ABDpred: Prediction of active antimicrobial compounds using supervised machine learning techniques.

BACKGROUND OBJECTIVES: Discovery of new antibiotics is the need of the hour to treat infectious diseases. An ever-increasing repertoire of multidrug-resistant pathogens poses an imminent threat to human lives across the globe. However, the low success rate of the existing approaches and technologies for antibiotic discovery remains a major bottleneck. In silico methods like machine learning (ML) deem more promising to meet the above challenges compared with the conventional experimental approaches. The goal of this study was to create ML models that may be used to successfully predict new antimicrobial compounds. METHODS: In this article, we employed eight different ML algorithms namely, extreme gradient boosting, random forest, gradient boosting classifier, deep neural network, support vector machine, multilayer perceptron, decision tree, and logistic regression. These models were trained using a dataset comprising 312 antibiotic drugs and a negative set of 936 non-antibiotic drugs in a five-fold cross validation approach. RESULTS: The top four ML classifiers (extreme gradient boosting, random forest, gradient boosting classifier and deep neural network) were able to achieve an accuracy of 80 per cent and above during the evaluation of testing and blind datasets. INTERPRETATION CONCLUSIONS: We aggregated the top performing four models through a soft-voting technique to develop an ensemble-based ML method and incorporated it into a freely accessible online prediction server named ABDpred ( http://clinicalmedicinessd.com.in/abdpred/ ).

The sensor kinase MtrB of Mycobacterium tuberculosis regulates hypoxic survival and establishment of infection.

Paired two-component systems (TCSs), having a sensor kinase (SK) and a cognate response regulator (RR), enable the human pathogen Mycobacterium tuberculosis to respond to the external environment and to persist within its host. Here, we inactivated the SK gene of the TCS MtrAB, mtrB, generating the strain ΔmtrB We show that mtrB loss reduces the bacterium's ability to survive in macrophages and increases its association with autophagosomes and autolysosomes. Notably, the ΔmtrB strain was markedly defective in establishing lung infection in mice, with no detectable lung pathology following aerosol challenge. ΔmtrB was less able to withstand hypoxic and acid stresses and to form biofilms and had decreased viability under hypoxia. Transcriptional profiling of ΔmtrB by gene microarray analysis, validated by quantitative RT-PCR, indicated down-regulation of the hypoxia-associated dosR regulon, as well as genes associated with other pathways linked to adaptation of M. tuberculosis to the host environment. Using in vitro biochemical assays, we demonstrate that MtrB interacts with DosR (a noncognate RR) in a phosphorylation-independent manner. Electrophoretic mobility shift assays revealed that MtrB enhances the binding of DosR to the hspX promoter, suggesting an unexpected role of MtrB in DosR-regulated gene expression in M. tuberculosis Taken together, these findings indicate that MtrB functions as a regulator of DosR-dependent gene expression and in the adaptation of M. tuberculosis to hypoxia and the host environment. We propose that MtrB may be exploited as a chemotherapeutic target against tuberculosis.

Interplay between miRNAs and human diseases.

MicroRNAs (miRNAs) are endogenous, non-coding RNAs, which have evoked a great deal of interest due to their importance in many aspects of homeostasis and diseases. MicroRNAs are stable and are essential components of gene regulatory networks. They play a crucial role in healthy individuals and their dysregulations have also been implicated in a wide range of diseases, including diabetes, cardiovascular disease, kidney disease, and cancer. This review summarized the current understanding of interactions between miRNAs and different diseases and their role in disease diagnosis and therapy.

Pediatric T-cell acute lymphoblastic leukemia blast signature and MRD associated immune environment changes defined by single cell transcriptomics analysis.

Different driver mutations and/or chromosomal aberrations and dysregulated signaling interactions between leukemia cells and the immune microenvironment have been implicated in the development of T-cell acute lymphoblastic leukemia (T-ALL). To better understand changes in the bone marrow microenvironment and signaling pathways in pediatric T-ALL, bone marrows collected at diagnosis (Dx) and end of induction therapy (EOI) from 11 patients at a single center were profiled by single cell transcriptomics (10 Dx, 5 paired EOI, 1 relapse). T-ALL blasts were identified by comparison with healthy bone marrow cells. T-ALL blast-associated gene signature included SOX4, STMN1, JUN, HES4, CDK6, ARMH1 among the most significantly overexpressed genes, some of which are associated with poor prognosis in children with T-ALL. Transcriptome profiles of the blast cells exhibited significant inter-patient heterogeneity. Post induction therapy expression profiles of the immune cells revealed significant changes. Residual blast cells in MRD+ EOI samples exhibited significant upregulation (P < 0.01) of PD-1 and RhoGDI signaling pathways. Differences in cellular communication were noted in the presence of residual disease in T cell and hematopoietic stem cell compartments in the bone marrow. Together, these studies generate new insights and expand our understanding of the bone marrow landscape in pediatric T-ALL.

Single-cell analysis reveals altered tumor microenvironments of relapse- and remission-associated pediatric acute myeloid leukemia.

Acute myeloid leukemia (AML) microenvironment exhibits cellular and molecular differences among various subtypes. Here, we utilize single-cell RNA sequencing (scRNA-seq) to analyze pediatric AML bone marrow (BM) samples from diagnosis (Dx), end of induction (EOI), and relapse timepoints. Analysis of Dx, EOI scRNA-seq, and TARGET AML RNA-seq datasets reveals an AML blasts-associated 7-gene signature (CLEC11A, PRAME, AZU1, NREP, ARMH1, C1QBP, TRH), which we validate on independent datasets. The analysis reveals distinct clusters of Dx relapse- and continuous complete remission (CCR)-associated AML-blasts with differential expression of genes associated with survival. At Dx, relapse-associated samples have more exhausted T cells while CCR-associated samples have more inflammatory M1 macrophages. Post-therapy EOI residual blasts overexpress fatty acid oxidation, tumor growth, and stemness genes. Also, a post-therapy T-cell cluster associated with relapse samples exhibits downregulation of MHC Class I and T-cell regulatory genes. Altogether, this study deeply characterizes pediatric AML relapse- and CCR-associated samples to provide insights into the BM microenvironment landscape.

Single cell transcriptomic landscape of diabetic foot ulcers.

Diabetic foot ulceration (DFU) is a devastating complication of diabetes whose pathogenesis remains incompletely understood. Here, we profile 174,962 single cells from the foot, forearm, and peripheral blood mononuclear cells using single-cell RNA sequencing. Our analysis shows enrichment of a unique population of fibroblasts overexpressing MMP1, MMP3, MMP11, HIF1A, CHI3L1, and TNFAIP6 and increased M1 macrophage polarization in the DFU patients with healing wounds. Further, analysis of spatially separated samples from the same patient and spatial transcriptomics reveal preferential localization of these healing associated fibroblasts toward the wound bed as compared to the wound edge or unwounded skin. Spatial transcriptomics also validates our findings of higher abundance of M1 macrophages in healers and M2 macrophages in non-healers. Our analysis provides deep insights into the wound healing microenvironment, identifying cell types that could be critical in promoting DFU healing, and may inform novel therapeutic approaches for DFU treatment.

Machine-learning techniques for the prediction of protein-protein interactions.

Protein-protein interactions (PPIs) are important for the study of protein functions and pathways involved in different biological processes, as well as for understanding the cause and progression of diseases. Several high-throughput experimental techniques have been employed for the identification of PPIs in a few model organisms, but still, there is a huge gap in identifying all possible binary PPIs in an organism. Therefore, PPI prediction using machine-learning algorithms has been used in conjunction with experimental methods for discovery of novel protein interactions. The two most popular supervised machine-learning techniques used in the prediction of PPIs are support vector machines and random forest classifiers. Bayesian-probabilistic inference has also been used but mainly for the scoring of high-throughput PPI dataset confidence measures. Recently, deep-learning algorithms have been used for sequence-based prediction of PPIs. Several clustering methods such as hierarchical and k-means are useful as unsupervised machine-learning algorithms for the prediction of interacting protein pairs without explicit data labelling. In summary, machine-learning techniques have been widely used for the prediction of PPIs thus allowing experimental researchers to study cellular PPI networks.

LMDIPred: A web-server for prediction of linear peptide sequences binding to SH3, WW and PDZ domains.

Protein-peptide interactions form an important subset of the total protein interaction network in the cell and play key roles in signaling and regulatory networks, and in major biological processes like cellular localization, protein degradation, and immune response. In this work, we have described the LMDIPred web server, an online resource for generalized prediction of linear peptide sequences that may bind to three most prevalent and well-studied peptide recognition modules (PRMs)-SH3, WW and PDZ. We have developed support vector machine (SVM)-based prediction models that achieved maximum Matthews Correlation Coefficient (MCC) of 0.85 with an accuracy of 94.55% for SH3, MCC of 0.90 with an accuracy of 95.82% for WW, and MCC of 0.83 with an accuracy of 92.29% for PDZ binding peptides. LMDIPred output combines predictions from these SVM models with predictions using Position-Specific Scoring Matrices (PSSMs) and string-matching methods using known domain-binding motif instances and regular expressions. All of these methods were evaluated using a five-fold cross-validation technique on both balanced and unbalanced datasets, and also validated on independent datasets. LMDIPred aims to provide a preliminary bioinformatics platform for sequence-based prediction of probable binding sites for SH3, WW or PDZ domains.

Computational Framework for Prediction of Peptide Sequences That May Mediate Multiple Protein Interactions in Cancer-Associated Hub Proteins.

A considerable proportion of protein-protein interactions (PPIs) in the cell are estimated to be mediated by very short peptide segments that approximately conform to specific sequence patterns known as linear motifs (LMs), often present in the disordered regions in the eukaryotic proteins. These peptides have been found to interact with low affinity and are able bind to multiple interactors, thus playing an important role in the PPI networks involving date hubs. In this work, PPI data and de novo motif identification based method (MEME) were used to identify such peptides in three cancer-associated hub proteins-MYC, APC and MDM2. The peptides corresponding to the significant LMs identified for each hub protein were aligned, the overlapping regions across these peptides being termed as overlapping linear peptides (OLPs). These OLPs were thus predicted to be responsible for multiple PPIs of the corresponding hub proteins and a scoring system was developed to rank them. We predicted six OLPs in MYC and five OLPs in MDM2 that scored higher than OLP predictions from randomly generated protein sets. Two OLP sequences from the C-terminal of MYC were predicted to bind with FBXW7, component of an E3 ubiquitin-protein ligase complex involved in proteasomal degradation of MYC. Similarly, we identified peptides in the C-terminal of MDM2 interacting with FKBP3, which has a specific role in auto-ubiquitinylation of MDM2. The peptide sequences predicted in MYC and MDM2 look promising for designing orthosteric inhibitors against possible disease-associated PPIs. Since these OLPs can interact with other proteins as well, these inhibitors should be specific to the targeted interactor to prevent undesired side-effects. This computational framework has been designed to predict and rank the peptide regions that may mediate multiple PPIs and can be applied to other disease-associated date hub proteins for prediction of novel therapeutic targets of small molecule PPI modulators.

LMPID: a manually curated database of linear motifs mediating protein-protein interactions.

Linear motifs (LMs), used by a subset of all protein-protein interactions (PPIs), bind to globular receptors or domains and play an important role in signaling networks. LMPID (Linear Motif mediated Protein Interaction Database) is a manually curated database which provides comprehensive experimentally validated information about the LMs mediating PPIs from all organisms on a single platform. About 2200 entries have been compiled by detailed manual curation of PubMed abstracts, of which about 1000 LM entries were being annotated for the first time, as compared with the Eukaryotic LM resource. The users can submit their query through a user-friendly search page and browse the data in the alphabetical order of the bait gene names and according to the domains interacting with the LM. LMPID is freely accessible at http://bicresources.jcbose. ac.in/ssaha4/lmpid and contains 1750 unique LM instances found within 1181 baits interacting with 552 prey proteins. In summary, LMPID is an attempt to enrich the existing repertoire of resources available for studying the LMs implicated in PPIs and may help in understanding the patterns of LMs binding to a specific domain and develop prediction model to identify novel LMs specific to a domain and further able to predict inhibitors/modulators of PPI of interest.

Allergen databases.

In this chapter, five popular allergen databases have been described: (1) Allergome is based on basic and clinical information on allergens causing an IgE-mediated disease; (2) AllergenOnline allows online search of peer-reviewed allergen list; (3) International Union of Immunological Societies Allergen nomenclature subcommittee database contains systematic nomenclature and molecular details of well-characterized allergens; (4) AllFam allows classifying allergens into protein families based on domain information; and (5) SDAP provides in detail structural information of the allergens.