{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Xu W"],"funding":["Fundamental Research Funds for the Central Universities","Spring City Plan{:}the High-level Talent Promotion and Training Project of Kunming","National Key Research and Development Program of China"],"pagination":["26705"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11535524"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["14(1)"],"pubmed_abstract":["Clinical proteomics analysis is of great significance for analyzing pathological mechanisms and discovering disease-related biomarkers. Using computational methods to accurately predict disease types can effectively improve patient disease diagnosis and prognosis. However, how to eliminate the errors introduced by peptide precursor identification and protein identification for pathological diagnosis remains a major unresolved issue. Here, we develop a powerful end-to-end deep learning model, termed \"MS1Former\", that is able to classify hepatocellular carcinoma tumors and adjacent non-tumor (normal) tissues directly using raw MS1 spectra without peptide precursor identification. Our model provides accurate discrimination of subtle m/z differences in MS1 between tumor and adjacent non-tumor "],"journal":["Scientific reports"],"pubmed_title":["A deep learning framework for hepatocellular carcinoma diagnosis using MS1 data."],"pmcid":["PMC11535524"],"funding_grant_id":["No.2022SCP002","No. 2022ZFJH003","No. 2019YFC0840600 and No. 2019YFC0840609"],"pubmed_authors":["Zheng X","Chen J","Yang K","Xie Z","Su K","Zhang L","Ju B","Qian X","Qu S","Sun N","He T","Zhou D","Wang Y","Xu W","Feng S","Tu X"],"additional_accession":[]},"is_claimable":false,"name":"A deep learning framework for hepatocellular carcinoma diagnosis using MS1 data.","description":"Clinical proteomics analysis is of great significance for analyzing pathological mechanisms and discovering disease-related biomarkers. Using computational methods to accurately predict disease types can effectively improve patient disease diagnosis and prognosis. However, how to eliminate the errors introduced by peptide precursor identification and protein identification for pathological diagnosis remains a major unresolved issue. Here, we develop a powerful end-to-end deep learning model, termed \"MS1Former\", that is able to classify hepatocellular carcinoma tumors and adjacent non-tumor (normal) tissues directly using raw MS1 spectra without peptide precursor identification. Our model provides accurate discrimination of subtle m/z differences in MS1 between tumor and adjacent non-tumor ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Nov","modification":"2026-06-03T00:23:52.612Z","creation":"2025-04-04T23:32:06.474Z"},"accession":"S-EPMC11535524","cross_references":{"pubmed":["39496730"],"doi":["10.1038/s41598-024-77494-4"]}}