Load therapeutics data commons datasets and run evaluation workflows for drug discovery.
npx skills add https://github.com/dralkh/seerai --skill pytdc-dralkh
Please help me install this Agent Skill. Skill: pytdc Source: https://github.com/dralkh/seerai/tree/main/skills/pytdc Command: npx skills add https://github.com/dralkh/seerai --skill pytdc-dralkh
PyTDC removes the friction of finding, splitting, evaluating, and comparing therapeutic machine learning datasets so researchers can focus on model development instead of dataset plumbing.
Use the pytdc skill to load a therapeutic dataset, apply the recommended split strategy, and prepare it for model training and evaluation.
High-intent search queries and answers about installing and using this skill.
You can access curated ADME, toxicity, DTI, DDI, and PPI datasets through a single workflow, applying standardized metrics and benchmark groups to evaluate drug discovery models across reproducible multi-seed experiments.
The best way to benchmark retrosynthesis models is using benchmark group evaluations that apply task-appropriate metrics and proper multi-seed protocols to ensure reproducible comparisons across different molecular generation algorithms.
Yes, you can use molecular oracles for goal-directed compound optimization by scoring generated molecules against target-specific and physicochemical objectives like QED or GSK3B to guide therapeutic molecular design.
Yes, pytdc supports scaffold splitting alongside cold splitting for reproducible machine learning evaluation, ensuring that therapeutic dataset partitions remain standardized across multi-seed model training experiments.
Molecular conversions and label transformations process therapeutic datasets by converting molecular formats, filtering compounds, and transforming labels to standardize inputs for downstream machine learning model training.
ZurybrConvert Python 2 scientific code to Python 3 with updated libraries.
KaiserWhoLearnsTrain and evaluate machine learning models across scikit-learn, PyTorch, and TensorFlow.
SologaCalculate molecular descriptors and generate fingerprints from SMILES strings.
ovachieverProvide standardized drug discovery datasets with train/validation/test splits.
