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

Privileged small molecules against neglected tropical diseases: A perspective from structure activity relationships

Neglected tropical diseases (NTDs) comprise diverse infections with more incidence in tropical/sub-tropical areas. In spite of preventive and therapeutic achievements, NTDs are yet serious threats to the public health. Epidemiological reports of world health organization (WHO) indicate that more than 1.5 billion people are afflicted with at least one NTD type. Among NTDs, leishmaniasis, chagas disease (CD) and human African trypanosomiasis (HAT) result in substantial morbidity and death, particularly within impoverished countries. The statistical facts call for robust efforts to manage the NTDs. Currently, most of the anti-NTD drugs are engaged with drug resistance, lack of efficient vaccines, limited spectrum of pharmacological effect and adverse reactions. To circumvent the issue, numerous scientific efforts have been directed to the synthesis and pharmacological development of chemical compounds as anti-infectious agents. A survey of the anti-NTD agents reveals that the majority of them possess privileged nitrogen, sulfur and oxygen-based heterocyclic structures. In this review, recent achievements in anti-infective small molecules against parasitic NTDs are described, particularly from the SAR (Structure activity relationship) perspective. We also explore current advocating strategies to extend the scope of anti-NTD agents.

Revisiting methotrexate and phototrexate Zinc15 library-based derivatives using deep learning in-silico drug design approach

Introduction: Cancer is the second most prevalent cause of mortality in the world, despite the availability of several medications for cancer treatment. Therefore, the cancer research community emphasized on computational techniques to speed up the discovery of novel anticancer drugs. Methods: In the current study, QSAR-based virtual screening was performed on the Zinc15 compound library (271 derivatives of methotrexate (MTX) and phototrexate (PTX)) to predict their inhibitory activity against dihydrofolate reductase (DHFR), a potential anticancer drug target. The deep learning-based ADMET parameters were employed to generate a 2D QSAR model using the multiple linear regression (MPL) methods with Leave-one-out cross-validated (LOO-CV) Q2 and correlation coefficient R2 values as high as 0.77 and 0.81, respectively. Results: From the QSAR model and virtual screening analysis, the top hits (09, 27, 41, 68, 74, 85, 99, 180) exhibited pIC50 ranging from 5.85 to 7.20 with a minimum binding score of -11.6 to -11.0 kcal/mol and were subjected to further investigation. The ADMET attributes using the message-passing neural network (MPNN) model demonstrated the potential of selected hits as an oral medication based on lipophilic profile Log P (0.19-2.69) and bioavailability (76.30% to 78.46%). The clinical toxicity score was 31.24% to 35.30%, with the least toxicity score (8.30%) observed with compound 180. The DFT calculations were carried out to determine the stability, physicochemical parameters and chemical reactivity of selected compounds. The docking results were further validated by 100 ns molecular dynamic simulation analysis. Conclusion: The promising lead compounds found endorsed compared to standard reference drugs MTX and PTX that are best for anticancer activity and can lead to novel therapies after experimental validations. Furthermore, it is suggested to unveil the inhibitory potential of identified hits via in-vitro and in-vivo approaches.

Artificial intelligence in parasitic disease control: A paradigm shift in health care

Parasitic diseases, including malaria, leishmaniasis, and trypanosomiasis, continue to plague populations worldwide, particularly in resource-limited settings and disproportionately affecting vulnerable populations. It has limited the use of conventional health-care delivery and disease control approaches and necessitated exploring innovative strategies. In this direction, artificial intelligence (AI) has emerged as a transformative tool with immense promise in parasitic disease control, offering the potential for enhanced diagnostics, precision drug discovery, predictive modeling, and personalized treatment. Predictive AI algorithms have assisted in understanding parasite transmission patterns and outbreaks by analyzing vast amounts of epidemiological data, environmental factors, and population demographics. This has strengthened public health interventions, resource allocation, and outbreak preparedness strategies, enabling proactive measures to mitigate disease spread. In diagnostics, AI-enabled accurate and rapid identification of parasites by analyzing microscopic images. This capability is particularly valuable in remote regions with limited access to diagnostic facilities. AI-driven computational methods have also assisted in drug discovery for parasitic diseases by identifying novel drug targets and predicting the efficacy and safety of potential drug candidates. This approach has streamlined drug development, leading to more effective and targeted therapies. This article reviews these current developments and their transformative impacts on the health-care sector. It also assessed the hurdles that require attention before these transformations can be realized in real-life scenarios.

Regulations of malaria in children with human immunodeficiency virus infection: A review

This comprehensive review explores the intricate relationship between 2 major global health challenges, malaria and HIV, with a specific focus on their impact on children. These diseases, both endemic in sub-Saharan Africa, create a dual burden that significantly elevates the risk of morbidity and mortality, particularly in children with compromised immune systems due to HIV. The review delves into the complex mechanisms by which these infections interact, from heightened clinical malaria frequencies in HIV-infected individuals to the potential impact of antiretroviral therapy on malaria treatment. Different research engines were utilized in writing this paper such as Web of Science, Google Scholar, Pubmed Central, ResearchGate, and Academia Edu. To address this critical health concern, the study identifies and discusses various regulatory and treatment strategies. It emphasizes the importance of daily cotrimoxazole prophylaxis and insecticide-treated nets in preventing malaria in children with HIV. The potential of antiretroviral protease inhibitors and mRNA-based vaccines as innovative solutions is highlighted. Additionally, the study underscores the significance of climate data and artificial intelligence in improving diagnostics and drug development. Furthermore, the review introduces the concept of genetically modified mosquitoes as a novel approach to vector control, offering a promising avenue to protect HIV-positive individuals from mosquito-borne diseases like malaria. Through a comprehensive analysis of these strategies, the study aims to provide a foundation for policymakers, healthcare professionals, and researchers to develop effective regulations and interventions that reduce the dual burden of malaria and HIV in children, improving public health outcomes in endemic regions.

Machine learning and drug discovery for neglected tropical diseases

Neglected tropical diseases affect millions of individuals and cause loss of productivity worldwide. They are common in developing countries without the financial resources for research and drug development. With increased availability of data from high throughput screening, machine learning has been introduced into the drug discovery process. Models can be trained to predict biological activities of compounds before working in the lab. In this study, we use three publicly available, high-throughput screening datasets to train machine learning models to predict biological activities related to inhibition of species that cause leishmaniasis, American trypanosomiasis (Chagas disease), and African trypanosomiasis (sleeping sickness). We compare machine learning models (tree based models, naive Bayes classifiers, and neural networks), featurizing methods (circular fingerprints, MACCS fingerprints, and RDKit descriptors), and techniques to deal with the imbalanced data (oversampling, undersampling, class weight/sample weight).

A QSAR Study for Antileishmanial 2-Phenyl-2,3-dihydrobenzofurans †

Leishmaniasis, a parasitic disease that represents a threat to the life of millions of people around the globe, is currently lacking effective treatments. We have previously reported on the antileishmanial activity of a series of synthetic 2-phenyl-2,3-dihydrobenzofurans and some qualitative structure-activity relationships within this set of neolignan analogues. Therefore, in the present study, various quantitative structure-activity relationship (QSAR) models were created to explain and predict the antileishmanial activity of these compounds. Comparing the performance of QSAR models based on molecular descriptors and multiple linear regression, random forest, and support vector regression with models based on 3D molecular structures and their interaction fields (MIFs) with partial least squares regression, it turned out that the latter (i.e., 3D-QSAR models) were clearly superior to the former. MIF analysis for the best-performing and statistically most robust 3D-QSAR model revealed the most important structural features required for antileishmanial activity. Thus, this model can guide decision-making during further development by predicting the activity of potentially new leishmanicidal dihydrobenzofurans before synthesis.

Exploring proteasome inhibition using atomic weighted vector indices and machine learning approaches

Ubiquitin-proteasome system (UPS) is a highly regulated mechanism of intracellular protein degradation and turnover. The UPS is involved in different biological activities, such as the regulation of gene transcription and cell cycle. Several researchers have applied cheminformatics and artificial intelligence methods to study the inhibition of proteasomes, including the prediction of UPP inhibitors. Following this idea, we applied a new tool for obtaining molecular descriptors (MDs) for modeling proteasome Inhibition in terms of EC₅₀ (µmol/L), in which a set of new MDs called atomic weighted vectors (AWV) and several prediction algorithms were used in cheminformatics studies. In the manuscript, a set of descriptors based on AWV are presented as datasets for training different machine learning techniques, such as linear regression, multiple linear regression (MLR), random forest (RF), K-nearest neighbors (IBK), multi-layer perceptron, best-first search, and genetic algorithm. The results suggest that these atomic descriptors allow adequate modeling of proteasome inhibitors despite artificial intelligence techniques, as a variant to build efficient models for the prediction of inhibitory activity.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

Application and extension of the UTAUT2 model for determining behavioral intention factors in use of the artificial intelligence virtual assistants

Virtual Assistants, also known as conversational artificial intelligence, are transforming the reality around us. These virtual assistants have challenged our daily lives by assisting us in the different dimensions of our lives, such as health, entertainment, home, and education, among others. The main purpose of this study is to develop and empirically test a model to predict factors that affect users' behavioral intentions when they use intelligent virtual assistants. As a theoretical basis for investigating behavioral intention of using virtual assistants from the consumers' perspective, researchers employed the extended Unified Theory of Acceptance and Use of Technology (UTAUT2). For this research paper, seven variables were analyzed: performance expectancy, effort expectancy, facilitating conditions, social influence, hedonic motivation, habit, and price/value. In order to improve consumer behavior prediction, three additional factors were included in the study: perceived privacy risk, trust, and personal innovativeness. Researchers carried out an online survey with 304 responses. The obtained sample was analyzed with Structural Equation Modeling (SEM) through IBM SPSS V. 27.0 and AMOS V 27.0. The main study results reveal that factors, such as habit, trust, and personal innovation, have a significant impact on the adoption of virtual assistants. However, on the other side, performance expectancy, effort expectancy, facilitating conditions, social influence, hedonic motivation, price/value, and perceived privacy risk were not significant factors in the users' intention to adopt this service. This research paper examines the effect of personal innovation, security, and trust variables in relation to the use of virtual assistants. It contributes to a more holistic understanding of the adoption of these intelligent devices and tries to fill the knowledge gap on this topic, as it is an emerging technology. This investigation also provides relevant information on how to successfully implement these technologies.

Leishmaniasis and Chagas disease: Is there hope in nanotechnology to fight neglected tropical diseases?

Nanotechnology is revolutionizing many sectors of science, from food preservation to healthcare to energy applications. Since 1995, when the first nanomedicines started being commercialized, drug developers have relied on nanotechnology to improve the pharmacokinetic properties of bioactive molecules. The development of advanced nanomaterials has greatly enhanced drug discovery through improved pharmacotherapeutic effects and reduction of toxicity and side effects. Therefore, highly toxic treatments such as cancer chemotherapy, have benefited from nanotechnology. Considering the toxicity of the few therapeutic options to treat neglected tropical diseases, such as leishmaniasis and Chagas disease, nanotechnology has also been explored as a potential innovation to treat these diseases. However, despite the significant research progress over the years, the benefits of nanotechnology for both diseases are still limited to preliminary animal studies, raising the question about the clinical utility of nanomedicines in this field. From this perspective, this review aims to discuss recent nanotechnological developments, the advantages of nanoformulations over current leishmanicidal and trypanocidal drugs, limitations of nano-based drugs, and research gaps that still must be filled to make these novel drug delivery systems a reality for leishmaniasis and Chagas disease treatment.

Applied Machine Learning Toward Drug Discovery Enhancement: Leishmaniases as a Case Study

Drug discovery (DD) research is a complex field with a high attrition rate. Machine learning (ML) approaches combined to chemoinformatics are of valuable input to this field. We, herein, focused on implementing multiple ML algorithms that shall learn from different molecular fingerprints (FPs) of 65 057 molecules that have been identified as active or inactive against Leishmania major promastigotes. We sought to build a classifier able to predict whether a given molecule has the potential of being anti-leishmanial or not. Using the RDkit library, we calculated 5 molecular FPs of the molecules. Then, we implemented 4 ML algorithms that we trained and tested for their ability to classify the molecules into active/inactive classes based on their chemical structure, encoded by the molecular FPs. Best performers were random forest (RF) and support vector machine (SVM), while atom-pair and topology torsion FPs were the best embedding functions. Both models were further assessed on different stratification levels of the dataset and showed stable performances. At last, we used them to predict the potential of molecules within the Food and Drug Administration (FDA)-approved drugs collection to present anti-Leishmania effects. We ranked these drugs according to their anti-Leishmanial probability and obtained in total seven anti-Leishmania agents, previously described in the literature, within the top 10 of each model. This validates the robustness of the approach, the algorithms, and FPs choices as well as the importance of the dataset size and content. We further engaged these molecules into reverse docking experiments on 3D crystal structures of seven well-studied Leishmania drug targets and could predict the molecular targets for 4 drugs. The results bring novel insights into anti-Leishmania compounds.

Success stories of AI in drug discovery - where do things stand?

INTRODUCTION

Artificial intelligence (AI) in drug discovery and development (DDD) has gained more traction in the past few years. Many scientific reviews have already been made available in this area. Thus, in this review, the authors have focused on the success stories of AI-driven drug candidates and the scientometric analysis of the literature in this field.

AREA COVERED

The authors explore the literature to compile the success stories of AI-driven drug candidates that are currently being assessed in clinical trials or have investigational new drug (IND) status. The authors also provide the reader with their expert perspectives for future developments and their opinions on the field.

EXPERT OPINION

Partnerships between AI companies and the pharma industry are booming. The early signs of the impact of AI on DDD are encouraging, and the pharma industry is hoping for breakthroughs. AI can be a promising technology to unveil the greatest successes, but it has yet to be proven as AI is still at the embryonic stage.

Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19

As of August 6th, 2021, the World Health Organization has notified 200.8 million laboratory-confirmed infections and 4.26 million deaths from COVID-19, making it the worst pandemic since the 1918 flu. The main challenges in mitigating COVID-19 are effective vaccination, treatment, and agile containment strategies. In this review, we focus on the potential of Artificial Intelligence (AI) in COVID-19 surveillance, diagnosis, outcome prediction, drug discovery and vaccine development. With the help of big data, AI tries to mimic the cognitive capabilities of a human brain, such as problem-solving and learning abilities. Machine Learning (ML), a subset of AI, holds special promise for solving problems based on experiences gained from the curated data. Advances in AI methods have created an unprecedented opportunity for building agile surveillance systems using the deluge of real-time data generated within a short span of time. During the COVID-19 pandemic, many reports have discussed the utility of AI approaches in prioritization, delivery, surveillance, and supply chain of drugs, vaccines, and non-pharmaceutical interventions. This review will discuss the clinical utility of AI-based models and will also discuss limitations and challenges faced by AI systems, such as model generalizability, explainability, and trust as pillars for real-life deployment in healthcare.

Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19

As of August 6th, 2021, the World Health Organization has notified 200.8 million laboratory-confirmed infections and 4.26 million deaths from COVID-19, making it the worst pandemic since the 1918 flu. The main challenges in mitigating COVID-19 are effective vaccination, treatment, and agile containment strategies. In this review, we focus on the potential of Artificial Intelligence (AI) in COVID-19 surveillance, diagnosis, outcome prediction, drug discovery and vaccine development. With the help of big data, AI tries to mimic the cognitive capabilities of a human brain, such as problem-solving and learning abilities. Machine Learning (ML), a subset of AI, holds special promise for solving problems based on experiences gained from the curated data. Advances in AI methods have created an unprecedented opportunity for building agile surveillance systems using the deluge of real-time data generated within a short span of time. During the COVID-19 pandemic, many reports have discussed the utility of AI approaches in prioritization, delivery, surveillance, and supply chain of drugs, vaccines, and non-pharmaceutical interventions. This review will discuss the clinical utility of AI-based models and will also discuss limitations and challenges faced by AI systems, such as model generalizability, explainability, and trust as pillars for real-life deployment in healthcare.

Prediction of antischistosomal small molecules using machine learning in the era of big data

Schistosomiasis is a neglected tropical disease caused by helminths of the Schistosoma genus. Despite its high morbidity and socio-economic burden, therapeutics are just a handful with praziquantel being the main drug. Praziquantel is an old drug registered for human use in 1982 and has since been administered en masse for chemotherapy, risking the development of resistance, thus the need for new drugs with different mechanisms of action. This review examines the use of machine learning (ML) in this era of big data to aid in the prediction of novel antischistosomal molecules. It first discusses the challenges of drug discovery in schistosomiasis. Explanations are then offered for big data, its characteristics and then, some open databases where large biochemical data on schistosomiasis can be obtained for ML model development are examined. The concepts of artificial intelligence, ML, and deep learning and their drug applications are explored in schistosomiasis. The use of binary classification in predicting antischistosomal compounds and some algorithms that have been applied including random forest and naive Bayesian are discussed. For this review, some deep learning algorithms (deep neural networks) are proposed as novel algorithms for predicting antischistosomal molecules via binary classification. Databases specifically designed for housing bioactivity data on antischistosomal molecules enriched with functional genomic datasets and ontologies are thus urgently needed for developing predictive ML models. This shows the application of machine learning techniques for the discovery of novel antischistosomal small molecules via binary classification in the era of big data.