EVALUATING MOLECULAR DYNAMICS FRAMES FOR BINDING AFFINITY PREDICTION AND VIRTUAL SCREENING
- 1Institute of Biochemistry and Biophysics, Polish Academy of Sciences, Pawinskiego 5a, Warsaw, Poland, 02-106
Abstract
Motivation: Machine-learning scoring functions are typically trained on static crystallographic structures, although protein-ligand recognition is inherently dynamic. It remains unclear whether MD derived conformations provide transferable information or instead shift the training data away from experimentally observed binding geometries. Results: We generated 20 ns molecular dynamics trajectories for 2,502 protein–ligand complexes and evaluated five scoring function architectures trained on crystallographic structures and MD-derived frames using four different sampling protocols. Across the CASF-2016 and CASF-2013 affinity benchmarks, MD-only training generally reduced predictive performance, whereas augmenting crystallographic structures with MD data improved four of the five architectures. Averaged across models, benchmarks, and sampling protocols, augmentation increased PCC by 0.072 and reduced RMSE by 0.165 relative to MD-only training. A nearest-neighbor analysis showed that the benefits of augmen-tation were not restricted to complexes similar to frames, arguing against a simple similarity-based explanation. The results suggest improvements were connected with exposing models to controlled structural perturbations around experimentally observed binding poses. Overall, MD conformations were most effective as augmentation rather than replacement for crystallographic training data. Availability: MD frames used for model training are available at: (https://zenodo.org/ records/20443988).
Related
- Optimizing Affinity and Pharmacokinetics of a Cysteine-sulfoxide Derivative as Potential Inhibitor of BACE-1 using Fragment Growing and Molecular Dynamics
- Runtime-steered ultrashort molecular dynamics enables million-pose protein–ligand screening
- Computational Evaluation of Carbazole–Chalcone Urea and Thiourea Derivatives Against EGFR: Molecular Docking, Pharmacokinetic Profiling, Target Prediction, and Molecular Dynamics Simulation
- Identification of novel serotonin transporter (SERT) inhibitors via large-scale machine learning-based virtual screening and molecular dynamics simulations
- Reliability of Short Molecular Dynamics Runs as Screening Labels: Noise Ceilings, Time Dependence and Adaptive Replicate Allocation
BibTeX
@misc{poziemski2026evaluating,
title = {{EVALUATING MOLECULAR DYNAMICS FRAMES FOR BINDING AFFINITY PREDICTION AND VIRTUAL SCREENING}},
author = {Jakub Poziemski and Pawel Siedlecki},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009259/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009259/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - EVALUATING MOLECULAR DYNAMICS FRAMES FOR BINDING AFFINITY PREDICTION AND VIRTUAL SCREENING
AU - Jakub Poziemski
AU - Pawel Siedlecki
PY - 2026
DA - 2026/09/22
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009259/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009259/v1
AB - Motivation: Machine-learning scoring functions are typically trained on static crystallographic structures, although protein-ligand recognition is inherently dynamic. It remains unclear whether MD derived conformations provide transferable information or instead shift the training data away from experimentally observed binding geometries. Results: We generated 20 ns molecular dynamics trajectories for 2,502 protein–ligand complexes and evaluated five scoring function architectures trained on crystallographic structures and MD-derived frames using four different sampling protocols. Across the CASF-2016 and CASF-2013 affinity benchmarks, MD-only training generally reduced predictive performance, whereas augmenting crystallographic structures with MD data improved four of the five architectures. Averaged across models, benchmarks, and sampling protocols, augmentation increased PCC by 0.072 and reduced RMSE by 0.165 relative to MD-only training. A nearest-neighbor analysis showed that the benefits of augmen-tation were not restricted to complexes similar to frames, arguing against a simple similarity-based explanation. The results suggest improvements were connected with exposing models to controlled structural perturbations around experimentally observed binding poses. Overall, MD conformations were most effective as augmentation rather than replacement for crystallographic training data. Availability: MD frames used for model training are available at: (https://zenodo.org/ records/20443988).
ER -