Cheminformatic models based on machine learning for pyruvate kinase inhibitors of Leishmania mexicana

Salma Jamal,Vinod Scaria

doi:10.1186/1471-2105-14-329

Abstract

BackgroundLeishmaniasis is a neglected tropical disease which affects approx. 12 million individuals worldwide and caused by parasite Leishmania. The current drugs used in the treatment of Leishmaniasis are highly toxic and has seen widespread emergence of drug resistant strains which necessitates the need for the development of new therapeutic options. The high throughput screen data available has made it possible to generate computational predictive models which have the ability to assess the active scaffolds in a chemical library followed by its ADME/toxicity properties in the biological trials.ResultsIn the present study, we have used publicly available, high-throughput screen datasets of chemical moieties which have been adjudged to target the pyruvate kinase enzyme of L. mexicana (LmPK). The machine learning approach was used to create computational models capable of predicting the biological activity of novel antileishmanial compounds. Further, we evaluated the molecules using the substructure based approach to identify the common substructures contributing to their activity.ConclusionWe generated computational models based on machine learning methods and evaluated the performance of these models based on various statistical figures of merit. Random forest based approach was determined to be the most sensitive, better accuracy as well as ROC. We further added a substructure based approach to analyze the molecules to identify potentially enriched substructures in the active dataset. We believe that the models developed in the present study would lead to reduction in cost and length of clinical studies and hence newer drugs would appear faster in the market providing better healthcare options to the patients.

Highlights

Leishmaniasis is a neglected tropical disease which affects approx. 12 million individuals worldwide and caused by parasite Leishmania
We evaluated the models based on the Receiver Operating Characteristic (ROC) curve which is the plot between the true positive rate and false positive rate
The standard classifiers were used to generate the models, cost sensitive classification was used in case of models having low False Positives (FP) rate and the cost was increased for FP up to 20%

Summary

Introduction

Leishmaniasis is a neglected tropical disease which affects approx. 12 million individuals worldwide and caused by parasite Leishmania. Leishmaniasis is a tropical disease affecting 12 million people worldwide, with approximately ~2 million (1.5 million incidences of cutaneous leishmaniasis and 500,000 visceral leishmaniasis) new people getting infected each year [1]. It is considered as one of the world’s most neglected disease given its strong association with poverty and limited resources invested in new tools for diagnosis, treatment, and control [2]. Leishmaniasis ranks second as a causative factor in mortality and fourth in morbidity and has been reported to occur in as much as 88 countries. The disease is considered as a major constraint to economic development with symptoms ranging from self-healing ulcers to highly disfiguring lesions and serious, often lethal visceral diseases which affect the haemopoetic organs [10]

Methods

Results

Conclusion