Fingerprint Matrix Files for "Machine Learning-based Bioactivity Classification of Natural Products Using LC-MS/MS Metabolomics"

These files are the necessary dataset to reproduce the observed machine learning metrics in the paper "Machine Learning-based Bioactivity Classification of Natural Products Using LC-MS/MS Metabolomics" in review at the Journal of Natural Products. 

Multiclassifier_23_Drug_Class_Train-Test_Fingerprint_Matrix.tsv is the accumulated positive training set for the 23 different classes demonstrated in the training and testing sets.

Negative_Train-Test_Fingerprint_Matrix.tsv is the negatives training and testing examples derived from the RIKEN NP Depo which represent a diverse set of natural product compounds that serve as the counter points to the positive examples.

GNPS_23_Drug_Class_Fingerprints_Matrix.tsv is the dataset of fingerprints generated from the publically available GNPS MSMS dataset. These training examples serve to confirm the ability of the machine learning model to generalize to experimental data. 

 Negative_Train-Test_Fingerprint_Matrix.tsv is the dataset of negative training examples derived from the publically available spectra from the GNPS dataset. It is composed of nearly 2,800 random MSMS spectra to compose a diverse negative evaluation set. 

Random_GNPS_Fingerprints.tsv is the dataset of fingeprints of 9,443 random spectra from GNPS used to evaluate the false positive rate of each model.