Predicting the locations of cryptic pockets from single protein structures using the PocketMiner graph neural network
By Artur Meller, Michael D. Ward, Jonathan Borowsky, Jeffrey M. Lotthammer, Meghana Kshirsagar, Felipe Oviedo, Juan M. Lavista Ferres, Gregory R. Bowman. 2022
69 citations recorded by the source corpus.
Cryptic pockets expand the scope of drug discovery by enabling targeting of proteins currently considered undruggable because they lack pockets in their ground state structures. However, identifying cryptic pockets is labor-intensive and slow. The ability to accurately and rapidly predict if and where cryptic pockets are likely to form from a protein structure would greatly accelerate the search for druggable pockets. Here, we present PocketMiner, a graph neural network trained to predict where pockets are likely to open in molecular dynamics simulations. Applying PocketMiner to single structures from a newly-curated dataset of 39 experimentally-confirmed cryptic pockets demonstrates that it accurately identifies cryptic pockets (ROC-AUC: 0.87) >1,000-fold faster than existing methods. We apply PocketMiner across the human proteome and show that predicted pockets open in simulations, suggesting that over half of proteins thought to lack pockets based on available structures are likely to contain cryptic pockets, vastly expanding the druggable proteome.
Subfields: Computational Theory and Mathematics, Molecular Biology, Spectroscopy
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
- Anima Anandkumar
- Weili Nie
- Shuya Nakata
- Shigenori Tanaka
- Arash Vahdat
- Thomas F. Miller
- Yoshiharu Mori
- Zhuoran Qiao
In Molecular Biology
- Anima Anandkumar
- Weili Nie
- Shuya Nakata
- Shigenori Tanaka
- Arash Vahdat
- Thomas F. Miller
- Yoshiharu Mori
- Zhuoran Qiao
In Spectroscopy
Citations in the corpus
- End-to-end protein–ligand complex structure generation with diffusion-based generative models (2022, methodology): “We performed conformational sampling on 23 complexes from the PocketMiner dataset [43], a collection of apo-holo protein structure pairs with significant conformational changes upon ligand binding.”
- Dynamic-Backbone Protein-Ligand Structure Prediction with Multiscale Generative Diffusion Models (2022, methodology): “Lastly, we assessed NeuralPLexer-sampled structures for 31 systems from the PocketMiner dataset [50] which represents proteins with substantial ligand-binding-induced conformation changes.”