aalto-ics-kepaco / msms_rt_ssvm

Implementation of the LC-MS²Struct model published in the manuscript "Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data" by Bach et al.
MIT License
6 stars 5 forks source link

Structure-disjunct Cross-validation #2

Open bachi55 opened 3 years ago

bachi55 commented 3 years ago

The training and test splits should be only based on the first part of the InChIKey to put stereo-isomers into the same cross-validation fold. This also needs to be done, when in the candidate database the molecular identifier is, e.g., set to InChI (encoding the stereo information).