Access AI-ready drug discovery datasets and benchmark machine learning models.
npx skills add https://github.com/galeep/plugin-place --skill pytdc-galeep
Please help me install this Agent Skill. Skill: pytdc Source: https://github.com/galeep/plugin-place/tree/main/plugins/sci-cheminformatics-drug-discovery/skills/pytdc Command: npx skills add https://github.com/galeep/plugin-place --skill pytdc-galeep
This Skill provides AI-ready datasets and benchmarks for drug discovery and development, streamlining the process and enhancing efficiency.
Install PyTDC using pip:
uv pip install PyTDC
To access datasets, use the following pattern:
from tdc.<problem> import <Task>
data = <Task>(name='<Dataset>')
split = data.get_split(method='scaffold', seed=1, frac=[0.7, 0.1, 0.2])
df = data.get_data(format='df')
High-intent search queries and answers about installing and using this skill.
To access AI-ready drug discovery datasets, use Python to load specific tasks like ADME or toxicity from the PyTDC library, then call the get_data method to retrieve data as a pandas DataFrame for machine learning modeling.
Benchmarking machine learning models for pharmaceutical research involves evaluating them on standardized drug discovery tasks using curated datasets, allowing you to compare model performance on predicting molecular properties and drug-target interactions consistently.
Yes, you can use scikit-learn and pandas with drug discovery datasets. The datasets are provided as pandas DataFrames, enabling seamless integration with scikit-learn for predicting molecular properties or generating novel molecules.
Yes, PyTDC supports scaffold splits for machine learning in drug development. You can use the get_split method with the scaffold parameter, specifying seed and fractions to partition data into training, validation, and test sets.
Available pharmaceutical datasets for predicting molecular properties include curated data for ADME, toxicity, and drug-target interactions. These standardized datasets streamline the process of evaluating models in drug discovery and development.
jasrajtulsiLoad and analyze Therapeutics Data Commons drug discovery datasets and benchmarks.
KaiserWhoLearnsTrain and evaluate machine learning models across scikit-learn, PyTorch, and TensorFlow.
galeepConvert SMILES strings and RDKit molecules into numerical features for machine learning.
jimmc414Trains neural networks for molecular property prediction and classification using DeepChem datasets like MNIST.