Load and evaluate AI-ready drug discovery datasets from PyTDC.
npx skills add https://github.com/tassiovale/claude-code-kit --skill pytdc-tassiovale
Please help me install this Agent Skill. Skill: pytdc Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/pytdc Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill pytdc-tassiovale
This Skill solves the problem of accessing and utilizing AI-ready drug discovery datasets and benchmarks for therapeutic machine learning and pharmacological prediction.
Use the PyTDC skill to load and evaluate a dataset for a specific task. For example, to load the ADME dataset 'Caco2_Wang', run: ```python from tdc.single_pred import ADME data = ADME(name='Caco2_Wang') split = data.get_split(method='scaffold', seed=1, frac=[0.7, 0.1, 0.2])
High-intent search queries and answers about installing and using this skill.
To load AI-ready drug discovery datasets for therapeutic machine learning, you import a specific prediction module like ADME and pass the dataset name to retrieve the data. You can then generate scaffold splits for model training.
Benchmarks for pharmacological prediction and molecular generation provide standardized evaluation tasks across single-instance prediction, multi-instance prediction, and generation tasks like MolGen and RetroSyn.
Yes, you can use scikit-learn and pandas for drug-target interaction prediction tasks. The framework requires these dependencies alongside numpy and fuzzywuzzy to support core data processing and model evaluation functionality.
To get scaffold splits for ADME and toxicity datasets, you call the get_split method on your loaded dataset object, specifying the split method as 'scaffold' along with seed and fraction parameters.
Yes, you need numpy and fuzzywuzzy to run the benchmarks, as they are required dependencies along with pandas, tqdm, seaborn, and scikit-learn for core functionality and data processing.
The best way to access standardized datasets for drug development and ADME prediction is through a centralized benchmark library that provides AI-ready data for single-instance and multi-instance therapeutic ML tasks.
Zeyuyang-0420Load and evaluate drug discovery datasets for therapeutic machine learning.
robinbarvaagAccesses PyTDC AI-ready drug discovery datasets and standardized benchmarks for ADME, toxicity, DTI, and molecular generation tasks.
leonardodalinkyGenerate statistical visualizations from pandas DataFrames using seaborn.
Yezez9Perform molecular property prediction and featurization using DeepChem.