Deep learning driven de novo drug design based on gastric proton pump structures.

Existing drugs often suffer in their effectiveness due to detrimental side effects, low binding affinity or pharmacokinetic problems. This may be overcome by the development of distinct compounds. Here, we exploit the rich structural basis of drug-bound gastric proton pump to develop compounds with strong inhibitory potency, employing a combinatorial approach utilizing deep generative models for de novo drug design with organic synthesis and cryo-EM structural analysis. Candidate compounds that satisfy pharmacophores defined in the drug-bound proton pump structures, were designed in silico utilizing our deep generative models, a workflow termed Deep Quartet. Several candidates were synthesized and screened according to their inhibition potencies in vitro, and their binding poses were in turn identified by cryo-EM. Structures reaching up to 2.10 Å resolution allowed us to evaluate and re-design compound structures, heralding the most potent compound in this study, DQ-18 (N-methyl-4-((2-(benzyloxy)-5-chlorobenzyl)oxy)benzylamine), which shows a Ki value of 47.6 nM. Further high-resolution cryo-EM analysis at 2.08 Å resolution unambiguously determined the DQ-18 binding pose. Our integrated approach offers a framework for structure-based de novo drug development based on the desired pharmacophores within the protein structure.

Identification of aminobenzoic acids as selective inhibitors of the N-terminal phosphatase of soluble epoxide hydrolase.

Soluble epoxide hydrolase (EC 3.3.2.10) is a key enzyme in the regulation of inflammation and metabolism, whereas, the role of its N-terminal phosphatase activity (N-phos) has been poorly understood because of a lack of selective inhibitors. Here we report 4-aminobenzoic (Ki 15.3 µm) and 3-amino-4-hydroxy benzoic acid (Ki 11.7 µm) as selective competitive inhibitors of N-phos.

Computational Prediction of Compound-Protein Interactions for Orphan Targets Using CGBVS.

A variety of Artificial Intelligence (AI)-based (Machine Learning) techniques have been developed with regard to in silico prediction of Compound-Protein interactions (CPI)-one of which is a technique we refer to as chemical genomics-based virtual screening (CGBVS). Prediction calculations done via pairwise kernel-based support vector machine (SVM) is the main feature of CGBVS which gives high prediction accuracy, with simple implementation and easy handling. We studied whether the CGBVS technique can identify ligands for targets without ligand information (orphan targets) using data from G protein-coupled receptor (GPCR) families. As the validation method, we tested whether the ligand prediction was correct for a virtual orphan GPCR in which all ligand information for one selected target was omitted from the training data. We have specifically expressed the results of this study as applicability index and developed a method to determine whether CGBVS can be used to predict GPCR ligands. Validation results showed that the prediction accuracy of each GPCR differed greatly, but models using Multiple Sequence Alignment (MSA) as the protein descriptor performed well in terms of overall prediction accuracy. We also discovered that the effect of the type compound descriptors on the prediction accuracy was less significant than that of the type of protein descriptors used. Furthermore, we found that the accuracy of the ligand prediction depends on the amount of ligand information with regard to GPCRs related to the target. Additionally, the prediction accuracy tends to be high if a large amount of ligand information for related proteins is used in the training.

Discovery of Novel eEF2K Inhibitors Using HTS Fingerprint Generated from Predicted Profiling of Compound-Protein Interactions.

Background: Eukaryotic elongation factor 2 kinase (eEF2K) regulates the elongation stage of protein synthesis by phosphorylating eEF2, a process related to various diseases including cancer and cardiovascular and neurodegenerative diseases. In this study, we describe the identification of novel eEF2K inhibitors using high-throughput screening fingerprints (HTSFP) generated from predicted profiling of compound-protein interactions (CPIs). Methods: We utilized computationally generated HTSFPs referred to as chemical genomics-based fingerprint (CGBFP). Generally, HTSFPs are generated from multiple biochemical or cell-based assay data. On the other hand, CGBFPs are generated from computational prediction of CPIs using the Chemical Genomics-Based Virtual Screening (CGBVS) method. Therefore, CGBFPs do not have missing information mainly caused by the absence of assay data. Results: Chemogenomics-Based Similarity Profiling (CGBSP) of the screening library (2.6 million compounds) yielded 27 compounds which were evaluated for in vitro eEF2K inhibitory activity. Three compounds with interesting results were identified. Compounds 2 (IC50 = 11.05 µM) and 4 (IC50 = 43.54 µM) are thieno[2,3-b]pyridine derivatives that have the same scaffolds with a known eEF2K inhibitor, while compound 13 (IC50 = 70.13 µM) was a new thiophene-2-amine-type eEF2K inhibitor. Conclusions: CGBSP supplied an efficient strategy in the identification of novel eEF2K inhibitors and provided useful scaffolds for optimization.

Design and Synthesis of DDR1 Inhibitors with a Desired Pharmacophore Using Deep Generative Models.

Discoidin domain receptor 1 (DDR1) inhibitors with a desired pharmacophore were designed using deep generative models (DGMs). DDR1 is a receptor tyrosine kinase activated by matrix collagens and implicated in diseases such as cancer, fibrosis and hypoxia. Herein we describe the synthesis and inhibitory activity of compounds generated from DGMs. Three compounds were found to have sub-micromolar inhibitory activity. The most potent of which, compound 3 (N-(4-chloro-3-((pyridin-3-yloxy)methyl)phenyl)-3-(trifluoromethyl)benzamide), had an IC50 value of 92.5 nM. Furthermore, these compounds were predicted to interact with DDR1, which have a desired pharmacophore derived from a known DDR1 inhibitor. The results of synthesis and experiments indicated that our de novo design strategy is practical for hit identification and scaffold hopping.

Strategies for Design of Molecular Structures with a Desired Pharmacophore Using Deep Reinforcement Learning.

The goal of drug design is to discover molecular structures that have suitable pharmacological properties in vast chemical space. In recent years, the use of deep generative models (DGMs) is getting a lot of attention as an effective method of generating new molecules with desired properties. However, most of the properties do not have three-dimensional (3D) information, such as shape and pharmacophore. In drug discovery, pharmacophores are valuable clues in finding active compounds. In this study, we propose a computational strategy based on deep reinforcement learning for generating molecular structures with a desired pharmacophore. In addition, to extract selective molecules against a target protein, chemical genomics-based virtual screening (CGBVS) is used as post-processing method of deep reinforcement learning. As an example study, we have employed this strategy to generate molecular structures of selective TIE2 inhibitors. This strategy can be adopted into general use for generating selective molecules with a desired pharmacophore.

A virtual active compound produced from the negative image of a ligand-binding pocket, and its application to in-silico drug screening.

We developed a new structure-based in-silico screening method using a negative image of a ligand-binding pocket and a multi-protein-compound interaction matrix. Based on the structure of the ligand pocket of the target protein, we designed a negative image, which consists of virtual atoms whose radii are close to those of carbon atoms. The virtual atoms fit the pocket ideally and achieve an optimal Coulomb interaction. A protein-compound docking program calculates the protein-compound interaction matrix for many proteins and many compounds including the negative image, which can be treated as a virtual compound. With specific attention to a vector of docking scores for a single compound with many proteins, we selected a compound whose score vector was similar to that of the negative image as a candidate hit compound. This method was applied to representative target proteins and showed high database enrichment with a relatively quick procedure.