BIG-TB: A Benchmark for Prediction and Interpretability of Sequence-Based Machine Learning Using Mycobacterium tuberculosis Genomes

BIG-TB provides standardized train/test splits, harmonized variant annotation, and interpretability metrics for model comparison across classical ML, deep neural networks, and biological foundation-model representations. It supports research into causal variant recovery and cross-drug generalization across 11 WHO-priority antibiotics and 17,942 M. tuberculosis isolates.

Recommended citation: Tasmin, M., Mohanty, S., Kulkarni, S., Farhat, M.R., Green, A.G. BIG-TB: A benchmark for prediction and interpretability of sequence-based machine learning using Mycobacterium tuberculosis genomes. bioRxiv (2026).
Download Paper