Access drug discovery datasets and benchmarks from Therapeutics Data Commons.
npx skills add https://github.com/fuzzy-dynamics/strings --skill pytdc-fuzzy-dynamics
Please help me install this Agent Skill. Skill: pytdc Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/pytdc Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill pytdc-fuzzy-dynamics
PyTDC centralizes access to AI-ready drug discovery datasets and benchmarks from the Therapeutics Data Commons, accelerating research workflows.
Load PyTDC data, apply a scaffold split for a chosen task, and evaluate results with the included evaluators.
High-intent search queries and answers about installing and using this skill.
Access AI-ready drug discovery datasets by loading single-prediction, multi-prediction, and generation tasks across ADME, toxicity, DTI, HTS, and QM domains from the Therapeutics Data Commons. It provides centralized benchmark-ready data for model evaluation.
The Therapeutics Data Commons is a centralized resource providing AI-ready drug discovery datasets and benchmarks. It supports single-prediction, multi-prediction, and generation tasks across ADME, toxicity, DTI, HTS, and QM domains to enable end-to-end model benchmarking.
Load and split therapeutics datasets using the included scripts, such as applying a scaffold split for your chosen task. The utilities provide benchmark-ready splits and evaluation tools to streamline data processing and model benchmarking.
Yes, you can use pandas and numpy for drug discovery data processing as they are core dependencies. The framework integrates these libraries to handle data loading, splitting, and processing utilities across the dataset catalogue.
Evaluation utilities for drug discovery benchmarks include model evaluators and benchmark-ready splits for single-prediction, multi-prediction, and generation tasks. These tools streamline the evaluation of results across ADME, toxicity, DTI, HTS, and QM domains.
Yes, the Skill includes a dataset references catalog providing citations for the broad catalogue of drug discovery datasets. This ensures traceability for the AI-ready data loaded for ADME, toxicity, DTI, HTS, and QM benchmarking tasks.
AlterLab-IEULoad AI-ready drug discovery datasets and benchmarks with PyTDC.
qinyan-aiLoad PyTDC datasets and benchmarks for drug discovery experiments.
Yezez9Convert SMILES strings and RDKit molecules into ML-ready feature representations.
biomaps-infraAccess PyTDC drug discovery datasets and benchmarks for machine learning.
