De Novo Molecular Design of Caspase-6 Inhibitors by a GRU-Based Recurrent Neural Network Combined with a Transfer Learning Approach.

Due to their potential in the treatment of neurodegenerative diseases, caspase-6 inhibitors have attracted widespread attention. However, the existing caspase-6 inhibitors showed more or less inevitable deficiencies that restrict their clinical development and applications. Therefore, there is an urgent need to develop novel caspase-6 candidate inhibitors. Herein, a gated recurrent unit (GRU)-based recurrent neural network (RNN) combined with transfer learning was used to build a molecular generative model of caspase-6 inhibitors. The results showed that the GRU-based RNN model can accurately learn the SMILES grammars of about 2.4 million chemical molecules including ionic and isomeric compounds and can generate potential caspase-6 inhibitors after transfer learning of the known 433 caspase-6 inhibitors. Based on the novel molecules derived from the molecular generative model, an optimal logistic regression model and Surflex-dock were employed for predicting and ranking the inhibitory activities. According to the prediction results, three potential caspase-6 inhibitors with different scaffolds were selected as the promising candidates for further research. In general, this paper provides an efficient combinational strategy for de novo molecular design of caspase-6 inhibitors.

Conformational transitions of caspase-6 in substrate-induced activation process explored by perturbation-response scanning combined with targeted molecular dynamics.

Caspase-6 participates in a series of neurodegenerative pathways, and has aroused widespread attentions as a promising molecular target for the treatment of neurodegeneration. Caspase-6 is a homodimer with 6 central-stranded ß-sheets and 5 α-helices in each monomer. Previous crystallographic studies suggested that the 60's, 90's and 130's helices of caspase-6 undergo a distinctive conformational transition upon substrate binding. Although the caspase-6 structures in apo and active states have been determined, the conformational transition process between the two states remains poorly understood. In this work, perturbation-response scanning (PRS) combined with targeted molecular dynamics (TMD) simulations was employed to unravel the atomistic mechanism of the dynamic conformational transitions underlying the substrate-induced activation process of caspase-6. The results showed that the conformational transition of caspase-6 from apo to active states is mainly characterized by structural rearrangements of the substrate-binding site as well as the conformational changes of 60's and 130's extended helices. The H-bond interactions between L1, 130's helix and 90's helix are proved to be key determinant factors for substrate-induced conformational transition. These findings provide valuable insights into the activation mechanism of caspase-6 as well as the molecular design of caspase-6 inhibitors.

A simple pan-specific RNN model for predicting HLA-II binding peptides.

The prediction of human leukocyte antigen (HLA) class II binding peptides plays important roles in understanding the mechanism of immune recognition and developing effective epitope-based vaccines. In this work, gated recurrent unit (GRU)-based recurrent neural network (RNN) was successfully employed to establish a pan-specific prediction model of HLA-II-binding peptides by using only the HLA and peptide sequence information. In comparison with the existing pan-specific models of HLA-II-binding peptides, the GRU-based RNN model covered a broad spectrum of HLA-II molecules including 50 HLA-DR, 47 HLA-DQ, and 19 HLA-DP molecules with peptide lengths varying from 8 to 43 mers. The results demonstrated strong discriminant capabilities of the GRU-based RNN model, of which the AUC values were 0.92, 0.88, and 0.88 for the training, validation, and test sets, respectively. Also, the GRU-based model showed state-of-the-art performances in predicting the binding peptides with the length ranging from 8-32 mers, which provides an efficient method for predicting HLA-II-binding peptides of longer lengths in comparison with the available methods. Overall, taking the advantages of the RNN architecture, the established pan-specific GRU model can be used for predicting accurately the HLA-II-binding peptides in a simple and direct manner.

Partial Least-Squares Discriminant Analysis and Ensemble-Based Flexible Docking of PD-1/PD-L1 Inhibitors: A Pilot Study.

Although mAbs targeting the programmed cell death protein 1 (PD-1)/programmed cell death ligand 1 (PD-L1) pathway have achieved remarkable therapeutic potential against multiple types of cancer, it is still of great interest for researchers to develop small-molecule PD-1/PD-L1 inhibitors without the mAb-related disadvantages of no oral bioavailability and poor solid tumor penetration. However, targeting the PD-1/PD-L1 pathway with small molecules is normally considered challenging because of the flat and large interaction surface of the PD-1/PD-L1 complex. In this paper, a total of 2558 PD-1/PD-L1 inhibitors were compiled from recent patents and literatures and then used for exploring the chemical space and structural features of PD-1/PD-L1 inhibitors by partial least-squares discriminant analysis. The results showed that intramolecular H bond, amphotericity indices, radius of gyration, nonbond electrostatic energy, fractional van der Waals surface area of H-bond donors, octanol-water partition coefficient, and molecular weight are the seven key features discriminating the PD-1/PD-L1 inhibitors from noninhibitors, with the prediction accuracy larger than 0.90. Based on the seven crystal structures of the PD-L1 dimer complexed with the patent Bristol Myers Squibb (BMS) inhibitors, the feasibility of molecular docking for this unconventional binding pocket was further investigated. The results showed that the ensemble-based flexible docking protocol can reproduce the near-native binding conformations of the BMS inhibitors with a strong correlation between the IC50 values and ligand-receptor interaction energies (R = 0.81). In general, this paper delineates, for the first time, the characteristic features of the PD-1/PD-L1 inhibitors as well as a high-quality flexible docking strategy for the unconventional binding pocket of the PD-L1 dimer.

A Pan-Specific GRU-Based Recurrent Neural Network for Predicting HLA-I-Binding Peptides.

Human leukocyte antigens (HLAs) play a critical role in human-acquired immune responses by the recognition of non-self-peptides derived from exogenous bacteria, fungi, virus, and so forth. The accurate prediction of HLA-binding peptides is thus extremely useful for the mechanistic research of cell-mediated immunity and related epitope-based vaccine design. In this work, a simple pan-specific gated recurrent unit (GRU)-based recurrent neural network model was successfully proposed for predicting HLA-I-binding peptides. In comparison with the available six allele-specific, four pan-specific, and two ensemble-based prediction models, the GRU model achieves the highest area under the receiver operating characteristic curve (AUC) scores for 21 of 64 entries of the test benchmark datasets. Besides, the GRU model also achieves satisfactory performance on other 24 entries, of which the AUC scores differ by less than 0.1 from the highest scores. Overall, taking the advantages of the GRU network and auto-embedding techniques into account, the established pan-specific GRU model is more simple and direct and shows satisfactory prediction performance for HLA-I-binding peptides with varying lengths.

In Silico Prediction of the Dissociation Rate Constants of Small Chemical Ligands by 3D-Grid-Based VolSurf Method.

Accumulated evidence suggests that binding kinetic properties-especially dissociation rate constant or drug-target residence time-are crucial factors affecting drug potency. However, quantitative prediction of kinetic properties has always been a challenging task in drug discovery. In this study, the VolSurf method was successfully applied to quantitatively predict the koff values of the small ligands of heat shock protein 90α (HSP90α), adenosine receptor (AR) and p38 mitogen-activated protein kinase (p38 MAPK). The results showed that few VolSurf descriptors can efficiently capture the key ligand surface properties related to dissociation rate; the resulting models demonstrated to be extremely simple, robust and predictive in comparison with available prediction methods. Therefore, it can be concluded that the VolSurf-based prediction method can be widely applied in the ligand-receptor binding kinetics and de novo drug design researches.

Computational insight into the conformational transition of human toll-like receptor 8 in the agonist-induced activation processes.

Communicated by Ramaswamy H. Sarma.

Subtle differences in chemical pattern between human toll-like receptor 8 agonists and antagonists: Emerging chemical patterns analysis.

Due to the potencies in the treatments of cancer, infectious diseases, and autoimmune diseases, the developments of human TLR8 (hTLR8) agonists and antagonists have attracted widespread attentions. The hTLR8 agonists and antagonists have similar structures but with completely opposite biological effects. Up to date, the subtle differences in the structures between the hTLR8 agonists and antagonists are still unknown. In this work, emerging chemical pattern (ECP) was successfully used to extract the key chemical patterns of the hTLR8 agonists and antagonists. By using CAEP classifier, an optimal ECP model with only 3 descriptors was established with the overall prediction accuracy larger than 90%. Further hierarchical cluster analysis and molecular docking showed that the H-bond and hydrophobic properties are the key features distinguishing the hTLR8 agonists from antagonists. Comparing with the antagonists, the agonists show stronger specific H-bond properties, while antagonists have stronger non-specific hydrophobic properties. The significant differences in the structural properties may be closely related to the activation/inhibition mechanism of hTLR8.