数据集获取

git clone https://github.com/langli-lab/drugcombo-data.git

curl -L -o repo.zip https://github.com/langli-lab/drugcombo-data/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

Drug Combo dataset

This repository contains the manual curation of published Phase I anticancer drug trials for Drug Combo.

Data Source

Publications from PubMed search.

Data curation guideline

Data Curation Guideline depicts how the data was curated from the publications. In this guideline, some examples are provided to demonstrate where the required data elements can be found in the papers. For example, the dose levels can be found in the figures or some paragraphs.

Data Files

File Name	Description
trial.csv	Some general information about the trials, including PMID, Trial Registed number, cancer subtypes, trial recruitment criteria.
drug.csv	The drug used in the trial, inclduing name, formula, and administration route. **Please note: There is no information about doing it in the file."
schema.csv	The statistical design of the trial
dlt_definition.csv	How dose-limiting toxicity (DLT) is defined in the trials
dose_level.csv	Detailed designed dosing information
mtd.csv	Maximum Tolerated Dose (MTD)
observed_dlt.csv	Reported DLTs in the publications

Data Dictionary

trial.csv

Column	Description
PMID	Pu

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/langli-lab/drugcombo-data