Load Therapeutics Data Commons datasets and tools for drug discovery tasks.
npx skills add https://github.com/Yezez9/Research-Agent --skill pytdc-yezez9
Please help me install this Agent Skill. Skill: pytdc Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/pytdc Command: npx skills add https://github.com/Yezez9/Research-Agent --skill pytdc-yezez9
This Skill provides access to a comprehensive suite of AI-ready datasets and benchmarks for drug discovery and development, streamlining the process of building and evaluating machine learning models in this domain.
ClinTox dataset and evaluate its performance using the admet_group benchmark.Load the Caco2_Wang ADME dataset and get a scaffold split.
High-intent search queries and answers about installing and using this skill.
Access curated drug discovery datasets for machine learning by loading single-instance prediction, multi-instance prediction, and generation tasks through the Therapeutics Data Commons interface. This provides AI-ready data for ADME, toxicity, and drug-target interactions to streamline model training.
A scaffold split is a data partitioning strategy that separates training and test sets based on molecular structure to ensure robust model validation. You can generate scaffold splits using the built-in data splitting utilities when loading molecular datasets like Caco2_Wang.
Yes, you can use Therapeutics Data Commons benchmarks to evaluate cheminformatics models. The system provides standardized benchmark groups, such as admet_group, enabling consistent model evaluation across multiple drug discovery datasets.
Yes, this Skill supports molecular generation tasks for drug development by providing access to specific generation task datasets within the Therapeutics Data Commons. It also includes oracles for evaluating molecular properties of generated compounds.
Available drug toxicity datasets for machine learning benchmarks include curated collections like ClinTox within the Therapeutics Data Commons. These datasets facilitate training and evaluating models to predict the toxicity of new drug candidates.
hxk622Load Therapeutics Data Commons datasets for drug discovery machine learning tasks.
Estrella-231Load PyTDC therapeutic datasets with scaffold and cold splits for ML modeling.
Lord1EgyptTrain graph neural networks for molecular property prediction on chemical datasets.
Yezez9Develop custom GNN architectures for molecular and protein data analysis with PyTorch.