Benchmarking the translational potential of AI-based drug-resistance prediction from Mycobacterium tuberculosis whole-genome sequencing data
C X Liu, Haoyue Zhu, Pengfei Zhou, Nguyen Trung Thanh, Nguyen Quoc Dat, Ines I. Atmosukarto, Io Hong Cheong, Zisis Kozlakidis, Wiku Adisasmito, Xiaoqi Zheng, H Y Wang, Yang Yang
This paper benchmarks AI-based drug-resistance prediction models for Mycobacterium tuberculosis using a large unified dataset, finding XGBoost performs best in precision-recall and F1 metrics, while neural models excel in AUROC.
bioRxiv · Jul 3, 2026 · PreprintBioinformatics