molecular-machine-learning

Configuration-driven, reproducible ML workflows for molecules and materials, with DOE, auditable artifacts and agent-assisted execution.

Code for the paper: M. Haeberle, P. van Gerwen, R. Laplaza, K. R. Briling, J. Weinreich, F. Eisenbrand, C. Corminboeuf, “Integer linear programming for unsupervised training set selection in molecular machine learning” Mach. Learn.: Sci. Technol. 6 025030 (2025)

Leakage-aware scaffold, random, and hash-based train/val/test splitting for molecular machine learning.

Ensemble Deep Learning for Asymmetric Catalysis

Open molecular discovery environment for interactive design, scientific computation, molecular ML, and traceable scientific workflows.

Graph Neural Networks for Molecular Property Prediction using the QM9 Quantum Chemistry Dataset.

Reproducible code and results for applicability-gated rule-residual learning under chemical-space shift.

A hands-on tutorial implementing Graph Convolutional Networks (GCNs) for molecular property prediction using PyTorch Geometric. Predicts water solubility from chemical structures with complete pipeline from SMILES to predictions.

Kaggle Bronze Medal solution for NeurIPS Open Polymer Prediction 2025 with molecular descriptors, GNN, CatBoost/XGBoost ensemble.

Quantum Kernel Machine Learning for Drug Design A rigorous, end-to-end Qiskit implementation of quantum kernel SVMs for predicting blood-brain barrier permeability (BBBP) — a core ADMET property in CNS drug discovery — with three controlled experiments that actually test whether the quantum part is doing anything useful.

Scaffold-aware molecular machine learning for predicting acetylcholinesterase (AChE) inhibitory potency from chemical structure using molecular fingerprints, RDKit descriptors, classical ensemble models, and graph neural networks.

AI-based prediction of BBB permeability using molecular features, machine learning, and graph neural networks.

Molecular property prediction on QM9 using Graph Neural Networks with PyTorch Geometric, including GCN and bond-aware NNConv models.

Predicting when pair-specific interaction effects transfer to unseen scientific entities across drug and chemical systems.

Distribution-free uncertainty for cancer drug response: a GNN predictor with split conformal prediction on GDSC1.

Quality checks for molecular datasets: integrity, duplicates, split leakage, ML readiness, and chemical space.

Reproducible molecular solubility benchmarks with PyTorch graph learning, RDKit baselines, conformal uncertainty, and CPU profiling.

implementation of MEGAN: Multi Explanation Graph Attention Network paper for explainable solubility prediction

E(3)-equivariant GNNs for protein-ligand binding-affinity prediction (EGNN + e3nn tensor-product), with a machine-precision invariance test suite.

A balance-aware approximation for scaling leakage-aware dataset splitting, evaluated on four molecular ML benchmarks.