SMSNet's training datasets (WCU-MS-BEST, DeepNovo, ProteomeTools)

This is the WCU-MS-BEST dataset of non-redundant MS/MS spectra for 1,217,750 unmodified peptides aggregated from the dataset used to train and evaluated SMSNet (https://pubmed.ncbi.nlm.nih.gov/31591261/). <br>Each row of the file contains raw file ID (this can be used to group spectra from the same experiment), PEP score (from MaxQuant's evidence), peptide sequence (MaxQuant's style), modification (MaxQuant's style), charge state, precursor m/z, retention time, and the observed MS/MS peaks in csv format.<br><br><b>Updated 9 December 2021</b>Due to limited 20GB constraint, we have to remove the DeepNovo and ProteomeTools datasets. Please download these datasets from the original sources listed below:<br>DeepNovo dataset consists of peptides identified through high-resolution MS/MS spectra on Q Exactive instruments as described in the DeepNovo article (Tran <i>et al</i>. PNAS 114:8247-8252, 2017). PRIDE accessions for these experiments are PXD005025, PXD004948, PXD004325, PXD004565,PXD004536, PXD004947, PXD003868, PXD004467, and PXD004424.<br>ProteomeTools dataset consists of synthetic peptides identified through high-resolution MS/MS spectra on Orbitrap Fusion Lumos as described in the ProteomeTools article (Zolg <i>et al</i>. Nat Methods 14:259-262, 2017).