DeepMalaria: Artificial Intelligence Driven Discovery of Potent Antiplasmodials

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.

MAIP: An Open-Source Tool to Enrich High-Throughput Screening Output and Identify Novel, Druglike Molecules with Antimalarial Activity

Efforts to tackle malaria must continue for a disease that threatens half of the global population. Parasite resistance to current therapies requires new chemotypes that are able to demonstrate effectiveness and safety. Previously, we developed a machine-learning-based approach to predict compound antimalarial activity, which was trained on the compound collections of several organizations. The resulting prediction platform, MAIP, was made freely available to the scientific community and offers a solution to prioritize molecules of interest in virtual screening and hit-to-lead optimization. Here, we experimentally validate MAIP and demonstrate how the approach was used in combination with a robust compound selection workflow and a recently introduced innovative high-throughput screening (HTS) cascade to select and purchase compounds from a public library for subsequent experimental screening. We observed a 12-fold enrichment compared with a randomly selected set of molecules, and the eight hits we ultimately selected exhibit good potency and absorption, distribution, metabolism, and excretion (ADME) profiles.

Machine Learning Approaches Identify Chemical Features for Stage-Specific Antimalarial Compounds

Efficacy data from diverse chemical libraries, screened against the various stages of the malaria parasite Plasmodium falciparum, including asexual blood stage (ABS) parasites and transmissible gametocytes, serve as a valuable reservoir of information on the chemical space of compounds that are either active (or not) against the parasite. We postulated that this data can be mined to define chemical features associated with the sole ABS activity and/or those that provide additional life cycle activity profiles like gametocytocidal activity. Additionally, this information could provide chemical features associated with inactive compounds, which could eliminate any future unnecessary screening of similar chemical analogs. Therefore, we aimed to use machine learning to identify the chemical space associated with stage-specific antimalarial activity. We collected data from various chemical libraries that were screened against the asexual (126 374 compounds) and sexual (gametocyte) stages of the parasite (93 941 compounds), calculated the compounds' molecular fingerprints, and trained machine learning models to recognize stage-specific active and inactive compounds. We were able to build several models that predict compound activity against ABS and dual activity against ABS and gametocytes, with Support Vector Machines (SVM) showing superior abilities with high recall (90 and 66%) and low false-positive predictions (15 and 1%). This allowed the identification of chemical features enriched in active and inactive populations, an important outcome that could be mined for essential chemical features to streamline hit-to-lead optimization strategies of antimalarial candidates. The predictive capabilities of the models held true in diverse chemical spaces, indicating that the ML models are therefore robust and can serve as a prioritization tool to drive and guide phenotypic screening and medicinal chemistry programs.

Molecular Descriptors Property Prediction Using Transformer-Based Approach

In this study, we introduce semi-supervised machine learning models designed to predict molecular properties. Our model employs a two-stage approach, involving pre-training and fine-tuning. Particularly, our model leverages a substantial amount of labeled and unlabeled data consisting of SMILES strings, a text representation system for molecules. During the pre-training stage, our model capitalizes on the Masked Language Model, which is widely used in natural language processing, for learning molecular chemical space representations. During the fine-tuning stage, our model is trained on a smaller labeled dataset to tackle specific downstream tasks, such as classification or regression. Preliminary results indicate that our model demonstrates comparable performance to state-of-the-art models on the chosen downstream tasks from MoleculeNet. Additionally, to reduce the computational overhead, we propose a new approach taking advantage of 3D compound structures for calculating the attention score used in the end-to-end transformer model to predict anti-malaria drug candidates. The results show that using the proposed attention score, our end-to-end model is able to have comparable performance with pre-trained models.

Structure-Based Optimization of Protease-Inhibitor Interactions to Enhance Specificity of Human Stefin-A against Falcipain-2 from the Plasmodium falciparum 3D7 Strain

The emergence of resistance in Plasmodium falciparum to frontline artemisinin-based combination therapies has raised global concerns and emphasized the identification of new drug targets for malaria. Cysteine protease falcipain-2 (FP2), involved in host hemoglobin degradation and instrumental in parasite survival, has long been proposed as a promising malarial drug target. However, designing active-site-targeted small-molecule inhibitors of FP2 becomes challenging due to their off-target specificity toward highly homologous human cysteine cathepsins. The use of proteinaceous inhibitors, which have nonconserved exosite interactions and larger interface area, can effectively circumvent this problem. In this study, we report for the first time that human stefin-A (STFA) efficiently inhibits FP2 with K_i values in the nanomolar range. The FP2-STFA complex crystal structure, determined in this study, and sequence analyses identify a unique nonconserved exosite interaction, compared to human cathepsins. Designing a mutation Lys68 > Arg in STFA amplifies its selectivity garnering a 3.3-fold lower K_i value against FP2, and the crystal structure of the FP2-STFAK68R complex shows stronger electrostatic interaction between side-chains of Arg68 (STFAK68R) and Asp109 (FP2). Comparative structural analyses and molecular dynamics (MD) simulation studies of the complexes further confirm higher buried surface areas, better interaction energies for FP2-STFAK68R, and consistency of the newly developed electrostatic interaction (STFA-R68-FP2-D109) in the MD trajectory. The STFA-K68R mutant also shows higher K_i values against human cathepsin-L and stefin, a step toward eliminating off-target specificity. Hence, this work underlines the design of host-based proteinaceous inhibitors against FP2, with further optimization to render them more potent and selective.

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.

Towards identification and development of alternative vaccines against pregnancy-associated malaria based on naturally acquired immunity

Pregnant women are particularly susceptible to Plasmodium falciparum malaria, leading to substantial maternal and infant morbidity and mortality. While highly effective malaria vaccines are considered an essential component towards malaria elimination, strides towards development of vaccines for pregnant women have been minimal. The leading malaria vaccine, RTS,S/AS01, has modest efficacy in children suggesting that it needs to be strengthened and optimized if it is to be beneficial for pregnant women. Clinical trials against pregnancy-associated malaria (PAM) focused on the classical VAR2CSA antigen are ongoing. However, additional antigens have not been identified to supplement these initiatives despite the new evidence that VAR2CSA is not the only molecule involved in pregnancy-associated naturally acquired immunity. This is mainly due to a lack of understanding of the immune complexities in pregnancy coupled with difficulties associated with expression of malaria recombinant proteins, low antigen immunogenicity in humans, and the anticipated complications in conducting and implementing a vaccine to protect pregnant women. With the accelerated evolution of molecular technologies catapulted by the global pandemic, identification of novel alternative vaccine antigens is timely and feasible. In this review, we discuss approaches towards novel antigen discovery to support PAM vaccine studies.

Artificial Intelligence-Based Data-Driven Strategy to Accelerate Research, Development, and Clinical Trials of COVID Vaccine

The global COVID-19 (coronavirus disease 2019) pandemic, which was caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has resulted in a significant loss of human life around the world. The SARS-CoV-2 has caused significant problems to medical systems and healthcare facilities due to its unexpected global expansion. Despite all of the efforts, developing effective treatments, diagnostic techniques, and vaccinations for this unique virus is a top priority and takes a long time. However, the foremost step in vaccine development is to identify possible antigens for a vaccine. The traditional method was time taking, but after the breakthrough technology of reverse vaccinology (RV) was introduced in 2000, it drastically lowers the time needed to detect antigens ranging from 5-15 years to 1-2 years. The different RV tools work based on machine learning (ML) and artificial intelligence (AI). Models based on AI and ML have shown promising solutions in accelerating the discovery and optimization of new antivirals or effective vaccine candidates. In the present scenario, AI has been extensively used for drug and vaccine research against SARS-COV-2 therapy discovery. This is more useful for the identification of potential existing drugs with inhibitory human coronavirus by using different datasets. The AI tools and computational approaches have led to speedy research and the development of a vaccine to fight against the coronavirus. Therefore, this paper suggests the role of artificial intelligence in the field of clinical trials of vaccines and clinical practices using different tools.

Exploring predictive frameworks for malaria in Burundi

In Burundi, malaria infection has been increasing in the last decade despite efforts to increase access to health services, and several intervention programs. The use of heterogeneous data can help to build predictive models of malaria cases. We built predictive frameworks: the generalized linear model (GLM), and artificial neural network (ANN), to predict malaria cases in four sub-groups and the overall general population. Descriptive results showed that more than half of malaria infections are observed in pregnant women and children under 5 years, with high burden to children between 12 and 59 months. Modelling results showed that, ANN model performed better in predicting total cases compared to GLM. Both model frameworks showed that education rates and Insecticide Treated Bed Nets (ITNs) had decreasing effects on malaria cases, some other variables had an increasing effect. Thus, malaria control and prevention interventions program are encouraged to understand those variables, and take appropriate measures such as providing ITNs, sensitization in schools and the communities, starting within high dense communities, among others. Early prediction of cases can provide timely information needed to be proactive for intervention strategies, and it can help to mitigate the epidemics and reduce its impact on populations and the economy.

Title: A Comprehensive Review on Classifying Fast-acting and Slow-acting Antimalarial Agents Based on Time of Action and Target Organelle of Plasmodium sp

The clinical resistance towards malarial parasites has rendered many antimalarials ineffective, likely due to a lack of understanding of time of action and stage specificity of all life stages. Therefore, to tackle this problem a more incisive comprehensive analysis of the fast and slow-acting profile of antimalarial agents relating to parasite time-kill kinetics and the target organelle on the progression of blood-stage parasites was carried out. It is evident from numerous findings that drugs targeting food vacuole, nuclear components, and endoplasmic reticulum mainly exhibit a fast-killing phenotype within 24h affecting first-cycle activity. Whereas drugs targeting mitochondria, apicoplast, microtubules, parasite invasion and egress exhibit a largely slow-killing phenotype within 96-120h, affecting second-cycle activity with few exemptions as moderately fast-killing. It is essential to understand the susceptibility of drugs on rings, trophozoites, schizonts, merozoites, and the appearance of organelle at each stage of 48h intraerythrocytic parasite cycle. Therefore, these parameters may facilitate the paradigm for understanding the timing of antimalarials action in deciphering its precise mechanism linked with time. Thus, classifying drugs based on the time of killing may promote designing new combination regimens against varied strains of P. falciparum and evaluating potential clinical resistance.

Machine Learning and Its Applications for Protozoal Pathogens and Protozoal Infectious Diseases

In recent years, massive attention has been attracted to the development and application of machine learning (ML) in the field of infectious diseases, not only serving as a catalyst for academic studies but also as a key means of detecting pathogenic microorganisms, implementing public health surveillance, exploring host-pathogen interactions, discovering drug and vaccine candidates, and so forth. These applications also include the management of infectious diseases caused by protozoal pathogens, such as Plasmodium, Trypanosoma, Toxoplasma, Cryptosporidium, and Giardia, a class of fatal or life-threatening causative agents capable of infecting humans and a wide range of animals. With the reduction of computational cost, availability of effective ML algorithms, popularization of ML tools, and accumulation of high-throughput data, it is possible to implement the integration of ML applications into increasing scientific research related to protozoal infection. Here, we will present a brief overview of important concepts in ML serving as background knowledge, with a focus on basic workflows, popular algorithms (e.g., support vector machine, random forest, and neural networks), feature extraction and selection, and model evaluation metrics. We will then review current ML applications and major advances concerning protozoal pathogens and protozoal infectious diseases through combination with correlative biology expertise and provide forward-looking insights for perspectives and opportunities in future advances in ML techniques in this field.

Target-Based Virtual Screening of Natural Compounds Identifies a Potent Antimalarial With Selective Falcipain-2 Inhibitory Activity

We employed a comprehensive approach of target-based virtual high-throughput screening to find potential hits from the ZINC database of natural compounds against cysteine proteases falcipain-2 and falcipain-3 (FP2 and FP3). Molecular docking studies showed the initial hits showing high binding affinity and specificity toward FP2 were selected. Furthermore, the enzyme inhibition and surface plasmon resonance assays were performed which resulted in a compound ZINC12900664 (ST72) with potent inhibitory effects on purified FP2. ST72 exhibited strong growth inhibition of chloroquine-sensitive (3D7; EC₅₀ = 2.8 µM) and chloroquine-resistant (RKL-9; EC₅₀ = 6.7 µM) strains of Plasmodium falciparum. Stage-specific inhibition assays revealed a delayed and growth defect during parasite growth and development in parasites treated with ST72. Furthermore, ST72 significantly reduced parasite load and increased host survival in a murine model infected with Plasmodium berghei ANKA. No Evans blue staining in ST72 treatment indicated that ST72 mediated protection of blood–brain barrier integrity in mice infected with P. berghei. ST72 did not show any significant hemolysis or cytotoxicity against human HepG2 cells suggesting a good safety profile. Importantly, ST72 with CQ resulted in improved growth inhibitory activity than individual drugs in both in vitro and in vivo studies.

MolData, a molecular benchmark for disease and target based machine learning

Deep learning’s automatic feature extraction has been a revolutionary addition to computational drug discovery, infusing both the capabilities of learning abstract features and discovering complex molecular patterns via learning from molecular data. Since biological and chemical knowledge are necessary for overcoming the challenges of data curation, balancing, training, and evaluation, it is important for databases to contain information regarding the exact target and disease of each bioassay. The existing depositories such as PubChem or ChEMBL offer the screening data for millions of molecules against a variety of cells and targets, however, their bioassays contain complex biological descriptions which can hinder their usage by the machine learning community. In this work, a comprehensive disease and target-based dataset is collected from PubChem in order to facilitate and accelerate molecular machine learning for better drug discovery. MolData is one the largest efforts to date for democratizing the molecular machine learning, with roughly 170 million drug screening results from 1.4 million unique molecules assigned to specific diseases and targets. It also provides 30 unique categories of targets and diseases. Correlation analysis of the MolData bioassays unveils valuable information for drug repurposing for multiple diseases including cancer, metabolic disorders, and infectious diseases. Finally, we provide a benchmark of more than 30 models trained on each category using multitask learning. MolData aims to pave the way for computational drug discovery and accelerate the advancement of molecular artificial intelligence in a practical manner. The MolData benchmark data is available at https://GitHub.com/Transilico/MolData as well as within the additional files.

Systematic review on the application of machine learning to quantitative structure-activity relationship modeling against Plasmodium falciparum

Malaria accounts for over two million deaths globally. To flatten this curve, there is a need to develop new and high potent drugs against Plasmodium falciparum. Some major challenges include the dearth of suitable animal models for anti-P. falciparum assays, resistance to first-line drugs, lack of vaccines and the complex life cycle of Plasmodium. Gladly, newer approaches to antimalarial drug discovery have emerged due to the release of large datasets by pharmaceutical companies. This review provides insights into these new approaches to drug discovery covering different machine learning tools, which enhance the development of new compounds. It provides a systematic review on the use and prospects of machine learning in predicting, classifying and clustering IC₅₀ values of bioactive compounds against P. falciparum. The authors identified many machine learning tools yet to be applied for this purpose. However, Random Forest and Support Vector Machines have been extensively applied though on a limited dataset of compounds.

The potential applications of artificial intelligence in drug discovery and development

Development of a new dug is a very lengthy and highly expensive process since only preclinical, pharmacokinetic, pharmacodynamic and toxicological studies include a multiple of in silico, in vitro, in vivo experimentations that traditionally last several years. In the present review, we briefly report some examples that demonstrate the power of the computer-assisted drug discovery process with some examples that are published and revealing the successful applications of artificial intelligence (AI) technology on this vivid area. Besides, we address the situation of drug repositioning (repurposing) in clinical applications. Yet few success stories in this regard that provide us with a clear evidence that AI will reveal its great potential in accelerating effective new drug finding. AI accelerates drug repurposing and AI approaches are altogether necessary and inevitable tools in new medicine development. In spite of the fact that AI in drug development is still in its infancy, the advancements in AI and machine-learning (ML) algorithms have an unprecedented potential. The AI/ML solutions driven by pharmaceutical scientists, computer scientists, statisticians, physicians and others are increasingly working together in the processes of drug development and are adopting AI-based technologies for the rapid discovery of medicines. AI approaches, coupled with big data, are expected to substantially improve the effectiveness of drug repurposing and finding new drugs for various complex human diseases.

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

The discovery and development of drugs is a long and expensive process with a high attrition rate. Computational drug discovery contributes to ligand discovery and optimization, by using models that describe the properties of ligands and their interactions with biological targets. In recent years, artificial intelligence (AI) has made remarkable modeling progress, driven by new algorithms and by the increase in computing power and storage capacities, which allow the processing of large amounts of data in a short time. This review provides the current state of the art of AI methods applied to drug discovery, with a focus on structure- and ligand-based virtual screening, library design and high-throughput analysis, drug repurposing and drug sensitivity, de novo design, chemical reactions and synthetic accessibility, ADMET, and quantum mechanics.

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.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

Investigation of REFINED CNN ensemble learning for anti-cancer drug sensitivity prediction

Motivation

Anti-cancer drug sensitivity prediction using deep learning models for individual cell line is a significant challenge in personalized medicine. Recently developed REFINED (REpresentation of Features as Images with NEighborhood Dependencies) CNN (Convolutional Neural Network)-based models have shown promising results in improving drug sensitivity prediction. The primary idea behind REFINED-CNN is representing high dimensional vectors as compact images with spatial correlations that can benefit from CNN architectures. However, the mapping from a high dimensional vector to a compact 2D image depends on the a priori choice of the distance metric and projection scheme with limited empirical procedures guiding these choices.

Results

In this article, we consider an ensemble of REFINED-CNN built under different choices of distance metrics and/or projection schemes that can improve upon a single projection based REFINED-CNN model. Results, illustrated using NCI60 and NCI-ALMANAC databases, demonstrate that the ensemble approaches can provide significant improvement in prediction performance as compared to individual models. We also develop the theoretical framework for combining different distance metrics to arrive at a single 2D mapping. Results demonstrated that distance-averaged REFINED-CNN produced comparable performance as obtained from stacking REFINED-CNN ensemble but with significantly lower computational cost.

Availability and implementation

The source code, scripts, and data used in the paper have been deposited in GitHub (https://github.com/omidbazgirTTU/IntegratedREFINED).

Supplementary information

Supplementary data are available at Bioinformatics online.

Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action

The rapid development of antimalarial resistance motivates the continued search for novel compounds with a mode of action (MoA) different to current antimalarials. Phenotypic screening has delivered thousands of promising hit compounds without prior knowledge of the compounds’ exact target or MoA. Whilst the latter is not initially required to progress a compound in a medicinal chemistry program, identifying the MoA early can accelerate hit prioritization, hit-to-lead optimization and preclinical combination studies in malaria research. The effects of drug treatment on a cell can be observed on systems level in changes in the transcriptome, proteome and metabolome. Machine learning (ML) algorithms are powerful tools able to deconvolute such complex chemically-induced transcriptional signatures to identify pathways on which a compound act and in this manner provide an indication of the MoA of a compound. In this study, we assessed different ML approaches for their ability to stratify antimalarial compounds based on varied chemically-induced transcriptional responses. We developed a rational gene selection approach that could identify predictive features for MoA to train and generate ML models. The best performing model could stratify compounds with similar MoA with a classification accuracy of 76.6 ± 6.4%. Moreover, only a limited set of 50 biomarkers was required to stratify compounds with similar MoA and define chemo-transcriptomic fingerprints for each compound. These fingerprints were unique for each compound and compounds with similar targets/MoA clustered together. The ML model was specific and sensitive enough to group new compounds into MoAs associated with their predicted target and was robust enough to be extended to also generate chemo-transcriptomic fingerprints for additional life cycle stages like immature gametocytes. This work therefore contributes a new strategy to rapidly, specifically and sensitively indicate the MoA of compounds based on chemo-transcriptomic fingerprints and holds promise to accelerate antimalarial drug discovery programs.

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

Neglected tropical diseases continue to create high levels of morbidity and mortality in a sizeable fraction of the world’s population, despite ongoing research into new treatments. Some of the most important technological developments that have accelerated drug discovery for diseases of affluent countries have not flowed down to neglected tropical disease drug discovery. Pharmaceutical development business models, cost of developing new drug treatments and subsequent costs to patients, and accessibility of technologies to scientists in most of the affected countries are some of the reasons for this low uptake and slow development relative to that for common diseases in developed countries. Computational methods are starting to make significant inroads into discovery of drugs for neglected tropical diseases due to the increasing availability of large databases that can be used to train ML models, increasing accuracy of these methods, lower entry barrier for researchers, and widespread availability of public domain machine learning codes. Here, the application of artificial intelligence, largely the subset called machine learning, to modelling and prediction of biological activities and discovery of new drugs for neglected tropical diseases is summarized. The pathways for the development of machine learning methods in the short to medium term and the use of other artificial intelligence methods for drug discovery is discussed. The current roadblocks to, and likely impacts of, synergistic new technological developments on the use of ML methods for neglected tropical disease drug discovery in the future are also discussed.

Exploring Heteroaromatic Rings as a Replacement for the Labile Amide of Antiplasmodial Pantothenamides

Malaria-causing Plasmodium parasites are developing resistance to antimalarial drugs, providing the impetus for new antiplasmodials. Although pantothenamides show potent antiplasmodial activity, hydrolysis by pantetheinases/vanins present in blood rapidly inactivates them. We herein report the facile synthesis and biological activity of a small library of pantothenamide analogues in which the labile amide group is replaced with a heteroaromatic ring. Several of these analogues display nanomolar antiplasmodial activity against Plasmodium falciparum and/or Plasmodium knowlesi, and are stable in the presence of pantetheinase. Both a known triazole and a novel isoxazole derivative were further characterized and found to possess high selectivity indices, medium or high Caco-2 permeability, and medium or low microsomal clearance in vitro. Although they fail to suppress Plasmodium berghei proliferation in vivo, the pharmacokinetic and contact time data presented provide a benchmark for the compound profile likely required to achieve antiplasmodial activity in mice and should facilitate lead optimization.

Artificial Intelligence Applied to the Rapid Identification of New Antimalarial Candidates with Dual-Stage Activity

Increasing reports of multidrug-resistant malaria parasites urge the discovery of new effective drugs with different chemical scaffolds. Protein kinases play a key role in many cellular processes such as signal transduction and cell division, making them interesting targets in many diseases. Protein kinase 7 (PK7) is an orphan kinase from the Plasmodium genus, essential for the sporogonic cycle of these parasites. Here, we applied a robust and integrative artificial intelligence-assisted virtual-screening (VS) approach using shape-based and machine learning models to identify new potential PK7 inhibitors with in vitro antiplasmodial activity. Eight virtual hits were experimentally evaluated, and compound LabMol-167 inhibited ookinete conversion of Plasmodium berghei and blood stages of Plasmodium falciparum at nanomolar concentrations with low cytotoxicity in mammalian cells. As PK7 does not have an essential role in the Plasmodium blood stage and our virtual screening strategy aimed for both PK7 and blood-stage inhibition, we conducted an in silico target fishing approach and propose that this compound might also inhibit P. falciparum PK5, acting as a possible dual-target inhibitor. Finally, docking studies of LabMol-167 with P. falciparum PK7 and PK5 proteins highlighted key interactions for further hit-to lead optimization.

Artificial intelligence in medicine and the disclosure of risks

This paper focuses on the use of 'black box' AI in medicine and asks whether the physician needs to disclose to patients that even the best AI comes with the risks of cyberattacks, systematic bias, and a particular type of mismatch between AI's implicit assumptions and an individual patient's background situation. Pace current clinical practice, I argue that, under certain circumstances, these risks do need to be disclosed. Otherwise, the physician either vitiates a patient's informed consent or violates a more general obligation to warn him about potentially harmful consequences. To support this view, I argue, first, that the already widely accepted conditions in the evaluation of risks, i.e. the 'nature' and 'likelihood' of risks, speak in favour of disclosure and, second, that principled objections against the disclosure of these risks do not withstand scrutiny. Moreover, I also explain that these risks are exacerbated by pandemics like the COVID-19 crisis, which further emphasises their significance.

Artificial Intelligence for COVID-19 Drug Discovery and Vaccine Development

SARS-COV-2 has roused the scientific community with a call to action to combat the growing pandemic. At the time of this writing, there are as yet no novel antiviral agents or approved vaccines available for deployment as a frontline defense. Understanding the pathobiology of COVID-19 could aid scientists in their discovery of potent antivirals by elucidating unexplored viral pathways. One method for accomplishing this is the leveraging of computational methods to discover new candidate drugs and vaccines in silico. In the last decade, machine learning-based models, trained on specific biomolecules, have offered inexpensive and rapid implementation methods for the discovery of effective viral therapies. Given a target biomolecule, these models are capable of predicting inhibitor candidates in a structural-based manner. If enough data are presented to a model, it can aid the search for a drug or vaccine candidate by identifying patterns within the data. In this review, we focus on the recent advances of COVID-19 drug and vaccine development using artificial intelligence and the potential of intelligent training for the discovery of COVID-19 therapeutics. To facilitate applications of deep learning for SARS-COV-2, we highlight multiple molecular targets of COVID-19, inhibition of which may increase patient survival. Moreover, we present CoronaDB-AI, a dataset of compounds, peptides, and epitopes discovered either in silico or in vitro that can be potentially used for training models in order to extract COVID-19 treatment. The information and datasets provided in this review can be used to train deep learning-based models and accelerate the discovery of effective viral therapies.

Updated pharmacokinetic considerations for the use of antimalarial drugs in pregnant women

INTRODUCTION

The association between pregnancy and altered drug pharmacokinetic (PK) properties is acknowledged, as is its impact on drug plasma concentrations and thus therapeutic efficacy. However, there have been few robust PK studies of antimalarial use in pregnancy. Given that inadequate dosing for prevention or treatment of malaria in pregnancy can result in negative maternal/infant outcomes, along with the potential to select for parasite drug resistance, it is imperative that reliable pregnancy-specific dosing recommendations are established.

AREAS COVERED

PK studies of antimalarial drugs in pregnancy. The present review summarizes the efficacy and PK properties of WHO-recommended therapies used in pregnancy, with a focus on PK studies published since 2014.

EXPERT OPINION

Changes in antimalarial drug disposition in pregnancy are well described, yet pregnant women continue to receive treatment regimens optimized for non-pregnant adults. Contemporary in silico modeling has recently identified a series of alternative dosing regimens that are predicted to provide optimal therapeutic efficacy for pregnant women.

TranScreen: Transfer Learning on Graph-Based Anti-Cancer Virtual Screening Model

Deep learning’s automatic feature extraction has proven its superior performance over traditional fingerprint-based features in the implementation of virtual screening models. However, these models face multiple challenges in the field of early drug discovery, such as over-training and generalization to unseen data, due to the inherently unbalanced and small datasets. In this work, the TranScreen pipeline is proposed, which utilizes transfer learning and a collection of weight initializations to overcome these challenges. An amount of 182 graph convolutional neural networks are trained on molecular source datasets and the learned knowledge is transferred to the target task for fine-tuning. The target task of p53-based bioactivity prediction, an important factor for anti-cancer discovery, is chosen to showcase the capability of the pipeline. Having trained a collection of source models, three different approaches are implemented to compare and rank them for a given task before fine-tuning. The results show improvement in performance of the model in multiple cases, with the best model increasing the area under receiver operating curve ROC-AUC from 0.75 to 0.91 and the recall from 0.25 to 1. This improvement is vital for practical virtual screening via lowering the false negatives and demonstrates the potential of transfer learning. The code and pre-trained models are made accessible online.