Artificial Neural Network Methods Applied to Drug Discovery for Neglected Diseases

Abstract

Among the chemometric tools used in rational drug design, we find artificial neural network methods (ANNs), a statistical learning algorithm similar to the human brain, to be quite powerful. Some ANN applications use biological and molecular data of the training series that are inserted to ensure the machine learning, and to generate robust and predictive models. In drug discovery, researchers use this methodology, looking to find new chemotherapeutic agents for various diseases. The neglected diseases are a group of tropical parasitic diseases that primarily affect poor countries in Africa, Asia, and South America. Current drugs against these diseases cause side effects, are ineffective during the chronic stages of the disease, and are often not available to the needy population, have relative high toxicity, and face developing resistance. Faced with so many problems, new chemotherapeutic agents to treat these infections are much needed. The present review reports on neural network research, which studies new ligands against Chagas' disease, sleeping sickness, malaria, tuberculosis, and leishmaniasis; a few of the neglected diseases.

Use of Artificial Intelligence and Machine Learning for Discovery of Drugs for Neglected Tropical Diseases

“…One of the main reasons for the current intense interest in deep learning methods is because they offer a potential solution to an important, long-standing problem in the QSAR field, how to objectively generate new, efficient, interpretable molecular descriptors for training models (Winkler and Le, 2017). Given the advantages these ML modelling methods provide, they are being increasingly used to design, discover, and optimize drugs for NTDs (Scotti et al, 2015). In particular, the application of these computational techniques to discover drugs for malaria, tuberculosis, trypanosomiasis, and leishmaniasis has been reviewed by Njogu et al (2016), for leishmaniasis and trypanosomiasis by Halder et al (2020), and for tuberculosis by van Wijk et al (2020) Case Studies Using AI and ML to Discover New Drugs for NTDs…”

Roles of Virtual Screening and Molecular Dynamics Simulations in Discovering and Understanding Antimalarial Drugs

“…In the end, it was determined that model 3, consisting of 7 descriptors and internal and external accuracies of 0.96 and 0.92, respectively, was the best model out of the 5 that were initially generated [74]. ANN and other ML techniques have also been applied to other compound sca used to target malaria [80,81]. However, with the current state of research for this tro disease, it is evident that more studies utilizing AI and ML tools are needed to inc the information available for antimalarial compounds and potentially enhance the bility of these methods in malaria drug discovery research.…”

“…However, with the current state of research for this tro disease, it is evident that more studies utilizing AI and ML tools are needed to inc the information available for antimalarial compounds and potentially enhance the bility of these methods in malaria drug discovery research. ANN and other ML techniques have also been applied to other compound scaffolds used to target malaria [80,81]. However, with the current state of research for this tropical disease, it is evident that more studies utilizing AI and ML tools are needed to increase the information available for antimalarial compounds and potentially enhance the reliability of these methods in malaria drug discovery research.…”

Artificial intelligence and machine learning in Leishmania drug discovery

“…Of these, nine research articles, ten reviews, and one editorial from 18 sources, the journal Current Topics in Medicinal Chemistry was the only one that submitted more than one document (three documents). Finally, all the documents found, after excluding the repeated ones, were as follows: [4,[21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39]. After reading the abstracts, the articles presented in Table 1 were selected.…”