong Han","doi":"10.1016/j.xgen.2025.100774","DOIUrl":null,"url":null,"abstract":"<p><p>DNA methylation (DNAm) is a key epigenetic mark with essential roles in gene regulation, mammalian development, and human diseases. Single-cell technologies enable profiling DNAm at cytosines in individual cells, but they often suffer from low coverage for CpG sites. We introduce scMeFormer, a transformer-based deep learning model for imputing DNAm states at each CpG site in single cells. Comprehensive evaluations across five single-nucleus DNAm datasets from human and mouse demonstrate scMeFormer's superior performance over alternative models, achieving high-fidelity imputation even with coverage reduced to 10% of original CpG sites. Applying scMeFormer to a single-nucleus DNAm dataset from the prefrontal cortex of patients with schizophrenia and controls identified thousands of schizophrenia-associated differentially methylated regions that would have remained undetectable without imputation and added granularity to our understanding of epigenetic alterations in schizophrenia. We anticipate that scMeFormer will be a valuable tool for advancing single-cell DNAm studies.</p>","PeriodicalId":72539,"journal":{"name":"Cell genomics","volume":" ","pages":"100774"},"PeriodicalIF":11.1000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11960545/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning imputes DNA methylation states in single cells and enhances the detection of epigenetic alterations in schizophrenia.\",\"authors\":\"Jiyun Zhou, Chongyuan Luo, Hanqing Liu, Matthew G Heffel, Richard E Straub, Joel E Kleinman, Thomas M Hyde, Joseph R Ecker, Daniel R Weinberger, Shizhong Han\",\"doi\":\"10.1016/j.xgen.2025.100774\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>DNA methylation (DNAm) is a key epigenetic mark with essential roles in gene regulation, mammalian development, and human diseases. Single-cell technologies enable profiling DNAm at cytosines in individual cells, but they often suffer from low coverage for CpG sites. We introduce scMeFormer, a transformer-based deep learning model for imputing DNAm states at each CpG site in single cells. Comprehensive evaluations across five single-nucleus DNAm datasets from human and mouse demonstrate scMeFormer's superior performance over alternative models, achieving high-fidelity imputation even with coverage reduced to 10% of original CpG sites. Applying scMeFormer to a single-nucleus DNAm dataset from the prefrontal cortex of patients with schizophrenia and controls identified thousands of schizophrenia-associated differentially methylated regions that would have remained undetectable without imputation and added granularity to our understanding of epigenetic alterations in schizophrenia. We anticipate that scMeFormer will be a valuable tool for advancing single-cell DNAm studies.</p>\",\"PeriodicalId\":72539,\"journal\":{\"name\":\"Cell genomics\",\"volume\":\" \",\"pages\":\"100774\"},\"PeriodicalIF\":11.1000,\"publicationDate\":\"2025-03-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11960545/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cell genomics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1016/j.xgen.2025.100774\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/2/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CELL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cell genomics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.xgen.2025.100774","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/21 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CELL BIOLOGY","Score":null,"Total":0}
Deep learning imputes DNA methylation states in single cells and enhances the detection of epigenetic alterations in schizophrenia.
DNA methylation (DNAm) is a key epigenetic mark with essential roles in gene regulation, mammalian development, and human diseases. Single-cell technologies enable profiling DNAm at cytosines in individual cells, but they often suffer from low coverage for CpG sites. We introduce scMeFormer, a transformer-based deep learning model for imputing DNAm states at each CpG site in single cells. Comprehensive evaluations across five single-nucleus DNAm datasets from human and mouse demonstrate scMeFormer's superior performance over alternative models, achieving high-fidelity imputation even with coverage reduced to 10% of original CpG sites. Applying scMeFormer to a single-nucleus DNAm dataset from the prefrontal cortex of patients with schizophrenia and controls identified thousands of schizophrenia-associated differentially methylated regions that would have remained undetectable without imputation and added granularity to our understanding of epigenetic alterations in schizophrenia. We anticipate that scMeFormer will be a valuable tool for advancing single-cell DNAm studies.