# DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction

arXiv: https://arxiv.org/abs/2507.06366 · HTML: https://mlsanity.com/paper/2507.06366/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 58 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](https://mlsanity.com/paper/1706.08566/) (2017)
- [TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials](https://mlsanity.com/paper/2202.02541/) (2022)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [Pre-training via Denoising for Molecular Property Prediction](https://mlsanity.com/paper/2206.00133/) (2022)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph](https://mlsanity.com/paper/2106.04509/) (2021)
- [GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction](https://mlsanity.com/paper/2109.11730/) (2021)
- [Development and evaluation of a deep learning model for protein-ligand binding affinity prediction](https://mlsanity.com/paper/1712.07042/) (2017)
- [PotentialNet for Molecular Property Prediction](https://mlsanity.com/paper/1803.04465/) (2018)
- [Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation](https://mlsanity.com/paper/2301.10814/) (2023)
- [Pre-training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding](https://mlsanity.com/paper/2204.08663/) (2022)
- [DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction](https://mlsanity.com/paper/1912.00318/) (2019)
- [Pre-training with Fractional Denoising to Enhance Molecular Property Prediction](https://mlsanity.com/paper/2407.11086/) (2024)

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

- [SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression](https://mlsanity.com/paper/2511.04838/) (2025)

## Abstract (arXiv)

Predicting the binding affinity of protein-ligand complexes plays a vital role in drug discovery. Unfortunately, progress has been hindered by the lack of large-scale and high-quality binding affinity labels. The widely used PDBbind dataset has fewer than 20K labeled complexes. Self-supervised learning, especially graph contrastive learning (GCL), provides a unique opportunity to break the barrier by pre-training graph neural network models based on vast unlabeled complexes and fine-tuning the models on much fewer labeled complexes. However, the problem faces unique challenges, including a lack of a comprehensive unlabeled dataset with well-defined positive/negative complex pairs and the need to design GCL algorithms that incorporate the unique characteristics of such data. To fill the gap, we propose DecoyDB, a large-scale, structure-aware dataset specifically designed for self-supervised GCL on protein-ligand complexes. DecoyDB consists of high-resolution ground truth complexes (less than 2.5 Angstrom) and diverse decoy structures with computationally generated binding poses that range from realistic to suboptimal (negative pairs). Each decoy is annotated with a Root Mean Squared Deviation (RMSD) from the native pose. We further design a customized GCL framework to pre-train graph neural networks based on DecoyDB and fine-tune the models with labels from PDBbind. Extensive experiments confirm that models pre-trained with DecoyDB achieve superior accuracy, label efficiency, and generalizability.