# Assessing interaction recovery of predicted protein-ligand poses

arXiv: https://arxiv.org/abs/2409.20227 · HTML: https://mlsanity.com/paper/2409.20227/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 52 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 2 of 2)

- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [State-specific protein-ligand complex structure prediction with a multi-scale deep generative model](https://mlsanity.com/paper/2209.15171/) (2022)

## Built on by (most cited first, 3 of 3)

- [FLOWR: Flow Matching for Structure-Aware De Novo, Interaction- and Fragment-Based Ligand Generation](https://mlsanity.com/paper/2504.10564/) (2025)
- [NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models](https://mlsanity.com/paper/2412.10743/) (2024)
- [Generative molecule evolution using 3D pharmacophore for efficient Structure-Based Drug Design](https://mlsanity.com/paper/2507.20130/) (2025)

## Abstract (arXiv)

The field of protein-ligand pose prediction has seen significant advances in recent years, with machine learning-based methods now being commonly used in lieu of classical docking methods or even to predict all-atom protein-ligand complex structures. Most contemporary studies focus on the accuracy and physical plausibility of ligand placement to determine pose quality, often neglecting a direct assessment of the interactions observed with the protein. In this work, we demonstrate that ignoring protein-ligand interaction fingerprints can lead to overestimation of model performance, most notably in recent protein-ligand cofolding models which often fail to recapitulate key interactions.