Machine Learning for Discovery of GSK3β Inhibitors

New Advances in the Pharmacology and Toxicology of Lithium: A Neurobiologically Oriented Overview

Over the last six decades, lithium has been considered the gold standard treatment for the long-term management of bipolar disorder due to its efficacy in preventing both manic and depressive episodes as well as suicidal behaviors. Nevertheless, despite numerous observed effects on various cellular pathways and biologic systems, the precise mechanism through which lithium stabilizes mood remains elusive. Furthermore, there is recent support for the therapeutic potential of lithium in other brain diseases. This review offers a comprehensive examination of contemporary understanding and predominant theories concerning the diverse mechanisms underlying lithium's effects. These findings are based on investigations utilizing cellular and animal models of neurodegenerative and psychiatric disorders. Recent studies have provided additional support for the significance of glycogen synthase kinase-3 (GSK3) inhibition as a crucial mechanism. Furthermore, research has shed more light on the interconnections between GSK3-mediated neuroprotective, antioxidant, and neuroplasticity processes. Moreover, recent advancements in animal and human models have provided valuable insights into how lithium-induced modifications at the homeostatic synaptic plasticity level may play a pivotal role in its clinical effectiveness. We focused on findings from translational studies suggesting that lithium may interface with microRNA expression. Finally, we are exploring the repurposing potential of lithium beyond bipolar disorder. These recent findings on the therapeutic mechanisms of lithium have provided important clues toward developing predictive models of response to lithium treatment and identifying new biologic targets. SIGNIFICANCE STATEMENT: Lithium is the drug of choice for the treatment of bipolar disorder, but its mechanism of action in stabilizing mood remains elusive. This review presents the latest evidence on lithium's various mechanisms of action. Recent evidence has strengthened glycogen synthase kinase-3 (GSK3) inhibition, changes at the level of homeostatic synaptic plasticity, and regulation of microRNA expression as key mechanisms, providing an intriguing perspective that may help bridge the mechanistic gap between molecular functions and its clinical efficacy as a mood stabilizer.

Machine learning in Alzheimer's disease drug discovery and target identification

Alzheimer's disease (AD) stands as a formidable neurodegenerative ailment that poses a substantial threat to the elderly population, with no known curative or disease-slowing drugs in existence. Among the vital and time-consuming stages in the drug discovery process, disease modeling and target identification hold particular significance. Disease modeling allows for a deeper comprehension of disease progression mechanisms and potential therapeutic avenues. On the other hand, target identification serves as the foundational step in drug development, exerting a profound influence on all subsequent phases and ultimately determining the success rate of drug development endeavors. Machine learning (ML) techniques have ushered in transformative breakthroughs in the realm of target discovery. Leveraging the strengths of large dataset analysis, multifaceted data processing, and the exploration of intricate biological mechanisms, ML has become instrumental in the quest for effective AD treatments. In this comprehensive review, we offer an account of how ML methodologies are being deployed in the pursuit of drug discovery for AD. Furthermore, we provide an overview of the utilization of ML in uncovering potential intervention strategies and prospective therapeutic targets for AD. Finally, we discuss the principal challenges and limitations currently faced by these approaches. We also explore the avenues for future research that hold promise in addressing these challenges.

New insights into glycogen synthase kinase-3: A common target for neurodegenerative diseases

Glycogen synthase kinase 3 (GSK-3) is a highly conserved protein serine/threonine kinase that plays a central role in a wide variety of cellular processes to coordinate catabolic and anabolic pathways and regulate cell growth and fate. There is increasing evidence showing that abnormal glycogen synthase kinase 3 (GSK-3) is associated with the pathogenesis and progression of many disorders, such as cancer, diabetes, psychiatric diseases, and neurodegenerative diseases. In this review, we summarize recent findings about the regulatory role of GSK-3 in the occurrence and development of multiple neurodegenerative diseases, mainly focusing on Alzheimer's disease, Parkinson's disease, and amyotrophic lateral sclerosis. The aim of this study is to provide new insight into the shared working mechanism of GSK-3 as a therapeutic target of multiple neurodegenerative diseases.

Artificial intelligence for dementia drug discovery and trials optimization

Drug discovery and clinical trial design for dementia have historically been challenging. In part these challenges have arisen from patient heterogeneity, length of disease course, and the tractability of a target for the brain. Applying big data analytics and machine learning tools for drug discovery and utilizing them to inform successful clinical trial design has the potential to accelerate progress. Opportunities arise at multiple stages in the therapy pipeline and the growing availability of large medical data sets opens possibilities for big data analyses to answer key questions in clinical and therapeutic challenges. However, before this goal is reached, several challenges need to be overcome and only a multi-disciplinary approach can promote data-driven decision-making to its full potential. Herein we review the current state of machine learning applications to clinical trial design and drug discovery, while presenting opportunities and recommendations that can break down the barriers to implementation.

Discovery of imidazole-based GSK-3 inhibitors for transdifferentiation of human mesenchymal stem cells to neurons: A potential single-molecule neurotherapeutic foresight

The transdifferentiation of human mesenchymal stem cells (hMSC) to functional neurons is crucial for the development of future neuro-regenerative therapeutics. Currently, transdifferentiation of hMSCs to neurons requires a "chemical cocktail" along with neural growth factors. The role of the individual molecules present in a "chemical cocktail" is poorly understood and may cause unwanted toxicity or adverse effects. Toward, this goal, we have showcased the discovery of an imidazole-based "single-molecule" transdifferentiation initiator SG-145C. This discovery was achieved via screening of a small molecule library through extensive in silico studies to shortlist the best-fitting molecules. This discovery evolved through a careful selection to target Glycogen synthase kinase-3β (GSK-3β), which is one of the important proteins responsible for neurogenesis. Rigorous computational experiments, as well as extensive biological assays, confirmed that SG-145C has significant potential to transdifferentiate hMSCs to neurons. Interestingly, our results suggest that SG-145C can inhibit the proteasomal degradation of phosphorylated β-catenin, in turn promoting transdifferentiation of hMSCs into neurons via the Wnt pathway.

The Commoditization of AI for Molecule Design

Anyone involved in designing or finding molecules in the life sciences over the past few years has witnessed a dramatic change in how we now work due to the COVID-19 pandemic. Computational technologies like artificial intelligence (AI) seemed to become ubiquitous in 2020 and have been increasingly applied as scientists worked from home and were separated from the laboratory and their colleagues. This shift may be more permanent as the future of molecule design across different industries will increasingly require machine learning models for design and optimization of molecules as they become "designed by AI". AI and machine learning has essentially become a commodity within the pharmaceutical industry. This perspective will briefly describe our personal opinions of how machine learning has evolved and is being applied to model different molecule properties that crosses industries in their utility and ultimately suggests the potential for tight integration of AI into equipment and automated experimental pipelines. It will also describe how many groups have implemented generative models covering different architectures, for de novo design of molecules. We also highlight some of the companies at the forefront of using AI to demonstrate how machine learning has impacted and influenced our work. Finally, we will peer into the future and suggest some of the areas that represent the most interesting technologies that may shape the future of molecule design, highlighting how we can help increase the efficiency of the design-make-test cycle which is currently a major focus across industries.

KUALA: a machine learning-driven framework for kinase inhibitors repositioning

The family of protein kinases comprises more than 500 genes involved in numerous functions. Hence, their physiological dysfunction has paved the way toward drug discovery for cancer, cardiovascular, and inflammatory diseases. As a matter of fact, Kinase binding sites high similarity has a double role. On the one hand it is a critical issue for selectivity, on the other hand, according to poly-pharmacology, a synergistic controlled effect on more than one target could be of great pharmacological interest. Another important aspect of binding similarity is the possibility of exploit it for repositioning of drugs on targets of the same family. In this study, we propose our approach called Kinase drUgs mAchine Learning frAmework (KUALA) to automatically identify kinase active ligands by using specific sets of molecular descriptors and provide a multi-target priority score and a repurposing threshold to suggest the best repurposable and non-repurposable molecules. The comprehensive list of all kinase-ligand pairs and their scores can be found at https://github.com/molinfrimed/multi-kinases .

In-silico discovery of inhibitors against human papillomavirus E1 protein

High-risk (HR) Human papillomavirus (e.g. HPV16 and HPV18) causes approximately two-thirds of all cervical cancers in women. Although the first and second-generation vaccines confer some protection against individuals, there are no approved drugs to treat HR-HPV infections to-date. The HPV E1 protein is an attractive drug target because the protein is highly conserved across all HPV types and is crucial for the regulation of viral DNA replication. Hence, we used the Random Forest algorithm to construct a Quantitative-Structure Activity Relationship (QSAR) model to predict the potential inhibitors against the HPV E1 protein. Our QSAR classification model achieved an accuracy of 87.5%, area under the receiver operating characteristic curve of 1.00, and F-measure of 0.87 when evaluated using an external test set. We conducted a drug repurposing campaign by deploying the model to screen the Drugbank database. The top three compounds, namely Cinalukast, Lobeglitazone, and Efatutazone were analyzed for their cell membrane permeability, toxicity, and carcinogenicity. Finally, these three compounds were subjected to molecular docking and 200 ns-long Molecular Dynamics (MD) simulations. The predicted binding free energies for the candidates were calculated using the MM-GBSA method. The binding free energies for Cinalukast, Lobeglitazone, and Efatutazone were -37.84 kcal/mol, -25.30 kcal/mol, and -29.89 kcal/mol respectively. Therefore, we propose their chemical scaffolds for future rational design of E1 inhibitors.Communicated by Ramaswamy H. Sarma.

Molecular docking study of GSK-3β interaction with nomilin, kihadanin B, and related limonoids and triterpenes with a furyl-δ-lactone core

Glycogen synthase kinase-3β (GSK-3β) is a target enzyme considered for the treatment of multiple human diseases, from neurodegenerative pathologies to viral infections and cancers. Numerous inhibitors of GSK-3β have been discovered but thus far only a few have reached clinical trials and only one drug, tideglusib (1), has been registered. Natural products targeting GSK-3β have been identified, including the two anticancer limonoids obacunone (5) and gedunin (4), both presenting a furyl-δ-lactone core. To help identifying novel GSK-3β ligands, we have performed a molecular docking study with 15 complementary natural products bearing a furyl-δ-lactone unit (such as limonin (6) and kihadanins A (8) and B (9)) or a closely related structure (such as cedrelone (10) and nimbolide (11)). The formation of GSK-3β-binding complexes for those natural products was compared to reference GSK-3β ATP-competitive inhibitors LY2090314 (3) and AR-A014418 (2). Our in silico analysis led to the identification of two new GSK-3β-binding natural products: kihadanin B (9) and nomilin (7). The latter surpassed the reference compounds in terms of calculated empirical energy of interaction (ΔE). Nomilin (7) can possibly bind to the active site of GSK-3β, notably via the furyl-δ-lactone core and its 1-acetyl group, implicated in the protein interaction. Compound structure-binding relationships are discussed. The study should help the discovery of novel natural products targeting GSK-3β.

MegaSyn: Integrating Generative Molecular Design, Automated Analog Designer, and Synthetic Viability Prediction

Generative machine learning models have become widely adopted in drug discovery and other fields to produce new molecules and explore molecular space, with the goal of discovering novel compounds with optimized properties. These generative models are frequently combined with transfer learning or scoring of the physicochemical properties to steer generative design, yet often, they are not capable of addressing a wide variety of potential problems, as well as converge into similar molecular space when combined with a scoring function for the desired properties. In addition, these generated compounds may not be synthetically feasible, reducing their capabilities and limiting their usefulness in real-world scenarios. Here, we introduce a suite of automated tools called MegaSyn representing three components: a new hill-climb algorithm, which makes use of SMILES-based recurrent neural network (RNN) generative models, analog generation software, and retrosynthetic analysis coupled with fragment analysis to score molecules for their synthetic feasibility. We show that by deconstructing the targeted molecules and focusing on substructures, combined with an ensemble of generative models, MegaSyn generally performs well for the specific tasks of generating new scaffolds as well as targeted analogs, which are likely synthesizable and druglike. We now describe the development, benchmarking, and testing of this suite of tools and propose how they might be used to optimize molecules or prioritize promising lead compounds using these RNN examples provided by multiple test case examples.

Artificial intelligence in virtual screening: models versus experiments

A typical drug discovery project involves identifying active compounds with significant binding potential for selected disease-specific targets. Experimental high-throughput screening (HTS) is a traditional approach to drug discovery, but is expensive and time-consuming when dealing with huge chemical libraries with billions of compounds. The search space can be narrowed down with the use of reliable computational screening approaches. In this review, we focus on various machine-learning (ML) and deep-learning (DL)-based scoring functions developed for solving classification and ranking problems in drug discovery. We highlight studies in which ML and DL models were successfully deployed to identify lead compounds for which the experimental validations are available from bioassay studies.

The Road to Personalized Medicine in Alzheimer’s Disease: The Use of Artificial Intelligence

Dementia remains an extremely prevalent syndrome among older people and represents a major cause of disability and dependency. Alzheimer’s disease (AD) accounts for the majority of dementia cases and stands as the most common neurodegenerative disease. Since age is the major risk factor for AD, the increase in lifespan not only represents a rise in the prevalence but also adds complexity to the diagnosis. Moreover, the lack of disease-modifying therapies highlights another constraint. A shift from a curative to a preventive approach is imminent and we are moving towards the application of personalized medicine where we can shape the best clinical intervention for an individual patient at a given point. This new step in medicine requires the most recent tools and analysis of enormous amounts of data where the application of artificial intelligence (AI) plays a critical role on the depiction of disease–patient dynamics, crucial in reaching early/optimal diagnosis, monitoring and intervention. Predictive models and algorithms are the key elements in this innovative field. In this review, we present an overview of relevant topics regarding the application of AI in AD, detailing the algorithms and their applications in the fields of drug discovery, and biomarkers.

Enhancing preclinical drug discovery with artificial intelligence

Artificial intelligence (AI) is becoming an integral part of drug discovery. It has the potential to deliver across the drug discovery and development value chain, starting from target identification and reaching through clinical development. In this review, we provide an overview of current AI technologies and a glimpse of how AI is reimagining preclinical drug discovery by highlighting examples where AI has made a real impact. Considering the excitement and hyperbole surrounding AI in drug discovery, we aim to present a realistic view by discussing both opportunities and challenges in adopting AI in drug discovery.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

Recent advances in drug repurposing using machine learning

Drug repurposing aims to find new uses for already existing and approved drugs. We now provide a brief overview of recent developments in drug repurposing using machine learning alongside other computational approaches for comparison. We also highlight several applications for cancer using kinase inhibitors, Alzheimer's disease as well as COVID-19.

Deep Scoring Neural Network Replacing the Scoring Function Components to Improve the Performance of Structure-Based Molecular Docking

Accurate prediction of protein-ligand interactions can greatly promote drug development. Recently, a number of deep-learning-based methods have been proposed to predict protein-ligand binding affinities. However, these methods independently extract the feature representations of proteins and ligands but ignore the relative spatial positions and interaction pairs between them. Here, we propose a virtual screening method based on deep learning, called Deep Scoring, which directly extracts the relative position information and atomic attribute information on proteins and ligands from the docking poses. Furthermore, we use two Resnets to extract the features of ligand atoms and protein residues, respectively, and generate an atom-residue interaction matrix to learn the underlying principles of the interactions between proteins and ligands. This is then followed by a dual attention network (DAN) to generate the attention for two related entities (i.e., proteins and ligands) and to weigh the contributions of each atom and residue to binding affinity prediction. As a result, Deep Scoring outperforms other structure-based deep learning methods in terms of screening performance (area under the receiver operating characteristic curve (AUC) of 0.901 for an unbiased DUD-E version), pose prediction (AUC of 0.935 for PDBbind test set), and generalization ability (AUC of 0.803 for the CHEMBL data set). Finally, Deep Scoring was used to select novel ERK2 inhibitor, and two compounds (D264-0698 and D483-1785) were obtained with potential inhibitory activity on ERK2 through the biological experiments.

Mechanisms and Therapeutic Implications of GSK-3 in Treating Neurodegeneration

Neurodegenerative disorders are spreading worldwide and are one of the greatest threats to public health. There is currently no adequate therapy for these disorders, and therefore there is an urgent need to accelerate the discovery and development of effective treatments. Although neurodegenerative disorders are broad ranging and highly complex, they may share overlapping mechanisms, and thus potentially manifest common targets for therapeutic interventions. Glycogen synthase kinase-3 (GSK-3) is now acknowledged to be a central player in regulating mood behavior, cognitive functions, and neuron viability. Indeed, many targets controlled by GSK-3 are critically involved in progressing neuron deterioration and disease pathogenesis. In this review, we focus on three pathways that represent prominent mechanisms linking GSK-3 with neurodegenerative disorders: cytoskeleton organization, the mammalian target of rapamycin (mTOR)/autophagy axis, and mitochondria. We also consider the challenges and opportunities in the development of GSK-3 inhibitors for treating neurodegeneration.

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies, we and others have applied multiple machine learning algorithms and modeling metrics and, in some cases, compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and in comparison of our proprietary software Assay Central with random forest, k-nearest neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (three layers). Model performance was assessed using an array of fivefold cross-validation metrics including area-under-the-curve, F1 score, Cohen's kappa, and Matthews correlation coefficient. Based on ranked normalized scores for the metrics or datasets, all methods appeared comparable, while the distance from the top indicated that Assay Central and support vector classification were comparable. Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case. If anything, Assay Central may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay Central performance, although support vector classification seems to be a strong competitor. We also applied Assay Central to perform prospective predictions for the toxicity targets PXR and hERG to further validate these models. This work appears to be the largest scale comparison of these machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors, and machine learning algorithms and further refine the methods for evaluating and comparing such models.