How does this skill help with drug discovery?

This skill provides specialized guidance for loading pharmaceutical datasets, applying chemically-aware data splits, and using molecular oracles for lead optimization.

Does this skill handle molecular format conversions?

Yes, it supports utilities for converting between common chemical representations including SMILES, SELFIES, PyG graphs, and DGL objects.

Can I use this for benchmarking ML models?

Absolutely. PyTDC includes standardized benchmark groups with fixed data splits and evaluation protocols to ensure reproducible and comparable scientific results.

PyTDC (Therapeutics Data Commons) is an open-science platform providing AI-ready datasets and benchmarks for the entire drug discovery and development pipeline.

What kind of datasets are available through this skill?

It includes datasets for ADME (absorption, distribution, metabolism, excretion), toxicity, drug-target interactions (DTI), and molecular generation tasks like retrosynthesis.

Therapeutics Data Commons (PyTDC)

Name: Therapeutics Data Commons (PyTDC)
Author: Blurjp

byBlurjp

データサイエンスとML

Provides AI-ready datasets and benchmarks for therapeutic machine learning and drug discovery tasks.

概要

PyTDC is a comprehensive open-science platform that streamlines the application of machine learning to drug discovery and development. It offers a curated collection of AI-ready datasets covering the entire therapeutics pipeline, including molecular property prediction (ADME/Tox), drug-target interactions, and molecule generation. By providing standardized evaluation metrics, scientifically rigorous data splits like scaffold and cold-start, and integrated molecular oracles, this skill enables researchers and developers to efficiently build, benchmark, and optimize models for pharmacological prediction within their development environment.

主な機能

0 GitHub stars
Built-in molecular oracles for property-based generation and optimization
Standardized drug-target (DTI) and drug-drug (DDI) interaction benchmarks
Scientific data splitting strategies including scaffold and cold-start splits
Access to curated ADME, toxicity, and bioactivity datasets
Molecular utility functions for SMILES, SELFIES, and graph conversions

ユースケース

Generating and optimizing lead compounds using goal-directed molecular oracles
Predicting pharmacokinetic properties like solubility, permeability, and toxicity
Benchmarking machine learning models on standardized pharmaceutical tasks

概要

主な機能

0 GitHub stars
Built-in molecular oracles for property-based generation and optimization
Standardized drug-target (DTI) and drug-drug (DDI) interaction benchmarks
Scientific data splitting strategies including scaffold and cold-start splits
Access to curated ADME, toxicity, and bioactivity datasets
Molecular utility functions for SMILES, SELFIES, and graph conversions

ユースケース

Generating and optimizing lead compounds using goal-directed molecular oracles
Predicting pharmacokinetic properties like solubility, permeability, and toxicity
Benchmarking machine learning models on standardized pharmaceutical tasks