# FlexVDW: A machine learning approach to account for protein flexibility in ligand docking

arXiv: https://arxiv.org/abs/2303.11494 · HTML: https://mlsanity.com/paper/2303.11494/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 39 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Machine Learning of coarse-grained Molecular Dynamics Force Fields](https://mlsanity.com/paper/1812.01736/) (2018)
- [Protein-Ligand Scoring with Convolutional Neural Networks](https://mlsanity.com/paper/1612.02751/) (2016)
- [Coarse Graining Molecular Dynamics with Graph Neural Networks](https://mlsanity.com/paper/2007.11412/) (2020)
- [Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction](https://mlsanity.com/paper/1910.02845/) (2019)
- [Protein model quality assessment using rotation-equivariant, hierarchical neural networks](https://mlsanity.com/paper/2011.13557/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhancing Ligand Pose Sampling for Molecular Docking](https://mlsanity.com/paper/2312.00191/) (2023)

## Abstract (arXiv)

Most widely used ligand docking methods assume a rigid protein structure. This leads to problems when the structure of the target protein deforms upon ligand binding. In particular, the ligand's true binding pose is often scored very unfavorably due to apparent clashes between ligand and protein atoms, which lead to extremely high values of the calculated van der Waals energy term. Traditionally, this problem has been addressed by explicitly searching for receptor conformations to account for the flexibility of the receptor in ligand binding. Here we present a deep learning model trained to take receptor flexibility into account implicitly when predicting van der Waals energy. We show that incorporating this machine-learned energy term into a state-of-the-art physics-based scoring function improves small molecule ligand pose prediction results in cases with substantial protein deformation, without degrading performance in cases with minimal protein deformation. This work demonstrates the feasibility of learning effects of protein flexibility on ligand binding without explicitly modeling changes in protein structure.