Relevant papers:

https://doi.org/10.1145/3459930.3469534

https://doi.org/10.1186/s13015-021-00198-1

https://doi.org/10.1093/bioinformatics/btx801

https://doi.org/10.1038/s41598-019-40561-2

Data sets: https://github.com/AmirHoseinSafari/M.tuberculosis-dataset-for-drug-resistant

The recommended goal is to develop a method that predicts drug resistance (AllLabels.csv) from whole-genome sequencing data (SNP_data_*). You can optionally utilize the information of which SNP falls into which gene (gene_data.csv).