skills.rest
jaechang-hits
jaechang-hitsCOMMUNITY
Explore all skills by this author →
GitHub

pytdc-therapeutics-data-commons

Load PyTDC drug discovery datasets with standardized splits and metrics.

298|27|Updated Feb 18, 2026
Search Tags:#benchmarking#machine learning#bioinformatics#drug discovery#cheminformatics#datasets
One-click install
npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill pytdc-therapeutics-data-commons
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pytdc-therapeutics-data-commons
Source: https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/structural-biology-drug-discovery/pytdc-therapeutics-data-commons
Command: npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill pytdc-therapeutics-data-commons

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyTDC, and includes references (resource) components.

What problem does it solve?

This Skill provides easy access to a comprehensive platform of AI-ready datasets and benchmarks specifically designed for drug discovery, streamlining model development and evaluation.

Core Features & Use Cases

  • Access Diverse Datasets: Load curated datasets for ADME, toxicity, drug-target interactions (DTI), and more.
  • Standardized Evaluation: Utilize built-in split methods (scaffold, cold splits) and evaluation metrics for robust benchmarking.
  • Molecule Generation: Access training sets and oracles for molecular design and retrosynthesis tasks.
  • Use Case: Train a machine learning model to predict drug toxicity by loading the ClinTox dataset, applying a scaffold split, and evaluating performance using ROC-AUC.

Quick Start

Load the Caco2_Wang ADME dataset and get a scaffold split with seed 42.

Frequently Asked Questions about pytdc-therapeutics-data-commons

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I load benchmark datasets for drug discovery machine learning tasks?▼

You can load curated drug discovery datasets for ADME, toxicity, and drug-target interactions by using the PyTDC library, which provides standardized data splits and evaluation metrics for model training.

What is a scaffold split and how does it work for molecular property prediction benchmarks?▼

A scaffold split partitions molecular datasets by chemical structure to ensure test compounds are structurally distinct from training compounds, providing a rigorous evaluation for machine learning property prediction.

Can I benchmark retrosynthesis and molecule generation models using standardized oracles?▼

Yes, you can access training sets and evaluation oracles specifically designed for molecular design and retrosynthesis tasks, allowing you to standardize generative model benchmarking.

Do I need to install PyTDC to access cheminformatics datasets for toxicity prediction?▼

Yes, installing the PyTDC library is required as a dependency to load, manipulate, and benchmark curated cheminformatics datasets like ClinTox for toxicity prediction.

What evaluation metrics are built into these drug-target interaction datasets?▼

The benchmarks provide standardized evaluation metrics such as ROC-AUC for tasks like drug-target interaction and toxicity prediction, ensuring consistent model performance evaluation across datasets.

Related Skills

Explore More Education & Research Skills→
jackspacejackspace
16

pytdc

Provide AI-ready drug-discovery datasets and benchmarks from PyTDC for AI/ML modeling.

Community
Intermediate
Phife726Phife726

ds-supervised-modeling

Build, evaluate, and compare supervised machine learning models.

Community
Advanced
jackspacejackspace
16

molfeat

Convert SMILES strings into machine-learning feature vectors using 100+ featurizers.

Community
Advanced
jkitchinjkitchin
34

idaes

Model, simulate, and optimize chemical processes with IDAES flowsheets.

Community
Advanced