The central event of each signaling step in biology is biomolecular recognition. Notwithstanding the importance of nucleic acids, carbohydrates, or lipids in ligand-target interactions, the effectors of most signal transduction processes are peptides. These can be fragments of proteins or stand-alone hormones, cytokines, toxins, antimicrobials, and many other types of peptides. At this point there is no good reason to classify peptides by the number of amino acid residues. We consider peptides as any polyamide (or even biopolymer with ester, thioester, or otherwise modified backbone) that can be made on a contemporary chemical peptide synthesizer. The limit in size is greater than the arbitrary cutoff of 50 amino acids set up by the US Food and Drug Administration (Carton and Strohl, 2013) for proteins and far exceeds that of biological recognition elements. While target recognition can occur with as low as a few residues (Ertl et al., 1991), even wide binding groves can be bound by 30–40 residue long peptides. Thus, in principle synthetic peptides can be used to regulate almost all receptor responses. The high specificity and low toxicity of peptide drugs derive from their extremely tight binding to their targets. This is due to the large chemical space the side-chain variations of native amino acids cover. Current databases estimate the total number of valid protein-ligand binding sites at 7700 (Khazanov and Carlson, 2013). Calculation based on 17 variable residues (Cys, Met, and Trp are significantly underrepresented in known ligands), show that an 83,000-member tetrapeptide library can be prepared that will essentially cover all unique protein binding regions. As the median length of an active site is 11 amino-acid residues (Khazanov and Carlson, 2013), designed ligands should also be longer. While historically six-residue positional scanning could identify ligands of receptors or epitopes of monoclonal antibodies (Dooley and Houghten, 1993), in our experience receptor agonists are 9–12 residue long (Otvos et al., 2008, 2011a) much like major histocompatibility complex binding peptides (Appella et al., 1995). Antagonists acting on the same receptor binding sites are somewhat shorter (vide infra). If it is assumed that conformational preferences improve the binding kinetics but only rarely thermodynamics, then the tremendous specificity of side-chain combinations of peptides over six residues in length can be even further expanded by using non-natural residues. Hundreds of appropriately protected and activated non-natural amino acid derivatives, ready for incorporation into synthetic peptides, are commercially available and indeed are frequently explored in peptidebased drug design. Importantly, chemical biology has provided both backbone and side-chain combinations for exploring an enormous chemical space and is expected to supply peptide chemists with further building blocks suitable for identifying close-to-ideal agonists and antagonists of any biologically important target. The selectivity of peptide drugs for their target is highlighted by the elevated success rate in clinical trials. According to a biotechnology report (Thomas, 2013), of the 40 approved drugs in 2012, five (12.5%) were peptides compared to 28 small molecule drugs and two monoclonal antibodies (in addition to three enzymes, a cell-based drug and a vaccine). However, in a recent report, the total number of peptide approvals between 2001 and 2012 was 19 (Kaspar and Reichert, 2013). Due to the low number of drug approvals, any particularly successful year can bias the ratios significantly. According to another report, the overall success rate of all drugs entering clinical trials is just 10.4% (Hay et al., 2014). Sixty-five percent of small molecules proceed from Phase I to Phase II in non-oncology applications, a figure identical for peptide/protein drugs. Interestingly peptides/proteins outperform small molecules at the Phase II → Phase III transition stage with 29% for small molecules and 42% for the larger drug candidates. While peptides have traditionally been considered safe in Phase I clinical trials, the public perception is that they are less beneficial in late clinical trials when they are compared side-by-side with different types of treatment modalities. It must be mentioned that peptides are less successful in oncology than in other applications. The cost of large scale peptide production might well-exceed those of small molecule drugs, but if one considers the total cost of the drug development process, the active pharmaceutical ingredient expense will remain under 3% (Otvos, 2014a). In direct opposition to concerns with expensive peptides, the increased clinical success rate, and thus, overall expense/approved drug ratio compared to small molecule chemical entities, make peptide drug development particularly attractive. The biochemical processes that activated receptors directly or indirectly regulate include protein phosphorylation, nucleic acid transcription, ion transport, and a series of enzyme activities (Yan
INTRODUCTION: A large number of drugs and drug candidates in clinical development contain halogen substituents. For a long time, only the steric and lipophilic contributions of halogens were considered when trying to exploit their effects on ligand binding. However, the ability of halogens to form stabilizing interactions, such as halogen bonding, hydrogen bonding and multipolar interactions, in biomolecular systems was revealed recently. Halogen bonding, the non-covalent interaction in which covalently bound halogens interact with Lewis bases, has now been utilized in the context of rational drug design. AREAS COVERED: The purpose of this review is to show how halogen bonding could be used in drug design, and in particular, to stimulate researchers to apply halogen bonding in lead optimization. This review article covers the recent advances relevant to halogen bonding in drug discovery and biological design over the past decade, including database survey of this interaction in protein-ligand complexes, molecular mechanical investigations of halogen bonding in drug discovery and applications of this interaction in the development of halogenated ligands as inhibitors and drugs for protein kinases, serine protease factor Xa, HIV reverse transcriptase and so on. EXPERT OPINION: Halogen bonding should intentionally be used as a powerful tool, comparable with hydrogen bonding, to enhance the binding affinity and also influence the binding selectivity. Rational design of new and potent inhibitors against therapeutic targets through halogen bonding continues to be an exciting area, which will be further elucidated with the combination of various experimental techniques and theoretical calculations in the forthcoming years.
OBJECTIVE: To attempt to determine the relative value of preclinical cardiac electrophysiology data (in vitro and in vivo) for predicting risk of torsade de pointes (TdP) in clinical use. METHODS: Published data on hERG (or I(Kr)) activity, cardiac action potential duration (at 90% repolarisation; APD(90)), and QT prolongation in dogs were compared against QT effects and reports of TdP in humans for 100 drugs. These data were set against the free plasma concentrations attained during clinical use (effective therapeutic plasma concentrations; ETPC(unbound)). The drugs were divided into five categories: (1) Class Ia and III antiarrhythmics; (2) Withdrawn from market due to TdP; (3) Measurable incidence/numerous reports of TdP in humans; (4) Isolated reports of TdP in humans; (5) No reports of TdP in humans. RESULTS: Data from hERG (or I(Kr)) assays in addition to ETPC(unbound) data were available for 52 drugs. For Category 1 drugs, data for hERG/I(Kr) IC(50), APD(90), QTc in animals and QTc in humans were generally close to or superimposed on the ETPC(unbound) values. This relationship was uncoupled in the other categories, with more complex relationships between the data. In Category 1 (except amiodarone), the ratios between hERG/I(Kr) IC(50) and ETPC(unbound) (max) ranged from 0.1- to 31-fold. Similar ranges were obtained for drugs in Category 2 (0.31- to 13-fold) and Category 3 (0.03- to 35-fold). A large spread was found for Category 4 drugs (0.13- to 35700-fold); this category embraced an assortment of mechanisms ranging from drugs which may well be affecting I(Kr) currents in clinical use (e.g. sparfloxacin) to others such as nifedipine (35700-fold) where channel block is not involved. Finally, for the majority of Category 5 drugs there was a >30-fold separation between hERG/I(Kr) activity and ETPC(unbound) values, with the notable exception of verapamil (1.7-fold), which is free from QT prolongation in man; this is probably explained by its multiple interactions with cardiac ion channels. CONCLUSIONS: The dataset confirms the widely-held belief that most drugs associated with TdP in humans are also associated with hERG K(+) channel block at concentrations close to or superimposed upon the free plasma concentrations found in clinical use. A 30-fold margin between C(max) and hERG IC(50) may suffice for drugs currently undergoing clinical evaluation, but for future drug discovery programmes, pharmaceutical companies should consider increasing this margin, particularly for drugs aimed at non-debilitating diseases. However, interactions with multiple cardiac ion channels can either mitigate or exacerbate the prolongation of APD and QT that would ensue from block of I(Kr) currents alone, and delay of repolarisation per se is not necessarily torsadogenic. Clearly, an integrated assessment of in vitro and in vivo data is required in order to predict the torsadogenic risk of a new candidate drug in humans.
INTRODUCTION: The study of drug-target interactions is essential for the understanding of biological processes and for the efforts to develop new therapeutic molecules. Increased ligand-binding assays have coincided with the advances in reagents, detection and instrumentation technologies, the expansion in therapeutic targets of interest, and the increasingly recognized importance of biochemical aspects of drug-target interactions in determining the clinical performance of drug molecules. Nowadays, ligand-binding assays can determine every aspect of many drug-target interactions. AREAS COVERED: Given that ligand-target interactions are very diverse, the author has decided to focus on the binding of small molecules to protein targets. This article first reviews the key biochemical aspects of drug-target interactions, and then discusses the detection principles of various ligand-binding techniques in the context of their primary applications for drug discovery and development. EXPERT OPINION: Equilibrium-binding affinity should not be used as a solo indicator for the in vivo pharmacology of drugs. The clinical relevance of drug-binding kinetics demands high throughput kinetics early in drug discovery. The dependence of ligand binding and function on the conformation of targets necessitates solution-based and whole cell-based ligand-binding assays. The increasing need to examine ligand binding at the proteome level, driven by the clinical importance of the polypharmacology of ligands, has started to make the structure-based in silico binding screen an indispensable technique for drug discovery and development. Integration of different ligand-binding assays is important to improve the efficiency of the drug discovery and development process.
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.
Drug development is expensive, time-consuming, and has a high failure rate. In recent years, artificial intelligence (AI) has emerged as a transformative tool in drug discovery, offering innovative solutions to complex challenges in the pharmaceutical industry. This manuscript covers the multifaceted role of AI in drug discovery, encompassing AI-assisted drug delivery design, the discovery of new drugs, and the development of novel AI techniques. We explore various AI methodologies, including machine learning and deep learning, and their applications in target identification, virtual screening, and drug design. This paper also discusses the historical development of AI in medicine, emphasizing its profound impact on healthcare. Furthermore, it addresses AI's role in the repositioning of existing drugs and the identification of drug combinations, underscoring its potential in revolutionizing drug delivery systems. The manuscript provides a comprehensive overview of the AI programs and platforms currently used in drug discovery, illustrating the technological advancements and future directions of this field. This study not only presents the current state of AI in drug discovery but also anticipates its future trajectory, highlighting the challenges and opportunities that lie ahead.
INTRODUCTION: Molecular dynamics (MD) simulations can provide not only plentiful dynamical structural information on biomacromolecules but also a wealth of energetic information about protein and ligand interactions. Such information is very important to understanding the structure-function relationship of the target and the essence of protein-ligand interactions and to guiding the drug discovery and design process. Thus, MD simulations have been applied widely and successfully in each step of modern drug discovery. Areas covered: In this review, the authors review the applications of MD simulations in novel drug discovery, including the pathogenic mechanisms of amyloidosis diseases, virtual screening and the interaction mechanisms between drugs and targets. Expert opinion: MD simulations have been used widely in investigating the pathogenic mechanisms of diseases caused by protein misfolding, in virtual screening, and in investigating drug resistance mechanisms caused by mutations of the target. These issues are very difficult to solve by experimental methods alone. Thus, in the future, MD simulations will have wider application with the further improvement of computational capacity and the development of better sampling methods and more accurate force fields together with more efficient analysis methods.
The COVID-19 pandemic has emphasized the need for novel drug discovery process. However, the journey from conceptualizing a drug to its eventual implementation in clinical settings is a long, complex, and expensive process, with many potential points of failure. Over the past decade, a vast growth in medical information has coincided with advances in computational hardware (cloud computing, GPUs, and TPUs) and the rise of deep learning. Medical data generated from large molecular screening profiles, personal health or pathology records, and public health organizations could benefit from analysis by Artificial Intelligence (AI) approaches to speed up and prevent failures in the drug discovery pipeline. We present applications of AI at various stages of drug discovery pipelines, including the inherently computational approaches of de novo design and prediction of a drug's likely properties. Open-source databases and AI-based software tools that facilitate drug design are discussed along with their associated problems of molecule representation, data collection, complexity, labeling, and disparities among labels. How contemporary AI methods, such as graph neural networks, reinforcement learning, and generated models, along with structure-based methods, (i.e., molecular dynamics simulations and molecular docking) can contribute to drug discovery applications and analysis of drug responses is also explored. Finally, recent developments and investments in AI-based start-up companies for biotechnology, drug design and their current progress, hopes and promotions are discussed in this article.
INTRODUCTION: The use of computational tools in the early stages of drug development has increased in recent decades. Machine learning (ML) approaches have been of special interest, since they can be applied in several steps of the drug discovery methodology, such as prediction of target structure, prediction of biological activity of new ligands through model construction, discovery or optimization of hits, and construction of models that predict the pharmacokinetic and toxicological (ADMET) profile of compounds. AREAS COVERED: This article presents an overview on some applications of ML techniques in drug design. These techniques can be employed in ligand-based drug design (LBDD) and structure-based drug design (SBDD) studies, such as similarity searches, construction of classification and/or prediction models of biological activity, prediction of secondary structures and binding sites docking and virtual screening. EXPERT OPINION: Successful cases have been reported in the literature, demonstrating the efficiency of ML techniques combined with traditional approaches to study medicinal chemistry problems. Some ML techniques used in drug design are: support vector machine, random forest, decision trees and artificial neural networks. Currently, an important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.
INTRODUCTION: The highly pathogenic coronaviruses severe acute respiratory syndrome coronavirus (SARS-CoV) and Middle East respiratory syndrome coronavirus (MERS-CoV) are lethal zoonotic viruses that have emerged into human populations these past 15 years. These coronaviruses are associated with novel respiratory syndromes that spread from person-to-person via close contact, resulting in high morbidity and mortality caused by the progression to Acute Respiratory Distress Syndrome (ARDS). Areas covered: The risks of re-emergence of SARS-CoV from bat reservoir hosts, the persistence of MERS-CoV circulation, and the potential for future emergence of novel coronaviruses indicate antiviral drug discovery will require activity against multiple coronaviruses. In this review, approaches that antagonize viral nonstructural proteins, neutralize structural proteins, or modulate essential host elements of viral infection with varying levels of efficacy in models of highly pathogenic coronavirus disease are discussed. Expert opinion: Treatment of SARS and MERS in outbreak settings has focused on therapeutics with general antiviral activity and good safety profiles rather than efficacy data provided by cellular, rodent, or nonhuman primate models of highly pathogenic coronavirus infection. Based on lessons learned from SARS and MERS outbreaks, lack of drugs capable of pan-coronavirus antiviral activity increases the vulnerability of public health systems to a highly pathogenic coronavirus pandemic.
The discovery and development of small molecule cancer drugs has been revolutionised over the last decade. Most notably, we have moved from a one-size-fits-all approach that emphasized cytotoxic chemotherapy to a personalised medicine strategy that focuses on the discovery and development of molecularly targeted drugs that exploit the particular genetic addictions, dependencies and vulnerabilities of cancer cells. These exploitable characteristics are increasingly being revealed by our expanding understanding of the abnormal biology and genetics of cancer cells, accelerated by cancer genome sequencing and other high-throughput genome-wide campaigns, including functional screens using RNA interference. In this review we provide an overview of contemporary approaches to the discovery of small molecule cancer drugs, highlighting successes, current challenges and future opportunities. We focus in particular on four key steps: Target validation and selection; chemical hit and lead generation; lead optimization to identify a clinical drug candidate; and finally hypothesis-driven, biomarker-led clinical trials. Although all of these steps are critical, we view target validation and selection and the conduct of biology-directed clinical trials as especially important areas upon which to focus to speed progress from gene to drug and to reduce the unacceptably high attrition rate during clinical development. Other challenges include expanding the envelope of druggability for less tractable targets, understanding and overcoming drug resistance, and designing intelligent and effective drug combinations. We discuss not only scientific and technical challenges, but also the assessment and mitigation of risks as well as organizational, cultural and funding problems for cancer drug discovery and development, together with solutions to overcome the 'Valley of Death' between basic research and approved medicines. We envisage a future in which addressing these challenges will enhance our rapid progress towards truly personalised medicine for cancer patients.
INTRODUCTION: Sulfur-containing functional groups are privileged motifs that occur in various pharmacologically effective substances and several natural products. Various functionalities are found with a sulfur atom at diverse oxidation states, as illustrated by thioether, sulfoxide, sulfone, sulfonamide, sulfamate, and sulfamide functions. They are valuable scaffolds in the field of medicinal chemistry and are part of a large array of approved drugs and clinical candidates. AREA COVERED: Herein, the authors review the current research on the development of organosulfur-based drug discovery. This article also covers details of their roles in the new lead compounds reported in the literature over the past five years 2017-2021. EXPERT OPINION: Given its prominent role in medicinal chemistry and its importance in drug discovery, sulfur has attracted continuing interest and has been used in the design of various valuable compounds that demonstrate a variety of biological and pharmacological feature activities. Overall, sulfur's role in medicinal chemistry continues to grow. However, many sulfur functionalities remain underused in small-molecule drug discovery and deserve special attention in the armamentarium for treating diverse diseases. Research efforts are also still required for the development of a synthetic methodology for direct access to these functions and late-stage functionalization.
The use of nanotechnology in medicine and more specifically drug delivery is set to spread rapidly. Currently many substances are under investigation for drug delivery and more specifically for cancer therapy. Interestingly pharmaceutical sciences are using nanoparticles to reduce toxicity and side effects of drugs and up to recently did not realize that carrier systems themselves may impose risks to the patient. The kind of hazards that are introduced by using nanoparticles for drug delivery are beyond that posed by conventional hazards imposed by chemicals in classical delivery matrices. For nanoparticles the knowledge on particle toxicity as obtained in inhalation toxicity shows the way how to investigate the potential hazards of nanoparticles. The toxicology of particulate matter differs from toxicology of substances as the composing chemical(s) may or may not be soluble in biological matrices, thus influencing greatly the potential exposure of various internal organs. This may vary from a rather high local exposure in the lungs and a low or neglectable exposure for other organ systems after inhalation. However, absorbed species may also influence the potential toxicity of the inhaled particles. For nanoparticles the situation is different as their size opens the potential for crossing the various biological barriers within the body. From a positive viewpoint, especially the potential to cross the blood brain barrier may open new ways for drug delivery into the brain. In addition, the nanosize also allows for access into the cell and various cellular compartments including the nucleus. A multitude of substances are currently under investigation for the preparation of nanoparticles for drug delivery, varying from biological substances like albumin, gelatine and phospholipids for liposomes, and more substances of a chemical nature like various polymers and solid metal containing nanoparticles. It is obvious that the potential interaction with tissues and cells, and the potential toxicity, greatly depends on the actual composition of the nanoparticle formulation. This paper provides an overview on some of the currently used systems for drug delivery. Besides the potential beneficial use also attention is drawn to the questions how we should proceed with the safety evaluation of the nanoparticle formulations for drug delivery. For such testing the lessons learned from particle toxicity as applied in inhalation toxicology may be of use. Although for pharmaceutical use the current requirements seem to be adequate to detect most of the adverse effects of nanoparticle formulations, it can not be expected that all aspects of nanoparticle toxicology will be detected. So, probably additional more specific testing would be needed.
INTRODUCTION: Throughout history, natural products (NPs) have provided a rich source of compounds that have wide applications in the fields of medicine, health sciences, pharmacy and biology. Although naturally active substances are good lead compounds for the discovery of new drugs, most of them suffer from various deficiencies or shortcomings, such as complex structures, poor stability and solubility. Therefore, structural modification of NPs is needed to develop novel compounds with specific properties. Areas covered: This article presents an overview on the structural modifications of NPs in drug development. The application of multiple classes of NPs to the treatment of conditions such as cancers, infection, Alzheimer's and diabetes are discussed. This article also reveals that modification of NPs is a versatile approach to explore their mode of actions, which may lead to the discovery of novel drugs. Expert opinion: NPs are usually described by structural diversity and complexity. The use of isolated NPs as scaffolds for modification is a good approach to drug discovery and development. Despite many limitations associated with NPs, the total synthesis, semisynthetic modification, SAR-based modification, sometimes even a single atom alteration, may lead to the discovery of a novel drug.
INTRODUCTION: The current drug discovery paradigm of 'one drug, multiple targets' has gained attention from both the academic medicinal chemistry community and the pharmaceutical industry. This is in response to the urgent need for effective agents to treat multifactorial chronic diseases. The molecular hybridization strategy is a useful tool that has been widely explored, particularly in the last two decades, for the design of multi-target drugs. AREAS COVERED: This review examines the current state of molecular hybridization in guiding the discovery of multitarget small molecules. The article discusses the design strategies and target selection for a multitarget polypharmacology approach to treat various diseases, including cancer, Alzheimer's disease, cardiac arrhythmia, endometriosis, and inflammatory diseases. EXPERT OPINION: Although the examples discussed highlight the importance of molecular hybridization for the discovery of multitarget bioactive compounds, it is notorious that the literature has focused on specific classes of targets. This may be due to a deep understanding of the pharmacophore features required for target binding, making targets such as histone deacetylases and cholinesterases frequent starting points. However, it is important to encourage the scientific community to explore diverse combinations of targets using the molecular hybridization strategy.
INTRODUCTION: Over the past couple of years, the cost of drug development has sharply increased along with the high rate of clinical trial failures. Such increase in expenses is partially due to the inability of the "one drug - one target" approach to predict drug side effects and toxicities. To tackle this issue, an alternative approach, known as polypharmacology, is being adopted to study small molecule interactions with multiple targets. Apart from developing more potent and effective drugs, this approach allows for studies of off-target activities and the facilitation of drug repositioning. Although exhaustive polypharmacology studies in-vitro or in-vivo are not practical, computational methods of predicting unknown targets or side effects are being developed. Areas covered: This article describes various computational approaches that have been developed to study polypharmacology profiles of small molecules. It also provides a brief description of the algorithms used in these state-of-the-art methods. Expert opinion: Recent success in computational prediction of multi-targeting drugs has established polypharmacology as a promising alternative approach to tackle some of the daunting complications in drug discovery. This will not only help discover more effective agents, but also present tremendous opportunities to study novel target pharmacology and facilitate drug repositioning efforts in the pharmaceutical industry.
INTRODUCTION: The role of lipophilicity in drug discovery and design is a critical one. Lipophilicity is a key physicochemical property that plays a crucial role in determining ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties and the overall suitability of drug candidates. There is increasing evidence to suggest that control of physicochemical properties such as lipophilicity, within a defined optimal range, can improve compound quality and the likelihood of therapeutic success. AREAS COVERED: This review focuses on understanding lipophilicity, techniques used to measure lipophilicity, and summarizes the importance of lipophilicity in drug discovery and development, including a discussion of its impact on individual ADMET parameters as well as its overall influence on the drug discovery and design process, specifically within the past 15 years. EXPERT OPINION: A current review of the literature reveals a continued reliance on the synthesis of novel structures with increased potency, rather than a focus on maintaining optimal physicochemical properties associated with ADMET throughout drug optimization. Particular attention to the optimum region of lipophilicity, as well as monitoring of lipophilic efficiency indices, may contribute significantly to the overall quality of candidate drugs at different stages of discovery.
INTRODUCTION: The concept of Digital Twins (DTs) translated to drug development and clinical trials describes virtual representations of systems of various complexities, ranging from individual cells to entire humans, and enables in silico simulations and experiments. DTs increase the efficiency of drug discovery and development by digitalizing processes associated with high economic, ethical, or social burden. The impact is multifaceted: DT models sharpen disease understanding, support biomarker discovery and accelerate drug development, thus advancing precision medicine. One way to realize DTs is by generative artificial intelligence (AI), a cutting-edge technology that enables the creation of novel, realistic and complex data with desired properties. AREAS COVERED: The authors provide a brief introduction to generative AI and describe how it facilitates the modeling of DTs. In addition, they compare existing implementations of generative AI for DTs in drug discovery and clinical trials. Finally, they discuss technical and regulatory challenges that should be addressed before DTs can transform drug discovery and clinical trials. EXPERT OPINION: The current state of DTs in drug discovery and clinical trials does not exploit the entire power of generative AI yet and is limited to simulation of a small number of characteristics. Nonetheless, generative AI has the potential to transform the field by leveraging recent developments in deep learning and customizing models for the needs of scientists, physicians and patients.
Introduction: Click chemistry has been exploited widely in the past to expedite lead discovery and optimization. Indeed, Copper-catalyzed azide-alkyne cycloaddition (CuAAC) click chemistry is a bioorthogonal reaction of widespread utility throughout medicinal chemistry and chemical biology.Areas covered: The authors review recent applications of CuAAC click chemistry to drug discovery based on the literature published since 2013. Furthermore, the authors provide the reader with their expert perspectives on the area including their outlook on future developments.Expert opinion: Click chemistry reactions are an important part of the medicinal chemistry toolbox and offer substantial advantages to medicinal chemists in terms of overcoming the limitations of useful chemical synthesis, increasing throughput, and improving the quality of compound libraries. To explore new chemical spaces for drug-like molecules containing a high degree of structural diversity, it may be useful to merge the diversity-oriented synthesis and ‘privileged’ substructure-based strategy with bioorthogonal reactions using sophisticated automation and flow systems to improve productivity. Large compound libraries obtained in this way should be of great value for the discovery of bioactive compounds and therapeutic agents.
INTRODUCTION: Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach. AREAS COVERED: In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps and associated methods, and a relatively new technique, deep learning. The most important technical issues are discussed including overfitting and its prevention through regularization, ensemble and multitask modeling, model interpretation, and estimation of applicability domain. Different aspects of using neural networks in drug discovery are considered: building structure-activity models with respect to various targets; predicting drug selectivity, toxicity profiles, ADMET and physicochemical properties; characteristics of drug-delivery systems and virtual screening. EXPERT OPINION: Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.