# Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity

arXiv: https://arxiv.org/abs/1703.10603 · HTML: https://mlsanity.com/paper/1703.10603/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2017.

## Built on by (most cited first, 22 of 22)

- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [Graph Neural Networks for Molecules](https://mlsanity.com/paper/2209.05582/) (2022)
- [Learning Neural Set Functions Under the Optimal Subset Oracle](https://mlsanity.com/paper/2203.01693/) (2022)
- [A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems](https://mlsanity.com/paper/2311.11228/) (2023)
- [Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers](https://mlsanity.com/paper/2103.02843/) (2021)
- [Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes](https://mlsanity.com/paper/2206.02789/) (2022)
- [HAC-Net: A Hybrid Attention-Based Convolutional Neural Network for Highly Accurate Protein-Ligand Binding Affinity Prediction](https://mlsanity.com/paper/2212.12440/) (2022)
- [High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Models](https://mlsanity.com/paper/2104.04547/) (2021)
- [A critical look at the current train/test split in machine learning](https://mlsanity.com/paper/2106.04525/) (2021)
- [Improved prediction of ligand-protein binding affinities by meta-modeling](https://mlsanity.com/paper/2310.03946/) (2023)
- [FragXsiteDTI: Revealing Responsible Segments in Drug-Target Interaction with Transformer-Driven Interpretation](https://mlsanity.com/paper/2311.02326/) (2023)
- [Open Source Infrastructure for Differentiable Density Functional Theory](https://mlsanity.com/paper/2309.15985/) (2023)
- [Enhancing Neural Subset Selection: Integrating Background Information into Set Representations](https://mlsanity.com/paper/2402.03139/) (2024)
- [A Modular Open Source Framework for Genomic Variant Calling](https://mlsanity.com/paper/2411.11513/) (2024)
- [Learning to Discover Medicines](https://mlsanity.com/paper/2202.07096/) (2022)
- [Recent Developments in Structure-Based Virtual Screening Approaches](https://mlsanity.com/paper/2211.03208/) (2022)
- [Open-Source Fermionic Neural Networks with Ionic Charge Initialization](https://mlsanity.com/paper/2401.10287/) (2024)
- [Open-Source Molecular Processing Pipeline for Generating Molecules](https://mlsanity.com/paper/2408.06261/) (2024)
- [Open Source Infrastructure for Automatic Cell Segmentation](https://mlsanity.com/paper/2409.08163/) (2024)
- [AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice](https://mlsanity.com/paper/2602.17747/) (2026)
- [Curvature-Guided Geometric Representation for Protein-Ligand Binding Affinity Prediction](https://mlsanity.com/paper/2606.14159/) (2026)
- [Advancing Optimal Subset Oracle via Learning Relaxation of Neural Set Functions](https://mlsanity.com/paper/2607.11555/) (2026)

## Abstract (arXiv)

Empirical scoring functions based on either molecular force fields or cheminformatics descriptors are widely used, in conjunction with molecular docking, during the early stages of drug discovery to predict potency and binding affinity of a drug-like molecule to a given target. These models require expert-level knowledge of physical chemistry and biology to be encoded as hand-tuned parameters or features rather than allowing the underlying model to select features in a data-driven procedure. Here, we develop a general 3-dimensional spatial convolution operation for learning atomic-level chemical interactions directly from atomic coordinates and demonstrate its application to structure-based bioactivity prediction. The atomic convolutional neural network is trained to predict the experimentally determined binding affinity of a protein-ligand complex by direct calculation of the energy associated with the complex, protein, and ligand given the crystal structure of the binding pose. Non-covalent interactions present in the complex that are absent in the protein-ligand sub-structures are identified and the model learns the interaction strength associated with these features. We test our model by predicting the binding free energy of a subset of protein-ligand complexes found in the PDBBind dataset and compare with state-of-the-art cheminformatics and machine learning-based approaches. We find that all methods achieve experimental accuracy and that atomic convolutional networks either outperform or perform competitively with the cheminformatics based methods. Unlike all previous protein-ligand prediction systems, atomic convolutional networks are end-to-end and fully-differentiable. They represent a new data-driven, physics-based deep learning model paradigm that offers a strong foundation for future improvements in structure-based bioactivity prediction.