skills.rest
Zeyuyang-0420
Zeyuyang-0420COMMUNITY
Explore all skills by this author →
GitHub

pytdc

Load and evaluate drug discovery datasets for therapeutic machine learning.

Updated May 8, 2026
Search Tags:#data science#machine learning#drug discovery#pharmacology#molecular generation#data benchmarking
One-click install
npx skills add https://github.com/Zeyuyang-0420/bio-ai-research-skills --skill pytdc-zeyuyang-0420
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pytdc
Source: https://github.com/Zeyuyang-0420/bio-ai-research-skills/tree/main/categories/ml-training-ai/pytdc
Command: npx skills add https://github.com/Zeyuyang-0420/bio-ai-research-skills --skill pytdc-zeyuyang-0420

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, tqdm, seaborn, scikit-learn, fuzzywuzzy, PyTDC, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides access to a comprehensive collection of AI-ready drug discovery datasets and benchmarks, enabling users to work with standardized evaluation metrics and meaningful data splits for therapeutic machine learning and pharmacological prediction.

Core Features & Use Cases

  • Access to Datasets: Offers a wide range of curated datasets for single-instance prediction (ADME, toxicity), multi-instance prediction (DDI, PPI), and generation (molecule generation, retrosynthesis).
  • Benchmarking: Allows systematic model evaluation using benchmark groups with standardized protocols.
  • Data Functions: Provides tools for dataset splitting, model evaluation, data processing, and molecular generation oracles.
  • Use Case: A drug discovery researcher might use this Skill to load and evaluate a toxicity dataset for their machine learning model, ensuring the model is trained on standardized data.

Quick Start

Install PyTDC using pip:

uv pip install PyTDC

Load ADME data:

from tdc.single_pred import ADME
data = ADME(name='Caco2_Wang')
split = data.get_split(method='scaffold')

Frequently Asked Questions about pytdc

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

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

PyTDC provides AI-ready drug discovery datasets for single-instance prediction (ADME, toxicity), multi-instance prediction (DDI, PPI), and generation tasks (molecule generation, retrosynthesis).

What drug discovery benchmark tasks are available for pharmacological prediction?▼

Benchmarking in drug discovery allows systematic model evaluation using benchmark groups with standardized protocols and meaningful data splits, ensuring models are trained on consistent data.

How do I split molecular data using scaffold methods in Python?▼

Install PyTDC using uv pip install PyTDC, then import the ADME class from the single_pred module and call get_split with method='scaffold' to retrieve scaffold-based data splits.

Do I need pandas and scikit-learn to use this drug discovery dataset Skill?▼

Yes, numpy, pandas, tqdm, seaborn, scikit-learn, and fuzzywuzzy are required dependencies, with additional packages needed for specific features like molecular generation oracles and dataset splitting.

How do I get scaffold splits for toxicity prediction datasets?▼

Data functions provided include tools for dataset splitting, model evaluation, data processing, and molecular generation oracles to support comprehensive drug discovery machine learning workflows.

What is the best way to benchmark machine learning models for drug-drug interaction prediction?▼

Use PyTDC's benchmark groups to systematically evaluate multi-instance prediction models like DDI and PPI with standardized protocols and meaningful data splits for consistent results.

Related Skills

Explore More Data & Analytics Skills→
GrupoUSGrupoUS
1

ai-data-analyst

Write and execute Python scripts for data analysis, modeling, and visualization.

Community
Intermediate
tassiovaletassiovale
13

pytdc

Load and evaluate AI-ready drug discovery datasets from PyTDC.

Community
Advanced
SologaSologa
1

pytdc

Access AI-ready drug discovery datasets and benchmarks for machine learning in therapeutics.

Community
Intermediate
tassiovaletassiovale
13

rdkit

Calculate molecular descriptors and manipulate molecular structures with RDKit.

Community
Advanced