Explore the vast range of titles available.

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.

The SARS-CoV-2 3CL protease is a critical drug target for small molecule COVID-19 therapy, given its likely druggability and essentiality in the viral maturation and replication cycle. Based on the conservation of 3CL protease substrate binding pockets across coronaviruses and using screening, we identified four structurally distinct lead compounds that inhibit SARS-CoV-2 3CL protease. After evaluation of their binding specificity, cellular antiviral potency, metabolic stability, and water solubility, we prioritized the GC376 scaffold as being optimal for optimization. We identified multiple drug-like compounds with <10 nM potency for inhibiting SARS-CoV-2 3CL and the ability to block SARS-CoV-2 replication in human cells, obtained co-crystal structures of the 3CL protease in complex with these compounds, and determined that they have pan-coronavirus activity. We selected one compound, termed coronastat, as an optimized lead and characterized it in pharmacokinetic and safety studies in vivo. Coronastat represents a new candidate for a small molecule protease inhibitor for the treatment of SARS-CoV-2 infection for eliminating pandemics involving coronaviruses. Small molecule drugs promise to remain a valuable tool in controlling the ongoing COVID-19 pandemic. Here the authors describe optimized drug-like small molecule inhibitors of the SARS-CoV-2 3CL protease for potential treatment of COVID-19.

Cancer immunotherapy based on antibodies targeting the immune checkpoint PD-1/PD-L1 pathway has seen unprecedented clinical responses and constitutes the new paradigm in cancer therapy. The antibody-based immunotherapies have several limitations such as high production cost of the antibodies or their long half-life. Small-molecule inhibitors of the PD-1/PD-L1 interaction have been highly anticipated as a promising alternative or complementary therapeutic to the monoclonal antibodies (mAbs). Currently, the field of developing anti-PD-1/PD-L1 small-molecule inhibitors is intensively explored. In this paper, we review anti-PD-1/PD-L1 small-molecule and peptide-based inhibitors and discuss recent structural and preclinical/clinical aspects of their development. Discovery of the therapeutics based on small-molecule inhibitors of the PD-1/PD-L1 interaction represents a promising but challenging perspective in cancer treatment.

The process for drug discovery and development is challenging, time consuming and expensive. Computer-aided drug discovery (CADD) tools can act as a virtual shortcut, assisting in the expedition of this long process and potentially reducing the cost of research and development. Today CADD has become an effective and indispensable tool in therapeutic development. The human genome project has made available a substantial amount of sequence data that can be used in various drug discovery projects. Additionally, increasing knowledge of biological structures, as well as increasing computer power have made it possible to use computational methods effectively in various phases of the drug discovery and development pipeline. The importance of in silico tools is greater than ever before and has advanced pharmaceutical research. Here we present an overview of computational methods used in different facets of drug discovery and highlight some of the recent successes. In this review, both structure-based and ligand-based drug discovery methods are discussed. Advances in virtual high-throughput screening, protein structure prediction methods, protein–ligand docking, pharmacophore modeling and QSAR techniques are reviewed.

Lenalidomide, an immunomodulatory drug (IMiD), is commonly used as a first-line therapy in many haematological cancers, such as multiple myeloma (MM) and 5q myelodysplastic syndromes (5q MDS), and it functions as a molecular glue for the protein degradation of neosubstrates by CRL4 CRBN . Proteolysis-targeting chimeras (PROTACs) using IMiDs with a target protein binder also induce the degradation of target proteins. The targeted protein degradation (TPD) of neosubstrates is crucial for IMiD therapy. However, current IMiDs and IMiD-based PROTACs also break down neosubstrates involved in embryonic development and disease progression. Here, we show that 6-position modifications of lenalidomide are essential for controlling neosubstrate selectivity; 6-fluoro lenalidomide induced the selective degradation of IKZF1, IKZF3, and CK1α, which are involved in anti-haematological cancer activity, and showed stronger anti-proliferative effects on MM and 5q MDS cell lines than lenalidomide. PROTACs using these lenalidomide derivatives for BET proteins induce the selective degradation of BET proteins with the same neosubstrate selectivity. PROTACs also exert anti-proliferative effects in all examined cell lines. Thus, 6-position-modified lenalidomide is a key molecule for selective TPD using thalidomide derivatives and PROTACs. Lenalidomide is effective for treating several hematological cancers but has teratogenic effect on the fetus. Here, the authors identify modifications that make lenalidomide more selective and effective when used as a stand-alone molecular glue or integrated in PROTACs.

We release a new, high quality data set of 1162 PDE10A inhibitors with experimentally determined binding affinities together with 77 PDE10A X-ray co-crystal structures from a Roche legacy project. This data set is used to compare the performance of different 2D- and 3D-machine learning (ML) as well as empirical scoring functions for predicting binding affinities with high throughput. We simulate use cases that are relevant in the lead optimization phase of early drug discovery. ML methods perform well at interpolation, but poorly in extrapolation scenarios—which are most relevant to a real-world application. Moreover, we find that investing into the docking workflow for binding pose generation using multi-template docking is rewarded with an improved scoring performance. A combination of 2D-ML and 3D scoring using a modified piecewise linear potential shows best overall performance, combining information on the protein environment with learning from existing SAR data.

Generative artificial intelligence is reshaping how researchers discover protein-binding compounds and develop them into drug candidates. Unlike traditional methods that screen existing molecules, structure-based generative AI designs novel compounds tailored to a protein’s three-dimensional binding pocket. This review outlines how these approaches are applied in early drug discovery, focusing on general principles. We categorize methods according to their generative modeling paradigms and their strategies for using structural data to guide molecular design, distinguishing de novo incremental builders from models that generate full structures. We also survey lead-optimization techniques, highlighting a recent shift toward generation-driven medicinal chemistry.

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.

Carbohydrates are a structurally-diverse group of natural products which play an important role in numerous biological processes, including immune regulation, infection, and cancer metastasis. Many diseases have been correlated with changes in the composition of cell-surface glycans, highlighting their potential as a therapeutic target. Unfortunately, native carbohydrates suffer from inherently weak binding affinities and poor pharmacokinetic properties. To enhance their usefulness as drug candidates, ‘glycomimetics’ have been developed: more drug-like compounds which mimic the structure and function of native carbohydrates. Approaches to improve binding affinities (e.g., deoxygenation, pre-organization) and pharmacokinetic properties (e.g., limiting metabolic degradation, improving permeability) have been highlighted in this review, accompanied by relevant examples. By utilizing these strategies, high-affinity ligands with optimized properties can be rationally designed and used to address therapies for novel carbohydrate-binding targets.

Computer-aided drug design and discovery methods have been essential in developing small molecules with therapeutic properties over the last decades. Application of computational resources includes drug target identification, hit discovery, and lead optimization. Accordingly, with tremendous research efforts and the availability of financial support from government agencies across the world, and multinational drug companies, the overall research level in this area will continue to advance. The methodology used in this review paper entailed a thorough examination of research studies on relevant literature on drug design and development using computational resources. Extensive searches using Scopus, International Pharmaceutical Abstracts (OvidSp, WHO Global Health Library, Cochrane, Google Scholar, Web of Science, Science Direct, ProQuest dissertation & theses, Worldwide Political Science Abstracts (CSA), and PubMed was carried out. A standardized template was used to ensure that the selected papers met the inclusion criteria, and relevant to the review. Ultimately, there are robust technologies developed to enhance the drug discovery process. Therefore, this review provides insights into computational resources in Silico and ab initio methods and algorithms, not restricted to drug metabolism predictions for drug design, and the practical applications of artificial intelligence (AI) in drug discovery. Computational tools and methods for drug design and development such as molecular dynamics (MD), molecular docking, quantum mechanics (QM), hybrid quantum mechanics/molecular mechanics (QM/MM), and Density functional theory (DFT) have been reviewed. Accordingly, the emerging technique of synergistically employing these techniques influences the fundamental challenges of conventional medicines for complex diseases. Herein, we discuss ligand-based and structure-based drug discoveries, force field models in MD simulations, docking algorithms, subtractive and additive QM/MM coupling. Nonetheless, as computer-aided drug (CADD) approaches continue to evolve with significant improvements, the focus areas will be on docking and virtual screening, scoring functions, optimization of hits, and assessment of adsorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. With the current success, the present computational resources will aid in the future discovery of novel compounds with high therapeutic performance. The ongoing oncology research efforts will also significantly contribute to UN sustainable development goals – good health and well-being, sustainable innovation and industrialization.