Access PyTDC drug discovery datasets and benchmarks for machine learning.
npx skills add https://github.com/biomaps-infra/blender-opencode --skill lib-pytdc
Please help me install this Agent Skill. Skill: lib-pytdc Source: https://github.com/biomaps-infra/blender-opencode/tree/main/.opencode/skills/lib-pytdc Command: npx skills add https://github.com/biomaps-infra/blender-opencode --skill lib-pytdc
This Skill provides access to a comprehensive suite of AI-ready datasets and benchmarks specifically designed for drug discovery and development, streamlining machine learning workflows in pharmacology.
Use the lib-pytdc skill to load the Caco2_Wang ADME dataset and get a scaffold split.
High-intent search queries and answers about installing and using this skill.
AI-ready datasets for drug discovery are provided through the Therapeutics Data Commons, offering curated molecular property prediction data for machine learning workflows. You can load specific ADME datasets like Caco2_Wang to train pharmacological models.
Standardized benchmarks for pharmacology machine learning models include pre-defined groups for systematic evaluation of drug-target interaction analysis and molecular generation. These benchmarks provide standardized data splits and evaluation metrics to ensure consistent model assessment.
Yes, drug-target interaction analysis and de novo molecular generation are supported through access to the PyTDC framework. It provides the necessary datasets and utilities to train and evaluate models for these specific cheminformatics tasks.
To get a scaffold split for ADME datasets like Caco2_Wang, load the dataset using the Skill's data utilities. These utilities provide standardized data splitting mechanisms specifically designed for cheminformatics and molecular property prediction tasks.
Yes, evaluation metrics for drug toxicity prediction models are provided as part of the standardized benchmark groups. You can train a machine learning model to predict drug toxicity and evaluate its performance using these built-in pharmacological metrics.
Data utilities for data splitting and molecule conversion are included to streamline cheminformatics workflows. These tools facilitate standardized data partitioning and molecular format transformations required for training accurate machine learning models in pharmacology.
jackspaceConvert SMILES strings into machine-learning feature vectors using 100+ featurizers.
Lord1EgyptAccess standardized drug discovery datasets and molecular evaluation oracles via PyTDC.
Imad-OuteAnalyze and modify molecular structures in cheminformatics workflows.
Yezez9Perform molecular property prediction and featurization using DeepChem.
