Predicting glycan structure from tandem mass spectrometry via deep learning

Curated set of LC-MS/MS data from glycomics studies. Used for training and applying CandyCrunch, a deep learning model to predict glycan structure from LC-MS/MS data, described in Urban et al., Nat Methods, 2024 and https://github.com/BojarLab/CandyCrunch.

Files:

full_dataset.xlsx: Full dataset with all annotated LC-MS/MS glycan spectra

X_train.pkl: spectra and metadata from our training set

y_train.pkl: labels from our training set

X_test.pkl: spectra and metadata from our independent test set

y_test.pkl: labels from our independent test set

glycans.pkl: glycans in IUPAC-condensed nomenclature in the same order as the label-encoding