Pretrained Spec2Vec model (trained on GNPS UniqueInchikey dataset)
Florian G. Huber · Zenodo (CERN European Organization for Nuclear Research) · 2020
Pretrained Gensim Word2Vec model for Spec2Vec: The model was trained for 50 iterations on the "UniqueInchikey" subset (12,797 spectra after filtering) of GNPS positive ionmode mass spectra as fully described here https://github.com/iomega/spec2vec_gnps_data_analysis/blob/master/notebooks/iomega-5-train-spec2vec-model.ipynb. Used for the Plos Computational Biology article on Spec2Vec --> https://doi.org/10.1371/journal.pcbi.1008724