In Silico and In Vitro Approach for Validating the Inhibition of Matrix Metalloproteinase-9 by Quercetin.

PURPOSE: To validate the mechanism and inhibitory activity of quercetin against matrix metalloproteinase-9 (MMP-9) using a hybrid in silico and in vitro approach. METHODS: The structure of MMP-9 was obtained from the Protein Data Bank, and the active site was identified using previous annotations from the Universal Protein Resource. The structure of quercetin was obtained from ZINC15. Molecular docking was performed to quantify the binding affinity of quercetin to the active site of MMP-9. The inhibitory effect of various concentrations of quercetin (0.0025, 0.025, 0.25, 1.0, and 1.5 mM) on MMP-9 was quantified using a commercially available fluorometric assay. The cytotoxicity of quercetin to immortalized human corneal epithelial cells (HCECs) was quantified by obtaining the metabolic activities of the cells exposed to various concentrations of quercetin for 24 hr. RESULTS: Quercetin interacts with MMP-9 by binding within the active site pocket and interacting with residues LEU 188, ALA 189, GLU 227, and MET 247. The binding affinity predicted by molecular docking was -9.9 kcal/mol. All concentrations of quercetin demonstrated significant inhibition of MMP-9 enzyme activity (all P <0.03). There was little to no reduction of HCEC metabolic activity after a 24-hr exposure to all concentrations of quercetin ( P >0.99). CONCLUSIONS: Quercetin inhibited MMP-9 in a dose-dependent manner and was well-tolerated by HCECs, suggesting a potential role in therapy for diseases with upregulated MMP-9 as part of its pathogenesis.

Investigating the Theranostic Potential of Graphene Quantum Dots in Alzheimer's Disease.

Alzheimer's disease (AD) is one of the leading causes of death worldwide, with no definitive diagnosis or known cure. The aggregation of Tau protein into neurofibrillary tangles (NFTs), which contain straight filaments (SFs) and paired helical filaments (PHFs), is a major hallmark of AD. Graphene quantum dots (GQDs) are a type of nanomaterial that combat many of the small-molecule therapeutic challenges in AD and have shown promise in similar pathologies. In this study, two sizes of GQDs, GQD7 and GQD28, were docked to various forms of Tau monomers, SFs, and PHFs. From the favorable docked poses, we simulated each system for at least 300 ns and calculated the free energies of binding. We observed a clear preference for GQD28 in the PHF6 (306VQIVYK311) pathological hexapeptide region of monomeric Tau, while GQD7 targeted both the PHF6 and PHF6* (275VQIINK280) pathological hexapeptide regions. In SFs, GQD28 had a high affinity for a binding site that is available in AD but not in other common tauopathies, while GQD7 behaved promiscuously. In PHFs, GQD28 interacted strongly near the protofibril interface at the putative disaggregation site for epigallocatechin-3-gallate, and GQD7 largely interacted with PHF6. Our analyses revealed several key GQD binding sites that may be used for detecting, preventing, and disassembling the Tau aggregates in AD.

Cardiac Late Sodium Channel Current Is a Molecular Target for the Sodium/Glucose Cotransporter 2 Inhibitor Empagliflozin.

BACKGROUND: SGLT2 (sodium/glucose cotransporter 2) inhibitors exert robust cardioprotective effects against heart failure in patients with diabetes, and there is intense interest to identify the underlying molecular mechanisms that afford this protection. Because the induction of the late component of the cardiac sodium channel current (late-INa) is involved in the etiology of heart failure, we investigated whether these drugs inhibit late-INa. METHODS: Electrophysiological, in silico molecular docking, molecular, calcium imaging, and whole heart perfusion techniques were used to address this question. RESULTS: The SGLT2 inhibitor empagliflozin reduced late-INa in cardiomyocytes from mice with heart failure and in cardiac Nav1.5 sodium channels containing the long QT syndrome 3 mutations R1623Q or ΔKPQ. Empagliflozin, dapagliflozin, and canagliflozin are all potent and selective inhibitors of H2O2-induced late-INa (half maximal inhibitory concentration = 0.79, 0.58, and 1.26 µM, respectively) with little effect on peak sodium current. In mouse cardiomyocytes, empagliflozin reduced the incidence of spontaneous calcium transients induced by the late-INa activator veratridine in a similar manner to tetrodotoxin, ranolazine, and lidocaine. The putative binding sites for empagliflozin within Nav1.5 were investigated by simulations of empagliflozin docking to a three-dimensional homology model of human Nav1.5 and point mutagenic approaches. Our results indicate that empagliflozin binds to Nav1.5 in the same region as local anesthetics and ranolazine. In an acute model of myocardial injury, perfusion of isolated mouse hearts with empagliflozin or tetrodotoxin prevented activation of the cardiac NLRP3 (nuclear-binding domain-like receptor 3) inflammasome and improved functional recovery after ischemia. CONCLUSIONS: Our results provide evidence that late-INa may be an important molecular target in the heart for the SGLT2 inhibitors, contributing to their unexpected cardioprotective effects.

PoseFilter: a PyMOL plugin for filtering and analyzing small molecule docking in symmetric binding sites.

SUMMARY: 'PoseFilter' is a PyMOL plugin that assists in analyses and filtering of docked poses. PoseFilter enables automatic detection of symmetric poses from docking outputs and can be accessed using both graphical user interface and command-line options within the PyMOL program. Two methods of analyses, root mean square deviations and interaction fingerprints, are available from this plugin. The capabilities of the plugin are demonstrated using docking outputs from different oligomeric protein-ligand complexes. AVAILABILITY AND IMPLEMENTATION: The plugin can be downloaded from the GitHub page, https://github.com/skalyaanamoorthy/PoseFilter. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

ModelFinder: fast model selection for accurate phylogenetic estimates.

Model-based molecular phylogenetics plays an important role in comparisons of genomic data, and model selection is a key step in all such analyses. We present ModelFinder, a fast model-selection method that greatly improves the accuracy of phylogenetic estimates by incorporating a model of rate heterogeneity across sites not previously considered in this context and by allowing concurrent searches of model space and tree space.

Development of Safe Drugs: The hERG Challenge.

Drug-induced blockade of human ether-a-go-go-related gene (hERG) remains a major impediment in delivering safe drugs to the market. Several drugs have been withdrawn from the market due to their severe cardiotoxic side effects triggered by their off-target interactions with hERG. Thus, identifying the potential hERG blockers at early stages of lead discovery is fast evolving as a standard in drug design and development. A number of in silico structure-based models of hERG have been developed as a low-cost solution to evaluate drugs for hERG liability, and it is now agreed that the hERG blockers bind at the large central cavity of the channel. Nevertheless, there is no clear convergence on the appropriate drug binding modes against the channel. The proposed binding modes differ in their orientations and interpretations on the role of key residues in the channel. Such ambiguities in the modes of binding remain to be a significant challenge in achieving efficient computational predictive models and in saving many important already Food and Drug Administration approved drugs. In this review, we discuss the spectrum of reported binding modes for hERG blockers, the various in silico models developed for predicting a drug's affinity to hERG, and the known successful optimization strategies to avoid off-target interactions with hERG.

Energy based pharmacophore mapping of HDAC inhibitors against class I HDAC enzymes.

Histone deacetylases (HDACs) are important class of enzymes that deacetylate the ε-amino group of the lysine residues in the histone tails to form a closed chromatin configuration resulting in the regulation of gene expression. Inhibition of these HDACs enzymes have been identified as one of the promising approaches for cancer treatment. The type-specific inhibition of class I HDAC enzymes is known to elicit improved therapeutic effects and thus, the search for promising type-specific HDAC inhibitors compunds remains an ongoing research interest in cancer drug discovery. Several different strategies are eployed to identify the features that could identify the isoform specificity factors in these HDAC enzymes. This study combines the insilico docking and energy-optomized pharmacophore (e-pharmacophore) mapping of several known HDACi's to identify the structural variants that are significant for the interactions against each of the four class I HDAC enzymes. Our hybrid approach shows that all the inhibitors with at least one aromatic ring in their linker regions hold higher affinities against target enzymes, while those without any aromatic rings remain as poor binders. We hypothesize the e-pharmacophore models for the HDACi's against all the four Class I HDAC enzymes which are not reported elsewhere. The results from this work will be useful in the rational design and virtual screening of more isoform specific HDACi's against the class I HDAC family of proteins.

A steered molecular dynamics mediated hit discovery for histone deacetylases.

The inhibitors of class I histone deacetylases (HDACIs) have gained significant interest in cancer therapeutics. Virtual high throughput screening (vHTS) is one of the popular approaches used in the identification of novel scaffolds of HDACIs. However, an accurate description of ligand-protein flexibilities in the vHTS remains challenging. In this work, we implement an integrated approach, which combines the vHTS with the 'state-of-the-art' steered molecular dynamics (SMD). This approach serves as an efficient tool to identify potential hits and characterize their binding potencies against the class I HDACs in a flexible solvent environment. A hybrid pharmacophore-based and structure-based vHTS method identifies the hits with more favourable physico-chemical features against the class I HDACs. Our pharmacophore-based screening enhanced the quality of the vHTS outcomes. Further, the molecular interactions between the hits and the HDACs are investigated using the SMD-driven force profiles, which in turn resulted in filtering the hits with higher binding potencies against the HDACs. Our results, therefore, reveal that vHTS and SMD can be a complementary and effective analytical tool for accelerating the hit identification phase in structure-based drug design.

Post-Translational Modifications in Tau and Their Roles in Alzheimer's Pathology.

Microtubule-Associated Protein Tau (also known as tau) has been shown to accumulate into paired helical filaments and neurofibrillary tangles, which are known hallmarks of Alzheimer's disease (AD) pathology. Decades of research have shown that tau protein undergoes extensive post-translational modifications (PTMs), which can alter the protein's structure, function, and dynamics and impact the various properties such as solubility, aggregation, localization, and homeostasis. There is a vast amount of information describing the impact and role of different PTMs in AD pathology and neuroprotection. However, the complex interplay between these PTMs remains elusive. Therefore, in this review, we aim to comprehend the key post-translational modifications occurring in tau and summarize potential connections to clarify their impact on the physiology and pathophysiology of tau. Further, we describe how different computational modeling methods have helped in understanding the impact of PTMs on the structure and functions of the tau protein. Finally, we highlight the tau PTM-related therapeutics strategies that are explored for the development of AD therapy.

Allosteric inhibition of tRNA synthetase Gln4 by N-pyrimidinyl-ß-thiophenylacrylamides exerts highly selective antifungal activity.

Candida species are among the most prevalent causes of systemic fungal infections, which account for ∼1.5 million annual fatalities. Here, we build on a compound screen that identified the molecule N-pyrimidinyl-ß-thiophenylacrylamide (NP-BTA), which strongly inhibits Candida albicans growth. NP-BTA was hypothesized to target C. albicans glutaminyl-tRNA synthetase, Gln4. Here, we confirmed through in vitro amino-acylation assays NP-BTA is a potent inhibitor of Gln4, and we defined how NP-BTA arrests Gln4's transferase activity using co-crystallography. This analysis also uncovered Met496 as a critical residue for the compound's species-selective target engagement and potency. Structure-activity relationship (SAR) studies demonstrated the NP-BTA scaffold is subject to oxidative and non-oxidative metabolism, making it unsuitable for systemic administration. In a mouse dermatomycosis model, however, topical application of the compound provided significant therapeutic benefit. This work expands the repertoire of antifungal protein synthesis target mechanisms and provides a path to develop Gln4 inhibitors.

Ligand release mechanisms and channels in histone deacetylases.

Exploring the molecular channels of class I histone deacetylases (HDACs) with buried active sites are important to understand their structures and functionalities. In this work, we perform hybrid classical molecular dynamics and random acceleration molecular dynamics simulations to explore the B3N [i.e., (4-(dimethylamino)N-[7(hydroxyamino)-7-oxoheptyle] benzamide)] exit channels in the x-ray crystal structures of HDAC3 and HDAC8 enzymes. Our simulations identify B3N release through four different channels in HDAC3 (denoted as A1, A2, B1, and B2) and HDAC8 (referred as A1, B1, B2, and B3) enzymes, among which egression through channel A1 is more predominant in both the enzymes. This mechanism is similar to ligand release in HDAC1 and HDAC2 described in our previous study and can be the fingerprint ligand release mechanisms in class I HDACs. Ligand release events through B channels, on the other hand, are different among HDAC3 and HDAC8, highlighting the significances of substituted residues in controlling the access to these channels This study reveals a novel aromatic gating mechanism elicited by TYR154-TRP141-TYR111 that controls the B3N access to all the B channels in HDAC8. The TRP141 in HDAC8 is substituted by LEU133 in HDAC3, which do not hinder the access to B channels in HDAC3. However, two hydrogen bonded barricades formed as ARG28-GLY297-GLY295-GLY131 and TRP129-ARG28-ALA130-LEU29-TRP129 obstruct the B3N from exploring the B channels in HDAC3. The structural and dynamical characterizations of molecular channels and ligand unbinding mechanisms reported in this study provide novel structural insights and atomic level perspectives on HDAC3 and HDAC8 enzymes, thereby potentially aiding in the design of more specific HDAC inhibitors.

Sequence- and structure-specific RNA oligonucleotide binding attenuates heterogeneous nuclear ribonucleoprotein A1 dysfunction.

The RNA binding protein heterogeneous nuclear ribonucleoprotein A1 (A1) regulates RNA metabolism, which is crucial to maintaining cellular homeostasis. A1 dysfunction mechanistically contributes to reduced cell viability and loss, but molecular mechanisms of how A1 dysfunction affects cell viability and loss, and methodologies to attenuate its dysfunction, are lacking. Utilizing in silico molecular modeling and an in vitro optogenetic system, this study examined the consequences of RNA oligonucleotide (RNAO) treatment on attenuating A1 dysfunction and its downstream cellular effects. In silico and thermal shift experiments revealed that binding of RNAOs to the RNA Recognition Motif 1 of A1 is stabilized by sequence- and structure-specific RNAO-A1 interactions. Using optogenetics to model A1 cellular dysfunction, we show that sequence- and structure-specific RNAOs significantly attenuated abnormal cytoplasmic A1 self-association kinetics and A1 cytoplasmic clustering. Downstream of A1 dysfunction, we demonstrate that A1 clustering affects the formation of stress granules, activates cell stress, and inhibits protein translation. With RNAO treatment, we show that stress granule formation is attenuated, cell stress is inhibited, and protein translation is restored. This study provides evidence that sequence- and structure-specific RNAO treatment attenuates A1 dysfunction and its downstream effects, thus allowing for the development of A1-specific therapies that attenuate A1 dysfunction and restore cellular homeostasis.

Comparative Proteomics Analysis of Growth-Primed Adult Dorsal Root Ganglia Reveals Key Molecular Mediators for Peripheral Nerve Regeneration.

Injuries to peripheral nerves are frequent, yet no drug therapies are available for effective nerve repair. The slow growth rate of axons and inadequate access to growth factors challenge natural repair of nerves. A better understanding of the molecules that can promote the rate of axon growth may reveal therapeutic opportunities. Molecular profiling of injured neurons at early intervals of injury, when regeneration is at the maximum, has been the gold standard for exploring growth promoters. A complementary in vitro regenerative priming model was recently shown to induce enhanced outgrowth in adult sensory neurons. In this work, we exploited the in vitro priming model to reveal novel candidates for adult nerve regeneration. We performed a whole-tissue proteomics analysis of the in vitro primed dorsal root ganglia (DRGs) from adult SD rats and compared their molecular profile with that of the in vivo primed, and control DRGs. The proteomics data generated are available via ProteomeXchange with identifier PXD031927. From the follow-up analysis, Bioinformatics interventions, and literature curation, we identified several molecules that were differentially expressed in the primed DRGs with a potential to modulate adult nerve regrowth. We then validated the growth promoting roles of mesencephalic astrocyte-derived neurotrophic factor (MANF), one of the hits we identified, in adult rat sensory neurons. Overall, in this study, we explored two growth priming paradigm and shortlisted several candidates, and validated MANF, as potential targets for adult nerve regeneration. We also demonstrate that the in vitro priming model is a valid tool for adult nerve regeneration studies.

The H163A mutation unravels an oxidized conformation of the SARS-CoV-2 main protease.

The main protease of SARS-CoV-2 (Mpro) is an important target for developing COVID-19 therapeutics. Recent work has highlighted Mpro's susceptibility to undergo redox-associated conformational changes in response to cellular and immune-system-induced oxidation. Despite structural evidence indicating large-scale rearrangements upon oxidation, the mechanisms of conformational change and its functional consequences are poorly understood. Here, we present the crystal structure of an Mpro point mutant (H163A) that shows an oxidized conformation with the catalytic cysteine in a disulfide bond. We hypothesize that Mpro adopts this conformation under oxidative stress to protect against over-oxidation. Our metadynamics simulations illustrate a potential mechanism by which H163 modulates this transition and suggest that this equilibrium exists in the wild type enzyme. We show that other point mutations also significantly shift the equilibrium towards this state by altering conformational free energies. Unique avenues of SARS-CoV-2 research can be explored by understanding how H163 modulates this equilibrium.

Design and Development of COX-II Inhibitors: Current Scenario and Future Perspective.

Innate inflammation beyond a threshold is a significant problem involved in cardiovascular diseases, cancer, and many other chronic conditions. Cyclooxygenase (COX) enzymes are key inflammatory markers as they catalyze prostaglandins production and are crucial for inflammation processes. While COX-I is constitutively expressed and is generally involved in "housekeeping" roles, the expression of the COX-II isoform is induced by the stimulation of different inflammatory cytokines and also promotes the further generation of pro-inflammatory cytokines and chemokines, which affect the prognosis of various diseases. Hence, COX-II is considered an important therapeutic target for drug development against inflammation-related illnesses. Several selective COX-II inhibitors with safe gastric safety profiles features that do not cause gastrointestinal complications associated with classic anti-inflammatory drugs have been developed. Nevertheless, there is mounting evidence of cardiovascular side effects from COX-II inhibitors that resulted in the withdrawal of market-approved anti-COX-II drugs. This necessitates the development of COX-II inhibitors that not only exhibit inhibit potency but also are free of side effects. Probing the scaffold diversity of known inhibitors is vital to achieving this goal. A systematic review and discussion on the scaffold diversity of COX inhibitors are still limited. To address this gap, herein we present an overview of chemical structures and inhibitory activity of different scaffolds of known COX-II inhibitors. The insights from this article could be helpful in seeding the development of next-generation COX-II inhibitors.

Exploring inhibitor release pathways in histone deacetylases using random acceleration molecular dynamics simulations.

Molecular channel exploration perseveres to be the prominent solution for eliciting structure and accessibility of active site and other internal spaces of macromolecules. The volume and silhouette characterization of these channels provides answers for the issues of substrate access and ligand swapping between the obscured active site and the exterior of the protein. Histone deacetylases (HDACs) are metal-dependent enzymes that are involved in the cell growth, cell cycle regulation, and progression, and their deregulations have been linked with different types of cancers. Hence HDACs, especially the class I family, are widely recognized as the important cancer targets, and the characterizations of their structures and functions have been of special interest in cancer drug discovery. The class I HDACs are known to possess two different protein channels, an 11 Å and a 14 Å (named channels A and B1, respectively), of which the former is a ligand or substrate occupying tunnel that leads to the buried active site zinc ion and the latter is speculated to be involved in product release. In this work, we have carried out random acceleration molecular dynamics (RAMD) simulations coupled with the classical molecular dynamics to explore the release of the ligand, N-(2-aminophenyl) benzamide (LLX) from the active sites of the recently solved X-ray crystal structure of HDAC2 and the computationally modeled HDAC1 proteins. The RAMD simulations identified significant structural and dynamic features of the HDAC channels, especially the key 'gate-keeping' amino acid residues that control these channels and the ligand release events. Further, this study identified a novel and unique channel B2, a subchannel from channel B1, in the HDAC1 protein structure. The roles of water molecules in the LLX release from the HDAC1 and HDAC2 enzymes are also discussed. Such structural and dynamic properties of the HDAC protein channels that govern the ligand escape reactions will provide further mechanistic insights into the HDAC enzymes, which, in the long run, have a potential to bring new ideas for developing more promising HDAC inhibitors as well as extend our atomic level understandings on their mechanisms of action.

Structure-based virtual screening, molecular dynamics and binding affinity calculations of some potential phytocompounds against SARS-CoV-2.

COVID-19 caused by a positive-sense single stranded RNA virus named as severe acute respiratory syndrome-Coronavirus-2 (SARS-CoV-2) triggered the global pandemic. This virus has infected about 10.37 Crores and taken lives of 2.24 Crores people of 213 countries to date. To cope-up this emergency clinical trials are undergoing with some existing drugs like remdesivir, flavipiravir, lopinavir-ritonavir, nafamostat, doxycycline, hydroxy-chloroquine, dexamethasone, etc., despite their severe toxicity and health hazards among diabetics, hypertensive, cardiac patients or normal individuals. The lack of safe and approved treatment for COVID-19 has forced the scientific community to find novel and safe compounds with potential efficacy. This study evaluates a few selective herbal compounds like glucoraphanin, vitexin, niazinin, etc., as a potential inhibitor of the spike protein and 3-chymotrypsin-like protease (3CLpro) or main protease (Mpro) of SARS-COV-2 through in-silico virtual studies such as molecular docking, target analysis, toxicity prediction and ADME prediction and supported by a Molecular-Dynamic simulation. Selective phytocompounds were docked successfully in the binding site of spike glycoprotein and 3CLpro (Mpro) of SARS-CoV-2. In-silico approaches also predict this molecule to have good solubility, pharmacodynamic property and target accuracy through MD simulation and ADME studies. These hit molecules niazinin, vitexin, glucoraphanin also obey Lipinski's rule along with their stable binding towards target protein of the virus, which makes them suitable for further biochemical and cell-based assays followed by clinical investigations to highlight their potential use in COVID-19 treatment.Communicated by Ramaswamy H. Sarma.

Engineering stable carbonic anhydrases for CO2 capture: a critical review.

Targeted inhibition of misregulated protein-protein interactions (PPIs) has been a promising area of investigation in drug discovery and development for human diseases. However, many constraints remain, including shallow binding surfaces and dynamic conformation changes upon interaction. A particularly challenging aspect is the undesirable off-target effects caused by inherent structural similarity among the protein families. To tackle this problem, phage display has been used to engineer PPIs for high-specificity binders with improved binding affinity and greatly reduced undesirable interactions with closely related proteins. Although general steps of phage display are standardized, library design is highly variable depending on experimental contexts. Here in this review, we examined recent advances in the structure-based combinatorial library design and the advantages and limitations of different approaches. The strategies described here can be explored for other protein-protein interactions and aid in designing new libraries or improving on previous libraries.

TRPV1 channels as a newly identified target for vitamin D.

Vitamin D is known to elicit many biological effects in diverse tissue types and is thought to act almost exclusively upon its canonical receptor within the nucleus, leading to gene transcriptional changes and the subsequent cellular response. However, not all the observed effects of vitamin D can be attributed to this sole mechanism, and other cellular targets likely exist but remain to be identified. Our recent discovery that vitamin D is a partial agonist of the Transient Receptor Potential Vanilloid family 1 (TRPV1) channel may provide new insights as to how this important vitamin exerts its biological effects either independently or in addition to the nuclear vitamin D receptor. In this review, we discuss the literature surrounding this apparent discrepancy in vitamin D signaling and compare vitamin D with known TRPV1 ligands with respect to their binding to TRPV1. Furthermore, we provide evidence supporting the notion that this novel vitamin D/TRPV1 axis may explain some of the beneficial actions of this vitamin in disease states where TRPV1 expression and vitamin D deficiency are known to overlap. Finally, we discuss whether vitamin D may also act on other members of the TRP family of ion channels.

GPCR_LigandClassify.py; a rigorous machine learning classifier for GPCR targeting compounds.

The current study describes the construction of various ligand-based machine learning models to be used for drug-repurposing against the family of G-Protein Coupled Receptors (GPCRs). In building these models, we collected > 500,000 data points, encompassing experimentally measured molecular association data of > 160,000 unique ligands against > 250 GPCRs. These data points were retrieved from the GPCR-Ligand Association (GLASS) database. We have used diverse molecular featurization methods to describe the input molecules. Multiple supervised ML algorithms were developed, tested and compared for their accuracy, F scores, as well as for their Matthews' correlation coefficient scores (MCC). Our data suggest that combined with molecular fingerprinting, ensemble decision trees and gradient boosted trees ML algorithms are on the accuracy border of the rather sophisticated deep neural nets (DNNs)-based algorithms. On a test dataset, these models displayed an excellent performance, reaching a ~ 90% classification accuracy. Additionally, we showcase a few examples where our models were able to identify interesting connections between known drugs from the Drug-Bank database and members of the GPCR family of receptors. Our findings are in excellent agreement with previously reported experimental observations in the literature. We hope the models presented in this paper synergize with the currently ongoing interest of applying machine learning modeling in the field of drug repurposing and computational drug discovery in general.