Collaborative Intelligence in Sequential Experiments: A Human-in-the-Loop Framework for Drug Discovery

Drug discovery increasingly requires a common understanding by researchers of the many and diverse factors that go into the making of new medicines. The scientist entering the field will immediately face important issues for which his education may not have prepared him: project teams, patent law, consultants, target product profiles, industry trends, Gantt charts, target validation, pharmacokinetics, proteomics, phenotype assays, biomarkers, and many other unfamiliar topics for which a basic understanding must somehow be obtained. Even the more experienced scientist can find it frustratingly difficult to get an overview of the many factors involved in modern drug discovery and often only after years of exploring does a whole and integrated picture emerge in the mind of the researcher. Real World Drug Discovery: A Chemist's Guide to Biotech and Pharmaceutical Research presents this kind of map of the landscape of drug discovery. In a single, readable volume it outlines processes and explains essential concepts and terms for the recent science graduate wondering what to expect in pharma or biotech, the medicinal chemist seeking a broader and more timely understanding of the industry, or the contractor or collaborator whose understanding of the commercial drug discovery process could increase the value of his contribution to it. This book includes interviews with well-known experts in many of the fields involved, giving insightful comments from authorities on many of the sub-disciplines important to cutting-edge drug discovery. It provides helpful suggestions gleaned from years of experience in biotech and pharma, which represents a repository drug discovery 'lore' not previously available in any book. It includes a 'Periodic Table of Drugs' listing current top-selling drugs arranged by target and laid out so that structural similarities and differences are plain and clear, with regular updates available at the book's website. It extensively uses diagrams to illustrate concepts like biotech startup models, preteomic profiling for target identification, Gantt charts for project planning, etc.

AI Power at Tempo

This scoping study explores the role of Human-in-the-Loop Artificial Intelligence (HITL AI) in precision agriculture and evaluates the benefits of using human expertise in combination with Artificial Intelligence (AI) systems in decision-making within modern smart agricultural environments. The development of Artificial Intelligence, Machine Learning, Internet of Things, and robotics has significantly impacted modern agriculture by providing automated crop monitoring, disease detection, yield prediction, and smart farm management systems. However, Artificial Intelligence systems also face challenges in terms of understanding, interpretability, flexibility, and trustworthiness in modern smart agricultural environments. This study is based on the literature regarding human-in-the-loop systems, human-centric Artificial Intelligence systems, and collaborative robotics systems in the context of smart agriculture. The structured scoping study methodology has been followed to identify and evaluate studies regarding Artificial Intelligence systems in smart agricultural environments, with a focus on automation-centric Artificial Intelligence systems and human-centric Artificial Intelligence systems within the context of Agriculture 5.0 concepts. The study concludes that although automation-centric AI systems show high accuracy in simulated smart agricultural environments, Human-In-The-Loop (HITL) AI systems show higher robustness in smart agricultural environments. Explainability in AI has shown significant potential in supporting the effectiveness of HITL AI systems in decision-making within smart agricultural environments. The study also identifies some important gaps in the literature regarding HITL AI systems in smart agriculture. The study concludes that for the development of modern smart precision agriculture, collaborative intelligence within smart agricultural environments is necessary to create sustainable smart agriculture systems.

Todeliver more therapeutics to more patients more quickly andeconomically is the ultimate goal of pharmaceutical researchers. Theadvent and rapid development of artificial intelligence (AI), in combinationwith other powerful computational methods in drug discovery, makesthis goal more practical than ever before. Here, we describe a newstrategy, retro drug design, or RDD, to create novel small-moleculedrugs from scratch to meet multiple predefined requirements, includingbiological activity against a drug target and optimal range of physicochemicaland ADMET properties. The molecular structure was represented by anatom typing based molecular descriptor system, optATP, which was furthertransformed to the space of loading vectors from principal componentanalysis. Traditional predictive models were trained over experimentaldata for the target properties using optATP and shallow machine learningmethods. The Monte Carlo sampling algorithm was then utilized to findthe solutions in the space of loading vectors that have the targetproperties. Finally, a deep learning model was employed to decodemolecular structures from the solutions. To test the feasibility ofthe algorithm, we challenged RDD to generate novel kinase inhibitorsfrom random numbers with five different ADMET properties optimizedat the same time. The best Tanimoto similarity score between the generatedvalid structures and the available 4,314 kinase inhibitors was <0.50, indicating a high extent of novelty of the generated compounds.From the 3,040 structures that met all six target properties, 20 wereselected for synthesis and experimental measurement of inhibitionactivity over 97 representative kinases and the ADMET properties.Fifteen and eight compounds were determined to be hits or strong hits,respectively. Five of the six strong kinase inhibitors have excellentexperimental ADMET properties. The results presented in this paperillustrate that RDD has the potential to significantly improve thecurrent drug discovery process.

AI-enabled language models (LMs) to large language models (LLMs) and multimodal large language models (MLLMs) in drug discovery and development

In response to national priorities and the frontiers of academic research，the development of digital and intelligent commerce in the era of large models depends not only on breakthroughs in key technologies such as artificial intelligence and their applications in the industry but also on the reengineering of traditional business processes and innovations in management theories. Deeply integrating data intelligence with business scenarios，overcoming core technological bottlenecks，fostering new industries and models，and achieving a new paradigm of intelligent，efficient，and collaborative digital and intelligent commerce represent crucial future directions. Based on the 406^th “Shuang Qing Forum”，focusing on the theories and methods of digital intelligence business in the era of large language models，this study delves into three aspects：key technologies and methods，intelligent collaboration and autonomous decision-making，and new models and forms. It further proposes a research agenda addressing advancements in AI methods and large model technologies，multi-agent decision-making and cross-agent collaboration，and human-AI integration in process-organization-market reengineering，along with funding recommendations prioritizing interdisciplinary research in management science and computational science for digital and intelligent commerce.

Review Advances of the Target-Based and Phenotypic Screenings and Strategies in Drug Discovery Shoubao Wang 1,*, Zihan Wang1, Lianhua Fang1, Yang Lv2, and Guanhua Du1,* 1 Beijing Key Laboratory of Drug Targets Identification and Drug Screening, Institute of Materia Medica, Chinese Academy of Medical Sciences &amp; Peking Union Medical College, Beijing, 100050, China. 2 Beijing Key Laboratory of Polymorphic Drugs, Institute of Materia Medica, Chinese Academy of Medical Sciences &amp; Peking Union Medical College, Beijing, 100050, China. * Correspondence: shoubaowang@imm.ac.cn (Shoubao Wang); dugh@imm.ac.cn (Guanhua Du). Received: 8 November 2022 Accepted: 15 November 2022 Published: 21 December 2022 Abstract: Drug discovery and development is a complex and expensive process. There are two approaches, phenotypic and target-based approaches, each holding different advantages for screening novel drug candidates when pursuing successful marketing authorization. However, the attrition rates of drug candidates continue to increase. In this review, we discuss recent successes and ongoing advances in phenotypic screening and target-based screening for drug discovery. We also explore how strategic and technological innovations may fuel new approaches in drug discovery. There are two approaches in drug discovery.

Dear Reader, the explosive growth of the young field of Chemical Biology (CB) is evident from its high-profile journals, including Nature Chemical Biology, ACS Chemical Biology, Cell Chemical Biology and ChemBioChem, and from its popular conferences, such as EMBO biannual chemical biology meeting, which attract increasing audiences from both academia and industry. Several prestigious Chemistry Departments have changed their names to Department of Chemistry and Chemical Biology to accommodate the glory and appeal of CB to the young generation of scientists.

The Indian pharmaceutical industry is the world’s second largest industry (by volume) that develops products and market drugs licensed for use as medications. Medicines manufactured in the modern era are associated with major controversies such as non–target specificity, resistance, repeated administration, immune rejection, and other adverse effects on the body. Thus, there is a great need to find drugs that do not raise the aforementioned issues. Nature is an excellent hub providing a diverse range of phytoconstituents that open the way to phototherapeutics, which need a scientific path to deliver the active elements in a supported way to increase patient compliance and reduce the need for repeated administration. To discover a novel phytochemical as a lead compound for a therapeutic purpose is a real challenge. In former times, drug discovery was a complex process, as it took several years to find a lead compound for use against a particular disease. Nowadays, however, virtual screening methods have been developed, which are target specific, time consuming, and cost effective. To avoid increased and repeated administration of a drug, nanosized drug delivery systems for herbal drugs have been developed to enhance the activity and overcome problems associated with synthetic medicines. This review summarizes three main fields: drug discovery, docking for drug design, and last—but not least—drug delivery systems. Nowadays, nanobased drug delivery systems are in demand for delivery of herbal medicines used for therapeutic purposes. Herbonanoceuticals—herbal drugs of a nanosize—have better remedial value and fewer detrimental effects than modern medicines. Therefore, herbonanoceuticals can be a boon in the field of therapeutics.

Drug discovery has traditionally been a time consuming and expensive endeavor. Additionally, drugs weren’t as effectively designed as those that are being predicted and developed through AI and ML today. Machine learning is a form of artificial intelligence that develops and evolves based on experience (similarly to the human mind), and is more recently being utilized in drug discovery and design. The integration of AI and ML into the drug discovery and development process has allowed for higher target precision, lower toxicity, and better dosage formulations. AI more generally has been introduced to and has been leveraged at, each step of drug development, including target identification and validation, hit identification, as well as hit to lead optimization, and has been key in shortening the previously lengthy drug screening process. AI and ML has also been applied downstream in drug formulation where it has maximized resource utilization and is allowing for web-based 3D printing of drugs. Application of AI in the drug development process has also been extended to the modeling of novel drug-like compounds to predict their ADMET properties. This review will address the stages of drug discovery and development in which the application of AI and ML modeling has altered the traditional development of drugs. Keywords: Drug discovery, machine learning, artificial intelligence, computational drug development.

Introduction Drug discovery is a complex and multifaceted process driven by scientific innovation and advanced technologies. Next-Generation Sequencing (NGS) platforms, encompassing both short-read and long-read technologies, have revolutionized the field by enabling the high-throughput and cost-effective analysis of DNA and RNA molecules. Continuous advancements in NGS-based technologies have enabled their seamless integration across preclinical and clinical workflows in drug discovery, encompassing early-stage drug target identification, candidate selection, genetically stratified clinical trials, and pharmacogenetic studies. Area covered This review provides an overview of the current and potential applications of NGS-based technologies in drug discovery and development process, including their roles in novel drug target identification, high-throughput screening, clinical trials, and clinical medication studies. The review is based on literature retrieval from the PubMed and Web of Science databases between 2018 and 2024. Expert opinion As technologies advance rapidly, NGS enhances accuracy and generates vast datasets. These datasets are extensively integrated with other heterogeneous data in systems biology and are mined using machine learning to extract significant insights, thereby driving progress in drug discovery.

Uniting homeostatic plasticity and exosome biology: A revision of the conceptual framework for drug discovery in neurodegenerative diseases?

The present state and challenges of active learning in drug discovery

Fragment-based drug discovery (FBDD) has emerged as a powerful strategy to confront the challenges faced by conventional drug development approaches, particularly in the context of central nervous system (CNS) disorders. FBDD involves the screening of libraries that comprise thousands of small molecular fragments, each no greater than 300 Da in size. Unlike the generally larger molecules from high-throughput screening that limit customisation, fragments offer a more strategic starting point. These fragments are inherently compact, providing a strong foundation with good binding affinity for the development of drug candidates. The minimal elaboration required to transition the hit into a drug-like molecule is not only accelerated, but also it allows for precise modifications to enhance both their activity and pharmacokinetic properties. This shift towards a fragment-centric approach has seen commercial success and holds considerable promise in the continued streamlining of the drug discovery and development process. In this review, we highlight how FBDD can be integrated into the CNS drug discovery process to enhance the exploration of a target. Furthermore, we provide recent examples where FBDD has been an integral component in CNS drug discovery programs, enabling the improvement of pharmacokinetic properties that have previously proven challenging. The FBDD optimisation process provides a systematic approach to explore this vast chemical space, facilitating the discovery and design of compounds piece by piece that are capable of modulating crucial CNS targets.

Drug finding is a complex process that includes the design and development of new drugs to treat miscellaneous afflictions and environments. While modern drug finding frequently depends state-of-the-art technologies and controlled designs, happenstance the accidental discovery of valuable compounds continues to play a important act engaged. This abstract explores the interaction betwixt orderly design and fortunate discovery in drug incident. Systematic drug design includes the deliberate labeling of drug marks, followed for one realistic design and combination of compounds that interact accompanying these aims to produce healing belongings. This approach relies on computational shaping, form-located drug design, and extreme-throughput screening methods to urge the finding process and optimize drug aspirants for productiveness and security. However, happenstance remains a valuable and changeable facet of drug finding. Many pioneering medications, containing medicine and Viagra, were found accidentally while scientists were fact-finding independent phantasms. Serendipitous discoveries frequently stand from surprising notes or side effects all the while dispassionate troubles or laboratory experiments. These chance judgments can bring about the labeling of novel drug marks or the repurposing of existing compounds for new healing clues. The cooperation 'tween systematic drug design and fortunate finding is essential for numbering drug innovation. While orderly approaches supply a organized framework for drug happening, happenstance supports artistry and opens new avenues for investigation. By taking advantage of two together plans, researchers can harness the entire range of space in drug discovery, eventually chief to the incident of more reliable, more effective drugs.