Our proposed hit-identification workflow extends pipelines developed by our team during CACHE Challenge 2 and 3. The core methodology consists of high-throughput docking followed by binding affinity estimation using Molecular Mechanics Poisson-Boltzman Surface Area (MMPBSA) on multiple poses drawn from a molecular dynamics (MD) run of the protein-ligand complex. Given the computational cost of running MD and MMPBSA. To ensure that we are able to explore most of the molecular space of Enamine REAL while only doing the expensive evaluations on the most promising molecules. We use an ensemble of Bayesian graph neural networks to predict the binding affinity scores derived from MMPBSA and a second model that distinguishes experimental hits with high binding affinity from decoys these ML models are used to quickly score molecules from Enamine REAL.
Bayesian Graph Neural Network (BGNN) binding affinity predictor: we create two training datasets which are used to train two separate binding affinity predictor models. The first dataset is generated by running MMPBSA on a few hundred molecules to generate binding affinity estimates. The second dataset is trained to distinguish between the experimentally observed hits for CBLB and decoy molecules with similar chemical properties. We then train BGNNs on each of these datasets using the Chemprop library to predict binding affinity. These models are used to generate predictions on the Enamine REAL database and those molecules which have the highest upper-confidence bound are selected to pass through the docking + MMPBSA pipeline. After obtaining more MMPBSA scores the first model can be re-trained and the cycle repeated. In CACHE 2 we were able to generate predictions for 1bn molecules per day and we found good concordance between the MMPBSA predicted score and the BGNN score.
A key aspect of our strategy is ensuring efficient sampling of the 5.5bn compound space of the Enamine REAL database, while also ensuring that the most computationally intensive methods (MMPBSA & FEP) are reserved for the most promising candidate molecules. Using cluster compute resources we are able to dock several million molecules: this includes carrying out ensemble docking against multiple conformations of the receptor.
The ~2.5 million curated set of molecules that we dock and score will be composed of the following:
- Molecules from Enamine REAL with high score from the BGNN
- ~2.1m molecules from the Enamine high-throughput screening library
- ~460k molecules from the Enamine hit locator library
- ~59k molecules from the Enamine premium collection
Ligands are initially screened for molecular weight and solubility. Final selections are screened against PAINS [BadApples webserver] to exclude ligands likely to be toxic or promiscuous binders. To ensure a diversity of structures in the final submission, we will cluster compounds based on structure and submit one sample from each cluster.