{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Ahsan MU"],"funding":["NICHD NIH HHS","NHGRI NIH HHS","NCI NIH HHS","NIGMS NIH HHS"],"pagination":["1448"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10873387"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15(1)"],"pubmed_abstract":["Oxford Nanopore sequencing can detect DNA methylations from ionic current signal of single molecules, offering a unique advantage over conventional methods. Additionally, adaptive sampling, a software-controlled enrichment method for targeted sequencing, allows reduced representation methylation sequencing that can be applied to CpG islands or imprinted regions. Here we present DeepMod2, a comprehensive deep-learning framework for methylation detection using ionic current signal from Nanopore sequencing. DeepMod2 implements both a bidirectional long short-term memory (BiLSTM) model and a Transformer model and can analyze POD5 and FAST5 signal files generated on R9 and R10 flowcells. Additionally, DeepMod2 can run efficiently on central processing unit (CPU) through model pruning and can in"],"journal":["Nature communications"],"pubmed_title":["A signal processing and deep learning framework for methylation detection using Oxford Nanopore sequencing."],"pmcid":["PMC10873387"],"funding_grant_id":["U01 CA279618","R35 GM146978","R01 HG013359","P50 HD105354"],"pubmed_authors":["Ahsan MU","Chan J","Zhou W","Gouru A","Wang K"],"additional_accession":[]},"is_claimable":false,"name":"A signal processing and deep learning framework for methylation detection using Oxford Nanopore sequencing.","description":"Oxford Nanopore sequencing can detect DNA methylations from ionic current signal of single molecules, offering a unique advantage over conventional methods. Additionally, adaptive sampling, a software-controlled enrichment method for targeted sequencing, allows reduced representation methylation sequencing that can be applied to CpG islands or imprinted regions. Here we present DeepMod2, a comprehensive deep-learning framework for methylation detection using ionic current signal from Nanopore sequencing. DeepMod2 implements both a bidirectional long short-term memory (BiLSTM) model and a Transformer model and can analyze POD5 and FAST5 signal files generated on R9 and R10 flowcells. Additionally, DeepMod2 can run efficiently on central processing unit (CPU) through model pruning and can in","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Feb","modification":"2026-06-02T06:57:20.485Z","creation":"2025-02-18T23:15:30.239Z"},"accession":"S-EPMC10873387","cross_references":{"pubmed":["38365920"],"doi":["10.1038/s41467-024-45778-y"]}}