Calculate ELASPIC features for the core and interface training sets, using the ELASPIC standalone pipeline.
Calculate ELASPIC features for core training sets, using the ELASPIC database pipeline.
Calculate ELASPIC features for interface training sets, using the ELASPIC database pipeline.
Prepare and combine all training, validation and test data into a single file for ML.
Compute basic statistics regarding the training and validation datasets.
Train the ELASPIC core and interface predictors.
Validate ELASPIC core and interface predictors on the validation and test datasets.
Use ELASPIC scores to predict whether a mutation is a cancer driver or a cancer passenger.
Analysing our homology modelling and mutation coverage for the human proteome.
Get a list of mutations from the validation and test datasets that remain to be calculated.