Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs.

Natural compounds constitute a rich resource of potential small molecule therapeutics. While experimental access to this resource is limited due to its vast diversity and difficulties in systematic purification, computational assessment of structural similarity with known therapeutic molecules offers a scalable approach. Here, we assessed functional similarity between natural compounds and approved drugs by combining multiple chemical similarity metrics and physicochemical properties using a machine-learning approach. We computed pairwise similarities between 1410 drugs for training classification models and used the drugs shared protein targets as class labels. The best performing models were random forest which gave an average area under the ROC of 0.9, Matthews correlation coefficient of 0.35, and F1 score of 0.33, suggesting that it captured the structure-activity relation well. The models were then used to predict protein targets of circa 11k natural compounds by comparing them with the drugs. This revealed therapeutic potential of several natural compounds, including those with support from previously published sources as well as those hitherto unexplored. We experimentally validated one of the predicted pair's activities, viz., Cox-1 inhibition by 5-methoxysalicylic acid, a molecule commonly found in tea, herbs and spices. In contrast, another natural compound, 4-isopropylbenzoic acid, with the highest similarity score when considering most weighted similarity metric but not picked by our models, did not inhibit Cox-1. Our results demonstrate the utility of a machine-learning approach combining multiple chemical features for uncovering protein binding potential of natural compounds.

Bioaccumulation of therapeutic drugs by human gut bacteria.

Bacteria in the gut can modulate the availability and efficacy of therapeutic drugs. However, the systematic mapping of the interactions between drugs and bacteria has only started recently1 and the main underlying mechanism proposed is the chemical transformation of drugs by microorganisms (biotransformation). Here we investigated the depletion of 15 structurally diverse drugs by 25 representative strains of gut bacteria. This revealed 70 bacteria-drug interactions, 29 of which had not to our knowledge been reported before. Over half of the new interactions can be ascribed to bioaccumulation; that is, bacteria storing the drug intracellularly without chemically modifying it, and in most cases without the growth of the bacteria being affected. As a case in point, we studied the molecular basis of bioaccumulation of the widely used antidepressant duloxetine by using click chemistry, thermal proteome profiling and metabolomics. We find that duloxetine binds to several metabolic enzymes and changes the metabolite secretion of the respective bacteria. When tested in a defined microbial community of accumulators and non-accumulators, duloxetine markedly altered the composition of the community through metabolic cross-feeding. We further validated our findings in an animal model, showing that bioaccumulating bacteria attenuate the behavioural response of Caenorhabditis elegans to duloxetine. Together, our results show that bioaccumulation by gut bacteria may be a common mechanism that alters drug availability and bacterial metabolism, with implications for microbiota composition, pharmacokinetics, side effects and drug responses, probably in an individual manner.

A comprehensive overview of computational resources to aid in precision genome editing with engineered nucleases.

Genome editing with engineered nucleases (zinc finger nucleases, TAL effector nucleases s and Clustered regularly inter-spaced short palindromic repeats/CRISPR-associated) has recently been shown to have great promise in a variety of therapeutic and biotechnological applications. However, their exploitation in genetic analysis and clinical settings largely depends on their specificity for the intended genomic target. Large and complex genomes often contain highly homologous/repetitive sequences, which limits the specificity of genome editing tools and could result in off-target activity. Over the past few years, various computational approaches have been developed to assist the design process and predict/reduce the off-target activity of these nucleases. These tools could be efficiently used to guide the design of constructs for engineered nucleases and evaluate results after genome editing. This review provides a comprehensive overview of various databases, tools, web servers and resources for genome editing and compares their features and functionalities. Additionally, it also describes tools that have been developed to analyse post-genome editing results. The article also discusses important design parameters that could be considered while designing these nucleases. This review is intended to be a quick reference guide for experimentalists as well as computational biologists working in the field of genome editing with engineered nucleases.

Machine Learning Approaches Toward Building Predictive Models for Small Molecule Modulators of miRNA and Its Utility in Virtual Screening of Molecular Databases.

The ubiquitous role of microRNAs (miRNAs) in a number of pathological processes has suggested that they could act as potential drug targets. RNA-binding small molecules offer an attractive means for modulating miRNA function. The availability of bioassay data sets for a variety of biological assays and molecules in public domain provides a new opportunity toward utilizing them to create models and further utilize them for in silico virtual screening approaches to prioritize or assign potential functions for small molecules. Here, we describe a computational strategy based on machine learning for creation of predictive models from high-throughput biological screens for virtual screening of small molecules with the potential to inhibit microRNAs. Such models could be potentially used for computational prioritization of small molecules before performing high-throughput biological assay.

Comparative whole-genome analysis of clinical isolates reveals characteristic architecture of Mycobacterium tuberculosis pangenome.

The tubercle complex consists of closely related mycobacterium species which appear to be variants of a single species. Comparative genome analysis of different strains could provide useful clues and insights into the genetic diversity of the species. We integrated genome assemblies of 96 strains from Mycobacterium tuberculosis complex (MTBC), which included 8 Indian clinical isolates sequenced and assembled in this study, to understand its pangenome architecture. We predicted genes for all the 96 strains and clustered their respective CDSs into homologous gene clusters (HGCs) to reveal a hard-core, soft-core and accessory genome component of MTBC. The hard-core (HGCs shared amongst 100% of the strains) was comprised of 2,066 gene clusters whereas the soft-core (HGCs shared amongst at least 95% of the strains) comprised of 3,374 gene clusters. The change in the core and accessory genome components when observed as a function of their size revealed that MTBC has an open pangenome. We identified 74 HGCs that were absent from reference strains H37Rv and H37Ra but were present in most of clinical isolates. We report PCR validation on 9 candidate genes depicting 7 genes completely absent from H37Rv and H37Ra whereas 2 genes shared partial homology with them accounting to probable insertion and deletion events. The pangenome approach is a promising tool for studying strain specific genetic differences occurring within species. We also suggest that since selecting appropriate target genes for typing purposes requires the expected target gene be present in all isolates being typed, therefore estimating the core-component of the species becomes a subject of prime importance.

Insights into structural variations and genome rearrangements in prokaryotic genomes.

Structural variations (SVs) are genomic rearrangements that affect fairly large fragments of DNA. Most of the SVs such as inversions, deletions and translocations have been largely studied in context of genetic diseases in eukaryotes. However, recent studies demonstrate that genome rearrangements can also have profound impact on prokaryotic genomes, leading to altered cell phenotype. In contrast to single-nucleotide variations, SVs provide a much deeper insight into organization of bacterial genomes at a much better resolution. SVs can confer change in gene copy number, creation of new genes, altered gene expression and many other functional consequences. High-throughput technologies have now made it possible to explore SVs at a much refined resolution in bacterial genomes. Through this review, we aim to highlight the importance of the less explored field of SVs in prokaryotic genomes and their impact. We also discuss its potential applicability in the emerging fields of synthetic biology and genome engineering where targeted SVs could serve to create sophisticated and accurate genome editing.

Draft Genome Sequence of a Clinical Isolate of Multidrug-Resistant Mycobacterium tuberculosis East African Indian Strain OSDD271.

We describe the genome sequencing and analysis of a clinical isolate of Mycobacterium tuberculosis East African Indian (EAI) strain OSDD271 from India.

Predictive modeling of anti-malarial molecules inhibiting apicoplast formation.

BACKGROUND: Malaria is a major healthcare problem worldwide resulting in an estimated 0.65 million deaths every year. It is caused by the members of the parasite genus Plasmodium. The current therapeutic options for malaria are limited to a few classes of molecules, and are fast shrinking due to the emergence of widespread resistance to drugs in the pathogen. The recent availability of high-throughput phenotypic screen datasets for antimalarial activity offers a possibility to create computational models for bioactivity based on chemical descriptors of molecules with potential to accelerate drug discovery for malaria. RESULTS: In the present study, we have used high-throughput screen datasets for the discovery of apicoplast inhibitors of the malarial pathogen as assayed from the delayed death response. We employed machine learning approach and developed computational predictive models to predict the biological activity of new antimalarial compounds. The molecules were further evaluated for common substructures using a Maximum Common Substructure (MCS) based approach. CONCLUSIONS: We created computational models using state-of-the-art machine learning algorithms. The models were evaluated based on multiple statistical criteria. We found Random Forest based approach provides for better accuracy as assessed from ROC curve analysis. We further evaluated the active molecules using a substructure based approach to identify common substructures enriched in the active set. We argue that the computational models generated could be effectively used to screen large molecular datasets to prioritize them for phenotypic screens, drastically reducing cost while improving the hit rate.

Computational analysis and predictive modeling of small molecule modulators of microRNA.

BACKGROUND: MicroRNAs (miRNA) are small endogenously transcribed regulatory RNA which modulates gene expression at a post transcriptional level. These small RNAs have now been shown to be critical regulators in a number of biological processes in the cell including pathophysiology of diseases like cancers. The increasingly evident roles of microRNA in disease processes have also motivated attempts to target them therapeutically. Recently there has been immense interest in understanding small molecule mediated regulation of RNA, including microRNA. RESULTS: We have used publicly available datasets of high throughput screens on small molecules with potential to inhibit microRNA. We employed computational methods based on chemical descriptors and machine learning to create predictive computational models for biological activity of small molecules. We further used a substructure based approach to understand common substructures potentially contributing to the activity. CONCLUSION: We generated computational models based on Naïve Bayes and Random Forest towards mining small RNA binding molecules from large molecular datasets. We complement this with substructure based approach to identify and understand potentially enriched substructures in the active dataset. We use this approach to identify miRNA binding potential of a set of approved drugs, suggesting a probable novel mechanism of off-target activity of these drugs. To the best of our knowledge, this is the first and most comprehensive computational analysis towards understanding RNA binding activities of small molecules and predictive modeling of these activities.

Computational models for in-vitro anti-tubercular activity of molecules based on high-throughput chemical biology screening datasets.

BACKGROUND: The emergence of Multi-drug resistant tuberculosis in pandemic proportions throughout the world and the paucity of novel therapeutics for tuberculosis have re-iterated the need to accelerate the discovery of novel molecules with anti-tubercular activity. Though high-throughput screens for anti-tubercular activity are available, they are expensive, tedious and time-consuming to be performed on large scales. Thus, there remains an unmet need to prioritize the molecules that are taken up for biological screens to save on cost and time. Computational methods including Machine Learning have been widely employed to build classifiers for high-throughput virtual screens to prioritize molecules for further analysis. The availability of datasets based on high-throughput biological screens or assays in public domain makes computational methods a plausible proposition for building predictive models. In addition, this approach would save significantly on the cost, effort and time required to run high throughput screens. RESULTS: We show that by using four supervised state-of-the-art classifiers (SMO, Random Forest, Naive Bayes and J48) we are able to generate in-silico predictive models on an extremely imbalanced (minority class ratio: 0.6%) large dataset of anti-tubercular molecules with reasonable AROC (0.6-0.75) and BCR (60-66%) values. Moreover, these models are able to provide 3-4 fold enrichment over random selection. CONCLUSIONS: In the present study, we have used the data from in-vitro screens for anti-tubercular activity from a high-throughput screen available in public domain to build highly accurate classifiers based on molecular descriptors of the molecules. We show that Machine Learning tools can be used to build highly effective predictive models for virtual high-throughput screens to prioritize molecules from large molecular libraries.

De novo identification of viral pathogens from cell culture hologenomes.

BACKGROUND: Fast, specific identification and surveillance of pathogens is the cornerstone of any outbreak response system, especially in the case of emerging infectious diseases and viral epidemics. This process is generally tedious and time-consuming thus making it ineffective in traditional settings. The added complexity in these situations is the non-availability of pure isolates of pathogens as they are present as mixed genomes or hologenomes. Next-generation sequencing approaches offer an attractive solution in this scenario as it provides adequate depth of sequencing at fast and affordable costs, apart from making it possible to decipher complex interactions between genomes at a scale that was not possible before. The widespread application of next-generation sequencing in this field has been limited by the non-availability of an efficient computational pipeline to systematically analyze data to delineate pathogen genomes from mixed population of genomes or hologenomes. FINDINGS: We applied next-generation sequencing on a sample containing mixed population of genomes from an epidemic with appropriate processing and enrichment. The data was analyzed using an extensive computational pipeline involving mapping to reference genome sets and de-novo assembly. In depth analysis of the data generated revealed the presence of sequences corresponding to Japanese encephalitis virus. The genome of the virus was also independently de-novo assembled. The presence of the virus was in addition, verified using standard molecular biology techniques. CONCLUSIONS: Our approach can accurately identify causative pathogens from cell culture hologenome samples containing mixed population of genomes and in principle can be applied to patient hologenome samples without any background information. This methodology could be widely applied to identify and isolate pathogen genomes and understand their genomic variability during outbreaks.

3D-QSAR based pharmacophore modeling and virtual screening for identification of novel pteridine reductase inhibitors.

Pteridine reductase is a promising target for development of novel therapeutic agents against Trypanosomatid parasites. A 3D-QSAR pharmacophore hypothesis has been generated for a series of L. major pteridine reductase inhibitors using Catalyst/HypoGen algorithm for identification of the chemical features that are responsible for the inhibitory activity. Four pharmacophore features, namely: two H-bond donors (D), one Hydrophobic aromatic (H) and one Ring aromatic (R) have been identified as key features involved in inhibitor-PTR1 interaction. These features are able to predict the activity of external test set of pteridine reductase inhibitors with a correlation coefficient (r) of 0.80. Based on the analysis of the best hypotheses, some potent Pteridine reductase inhibitors were screened out and predicted with anti-PTR1 activity. It turned out that the newly identified inhibitory molecules are at least 300 fold more potent than the current crop of existing inhibitors. Overall the current SAR study is an effort for elucidating quantitative structure-activity relationship for the PTR1 inhibitors. The results from the combined 3D-QSAR modeling and molecular docking approach have led to the prediction of new potent inhibitory scaffolds.

Predictive models for anti-tubercular molecules using machine learning on high-throughput biological screening datasets.

BACKGROUND: Tuberculosis is a contagious disease caused by Mycobacterium tuberculosis (Mtb), affecting more than two billion people around the globe and is one of the major causes of morbidity and mortality in the developing world. Recent reports suggest that Mtb has been developing resistance to the widely used anti-tubercular drugs resulting in the emergence and spread of multi drug-resistant (MDR) and extensively drug-resistant (XDR) strains throughout the world. In view of this global epidemic, there is an urgent need to facilitate fast and efficient lead identification methodologies. Target based screening of large compound libraries has been widely used as a fast and efficient approach for lead identification, but is restricted by the knowledge about the target structure. Whole organism screens on the other hand are target-agnostic and have been now widely employed as an alternative for lead identification but they are limited by the time and cost involved in running the screens for large compound libraries. This could be possibly be circumvented by using computational approaches to prioritize molecules for screening programmes. RESULTS: We utilized physicochemical properties of compounds to train four supervised classifiers (Naïve Bayes, Random Forest, J48 and SMO) on three publicly available bioassay screens of Mtb inhibitors and validated the robustness of the predictive models using various statistical measures. CONCLUSIONS: This study is a comprehensive analysis of high-throughput bioassay data for anti-tubercular activity and the application of machine learning approaches to create target-agnostic predictive models for anti-tubercular agents.