Data Mining Practical Machine Learning Tools and Techniques

The war on multidrug resistance (MDR) has resulted in the greatest loss to the world’s economy. Antibiotics, the bedrock, and wonder drug of the 20th century have played a central role in treating infectious diseases. However, the inappropriate, irregular, and irrational uses of antibiotics have resulted in the emergence of antimicrobial resistance. This has resulted in an increased interest in medicinal plants since 30–50% of current pharmaceuticals and nutraceuticals are plant-derived. The question we address in this review is whether plants, which produce a rich diversity of secondary metabolites, may provide novel antibiotics to tackle MDR microbes and novel chemosensitizers to reclaim currently used antibiotics that have been rendered ineffective by the MDR microbes. Plants synthesize secondary metabolites and phytochemicals and have great potential to act as therapeutics. The main focus of this mini-review is to highlight the potential benefits of plant derived multiple compounds and the importance of phytochemicals for the development of biocompatible therapeutics. In addition, this review focuses on the diverse effects and efficacy of herbal compounds in controlling the development of MDR in microbes and hopes to inspire research into unexplored plants with a view to identify novel antibiotics for global health benefits.

https://www.mdpi.com/2218-1989/9/11/258/pdf

A Comprehensive Review on Medicinal Plants as Antimicrobial Therapeutics: Potential Avenues of Biocompatible Drug Discovery.

Network pharmacology applications to map the unexplored target space and therapeutic potential of natural products

Phytochemicals of medicinal plants encompass a diverse chemical space for drug discovery. India is rich with a flora of indigenous medicinal plants that have been used for centuries in traditional Indian medicine to treat human maladies. A comprehensive online database on the phytochemistry of Indian medicinal plants will enable computational approaches towards natural product based drug discovery. In this direction, we present, IMPPAT, a manually curated database of 1742 Indian Medicinal Plants, 9596 Phytochemicals, And 1124 Therapeutic uses spanning 27074 plant-phytochemical associations and 11514 plant-therapeutic associations. Notably, the curation effort led to a non-redundant in silico library of 9596 phytochemicals with standard chemical identifiers and structure information. Using cheminformatic approaches, we have computed the physicochemical, ADMET (absorption, distribution, metabolism, excretion, toxicity) and drug-likeliness properties of the IMPPAT phytochemicals. We show that the stereochemical complexity and shape complexity of IMPPAT phytochemicals differ from libraries of commercial compounds or diversity-oriented synthesis compounds while being similar to other libraries of natural products. Within IMPPAT, we have filtered a subset of 960 potential druggable phytochemicals, of which majority have no significant similarity to existing FDA approved drugs, and thus, rendering them as good candidates for prospective drugs. IMPPAT database is openly accessible at: https://cb.imsc.res.in/imppat .

/pdf/imppat-a-curated-database-of-indian-medicinal-plants-58wbbtuwqx.pdf

IMPPAT: A curated database of Indian Medicinal Plants, Phytochemistry And Therapeutics.

Phytochemical constituents of medicinal plants encompass a diverse space of chemical scaffolds which can be used for rational design of novel drugs. India is rich with a flora of indigenous medicinal plants that have been used for centuries in traditional Indian medicine to treat human maladies. A comprehensive online database on the phytochemistry of Indian medicinal plants will enable the application of systems biology and cheminformatic approaches towards natural product based drug discovery. In this direction, we here present, IMPPAT, a manually curated database of Indian Medicinal Plants, Phytochemistry, And Therapeutics. IMPPAT contains 1742 Indian medicinal plants, 9596 phytochemicals and 1124 therapeutic uses which span across 27074 plant-phytochemical associations and 11514 plant-therapeutic associations. Notably, the curation effort led to a non-redundant in silico chemical library of 9596 phytochemicals with standard chemical identifiers and structure information. Using cheminformatic approaches, we have computed the physicochemical properties and drug-likeliness of the phytochemicals in IMPPAT which led to a filtered subset of 960 potential druggable phytochemicals. Moreover, a comparative analysis against FDA approved drugs suggests that majority of the druggable phytochemicals in IMPPAT are good candidates for novel prospective drugs as they have little or no structural similarity with existing drugs. The IMPPAT database is openly accessible at: https://www.imsc.res.in/~asamal/resources/imppat/home.

/pdf/imppat-a-curated-database-of-indian-medicinal-plants-1jgsfbxsvk.pdf

IMPPAT: A curated database of Indian Medicinal Plants, Phytochemistry And Therapeutics

https://pubs.rsc.org/en/content/getauthorversionpdf/C4NP00068D

Chemo- and bioinformatics resources for in silico drug discovery from medicinal plants beyond their traditional use: a critical review

Bio- and chemoinformatics methods are widely used for the detection of mechanisms of cancer, to search for potential drug targets and their ligands. Regulatory network analysis based on signalling pathways, and cell cycle regulation provides better understanding of diseases with multiple mechanisms of pathogenesis. We developed an approach for in silico prediction of the cytotoxic effect of chemical compounds in non-transformed and breast cancer cell lines. This approach combines the prediction of the interaction between chemical compounds and human proteins, cytotoxicity and regulatory network modelling taking into account gene expression. Application of our approach to virtual screening of libraries of commercially available compounds allowed selection of dozens of promising hits. These molecules are predicted to interact with the identified targets and exhibit cytotoxicity against breast cancer cell lines but not non-tumour human cell lines. Experimental testing of 49 selected compounds against MDA-MB-231 and MCF7 breast cancer cell lines confirmed the activity of eight compounds with IC50 values ranged from 0.8 to 50 μM. Thus, the developed approach may be applied for virtual screening for cytotoxic compounds against tumour cell lines.

Virtual screening of chemical compounds active against breast cancer cell lines based on cell cycle modelling, prediction of cytotoxicity and interaction with targets.

Varvara I. Konova

Papers

Chemo- and bioinformatics resources for in silico drug discovery from medicinal plants beyond their traditional use: a critical review

Virtual screening of chemical compounds active against breast cancer cell lines based on cell cycle modelling, prediction of cytotoxicity and interaction with targets.