amirhoseinsafari/m.tuberculosis-dataset-for-drug-resistant

The SNP and gene datasets of M. Tuberculosis for drug resistance prediction.

M.tuberculosis dataset for drug resistant

The SNP and gene datasets of M. Tuberculosis for drug resistance prediction. Here is a brief description of each file:

• AllLabels.csv contains the susceptibility/resistance status (susceptibility:0 and resistance:1) for each sample isolate to 12 different drugs.
• SNPList.csv contains the list of all loci on the MTB genome where a mutation was detected using the variant calling tools, based on the reference genome provided here.
• SNP_data_part*.zip contains csv files with the binary SNPs. The csv files are concatenated using loading_data package (refer to this repo).
• gene_data.csv.zip contians a csv file that summarizes the SNPs based on the gene that they fall into to form a matrix that contains a single feature for each gene of each sample isolate.
• iso_list.csv a list of all isolates IDs used in the training data.
• sparsetableFeb27.npz The binary SNP file in npz format for ease of use.

For understanding how to load and use this data please visit the LRCN-drug-resistance repository, especially the loading_data section.

---

Citation

If you found the content of this repository useful, please cite us:

https://dl.acm.org/doi/abs/10.1145/3459930.3469534

---

m.tuberculosis-dataset-for-drug-resistant's Issues

column names for gene_data.csv

Hi Amir,

I understand gene_data.csv contains ~4000 genes which have at least one mutation in the data.
Where can i find the names of these genes?

Many thanks,
Fernando