TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction

By Wei Lu, Qifeng Wu, Jixian Zhang, Jiahua Rao, Chengtao Li, Shuangjia Zheng. 2022

237 citations recorded by the source corpus.

Illuminating interactions between proteins and small drug molecules is a longstanding challenge in the field of drug discovery. Despite the importance of understanding these interactions, most previous works are limited by hand-designed scoring functions and insufficient conformation sampling. The recently-proposed graph neural network-based methods provides alternatives to predict protein-ligand complex conformation in a one-shot manner. However, these methods neglect the geometric constraints of the complex structure and weaken the role of local functional regions. As a result, they might produce unreasonable conformations for challenging targets and generalize poorly to novel proteins. In this paper, we propose Trigonometry-Aware Neural networKs for binding structure prediction, TANKBind, that builds trigonometry constraint as a vigorous inductive bias into the model and explicitly attends to all possible binding sites for each protein by segmenting the whole protein into functional blocks. We construct novel contrastive losses with local region negative sampling to jointly optimize the binding interaction and affinity. Extensive experiments show substantial performance gains in comparison to state-of-the-art physics-based and deep learning-based methods on commonly-used benchmark datasets for both binding structure and affinity predictions with variant settings.

Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology, Model Architectures, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Shigenori Tanaka
4. Shuya Nakata
5. Yoshiharu Mori
6. Bowen Jing
7. Gabriele Corso
8. Hannes Stärk

In Molecular Biology

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Hannes Stärk
4. Shuya Nakata
5. Shigenori Tanaka
6. Yoshiharu Mori
7. Bowen Jing
8. Gabriele Corso

In Pharmacology

1. Regina Barzilay
2. Tommi S. Jaakkola

In Model Architectures

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Gabriele Corso
4. Bowen Jing
5. Hannes Stärk
6. Guolin Ke

In Computational Chemistry & Drug Discovery

1. Tommi S. Jaakkola
2. Shuya Nakata
3. Shigenori Tanaka
4. Yoshiharu Mori
5. Regina Barzilay
6. Gabriele Corso
7. Bowen Jing
8. Hannes Stärk

Citations in the corpus

• End-to-end protein–ligand complex structure generation with diffusion-based generative models (2022, methodology): “The authors reported significant performance gains over existing methods on the PDBbind [37] benchmark dataset and highlighted the critical issues with regression-based frameworks [38,39].”
• DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, methodology): “We evaluate our method on the complexes from PDBBind [12], a large collection of protein-ligand structures collected from PDB [13], which was used with time-based splits to benchmark many previous works [3, 14, 4].”
• Do Deep Learning Models Really Outperform Traditional Approaches in Molecular Docking? (2023, methodology): “• TANKBind [11], we use the number reported in DiffDock [12] paper.”
• Artificial intelligence in drug development (2025, unknown): “AI-based receptor–ligand docking models can predict ligand spatial transformations, directly generate complex atomic coordinates using algorithms like equivariant neural networks 44–46 and learn the probability density distribution of receptor– ligand distances to generate binding poses 47–49 .”
• Structure-based drug design with equivariant diffusion models (2022, unknown): “Even though utilizing deep learning as surrogate docking models has achieved remarkable progress (Lu et al., 2022; Stärk et al., 2022), deep learning-based ∗Equal contribution.”