RubricOE

Method

rubricOE is a machine learning framework, implementated in python, with error bar computations to obtain interpretable genetic and non-genetic features from genomic or transcriptomic data combined with clinical factors in the form of electronic health records.

This is a schematic view of rubricoe’s processing flow

The entire rubricOE pipeline can be executed by:

compute(df, iterations, curve_steps, ...[, ...])

Function to run the full RubricOE analysis

Alternative RubricOE can be exectude using the available API:

compute_curves(X, y, iterations, ...[, ...])	Splits data into working and validation, then computes as many score curves as specified in the iterations parameter using only validation data.
compute_feature_counts(ranked_features_list, ...)	Computes the proportion of iterations where a feature was selected as a top feature according to its corresponding curve.
compute_top_features(feature_counts[, threshold])	Filters out top features according to threshold.

An example can be found in this tutorial

Citation

Please cite the following article if you use RubricOE: