数据集获取

git clone https://github.com/AmirHoseinSafari/M.tuberculosis-dataset-for-drug-resistant.git

curl -L -o repo.zip https://github.com/AmirHoseinSafari/M.tuberculosis-dataset-for-drug-resistant/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

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

数据加载示例（表格/文本类）

import pandas as pd, glob, os

files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))

完整仓库：github.com/AmirHoseinSafari/M.tuberculosis-dataset-for-drug-resistant