Combined Molecular Graph Neural Network and Structural Docking Selects Potent Programmable Cell Death Protein 1/Programmable Death-Ligand 1 (PD-1/PD-L1) Small Molecule Inhibitors

Abstract

The Programmable Cell Death Protein 1/Programmable Death-Ligand 1 (PD-1/PD-L1) interaction is an immune checkpoint utilized by cancer cells to enhance immune suppression. There exists a huge need to develop small molecules drugs that are fast acting, cheap, and readily bioavailable compared to antibodies. Unfortunately, synthesizing and validating large libraries of small-molecule to inhibit PD-1/PD-L1 interaction in a blind manner is a both time-consuming and expensive. To improve this drug discovery pipeline, we have developed a machine learning methodology trained on patent data to identify, synthesize and validate PD-1/PD-L1 small molecule inhibitors. Our model incorporates two features: docking scores to represent the energy of binding (E) as a global feature and sub-graph features through a graph neural network (GNN) to represent local features. This Energy-Graph Neural Network (EGNN) model outperforms traditional machine learning methods as well as a simple GNN with an average F1 score of 0.997 (± 0.004) suggesting that the topology of the small molecule, the structural interaction in the binding pocket, and chemical diversity of the training data are all important considerations for enhancing model performance. A Bootstrapped EGNN model was used to select compounds for synthesis and experimental validation with predicted high and low potency to inhibit PD-1/PD-L1 interaction. The new potent inhibitor, (4-((3-(2,3-dihydrobenzo[<i>b</i>][1,4]dioxin-6-yl)-2-methylbenzyl)oxy)-2,6-dimethoxybenzyl)-D-serine, is a hybrid of two known bioactive scaffolds, and has an IC<sub>50</sub> values of 339.9 nM that is comparatively better than the known bioactive compound. We conclude that our EGNN model can identify active molecules designed by scaffold hopping, a well-known medicinal chemistry technique and will be useful to identify new potent small molecule inhibitors for specific targets.

Selecting machine-learning scoring functions for structure-based virtual screening

“…For instance, a retrospective analysis based on random decoys found that a ML-based SF (MIEC-SVM) was much more predictive than a classical SF (Autodock4.2) on the ALK target, which was exactly what was later observed prospectively [8]. This is not the only ML-based SF reporting excellent prospective SBVS results without any use of PM decoys [14,34]. It is important to note too that PM decoys are not required either to train or test QSAR models [35], despite predicting exactly the same in vitro potency/affinity endpoints as SFs (e.g.…”

Accurate Prediction of Inhibitor Binding to HIV-1 Protease Using CANDOCK

“…Leveraging some of our recently developed programs, based on machine learning and graph neural networks, we can iteratively select synthetically feasible bioactive protease inhibitors based on bioactivity data and CANDOCK-generated pose of molecules ( Majumder et al, 2018 ; Wijewardhane et al, 2020 ). Exploration of CANDOCK efficacy on other HIV-1 targets, such as reverse transcriptase, would enable proteomic-based drug discovery, which we have shown to be useful for drug repurposing, and could lead to more potent HIV-1 therapeutics ( Chopra et al, 2016 ; Chopra and Samudrala, 2016 ; Hernandez-Perez et al, 2017 ; Majumder et al, 2017 ; Fine et al, 2019 ; Mangione et al, 2020 ; Robertson et al, 2020 ).…”

Optochemical Control of Immune Checkpoint Blockade via Light‐Triggered PD‐L1 Dimerization

“…The compound BMS-1 exhibited a strong inhibitory activity on PD-1/PD-L1 binding with an IC 50 of 91.94 nM (Figure 2B), which is consistent with the reported range (6-100 nM). [26] Without light irradiation, the prodrug did not efficiently inhibit PD-1/PD-L1 binding with an IC 50 of 12.55 μM, while the inhibitory effect was restored after light irradiation with an IC 50 (1.032 μM). IC 50 is larger than that of BMS-1, which is due to relatively low recovery efficiency of the released BMS-1 under light irradiation.…”