skills.rest
pradyumnasagar
pradyumnasagarCOMMUNITY
Explore all skills by this author →
𝕏@pradyumnasagarGitHub

qsar-modeling

Automate QSAR/QSPR model construction for bioassay and ADMET prediction.

6|2|Updated Jun 11, 2026
Search Tags:#cheminformatics#predictive modeling#qsar#admet#qspr
One-click install
npx skills add https://github.com/pradyumnasagar/open-research-skills --skill qsar-modeling
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qsar-modeling
Source: https://github.com/pradyumnasagar/open-research-skills/tree/main/skills/chemoinformatics/qsar-modeling
Command: npx skills add https://github.com/pradyumnasagar/open-research-skills --skill qsar-modeling

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chemprop, rdkit, scikit-learn, mapie, shap, pytorch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of building QSAR/QSPR models, enabling the prediction of bioassay data, ADMET endpoints, and selectivity profiles.

Core Features & Use Cases

  • QSAR/QSPR Modeling: Utilizes chemprop D-MPNN, MolFormer, Uni-Mol, ChemBERTa, random forest baselines, and Gaussian processes.
  • Applicability Domain Handling: Implements OECD 5 principles, kNN, leverage, conformal prediction, Mahalanobis, and scaffold-balanced splits.
  • Ensemble Uncertainty and Calibration: Incorporates Platt scaling, isotonic regression, and SHAP for feature importance.
  • Use Case: For a pharmaceutical company developing new drug compounds, this Skill can predict the ADME properties of compounds based on their molecular structure.

Quick Start

Use the qsar-modeling skill to train a QSAR model on your bioassay data using chemprop 2.0 D-MPNN.

Frequently Asked Questions about qsar-modeling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a QSAR model for ADMET prediction?▼

To build a QSAR model for ADMET prediction, you can use this Skill to train chemprop D-MPNN or Gaussian process models on your bioassay data, enabling predictive analysis of molecular properties.

What models can I use for cheminformatics predictive modeling?▼

For cheminformatics predictive modeling, you can utilize chemprop D-MPNN, MolFormer, Uni-Mol, ChemBERTa, random forest baselines, and Gaussian processes to predict bioassay data and selectivity profiles.

How does conformal prediction handle the applicability domain in QSAR?▼

Conformal prediction defines the applicability domain in QSAR by quantifying prediction uncertainty, working alongside kNN, leverage, and Mahalanobis distance to satisfy OECD 5 validation principles.

Can I use SHAP for feature importance in QSPR models?▼

Yes, you can use SHAP for feature importance in QSPR models, integrating it with ensemble uncertainty calibration techniques like Platt scaling and isotonic regression to interpret predictions.

Do I need RDKit and PyTorch to train chemprop D-MPNN models?▼

Yes, you need RDKit and PyTorch to train chemprop D-MPNN models, along with scikit-learn and MAPIE to execute the full QSAR modeling and applicability domain workflow.

What is the best way to validate QSAR models using OECD principles?▼

The best way to validate QSAR models using OECD principles is to apply scaffold-balanced splits, conformal prediction, and Mahalanobis distance to rigorously define the applicability domain.

Related Skills

Explore More Data & Analytics Skills→
inflexa-aiinflexa-ai
29

cheminformatics

Automate molecular structure analysis and QSAR modeling workflows with RDKit and DeepChem.

Official
Advanced
tomlupotomlupo

shap

Explain model predictions by attributing outputs to input features with SHAP values.

Community
Advanced
nahisahonahisaho
3

scientific-uncertainty-quantification

Quantify machine learning predictive uncertainty with conformal prediction, MC dropout, and deep ensembles.

Community
Advanced
RamanEbrahimiRamanEbrahimi
3

shap

Compute SHAP values and generate SHAP plots for machine learning model predictions.

Community
Advanced