Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested.We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods.To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.

Persisters are a small fraction of drug-tolerant bacteria without any genotype variations. Their existence in many life-threatening infectious diseases presents a major challenge to antibiotic therapy. Persistence is highly related to toxin–antitoxin modules. HipA (high persistence A) was the first toxin found to contribute to Escherichia coli persistence. In this study, we used structure-based virtual screening for HipA inhibitors discovery and identified several novel inhibitors of HipA that remarkably reduced E. coli persistence. The most potent one decreased the persister fraction by more than five-fold with an in vitro KD of 270 ± 90 nM and an ex vivo EC50 of 46 ± 2 and 28 ± 1 μM for ampicillin and kanamycin screening, respectively. These findings demonstrated that inhibition of toxin can reduce bacterial persistence independent of the antibiotics used and provided a framework for persistence treatment by interfering with the toxin–antitoxin modules.Keywords: drug discovery; HipA (high persistence A); Persistence; toxin-antitoxin (TA) module

Drug-induced liver injury (DILI) has been the single most frequent cause of safety-related drug marketing withdrawals for the past 50 years. Recently, deep learning (DL) has been successfully applied in many fields due to its exceptional and automatic learning ability. In this study, DILI prediction models were developed using DL architectures, and the best model trained on 475 drugs predicted an external validation set of 198 drugs with an accuracy of 86.9%, sensitivity of 82.5%, specificity of 92.9%, and area under the curve of 0.955, which is better than the performance of previously described DILI prediction models. Furthermore, with deep analysis, we also identified important molecular features that are related to DILI. Such DL models could improve the prediction of DILI risk in humans. The DL DILI prediction models are freely available at http://www.repharma.cn/DILIserver/DILI_home.php.

It has been a consensus in cancer research that cancer is a disease caused primarily by genomic alterations, especially somatic mutations. However, the mechanism of mutation-induced oncogenesis is not fully understood. Here, we used the mitochondrial apoptotic pathway as a case study and performed a systematic analysis of integrating pathway dynamics with protein interaction kinetics to quantitatively investigate the causal molecular mechanism of mutation-induced oncogenesis. A mathematical model of the regulatory network was constructed to establish the functional role of dynamic bifurcation in the apoptotic process. The oncogenic mutation enrichment of each of the protein functional domains involved was found strongly correlated with the parameter sensitivity of the bifurcation point. We further dissected the causal mechanism underlying this correlation by evaluating the mutational influence on protein interaction kinetics using molecular dynamics simulation. We analyzed 29 matched mutant–wild-type and 16 matched SNP—wild-type protein systems. We found that the binding kinetics changes reflected by the changes of free energy changes induced by protein interaction mutations, which induce variations in the sensitive parameters of the bifurcation point, were a major cause of apoptosis pathway dysfunction, and mutations involved in sensitive interaction domains show high oncogenic potential. Our analysis provided a molecular basis for connecting protein mutations, protein interaction kinetics, network dynamics properties, and physiological function of a regulatory network. These insights provide a framework for coupling mutation genotype to tumorigenesis phenotype and help elucidate the logic of cancer initiation.

Alpha-cyclodextrin (α-CD) glycosyltransferase (α-CGTase) can convert starch into α-CD blended with various proportions of β-cyclodextrin (β-CD) and/or γ-cyclodextrin (γ-CD). In this study, we verified the catalytic characteristics of purified Y195I α-CGTase and elucidated the mechanism of action with molecular dynamic (MD) simulations. We found that purified Y195I α-CGTase produced less α-CD, slightly more β-CD, and significantly more γ-CD than wild-type α-CGTase. Correspondingly, α-CD-based Km values increased, and β-CD- and γ-CD-based Km values decreased. MD simulation studies revealed that the dynamic trajectories of the substrate oligosaccharide chain in the mutant CGTase binding site were significantly different from those in the wild-type enzyme, with reduced hydrophobic interaction, finally resulting in different product specificity and more γ-CD formation.

The discovery of multitarget drugs has recently attracted much attention. Most of the reported multitarget ligands have been serendipitous discoveries. Although a few methods have been developed for rational multitarget drug discovery, there is a lack of elegant methods for de novo multitarget drug design and optimization, especially for multiple targets with large differences in their binding sites. In this paper, we report the first de novo multitarget ligand design method, with an iterative fragment-growing strategy. Using this method, dual-target inhibitors for COX-2 and LTA4H were designed, with the most potent one inhibiting PGE2 and LTB4 production in the human whole blood assay with IC50 values of 7.0 and 7.1 μM, respectively. Our strategy is generally applicable in rational and efficient multitarget drug design, especially for the design of highly integrated inhibitors for proteins with dissimilar binding pockets.

The battle against influenza is an enduring one. For hundreds of years, people have fought such small viruses with practices such as traditional Chinese medicine (TCM), however only recently has it been possible to use cutting-edge technology to investigate their mechanisms. Here, we re-created this ancient Chinese knowledge to explore the chemistry of herbs and elucidate their mechanism of action using molecular computational methods. Our results show that TCM compounds can inhibit influenza viral proteins in a multi-target/multi-component manner, revealing the versatility of TCM for treating different influenza virus subtypes, including the recently emerged H7N9.

We have developed a new version (2.0) of the de novo drug design program LigBuilder. With LigBuilder 2.0, the synthesis accessibility of designed compounds can be analyzed, and a cavity detection procedure is implemented to detect the positions and shapes of the binding sites on the surface of a given protein structure and to quantitatively estimate drugability. Ligands are designed to best fit the detected cavities using a set of rules for evaluation. Drug-like and privileged fragments are used to construct the ligands with the aid of internal and external absorption, distribution, metabolism, excretion, and toxicity (ADME/T) and drug-like filters.

This work describes an integrated approach of de novo drug design, chemical synthesis, and bioassay for quick identification of a series of novel small molecule cyclophilin A (CypA) inhibitors (1−3). The activities of the two most potent CypA inhibitors (3h and 3i) are 2.59 and 1.52 nM, respectively, which are about 16 and 27 times more potent than that of cyclosporin A. This study clearly demonstrates the power of our de novo drug design strategy and the related program LigBuilder 2.0 in drug discovery.