Interdisciplinary Sciences: Computational Life Sciences

Chemogenomics, also known as proteochemometrics, covers various computational methods for predicting interactions between related drugs and targets on large-scale data. Chemogenomics is used in the early stages of drug discovery to predict the off-target effects of proteins against therapeutic candidates. This study aims to predict unknown ligand–target interactions using one-dimensional SMILES as inputs for ligands and binding site residues for proteins in a computationally efficient manner. We first formulate a Deep learning CNN model using one-dimensional SMILES for drugs and motif-rich binding pocket subsequences of proteins as inputs. We evaluate and compare the proposed deep learning model trained on expert-based features against shallow feature-based machine learning methods. The proposed method achieved better or similar performance on the MSE and AUPR metrics than the shallow methods. Additionally, We show that our deep learning model, DeepPS is computationally more efficient than the deep learning model trained on full-length raw sequences of proteins. We conclude that a beneficial research approach would be to integrate structural information of proteins for modeling drug-target interaction prediction of large datasets for more interpretability, high throughput, and broad applicability.

At the initial stage of drug discovery, identifying novel targets with maximal efficacy and minimal side effects can improve the success rate and portfolio value of drug discovery projects while simultaneously reducing cycle time and cost. However, harnessing the full potential of big data to narrow the range of plausible targets through existing computational methods remains a key issue in this field. This paper reviews two categories of in silico methods—comparative genomics and network-based methods—for finding potential therapeutic targets among cellular functions based on understanding their related biological processes. In addition to describing the principles, databases, software, and applications, we discuss some recent studies and prospects of the methods. While comparative genomics is mostly applied to infectious diseases, network-based methods can be applied to infectious and non-infectious diseases. Nonetheless, the methods often complement each other in their advantages and disadvantages. The information reported here guides toward improving the application of big data-driven computational methods for therapeutic target discovery.

Secreted aspartyl proteinases (SAP) are the key virulence factors that play a central role in the pathogenesis of Candida albicans and always are the best target for designing potent antifungal agents. Cyanobacteria have already been recognized to provide chemical and pharmacological novelty and diversity over conventional sources of drugs for combating major diseases ranging from AIDS to cancer. In this study, the two ABC transporter systems — permease proteins from Microcoleus chthonoplastes PCC 7420 were modeled and the protein-protein interaction assessment of the modeled proteins with selective secreted aspartyl proteinases of Candida albicans was attempted. The modeled proteins were assigned PMDB IDs PM0077423 and PM0077424. The secreted aspartyl protease 5 of Candida albicans showed effective interaction with ABC transporter permease protein 2 of Microcoleus chthonoplastes PCC 7420. Hydrophobic interactions were found between Tyr, Phe and Pro in chain A and Pro and Tyr in chain B. Our results of the docked complexes clearly demonstrated the potentiality of permease proteins in arresting the virulence nature of SAP of Candida albicans effectively. This study is first of its kind in addressing the therapeutic intervention of virulence nature of Candida albicans by the cyanobacterial system.

Microbial oxidation–reduction reactions utilizing the environmental thiosulfate ions and mediated mainly by the sox operon are very much essential to maintain the sulfur balance in the environment. Majority of the previously documented wet laboratory studies show genetics behind the functionality of Sox proteins encoded by the sox operon. However, the molecular details of the involvements of the essential SoxB, SoxY and SoxZ proteins in the beta-proteobacteria have not yet been elucidated. In this work, an attempt was made to analyze the interaction profiles of the aforementioned SoxB, SoxY and SoxZ proteins to predict their roles in biological sulfur oxidation process. In order to establish the possible roles of these Sox proteins, we built the homology models of these proteins from the two different beta-proteobacteria Dechloromonas aromatica and Thiobacillus denitrificans. We then used molecular docking and simulation studies to further analyze the interaction profiles of these sox proteins. Our analyses revealed that SoxB protein from T. denitrificans exhibited steadier and stronger interactions with SoxYZ protein complex. On the other hand, SoxB protein from D. aromatica was found to exhibit a spontaneous interaction with greater ΔG values and therefore was well documented to exhibit a dual role. This is the first research article to discern the molecular level of interaction profiles of SoxB with SoxYZ protein complex in the beta-proteobacteria D. aromatica and T. denitrificans during the oxidations of thiosulfate. It would further prompt the future investigation into the mutational impact on the sequential interaction pattern in sox operon.

The argonaute protein (Ago) exists in almost all organisms. In eukaryotes, it functions as a regulatory system for gene expression. In prokaryotes, it is a type of defense system against foreign invasive genomes. The Ago system has been engineered for gene silencing and genome editing and plays an important role in biological studies. With an increasing number of genomes and proteomes of various microbes becoming available, computational tools for identifying and annotating argonaute proteins are urgently needed. We introduce AGONOTES (Argonaute Notes). It is a web service especially designed for identifying and annotating Ago. AGONOTES uses the BLASTP similarity search algorithm to categorize all submitted proteins into three groups: prokaryotic argonaute protein (pAgo), eukaryotic argonaute protein (eAgo), and non-argonaute protein (non-Ago). Argonaute proteins can then be aligned to the corresponding standard set of Ago sequences using the multiple sequence alignment program MUSCLE. All functional domains of Ago can further be curated from the alignment results and visualized easily through Bio::Graphic modules in the BioPerl bundle. Compared with existing tools such as CD-Search and available databases such as UniProt and AGONOTES showed a much better performance on domain annotations, which is fundamental in studying the new Ago. AGONOTES can be freely accessed at http://i.uestc.edu.cn/agonotes/. AGONOTES is a friendly tool for annotating Ago domains from a proteome or a series of protein sequences.

The Gram-negative bacterium Klebsiella pneumoniae, responsible for a wide variety of nosocomial infections in immuno-deficient patients, involves the respiratory, urinary and gastrointestinal tract infections and septicemia. Extended spectrum β-lactamases (ESBL) belong to β-lactamases capable of conferring antibiotic resistance in Gram-negative bacteria. CTX-M-15, a prevalent ESBL reported from Enterobacteriaceae including K. pneumoniae, was selected as a potent anti-bacterial target. To identify the novel drug-like compounds, structure-based screening procedure was employed against downloaded drug-like compounds from ZINC database. An acronym for “ZINC” is not commercial. The docking free energy values were investigated and compared to the known inhibitor Avibactam. Six best novel drug-like compounds were selected and their hydrogen bindings with the receptor were determined. Based on the binding efficiency mode, three among these six identified most potential inhibitors, ZINC21811621, ZINC93091917 and ZINC19488569, were predicted as potential competitive inhibitors against CTX-M-15 compared to Avibactam. These three inhibitors may provide a framework for the experimental studies to develop anti-Klebsiella novel drug candidates targeting CTX-M-15.

Exploring the interrelationships between microbes and disease can help microbiologists make decisions and plan treatments. Predicting new microbe–disease associations currently relies on biological experiments and domain knowledge, which is time-consuming and inefficient. Automated algorithms are used to uncover the intrinsic link between microbes and disease. However, due to data noise and inadequate understanding of relevant biology, the efficient prediction of microbe–disease associations is still crucial. This study develops a multi-view graph augmentation convolutional network (MVGCNMDA) to predict potential disease-associated microbes. First, we use two data augmentation methods, edge perturbation and node dropping, to remove the data noise in the preprocessing stage. Second, we calculate Gaussian interaction profile kernel similarity and cosine similarity. Therefore, the Graph Convolutional Network(GCN) can fully use multi-view features. Then, the multi-view features are fed into the multi-attention block to learn the weights of different features adaptively. Finally, the embedding results are obtained using a Convolutional Neural Network (CNN) combiner, and the matrix completion is used to predict the relationship between potential microbes and diseases. We test our model on the Human microbe–disease Association Database (HMDAD), Disbiome, and the Combined Dataset (Peryton and MicroPhenoDB). The area under PR curve (AUPR), area under ROC curve (AUC), F1 score, and RECALL value are calculated to evaluate the performance of the developed MVGCNMDA. The AUPR is 0.9440, AUC is 0.9428, F1 score is 0.9383, and RECALL value is 0.8858. The experiments show that our model can accurately predict potential microbe–disease associations compared with the state-of-the-art works on the global Leave-One-Out-Cross-Validation (LOOCV) and the fivefold Cross-Validation (fivefold CV). To further verify the effectiveness of the proposed graph data augmentation, we designed five different settings in the ablation study. Furthermore, we present two case studies that validate the prediction of the potential association between microbes and diseases by MVGCNMDA.