<HashMap><database>panorama</database><scores/><additional><omics_type>Proteomics</omics_type><submitter>Bo Wen</submitter><species>Homo Sapiens</species><species>Saccharomyces Cerevisiae</species><full_dataset_link>https://panoramaweb.org/Carafe2.url</full_dataset_link><submitter_email>bwen1@uw.edu</submitter_email><submitter_affiliation>University of Washington</submitter_affiliation><sample_protocol></sample_protocol><repository>PanoramaPublic</repository><data_protocol></data_protocol></additional><is_claimable>false</is_claimable><name>Carafe2 enables high quality in silico spectral library generation for timsTOF data-independent acquisition proteomics</name><description>Carafe (https://github.com/Noble-Lab/Carafe) is a software tool that uses deep learning models to generate high-quality, experiment-specific in silico libraries by training
directly on DIA data. In this study, we extend Carafe to generate libraries for timsTOF DIA data, which involves fine-tuning retention time, fragment ion intensity, and ion mobility prediction models using timsTOF DIA data. Carafe2 operates directly on native timsTOF raw data (Bruker .d directories) without the need for data conversion.</description><dates><publication>Tue Mar 31 00:00:00 BST 2026</publication></dates><accession>PXD075483</accession><cross_references><TAXONOMY>9606</TAXONOMY><TAXONOMY>4932</TAXONOMY></cross_references></HashMap>