John D. Chodera

The paper evaluates how many crystal structures are needed for accurate pose prediction in drug discovery, finding that five structures per scaffold often suffice.

The paper shows that incorporating physics-based priors improves structure-based binding affinity models, achieving performance comparable to ligand-only models on a drug discovery dataset.

A public crystallographic structure and affinity dataset for enteroviral 2A protease (925 binding events, 699 compounds), with docking, cofolding and screening baselines. Fragment fine-tuning of OpenFold3-p2 improves follow-on predictions.

The paper uses MCCE to analyze how kinase inhibitors affect protonation and tautomeric states, finding that inhibitor charges change dynamically and minority tautomers can dominate binding.

The paper compares three data analysis methods for MERS-CoV MPro inhibitors, finding that modeling the complete concentration-response curve best predicts cellular efficacy.

This study investigates how adenine nucleotides potentiate human type 2 IP3R activity by rigidifying the juxtamembrane domain through structural and computational analysis.

This paper describes the development of KinoML, a framework for structure-enabled machine learning in drug discovery, focusing on kinases, and highlights key lessons in data management and model reproducibility.

This paper introduces a computational pipeline for identifying broad-spectrum antivirals by analyzing viral sequences, predicting ligand poses, and scoring protein-ligand complexes, validated on SARS-CoV-2 and MERS-CoV datasets.

This paper describes the optimization of a SARS-CoV-2 Mpro inhibitor to address genotoxic and metabolic liabilities, leading to improved in vivo efficacy and exposure.

The paper evaluates structure-based methods to predict how kinase mutations affect inhibitor binding, finding they accurately classify mutations as resistant or sensitizing.

This study fine-tunes a GNN-based molecular mechanics force field using experimental hydration free energy data to improve predictions of related free energies.

DrugGym simulates drug discovery processes to evaluate how different strategies affect success rates and costs in achieving target candidate profiles.

The paper introduces a new approach to molecular mechanics force fields using direct chemical perception, reducing parameter count while maintaining accuracy.