Interpretable Surrogate Modeling for Polymers: A SHAP-Guided Framework for Descriptor-Level Analysis (Data and Code)

This repository contains curated datasets and the Python-based MD-XAI computational framework supporting the manuscript “Interpretable Surrogate Modeling for Polymers: A SHAP-Guided Framework for Descriptor-Level Analysis.” The archive includes: Processed datasets: Structural and thermodynamic descriptors derived from molecular-dynamics simulations of polymer systems. Analysis scripts: Python workflows (using scikit-learn and SHAP) for training random-forest surrogate models and generating interpretability plots (feature importance, dependence, and beeswarm).