# Improving detection of protein-ligand binding sites with 3D segmentation

arXiv: https://arxiv.org/abs/1904.06517 · HTML: https://mlsanity.com/paper/1904.06517/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2019.

## Built on by (most cited first, 15 of 15)

- [Multi-Scale Representation Learning on Proteins](https://mlsanity.com/paper/2204.02337/) (2022)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction](https://mlsanity.com/paper/2302.12177/) (2023)
- [VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification](https://mlsanity.com/paper/2404.07194/) (2024)
- [Structure-based drug discovery with deep learning](https://mlsanity.com/paper/2212.13295/) (2022)
- [Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence](https://mlsanity.com/paper/2312.03016/) (2023)
- [Geometric Deep Learning for Structure-Based Drug Design: A Survey](https://mlsanity.com/paper/2306.11768/) (2023)
- [RAPID-Net: Accurate Pocket Identification for Binding-Site-Agnostic Docking](https://mlsanity.com/paper/2502.02371/) (2025)
- [ParaVS: A Simple, Fast, Efficient and Flexible Graph Neural Network Framework for Structure-Based Virtual Screening](https://mlsanity.com/paper/2102.06086/) (2021)
- [Boosting Convolutional Neural Networks' Protein Binding Site Prediction Capacity Using SE(3)-invariant transformers, Transfer Learning and Homology-based Augmentation](https://mlsanity.com/paper/2303.08818/) (2023)
- [GENEOnet: Statistical analysis supporting explainability and trustworthiness](https://mlsanity.com/paper/2503.09199/) (2025)
- [GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Prediction](https://mlsanity.com/paper/2603.19817/) (2026)
- [SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggability](https://mlsanity.com/paper/2606.04020/) (2026)
- [From Surfaces to Volumes: Registered Geometry for Protein Representation Learning](https://mlsanity.com/paper/2609.36277/) (2026)
- [Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures](https://mlsanity.com/paper/2610.00988/) (2026)

## Abstract (arXiv)

In recent years machine learning (ML) took bio- and cheminformatics fields by storm, providing new solutions for a vast repertoire of problems related to protein sequence, structure, and interactions analysis. ML techniques, deep neural networks especially, were proven more effective than classical models for tasks like predicting binding affinity for molecular complex. In this work we investigated the earlier stage of drug discovery process - finding druggable pockets on protein surface, that can be later used to design active molecules. For this purpose we developed a 3D fully convolutional neural network capable of binding site segmentation. Our solution has high prediction accuracy and provides intuitive representations of the results, which makes it easy to incorporate into drug discovery projects. The model's source code, together with scripts for most common use-cases is freely available at http://gitlab.com/cheminfIBB/kalasanty