Public Data files for MassFormer

Public data files for experiments in MassFormer. See the Github repository for instructions on how to use this data. <strong>Raw Data:</strong> casmi_2016.tgz - Critical Assessment of Small Molecule Identification 2016, used for model evaluation. casmi_2022.tgz - Critical Assessment of Small Molecule Identification 2022, used for model evaluation. mb_na_msms.msp.gz - MassBank of North America export of LC-MS/MS spectra, used for model evaluation. cid_smiles.tsv.gz - Mapping of CID to SMILES strings, obtained from PubChem. <strong>Processed Data:</strong> proc_casmi_2016.tgz - Processed spectrum and molecule data for the CASMI 2016 benchmark. proc_casmi_2022.tgz - Processed spectrum and molecule data for the CASMI 2022 benchmark. proc_nist20_outlier.tgz - Processed spectrum and molecule data for the NIST20 Outlier benchmark (formerly called pseudo-CASMI). proc_demo.tgz - Processed spectrum and molecule data for the demo (refer to code repository for more information). cfm.tgz - Predicted spectra for the Competitive Fragmentation Modelling (CFM) baseline. <strong>Model Checkpoints:</strong> demo.pkl - Checkpoint of a MassFormer model trained on MoNA data, for the purposes of running the demo. checkpoint_best_pcqm4mv2.pt - Checkpoint of a Graphormer model pretrained on the PCQM4M dataset, used for initialization of some MassFormer models. Copied from this url. Please refer to the Graphormer repository for more information.