Artificial Intelligence (AI) Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine.

Artificial intelligence (AI) encompasses a broad spectrum of techniques that have been utilized by pharmaceutical companies for decades, including machine learning, deep learning, and other advanced computational methods. These innovations have unlocked unprecedented opportunities for the acceleration of drug discovery and delivery, the optimization of treatment regimens, and the improvement of patient outcomes. AI is swiftly transforming the pharmaceutical industry, revolutionizing everything from drug development and discovery to personalized medicine, including target identification and validation, selection of excipients, prediction of the synthetic route, supply chain optimization, monitoring during continuous manufacturing processes, or predictive maintenance, among others. While the integration of AI promises to enhance efficiency, reduce costs, and improve both medicines and patient health, it also raises important questions from a regulatory point of view. In this review article, we will present a comprehensive overview of AI's applications in the pharmaceutical industry, covering areas such as drug discovery, target optimization, personalized medicine, drug safety, and more. By analyzing current research trends and case studies, we aim to shed light on AI's transformative impact on the pharmaceutical industry and its broader implications for healthcare.

Data-centric challenges with the application and adoption of artificial intelligence for drug discovery.

INTRODUCTION: Artificial intelligence (AI) is exhibiting tremendous potential to reduce the massive costs and long timescales of drug discovery. There are however important challenges currently limiting the impact and scope of AI models. AREAS COVERED: In this perspective, the authors discuss a range of data issues (bias, inconsistency, skewness, irrelevance, small size, high dimensionality), how they challenge AI models, and which issue-specific mitigations have been effective. Next, they point out the challenges faced by uncertainty quantification techniques aimed at enhancing and trusting the predictions from these AI models. They also discuss how conceptual errors, unrealistic benchmarks and performance misestimation can confound the evaluation of models and thus their development. Lastly, the authors explain how human bias, whether from AI experts or drug discovery experts, constitutes another challenge that can be alleviated by gaining more prospective experience. EXPERT OPINION: AI models are often developed to excel on retrospective benchmarks unlikely to anticipate their prospective performance. As a result, only a few of these models are ever reported to have prospective value (e.g. by discovering potent and innovative drug leads for a therapeutic target). The authors have discussed what can go wrong in practice with AI for drug discovery. The authors hope that this will help inform the decisions of editors, funders investors, and researchers working in this area.

Application of Mechanistic Multiparameter Optimization and Large-Scale In Vitro to In Vivo Pharmacokinetics Correlations to Small-Molecule Therapeutic Projects.

Computational chemistry and machine learning are used in drug discovery to predict the target-specific and pharmacokinetic properties of molecules. Multiparameter optimization (MPO) functions are used to summarize multiple properties into a single score, aiding compound prioritization. However, over-reliance on subjective MPO functions risks reinforcing human bias. Mechanistic modeling approaches based on physiological relevance can be adapted to meet different potential key objectives of the project (e.g., minimizing dose, maximizing safety margins, and/or minimizing drug-drug interaction risk) while retaining the same underlying model structure. The current work incorporates recent approaches to predict in vivo pharmacokinetic (PK) properties and validates in vitro to in vivo correlation analysis to support mechanistic PK MPO. Examples of use and impact in small-molecule drug discovery projects are provided. Overall, the mechanistic MPO identifies 83% of the compounds considered as short-listed for clinical experiments in the top second percentile, and 100% in the top 10th percentile, resulting in an area under the receiver operating characteristic curve (AUCROC) > 0.95. In addition, the MPO score successfully recapitulates the chronological progression of the optimization process across different scaffolds. Finally, the MPO scores for compounds characterized in pharmacokinetics experiments are markedly higher compared with the rest of the compounds being synthesized, highlighting the potential of this tool to reduce the reliance on in vivo testing for compound screening.

Discovery of novel anti-infective agents.

Academic and other non-profit institutions have a long-term vision to improve human health where commercial interests can be limited for profit organizations. Medicinal chemistry to these diseases with no commercial benefit needs is well suited in the academic environment and this chapter outlines some work conducted at Calibr-Skaggs around antibiotic drug development that has led to initiation of multiple clinical trials over the last decade.

Degradation-Risk-Inspired Optimization of the Antifungal Oxazolinyl Aniline Lead by a Fusion of Triazole with Nicotinamide.

The discovery of readily available and easily modifiable new models is a crucial and practical solution for agrochemical innovation. Antifungal function-oriented fusion of triazole with the prevalidated lead (R)-LE001 affords a novel framework with a broad and enhanced antifungal spectrum. Characterized by the easy accessibility and adjustability of [1,2,4]triazolo[4,3-a]pyridine, modular fine-tuning provided a set of unprecedented leads (e.g., Z23, Z25, Z26, etc.) with superior antifungal potentials than the positive control boscalid. Candidate Z23 exhibited a more promising antifungal activity against Sclerotinia sclerotiorum, Botrytis cinerea, and Phytophthora capsici with EC50 values of 0.7, 0.6, and 0.5 µM, respectively. This candidate could effectively control boscalid-resistant B. cinerea strains and also exhibit good vivo efficacy in controlling gray mold. Noteworthily, both the SDH-inhibition and the efficiency against Oomycete P. capsici are quite distinct from that of the positive control boscalid. A molecular docking simulation also differentiates Z23 from boscalid. These findings highlight the potential of [1,2,4]triazolo[4,3-a]pyridine amide as a novel antifungal model.

Synthesis, design, and optimization of a potent and selective series of pyridylpiperazines as promising antimalarial agents.

An optimization of the pyridylpiperazine series against Plasmodium falciparum has been performed, exploring a structure-activity relationship carried out on the toluyl fragment of hit 1, a compound with low micromolar activity against Plasmodium falciparum discovered by high-throughput screening. After confirming the crucial role played by this aryl fragment in the antiplasmodial activity, the replacement of the ortho-methyl substituent of 1 by halogenated ones led to an improvement for four analogs, either in terms of potency, expected pharmacokinetics profile, or both. Further introduction of endocyclic nitrogens in this fragment identified two more optimized compounds, 20 and 23, which are expected to be much more metabolically stable than 1. Additional assessment of the cytotoxicity, Ligand Lipophilic Efficiency, potency against the chloroquine-resistant Dd2 strain and in silico ADMET predictions revealed a satisfactory profile for most compounds, ultimately identifying the four optimized compounds 7, 9, 20 and 23 as promising compounds for further lead optimization of this series against Plasmodium falciparum.

Bioisosteric heterocyclic analogues of natural bioactive flavonoids by scaffold-hopping approaches: State-of-the-art and perspectives in medicinal chemistry.

The flavonoid family is a set of well-known bioactive natural molecules, with a wide range of potential therapeutic applications. Despite the promising results obtained in preliminary in vitro/vivo studies, their pharmacokinetic and pharmacodynamic profiles are severely compromised by chemical instability. To address this issue, the scaffold-hopping approach is a promising strategy for the structural optimization of natural leads to discover more potent analogues. In this scenario, this Perspective provides a critical analysis on how the replacement of the chromon-4-one flavonoid core with other bioisosteric nitrogen/sulphur heterocycles might affect the chemical, pharmaceutical and biological properties of the resulting new chemical entities. The investigated derivatives were classified on the basis of their biological activity and potential therapeutic indications. For each session, the target(s), the specific mechanism of action, if available, and the key pharmacophoric moieties were highlighted, as revealed by X-ray crystal structures and in silico structure-based studies. Biological activity data, in vitro/vivo studies, were examined: a particular focus was given on the improvements observed with the new heterocyclic analogues compared to the natural flavonoids. This overview of the scaffold-hopping advantages in flavonoid compounds is of great interest to the medicinal chemistry community to better exploit the vast potential of these natural molecules and to identify new bioactive molecules.

Fungicidal Activity of New Pyrrolo[2,3-d]thiazoles and Their Potential Action on the Tryptophan Metabolic Pathway and Wax Biosynthesis.

The main challenge in the development of agrochemicals is the lack of new leads and/or targets. It is critical to discover new molecular targets and their corresponding ligands. YZK-C22, which contains a 1,2,3-thiadiazol-[1,2,4]triazolo[3,4-b][1,3,4]thiadiazole skeleton, is a fungicide lead compound with broad-spectrum fungicidal activity. Previous studies suggested that the [1,2,4]triazolo[3,4-b][1,3,4]thiadiazole scaffold exhibited good antifungal activity. Inspired by this, a series of pyrrolo[2,3-d]thiazole derivatives were designed and synthesized through a bioisosteric strategy. Compounds C1, C9, and C20 were found to be more active against Rhizoctonia solani than the positive control YZK-C22. More than half of the target compounds provided favorable activity against Botrytis cinerea, where the EC50 values of compounds C4, C6, C8, C10, and C20 varied from 1.17 to 1.77 µg/mL. Surface plasmon resonance and molecular docking suggested that in vitro potent compounds C9 and C20 have a new mode of action instead of acting as pyruvate kinase inhibitors. Transcriptome analysis revealed that compound C20 can impact the tryptophan metabolic pathway, cutin, suberin, and wax biosynthesis of B. cinerea. Overall, pyrrolo[2,3-d]thiazole is discovered as a new fungicidal lead structure with a potential new mode of action for further exploration.

Synthesis and biological evaluation of orally active anti-Trypanosoma agents.

In previous studies, we developed anti-trypanosome tubulin inhibitors with promising in vitro selectivity and activity against Human African Trypanosomiasis (HAT). However, for such agents, oral activity is crucial. This study focused on further optimizing these compounds to enhance their ligand efficiency, aiming to reduce bulkiness and hydrophobicity, which should improve solubility and, consequently, oral bioavailability. Using Trypanosoma brucei brucei cells as the parasite model and human normal kidney cells and mouse macrophage cells as the host model, we evaluated 30 new analogs synthesized through combinatorial chemistry. These analogs have fewer aromatic moieties and lower molecular weights than their predecessors. Several new analogs demonstrated IC50s in the low micromolar range, effectively inhibiting trypanosome cell growth without harming mammalian cells at the same concentration. We conducted a detailed structure-activity relationship (SAR) analysis and a docking study to assess the compounds' binding affinity to trypanosome tubulin homolog. The results revealed a correlation between binding energy and anti-Trypanosoma activity. Importantly, compound 7 displayed significant oral activity, effectively inhibiting trypanosome cell proliferation in mice.

The Art and Science of Molecular Docking.

Molecular docking has become an essential part of a structural biologist's and medicinal chemist's toolkits. Given a chemical compound and the three-dimensional structure of a molecular target-for example, a protein-docking methods fit the compound into the target, predicting the compound's bound structure and binding energy. Docking can be used to discover novel ligands for a target by screening large virtual compound libraries. Docking can also provide a useful starting point for structure-based ligand optimization or for investigating a ligand's mechanism of action. Advances in computational methods, including both physics-based and machine learning approaches, as well as in complementary experimental techniques, are making docking an even more powerful tool. We review how docking works and how it can drive drug discovery and biological research. We also describe its current limitations and ongoing efforts to overcome them.

Structure-property Relationships Reported for the New Drugs Approved in 2023.

Drug-like properties play pivotal roles in drug adsorption, distribution, metabolism, excretion, and toxicity. Therefore, efficiently optimizing these properties is essential for the successful development of novel therapeutics. Understanding the structure-property relationships of clinically approved drugs can provide valuable insights for drug design and optimization strategies. Among the new drugs approved in 2023, which include 31 small-molecule drugs in the US, the structureproperty relationships of nine drugs were compiled from the medicinal chemistry literature, in which detailed information on pharmacokinetic and/or physicochemical properties was reported not only for the final drug but also for its key analogs generated during drug development. The structure- property relationships of nine newly approved drugs are summarized, including three kinase inhibitors and three G-protein-coupled receptor antagonists. Several optimization strategies, such as bioisosteric replacement and steric handle installation, have successfully produced clinical candidates with enhanced physicochemical and pharmacokinetic properties. The summarized structure- property relationships demonstrate how appropriate structural modifications can effectively improve overall drug-like properties. The ongoing exploration of structure-property relationships of clinically approved drugs is expected to offer valuable guidance for developing future drugs.

Optimization of benzenesulfonyl derivatives as anti-Trypanosomatidae agents: Structural design, synthesis, and pharmacological assessment against Trypanosoma cruzi and Leishmania infantum.

Leishmaniasis and Chagas disease are neglected tropical diseases caused by Trypanosomatidae parasites. Given the numerous limitations associated with current treatments, such as extended treatment duration, variable efficacy, and severe side effects, there is an urgent imperative to explore novel therapeutic options. This study details the early stages of hit-to-lead optimization for a benzenesulfonyl derivative, denoted as initial hit, against Trypanossoma cruzi (T. cruzi), Leishmania infantum (L. infantum) and Leishmania braziliensis (L. braziliensis). We investigated structure - activity relationships using a series of 26 newly designed derivatives, ultimately yielding potential lead candidates with potent low-micromolar and sub-micromolar activities against T. cruzi and Leishmania spp, respectively, and low in vitro cytotoxicity against mammalian cells. These discoveries emphasize the significant promise of this chemical class in the fight against Chagas disease and leishmaniasis.

Computational resources and chemoinformatics for translational health research.

The integration of computational resources and chemoinformatics has revolutionized translational health research. It has offered a powerful set of tools for accelerating drug discovery. This chapter overviews the computational resources and chemoinformatics methods used in translational health research. The resources and methods can be used to analyze large datasets, identify potential drug candidates, predict drug-target interactions, and optimize treatment regimens. These resources have the potential to transform the drug discovery process and foster personalized medicine research. We discuss insights into their various applications in translational health and emphasize the need for addressing challenges, promoting collaboration, and advancing the field to fully realize the potential of these tools in transforming healthcare.

Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery.

INTRODUCTION: Targeting RNAs with small molecules offers an alternative to the conventional protein-targeted drug discovery and can potentially address unmet and emerging medical needs. The recent rise of interest in the strategy has already resulted in large amounts of data on disease associated RNAs, as well as on small molecules that bind to such RNAs. Artificial intelligence (AI) approaches, including machine learning and deep learning, present an opportunity to speed up the discovery of RNA-targeted small molecules by improving decision-making efficiency and quality. AREAS COVERED: The topics described in this review include the recent applications of AI in the identification of RNA targets, RNA structure determination, screening of chemical compound libraries, and hit-to-lead optimization. The impact and limitations of the recent AI applications are discussed, along with an outlook on the possible applications of next-generation AI tools for the discovery of novel RNA-targeted small molecule drugs. EXPERT OPINION: Key areas for improvement include developing AI tools for understanding RNA dynamics and RNA - small molecule interactions. High-quality and comprehensive data still need to be generated especially on the biological activity of small molecules that target RNAs.

ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization.

Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

A synthetic agent ameliorates polycystic kidney disease by promoting apoptosis of cystic cells through increased oxidative stress.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common monogenic cause of chronic kidney disease and the fourth leading cause of end-stage kidney disease, accounting for over 50% of prevalent cases requiring renal replacement therapy. There is a pressing need for improved therapy for ADPKD. Recent insights into the pathophysiology of ADPKD revealed that cyst cells undergo metabolic changes that up-regulate aerobic glycolysis in lieu of mitochondrial respiration for energy production, a process that ostensibly fuels their increased proliferation. The present work leverages this metabolic disruption as a way to selectively target cyst cells for apoptosis. This small-molecule therapeutic strategy utilizes 11beta-dichloro, a repurposed DNA-damaging anti-tumor agent that induces apoptosis by exacerbating mitochondrial oxidative stress. Here, we demonstrate that 11beta-dichloro is effective in delaying cyst growth and its associated inflammatory and fibrotic events, thus preserving kidney function in perinatal and adult mouse models of ADPKD. In both models, the cyst cells with homozygous inactivation of Pkd1 show enhanced oxidative stress following treatment with 11beta-dichloro and undergo apoptosis. Co-administration of the antioxidant vitamin E negated the therapeutic benefit of 11beta-dichloro in vivo, supporting the conclusion that oxidative stress is a key component of the mechanism of action. As a preclinical development primer, we also synthesized and tested an 11beta-dichloro derivative that cannot directly alkylate DNA, while retaining pro-oxidant features. This derivative nonetheless maintains excellent anti-cystic properties in vivo and emerges as the lead candidate for development.

MolOptimizer: A Molecular Optimization Toolkit for Fragment-Based Drug Design.

MolOptimizer is a user-friendly computational toolkit designed to streamline the hit-to-lead optimization process in drug discovery. MolOptimizer extracts features and trains machine learning models using a user-provided, labeled, and small-molecule dataset to accurately predict the binding values of new small molecules that share similar scaffolds with the target in focus. Hosted on the Azure web-based server, MolOptimizer emerges as a vital resource, accelerating the discovery and development of novel drug candidates with improved binding properties.

Structure-based development of potent and selective type-II kinase inhibitors of RIPK1.

Receptor-interacting serine/threonine-protein kinase 1 (RIPK1) functions as a key regulator in inflammation and cell death and is involved in mediating a variety of inflammatory or degenerative diseases. A number of allosteric RIPK1 inhibitors (RIPK1i) have been developed, and some of them have already advanced into clinical evaluation. Recently, selective RIPK1i that interact with both the allosteric pocket and the ATP-binding site of RIPK1 have started to emerge. Here, we report the rational development of a new series of type-II RIPK1i based on the rediscovery of a reported but mechanistically atypical RIPK3i. We also describe the structure-guided lead optimization of a potent, selective, and orally bioavailable RIPK1i, 62, which exhibits extraordinary efficacies in mouse models of acute or chronic inflammatory diseases. Collectively, 62 provides a useful tool for evaluating RIPK1 in animal disease models and a promising lead for further drug development.

The Structure-property Relationships of Clinically Approved Protease Inhibitors.

BACKGROUND: Proteases play important roles in the regulation of many physiological processes, and protease inhibitors have become one of the important drug classes. Especially because the development of protease inhibitors often starts from a substrate- based peptidomimetic strategy, many of the initial lead compounds suffer from pharmacokinetic liabilities. OBJECTIVE: To reduce drug attrition rates, drug metabolism and pharmacokinetics studies are fully integrated into modern drug discovery research, and the structure-property relationship illustrates how the modification of the chemical structure influences the pharmacokinetic and toxicological properties of drug compounds. Understanding the structure- property relationships of clinically approved protease inhibitor drugs and their analogues could provide useful information on the lead-to-candidate optimization strategies. METHODS: About 70 inhibitors against human or pathogenic viral proteases have been approved until the end of 2021. In this review, 17 inhibitors are chosen for the structure- property relationship analysis because detailed pharmacological and/or physicochemical data have been disclosed in the medicinal chemistry literature for these inhibitors and their close analogues. RESULTS: The compiled data are analyzed primarily focusing on the pharmacokinetic or toxicological deficiencies found in lead compounds and the structural modification strategies used to generate candidate compounds. CONCLUSION: The structure-property relationships hereby summarized how the overall druglike properties could be successfully improved by modifying the structure of protease inhibitors. These specific examples are expected to serve as useful references and guidance for developing new protease inhibitor drugs in the future.