QSAR Modeling for Multi-Target Drug Discovery: Designing Simultaneous Inhibitors of Proteins in Diverse Pathogenic Parasites

Abstract

Parasitic diseases remain as unresolved health issues worldwide. While for some parasites the treatments involve drug combinations with serious side effects, for others, chemical therapies are inefficient due to the emergence of drug resistance. This urges the search for novel antiparasitic agents able to act through multiple mechanisms of action. Here, we report the first multi-target model based on quantitative structure-activity relationships and a multilayer perceptron neural network (mt-QSAR-MLP) to virtually design and predict versatile inhibitors of proteins involved in the survival and/or infectivity of different pathogenic parasites. The mt-QSAR-MLP model exhibited high accuracy (>80%) in both training and test sets for the classification/prediction of protein inhibitors. Several fragments were directly extracted from the physicochemical and structural interpretations of the molecular descriptors in the mt-QSAR-MLP model. Such interpretations enabled the generation of four molecules that were predicted as multi-target inhibitors against at least three of the five parasitic proteins reported here with two of the molecules being predicted to inhibit all the proteins. Docking calculations converged with the mt-QSAR-MLP model regarding the multi-target profile of the designed molecules. The designed molecules exhibited drug-like properties, complying with Lipinski’s rule of five, as well as Ghose’s filter and Veber’s guidelines.

In Silico Drug Repurposing for Anti-Inflammatory Therapy: Virtual Search for Dual Inhibitors of Caspase-1 and TNF-Alpha

“…Therefore, we calculated a series of topological indices that fused chemical and biological information. To do so, we employed an adaptation of the Box-Jenkins approach, which is the key of the PTML modeling philosophy and for which great successful applications in different research areas have been reported in the scientific literature [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 55 , 56 , 57 ]. In the first step of this approach, we used the following mathematical formula: …”

“…Particularly, as depicted in Table 1 , the purpose here was to build an mtc-QSAR-MLP model to predict the inhibitory activity of a molecule under eight different experimental conditions. As mentioned in the previous section, such a capability of simultaneously predicting complex biological endpoints under dissimilar experimental conditions is an intrinsic characteristic of any PTML model [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 55 , 56 , 57 ].…”

“…This comes from the fact that the PTML models can integrate different kinds of chemical and biological data, and in doing so, they can simultaneously predict multiple biological endpoints (activity, toxicity, and/or pharmacokinetic properties) against many different targets (e.g., proteins, microorganisms, cell lines, laboratory animals, and/or humans), and by considering diverse assay protocols. As a result, PTML models have had great success in therapeutic areas such as infectious diseases [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ], cancer [ 36 , 37 , 38 , 39 ], and neurological disorders [ 40 , 41 , 42 , 43 ].…”

An Overview on Target-Based Drug Design against Kinetoplastid Protozoan Infections: Human African Trypanosomiasis, Chagas Disease and Leishmaniases

“…A new protocol called mt-QSAR-MLP uses QSAR for the application of multi-target drug discovery against parasitic diseases and aims to predict inhibitors that target proteins of various parasites, simultaneously. This protocol afforded derivatives, e.g., compound 37 that successfully inhibit DHFR-TS, as well as enzymes of other parasites [ 96 ].…”

Multi-Target In Silico Prediction of Inhibitors for Mitogen-Activated Protein Kinase-Interacting Kinases

“…ebi.ac.uk/chembl/, accessed on 7 June 2021) comprises a total of 1892 compounds with activity estimated against MNKs under different experimental conditions (c j ). The latter are better expressed as an ontology [10][11][12][13] of the form c j → (b t , m e , a t ), that is, by defining them according to the following elements: b t -the 'biological target', accounting for the specific MNK enzyme isoform against which the compounds have been tested, m e -the kind of 'measures of biological effects' considered, namely, half-maximal inhibitory concentration (IC 50 ), inhibition (K i ) or dissociation (K d ) constants, and a t -the 'assay type', focusing on either the binding affinity (B) or functional (F) responses. As such, each data-point of the input dataset pertains to one specific combination of the elements b t , m e , and a t or experimental condition c j , and then classified into two categories: positive (IAc j = +1; for high inhibitory potential) or negative (IAc j = −1; for low inhibitory potential).…”