pytdc

Name: pytdc
Availability: InStock
Author: estrella-231

Load PyTDC therapeutic datasets with scaffold and cold splits for ML modeling.

Updated May 24, 2026

Search Tags:#benchmarking #drug discovery #DTI #dataset loading #scaffold split #molecule generation #toxicity prediction

Ready to run

npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pytdc-estrella-231

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pytdc
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/pytdc
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pytdc-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PyTDC removes friction in therapeutic ML by providing standardized, AI-ready drug discovery datasets with consistent splits and evaluation-friendly formats.

Core Features & Use Cases

Curated therapeutic dataset access: Load ADME, toxicity, and interaction datasets with consistent schema for modeling and benchmarking.
Meaningful dataset splitting: Use scaffold and cold-split strategies to better measure generalization in drug discovery settings.
Multi-task coverage across prediction and generation: Support single-instance prediction (molecule/protein properties), multi-instance prediction (DTI/DDI/PPI), and generation tasks with benchmark datasets and utilities.

Quick Start

Load an ADME dataset with a scaffold split to train and benchmark your property-prediction model.

Frequently Asked Questions about pytdc

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

FAQPage Schema

How do I load drug discovery datasets for machine learning benchmarking?▼

To load drug discovery datasets for machine learning benchmarking, use the TDC dataset and task APIs to retrieve AI-ready therapeutic data with consistent schemas for modeling and assessment. You must install PyTDC via pip before calling the APIs to fetch ADME, toxicity, or interaction datasets.

What is a scaffold split and when do I need it for molecule property prediction?▼

A scaffold split partitions molecules based on their chemical structure to better measure generalization in drug discovery settings. You need scaffold splits for molecule property prediction when evaluating whether your model truly learns predictive rules rather than memorizing similar chemical scaffolds.

Can I benchmark drug-target interaction models using standardized dataset splits?▼

Yes, you can benchmark drug-target interaction models using standardized dataset splits. The framework provides multi-instance prediction datasets for DTI, DDI, and PPI tasks, offering consistent tabular representations and cold split strategies for training and assessment.

Does PyTDC support molecule generation tasks or is it only for property prediction?▼

PyTDC supports both molecule generation tasks and property prediction workflows. It provides benchmark datasets and utilities for generation tasks alongside single-instance prediction for molecule and protein properties, covering a wide range of therapeutic machine learning applications.

What dependencies do I need to install before using these therapeutic ML datasets?▼

You need to install PyTDC via pip and ensure SciPy is available in your environment to use these therapeutic ML datasets. SciPy is the required dependency for handling the standardized tabular representations and dataset loading operations.

Why does my drug discovery model evaluation fail to generalize across different chemical structures?▼

Your drug discovery model evaluation may fail to generalize because random data splits leak structurally similar molecules into both training and test sets. Using scaffold splits or cold splits ensures structurally distinct compounds are separated, providing a rigorous measure of model generalization.