Ligand-Receptor Interactions and Machine Learning in GCGR and GLP-1R Drug Discovery

Keras/TensorFlow in Drug Design for Immunity Disorders

Homeostasis of the host immune system is regulated by white blood cells with a variety of cell surface receptors for cytokines. Chemotactic cytokines (chemokines) activate their receptors to evoke the chemotaxis of immune cells in homeostatic migrations or inflammatory conditions towards inflamed tissue or pathogens. Dysregulation of the immune system leading to disorders such as allergies, autoimmune diseases, or cancer requires efficient, fast-acting drugs to minimize the long-term effects of chronic inflammation. Here, we performed structure-based virtual screening (SBVS) assisted by the Keras/TensorFlow neural network (NN) to find novel compound scaffolds acting on three chemokine receptors: CCR2, CCR3, and one CXC receptor, CXCR3. Keras/TensorFlow NN was used here not as a typically used binary classifier but as an efficient multi-class classifier that can discard not only inactive compounds but also low- or medium-activity compounds. Several compounds proposed by SBVS and NN were tested in 100 ns all-atom molecular dynamics simulations to confirm their binding affinity. To improve the basic binding affinity of the compounds, new chemical modifications were proposed. The modified compounds were compared with known antagonists of these three chemokine receptors. Known CXCR3 compounds were among the top predicted compounds; thus, the benefits of using Keras/TensorFlow in drug discovery have been shown in addition to structure-based approaches. Furthermore, we showed that Keras/TensorFlow NN can accurately predict the receptor subtype selectivity of compounds, for which SBVS often fails. We cross-tested chemokine receptor datasets retrieved from ChEMBL and curated datasets for cannabinoid receptors. The NN model trained on the cannabinoid receptor datasets retrieved from ChEMBL was the most accurate in the receptor subtype selectivity prediction. Among NN models trained on the chemokine receptor datasets, the CXCR3 model showed the highest accuracy in differentiating the receptor subtype for a given compound dataset.

Chemokine Receptors-Structure-Based Virtual Screening Assisted by Machine Learning

Chemokines modulate the immune response by regulating the migration of immune cells. They are also known to participate in such processes as cell-cell adhesion, allograft rejection, and angiogenesis. Chemokines interact with two different subfamilies of G protein-coupled receptors: conventional chemokine receptors and atypical chemokine receptors. Here, we focused on the former one which has been linked to many inflammatory diseases, including: multiple sclerosis, asthma, nephritis, and rheumatoid arthritis. Available crystal and cryo-EM structures and homology models of six chemokine receptors (CCR1 to CCR6) were described and tested in terms of their usefulness in structure-based drug design. As a result of structure-based virtual screening for CCR2 and CCR3, several new active compounds were proposed. Known inhibitors of CCR1 to CCR6, acquired from ChEMBL, were used as training sets for two machine learning algorithms in ligand-based drug design. Performance of LightGBM was compared with a sequential Keras/TensorFlow model of neural network for these diverse datasets. A combination of structure-based virtual screening with machine learning allowed to propose several active ligands for CCR2 and CCR3 with two distinct compounds predicted as CCR3 actives by all three tested methods: Glide, Keras/TensorFlow NN, and LightGBM. In addition, the performance of these three methods in the prediction of the CCR2/CCR3 receptor subtype selectivity was assessed.

Feasibility and application of machine learning enabled fast screening of poly-beta-amino-esters for cartilage therapies

Despite the large prevalence of diseases affecting cartilage (e.g. knee osteoarthritis affecting 16% of population globally), no curative treatments are available because of the limited capacity of drugs to localise in such tissue caused by low vascularisation and electrostatic repulsion. While an effective delivery system is sought, the only option is using high drug doses that can lead to systemic side effects. We introduced poly-beta-amino-esters (PBAEs) to effectively deliver drugs into cartilage tissues. PBAEs are copolymer of amines and di-acrylates further end-capped with other amine; therefore encompassing a very large research space for the identification of optimal candidates. In order to accelerate the screening of all possible PBAEs, the results of a small pool of polymers (n = 90) were used to train a variety of machine learning (ML) methods using only polymers properties available in public libraries or estimated from the chemical structure. Bagged multivariate adaptive regression splines (MARS) returned the best predictive performance and was used on the remaining (n = 3915) possible PBAEs resulting in the recognition of pivotal features; a further round of screening was carried out on PBAEs (n = 150) with small variations of structure of the main candidates from the first round. The refinements of such characteristics enabled the identification of a leading candidate predicted to improve drug uptake > 20 folds over conventional clinical treatment; this uptake improvement was also experimentally confirmed. This work highlights the potential of ML to accelerate biomaterials development by efficiently extracting information from a limited experimental dataset thus allowing patients to benefit earlier from a new technology and at a lower price. Such roadmap could also be applied for other drug/materials development where optimisation would normally be approached through combinatorial chemistry.

The Nonpeptide Agonist MK-5046 Functions As an Allosteric Agonist for the Bombesin Receptor Subtype-3

Allosteric ligands of various G-protein-coupled receptors are being increasingly described and are providing important advances in the development of ligands with novel selectivity and efficacy. These unusual properties allow expanded opportunities for pharmacologic studies and treatment. Unfortunately, no allosteric ligands are yet described for the bombesin receptor family (BnRs), which are proposed to be involved in numerous physiologic/pathophysiological processes in both the central nervous system and peripheral tissues. In this study, we investigate the possibility that the bombesin receptor subtype-3 (BRS-3) specific nonpeptide receptor agonist MK-5046 [(2S)-1,1,1-trifluoro-2-[4-(1H-pyrazol-1-yl)phenyl]-3-(4-[[1-(trifluoromethyl)cyclopropyl]methyl]-1H-imidazol-2-yl)propan-2-ol] functions as a BRS-3 allosteric receptor ligand. We find that in BRS-3 cells, MK-5046 only partially inhibits iodine-125 radionuclide (125I)-Bantag-1 [Boc-Phe-His-4-amino-5-cyclohexyl-2,4,5-trideoxypentonyl-Leu-(3-dimethylamino) benzylamide N-methylammonium trifluoroacetate] binding and that both peptide-1 (a universal BnR-agonist) and MK-5046 activate phospholipase C; however, the specific BRS-3 peptide antagonist Bantag-1 inhibits the action of peptide-1 competitively, whereas for MK-5046 the inhibition is noncompetitive and yields a curvilinear Schild plot. Furthermore, MK-5046 shows other allosteric behaviors, including slowing dissociation of the BRS-3 receptor ligand 125I-Bantag-1, dose-inhibition curves being markedly affected by increasing ligand concentration, and MK-5046 leftward shifting the peptide-1 agonist dose-response curve. Lastly, receptor chimeric studies and site-directed mutagenesis provide evidence that MK-5046 and Bantag-1 have different binding sites determining their receptor high affinity/selectivity. These results provide evidence that MK-5046 is functioning as an allosteric agonist at the BRS-3 receptor, which is the first allosteric ligand described for this family of receptors. SIGNIFICANCE STATEMENT: G-protein-coupled receptor allosteric ligands providing higher selectivity, selective efficacy, and safety that cannot be obtained using usual orthosteric receptor-based strategies are being increasingly described, resulting in enhanced usefulness in exploring receptor function and in treatment. No allosteric ligands exist for any of the mammalian bombesin receptor (BnR) family. Here we provide evidence for the first such example of a BnR allosteric ligand by showing that MK-5046, a nonpeptide agonist for bombesin receptor subtype-3, is functioning as an allosteric agonist.

Drug Repositioning For Allosteric Modulation of VIP and PACAP Receptors

Vasoactive intestinal peptide (VIP) and pituitary adenylate cyclase-activating polypeptide (PACAP) are two neuropeptides that contribute to the regulation of intestinal motility and secretion, exocrine and endocrine secretions, and homeostasis of the immune system. Their biological effects are mediated by three receptors named VPAC1, VPAC2 and PAC1 that belong to class B GPCRs. VIP and PACAP receptors have been identified as potential therapeutic targets for the treatment of chronic inflammation, neurodegenerative diseases and cancer. However, pharmacological use of endogenous ligands for these receptors is limited by their lack of specificity (PACAP binds with high affinity to VPAC1, VPAC2 and PAC1 receptors while VIP recognizes both VPAC1 and VPAC2 receptors), their poor oral bioavailability (VIP and PACAP are 27- to 38-amino acid peptides) and their short half-life. Therefore, the development of non-peptidic small molecules or specific stabilized peptidic ligands is of high interest. Structural similarities between VIP and PACAP receptors are major causes of difficulties in the design of efficient and selective compounds that could be used as therapeutics. In this study we performed structure-based virtual screening against the subset of the ZINC15 drug library. This drug repositioning screen provided new applications for a known drug: ticagrelor, a P2Y12 purinergic receptor antagonist. Ticagrelor inhibits both VPAC1 and VPAC2 receptors which was confirmed in VIP-binding and calcium mobilization assays. A following analysis of detailed ticagrelor binding modes to all three VIP and PACAP receptors with molecular dynamics revealed its allosteric mechanism of action. Using a validated homology model of inactive VPAC1 and a recently released cryo-EM structure of active VPAC1 we described how ticagrelor could block conformational changes in the region of 'tyrosine toggle switch' required for the receptor activation. We also discuss possible modifications of ticagrelor comparing other P2Y12 antagonist - cangrelor, closely related to ticagrelor but not active for VPAC1/VPAC2. This comparison with inactive cangrelor could lead to further improvement of the ticagrelor activity and selectivity for VIP and PACAP receptor sub-types.