M. Wieder

Improving Small Molecule pKa Prediction Using Transfer Learning with Graph Neural Networks

The paper develops a graph neural network model for predicting small molecule pKa values, fine-tuned on experimental data and integrated into an open-source tool for accurate protonation state enumeration.

Teaching free energy calculations to learn from experimental data

This paper uses quantum machine learning potentials to improve alchemical free energy calculations by overcoming limitations in force fields and enabling learning from experimental data.

Fitting quantum machine learning potentials to experimental free energy data: Predicting tautomer ratios in solution

This paper uses quantum machine learning to predict tautomer ratios in solution by correcting limitations in quantum chemical thermochemistry approximations.

Towards chemical accuracy for alchemical free energy calculations with hybrid physics-based machine learning / molecular mechanics potentials

This paper improves the accuracy of alchemical free energy calculations for protein-ligand binding by combining machine learning and molecular mechanics potentials, reducing errors from 0.97 to 0.47 kcal mol-1.

Computational identification of novel Kir6 channel inhibitors

This study identifies novel Kir6 channel inhibitors using computational methods, validated by experimental analysis, with potential for treating Cantu syndrome.