# Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models

arXiv: https://arxiv.org/abs/2310.13913 · HTML: https://mlsanity.com/paper/2310.13913/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 85 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [Evaluating Protein Transfer Learning with TAPE](https://mlsanity.com/paper/1906.08230/) (2019)
- [ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction](https://mlsanity.com/paper/2106.06130/) (2021)
- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [Revisiting Neural Scaling Laws in Language and Vision](https://mlsanity.com/paper/2209.06640/) (2022)
- [Scaling Laws for Neural Machine Translation](https://mlsanity.com/paper/2109.07740/) (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)
- [Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference](https://mlsanity.com/paper/2005.07704/) (2020)
- [Structure-aware Protein Self-supervised Learning](https://mlsanity.com/paper/2204.04213/) (2022)
- [HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative](https://mlsanity.com/paper/2207.13921/) (2022)
- [LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction](https://mlsanity.com/paper/2106.14494/) (2021)
- [APObind: A Dataset of Ligand Unbound Protein Conformations for Machine Learning Applications in De Novo Drug Design](https://mlsanity.com/paper/2108.09926/) (2021)
- [HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer](https://mlsanity.com/paper/2205.08055/) (2022)

## Built on by (most cited first, 5 of 5)

- [FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation](https://mlsanity.com/paper/2403.20261/) (2024)
- [Technical Report of HelixFold3 for Biomolecular Structure Prediction](https://mlsanity.com/paper/2408.16975/) (2024)
- [Advances in Protein Representation Learning: Methods, Applications, and Future Directions](https://mlsanity.com/paper/2503.16659/) (2025)
- [Dockformer: A transformer-based molecular docking paradigm for large-scale virtual screening](https://mlsanity.com/paper/2411.06740/) (2024)
- [Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design](https://mlsanity.com/paper/2601.09693/) (2026)

## Abstract (arXiv)

Protein-ligand structure prediction is an essential task in drug discovery, predicting the binding interactions between small molecules (ligands) and target proteins (receptors). Recent advances have incorporated deep learning techniques to improve the accuracy of protein-ligand structure prediction. Nevertheless, the experimental validation of docking conformations remains costly, it raises concerns regarding the generalizability of these deep learning-based methods due to the limited training data. In this work, we show that by pre-training on a large-scale docking conformation generated by traditional physics-based docking tools and then fine-tuning with a limited set of experimentally validated receptor-ligand complexes, we can obtain a protein-ligand structure prediction model with outstanding performance. Specifically, this process involved the generation of 100 million docking conformations for protein-ligand pairings, an endeavor consuming roughly 1 million CPU core days. The proposed model, HelixDock, aims to acquire the physical knowledge encapsulated by the physics-based docking tools during the pre-training phase. HelixDock has been rigorously benchmarked against both physics-based and deep learning-based baselines, demonstrating its exceptional precision and robust transferability in predicting binding confirmation. In addition, our investigation reveals the scaling laws governing pre-trained protein-ligand structure prediction models, indicating a consistent enhancement in performance with increases in model parameters and the volume of pre-training data. Moreover, we applied HelixDock to several drug discovery-related tasks to validate its practical utility. HelixDock demonstrates outstanding capabilities on both cross-docking and structure-based virtual screening benchmarks.