The MGF files used for analysis in the paper can be found in datasets.zip. mzmine443_Tomato200_InclusionListA_15000A.mgf for the Pesticides case study. Case_Study_Fungal_dataset.mgf for the Natural Product case study GNPS-SUSPECTLIST.mgf is a copy of the GNPS-SUSPECTLIST mgf file, downloaded from https://external.gnps2.org/gnpslibrary at the time of analysis in the paper. For running the automated guidance annotation (SAG) in MS2LDA 2.0 you need to download the following files: Please extract Spec2Vec.zip, and inside it you can find:150225_CleanedLibraries_Spec2Vec_pos_embeddings.npy, 150225_Spec2Vec_pos_CleanedLibraries.model, 150225_Spec2Vec_pos_CleanedLibraries.model.wv.vectors.npy, 150225_CombLibraries_spectra.db, and 150225_Spec2Vec_pos_CleanedLibraries.model.syn1neg.npy. Place all these into a single folder for Spec2Vec/positive_mode/* in a place that can be found by MS2LDA. The command ms2lda --only-download can also be used to download these model files and place them in the right location. The rest of the files are the results for the MS2LDA 2.0 manuscript. *.bin for the saved Tomotopy model, while *viz.json.gz for the compressed visualization results that can be loaded into MS2LDAViz Dash app.