{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["16(1)"],"submitter":["Liu Z"],"pubmed_abstract":["Data-independent acquisition mass spectrometry (DIA-MS) has become increasingly pivotal in quantitative proteomics. In this study, we present DIA-BERT, a software tool that harnesses a transformer-based pre-trained artificial intelligence (AI) model for analyzing DIA proteomics data. The identification model was trained using over 276 million high-quality peptide precursors extracted from existing DIA-MS files, while the quantification model was trained on 34 million peptide precursors from synthetic DIA-MS files. When compared to DIA-NN, DIA-BERT demonstrated a 51% increase in protein identifications and 22% more peptide precursors on average across five human cancer sample sets (cervical cancer, pancreatic adenocarcinoma, myosarcoma, gallbladder cancer, and gastric carcinoma), achieving "],"journal":["Nature communications"],"pagination":["3530"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11997033"],"repository":["biostudies-literature"],"pubmed_title":["DIA-BERT: pre-trained end-to-end transformer models for enhanced DIA proteomics data analysis."],"pmcid":["PMC11997033"],"pubmed_authors":["Liu Z","Zhang Y","Zhang X","Liu P","Nie Z","Chen Y","Guo T","Sun Y"],"additional_accession":[]},"is_claimable":false,"name":"DIA-BERT: pre-trained end-to-end transformer models for enhanced DIA proteomics data analysis.","description":"Data-independent acquisition mass spectrometry (DIA-MS) has become increasingly pivotal in quantitative proteomics. In this study, we present DIA-BERT, a software tool that harnesses a transformer-based pre-trained artificial intelligence (AI) model for analyzing DIA proteomics data. The identification model was trained using over 276 million high-quality peptide precursors extracted from existing DIA-MS files, while the quantification model was trained on 34 million peptide precursors from synthetic DIA-MS files. When compared to DIA-NN, DIA-BERT demonstrated a 51% increase in protein identifications and 22% more peptide precursors on average across five human cancer sample sets (cervical cancer, pancreatic adenocarcinoma, myosarcoma, gallbladder cancer, and gastric carcinoma), achieving ","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Apr","modification":"2026-06-01T12:57:01.87Z","creation":"2026-04-08T12:37:21.295Z"},"accession":"S-EPMC11997033","cross_references":{"pubmed":["40229248"],"doi":["10.1038/s41467-025-58866-4"]}}