Data-Driven Design of Targeted Gene Panels for Estimating Immunotherapy Biomarkers
Fit Generative Model
Fit Generative Model Without Gene/Variant Type-Specific Interactions
Fit Generative Model Without Sample-Specific Effects
Generate mutation data.
AUPRC Metrics for Predictions
Produce a Table of Biomarker Values from a MAF
Get True Biomarker Values on Training, Validation and Test Sets
Investigate Generative Model Comparisons
Construct Bias Penalisation
Group and Filter Mutation Types
Produce Training, Validation and Test Matrices
Construct Optimisation Parameters.
Extract Panel Details from Group Lasso Fit
Produce Predictions on an Unseen Dataset
R Squared Metrics for Predictions
Metrics for Predictive Performance
Produce a Mutation Matrix from a MAF
ICBioMark: A package for cost-effective design of gene panels to predi...
First-Fit Predicitve Model with Group Lasso
Produce Error Bounds for Predictions
Refitted Predictive Model for a Given Panel
Get Refitted Predictive Models for a First-Fit Range of Panels
Visualise Generative Model Fit
Implementation of the methodology proposed in 'Data-driven design of targeted gene panels for estimating immunotherapy biomarkers', Bradley and Cannings (2021) <arXiv:2102.04296>. This package allows the user to fit generative models of mutation from an annotated mutation dataset, and then further to produce tunable linear estimators of exome-wide biomarkers. It also contains functions to simulate mutation annotated format (MAF) data, as well as to analyse the output and performance of models.