Machine learning and metabolic modeling-based identification of hypoxia-driven metabolic signatures in pediatric cancers

The repository contains codes for

1. Addition of RS and basal essential media to pediatric cancer GEMs
   • 01_grrules_create.m
   • 02_mem_constraint.m
   • 03_mem_sink.m
   • 04_rs_merge.m
   • 05_loop_check.m
2. Generation of parsimonious flux data and generation of machine learning features from flux data
   • 06_pfba.ipynb
   • 07_feature_generation.ipynb
3. Machine learning and feature interpretation using SHAP 
   • 08_ML_analysis.ipynb

Additional files

• loopcheck.m - to check the presence of thermodynamically infeasible cycles
• memhuman.m - details about uptake rates of nutrients from basal essential media
• RS_demands.py - to add compartmental and total demand reactions to the reactive species