Artificial-Intelligence-Driven Organic Synthesis-En Route towards Autonomous Synthesis?

Finding Relevant Retrosynthetic Disconnections for Stereocontrolled Reactions

Machine learning-driven computer-aided synthesis planning (CASP) tools have become important tools for idea generation in the design of complex molecule synthesis but do not adequately address the stereochemical features of the target compounds. A novel approach to automated extraction of templates used in CASP that includes stereochemical information included in the US Patent and Trademark Office (USPTO) and an internal AstraZeneca database containing reactions from Reaxys, Pistachio, and AstraZeneca electronic lab notebooks is implemented in the freely available AiZynthFinder software. Three hundred sixty-seven templates covering reagent- and substrate-controlled as well as stereospecific reactions were extracted from the USPTO, while 20,724 templates were from the AstraZeneca database. The performance of these templates in multistep CASP is evaluated for 936 targets from the ChEMBL database and an in-house selection of 791 AZ designs. The potential and limitations are discussed for four case studies from ChEMBL and examples of FDA-approved drugs.

The Millennia-Long Development of Drugs Associated with the 80-Year-Old Artificial Intelligence Story: The Therapeutic Big Bang?

The journey of drug discovery (DD) has evolved from ancient practices to modern technology-driven approaches, with Artificial Intelligence (AI) emerging as a pivotal force in streamlining and accelerating the process. Despite the vital importance of DD, it faces challenges such as high costs and lengthy timelines. This review examines the historical progression and current market of DD alongside the development and integration of AI technologies. We analyse the challenges encountered in applying AI to DD, focusing on drug design and protein-protein interactions. The discussion is enriched by presenting models that put forward the application of AI in DD. Three case studies are highlighted to demonstrate the successful application of AI in DD, including the discovery of a novel class of antibiotics and a small-molecule inhibitor that has progressed to phase II clinical trials. These cases underscore the potential of AI to identify new drug candidates and optimise the development process. The convergence of DD and AI embodies a transformative shift in the field, offering a path to overcome traditional obstacles. By leveraging AI, the future of DD promises enhanced efficiency and novel breakthroughs, heralding a new era of medical innovation even though there is still a long way to go.

A Comprehensive Survey on Deep Graph Representation Learning

Graph representation learning aims to effectively encode high-dimensional sparse graph-structured data into low-dimensional dense vectors, which is a fundamental task that has been widely studied in a range of fields, including machine learning and data mining. Classic graph embedding methods follow the basic idea that the embedding vectors of interconnected nodes in the graph can still maintain a relatively close distance, thereby preserving the structural information between the nodes in the graph. However, this is sub-optimal due to: (i) traditional methods have limited model capacity which limits the learning performance; (ii) existing techniques typically rely on unsupervised learning strategies and fail to couple with the latest learning paradigms; (iii) representation learning and downstream tasks are dependent on each other which should be jointly enhanced. With the remarkable success of deep learning, deep graph representation learning has shown great potential and advantages over shallow (traditional) methods, there exist a large number of deep graph representation learning techniques have been proposed in the past decade, especially graph neural networks. In this survey, we conduct a comprehensive survey on current deep graph representation learning algorithms by proposing a new taxonomy of existing state-of-the-art literature. Specifically, we systematically summarize the essential components of graph representation learning and categorize existing approaches by the ways of graph neural network architectures and the most recent advanced learning paradigms. Moreover, this survey also provides the practical and promising applications of deep graph representation learning. Last but not least, we state new perspectives and suggest challenging directions which deserve further investigations in the future.

Photochemistry in Medicinal Chemistry and Chemical Biology

Photochemistry has emerged as a transformative force in organic chemistry, significantly expanding the chemical space accessible for medicinal chemistry. Light-induced reactions enable the efficient synthesis of intricate organic structures and have found applications throughout the different stages of the drug discovery and development processes. Moreover, photochemical techniques provide innovative solutions in chemical biology, allowing precise spatiotemporal drug activation and targeted delivery. In this Perspective, we highlight the already numerous remarkable applications and the even more promising future of photochemistry in medicinal chemistry and chemical biology.

How Amorphous Nanomaterials Enhanced Electrocatalytic, SERS, and Mechanical Properties

There is ever-growing research interest in nanomaterials because of the unique properties that emerge on the nanometer scale. While crystalline nanomaterials have received a surge of attention for exhibiting state-of-the-art properties in various fields, their amorphous counterparts have also attracted attention in recent years owing to their unique structural features that crystalline materials lack. In short, amorphous nanomaterials only have short-range order at the atomic scale, and their atomic packing lacks long-range periodic arrangement, in which the coordinatively unsaturated environment, isotropic atomic structure, and modulated electron state all contribute to their outstanding performance in various applications. Given their intriguing characteristics, we herein present a series of representative works to elaborate on the structural advantages of amorphous nanomaterials as well as their enhanced electrocatalytic, surface-enhanced Raman scattering (SERS), and mechanical properties, thereby elucidating the underlying structure-function relationship. We hope that this proposed relationship will be universally applicable, thus encouraging future work in the design of amorphous materials that show promising performance in a wide range of fields.

Communicating Supraparticles to Enable Perceptual, Information-Providing Matter

Materials are the fundament of the physical world, whereas information and its exchange are the centerpieces of the digital world. Their fruitful synergy offers countless opportunities for realizing desired digital transformation processes in the physical world of materials. Yet, to date, a perfect connection between these worlds is missing. From the perspective, this can be achieved by overcoming the paradigm of considering materials as passive objects and turning them into perceptual, information-providing matter. This matter is capable of communicating associated digitally stored information, for example, its origin, fate, and material type as well as its intactness on demand. Herein, the concept of realizing perceptual, information-providing matter by integrating customizable (sub-)micrometer-sized communicating supraparticles (CSPs) is presented. They are assembled from individual nanoparticulate and/or (macro)molecular building blocks with spectrally differentiable signals that are either robust or stimuli-susceptible. Their combination yields functional signal characteristics that provide an identification signature and one or multiple stimuli-recorder features. This enables CSPs to communicate associated digital information on the tagged material and its encountered stimuli histories upon signal readout anywhere across its life cycle. Ultimately, CSPs link the materials and digital worlds with numerous use cases thereof, in particular fostering the transition into an age of sustainability.

Prospects and challenges for autonomous catalyst discovery viewed from an experimental perspective

Autonomous catalysis research requires elaborate integration of operando experiments into automated workflows. Suitable experimental data for analysis by artificial intelligence can be measured more readily according to standard operating procedures.

Towards 4th industrial revolution efficient and sustainable continuous flow manufacturing of active pharmaceutical ingredients

The convergence of end-to-end continuous flow synthesis with downstream processing, process analytical technology (PAT), artificial intelligence (AI), machine learning and automation in ensuring improved accessibility of quality medicines on demand.

Accelerated screening of colloidal nanocrystals using artificial neural network-assisted autonomous flow reactor technology

Colloidal semiconductor nanocrystals with tunable optical and electronic properties are opening up exciting opportunities for high-performance optoelectronics, photovoltaics, and bioimaging applications. Identifying the optimal synthesis conditions and screening of synthesis recipes in search of efficient synthesis pathways to obtain nanocrystals with desired optoelectronic properties, however, remains one of the major bottlenecks for accelerated discovery of colloidal nanocrystals. Conventional strategies, often guided by limited understanding of the underlying mechanisms remain expensive in both time and resources, thus significantly impeding the overall discovery process. In response, an autonomous experimentation platform is presented as a viable approach for accelerated synthesis screening and optimization of colloidal nanocrystals. Using a machine-learning-based predictive synthesis approach, integrated with automated flow reactor and inline spectroscopy, indium phosphide nanocrystals are autonomously synthesized. Their polydispersity for different target absorption wavelengths across the visible spectrum is simultaneously optimized during the autonomous experimentation, while utilizing minimal self-driven experiments (less than 50 experiments within 2 days). Starting with no-prior-knowledge of the synthesis, an ensemble neural network is trained through autonomous experiments to accurately predict the reaction outcome across the entire synthesis parameter space. The predicted parameter space map also provides new nucleation-growth kinetic insights to achieve high monodispersity in size of colloidal nanocrystals.

Quantum Dot Photocatalysts for Organic Transformations

Quantum dots (QDs) with tunable photo-optical properties and colloidal nature are ideal for a wide range of photocatalytic reactions. In particular, QD photocatalysts for organic transformations can provide new and effective synthetic routes to high value-added molecules under mild conditions. In this Perspective, we discuss the advances of employing QDs for visible-light-driven organic transformations categorized into net reductive reactions, net oxidative reactions, and redox neutral reactions. We then provide our outlook for potential future directions in the field: nanostructure engineering to improve charge separation efficiencies, ligand shell engineering to optimize overall catalyst performance, in situ comprehensive studies to delineate underlying reaction mechanisms, and laboratory automation with the assistance of modern computing techniques to revolutionize the reaction optimization process.

AI in drug development: a multidisciplinary perspective

The introduction of a new drug to the commercial market follows a complex and long process that typically spans over several years and entails large monetary costs due to a high attrition rate. Because of this, there is an urgent need to improve this process using innovative technologies such as artificial intelligence (AI). Different AI tools are being applied to support all four steps of the drug development process (basic research for drug discovery; pre-clinical phase; clinical phase; and postmarketing). Some of the main tasks where AI has proven useful include identifying molecular targets, searching for hit and lead compounds, synthesising drug-like compounds and predicting ADME-Tox. This review, on the one hand, brings in a mathematical vision of some of the key AI methods used in drug development closer to medicinal chemists and, on the other hand, brings the drug development process and the use of different models closer to mathematicians. Emphasis is placed on two aspects not mentioned in similar surveys, namely, Bayesian approaches and their applications to molecular modelling and the eventual final use of the methods to actually support decisions. Promoting a perfect synergy.

Artificial Intelligence and Cancer Drug Development

BACKGROUND

The development of cancer drugs is among the most focused "bench to bedside activities" to improve human health. Because of the amount of data publicly available to cancer research, drug development for cancers has significantly benefited from big data and AI. In the meantime, challenges, like curating the data of low quality, remain to be resolved.

OBJECTIVE

This review focused on the recent advancements in and challenges of AI in developing cancer drugs.

METHOD

We discussed target validation, drug repositioning, de novo design, and compounds' synthetic strategies.

RESULTS AND CONCLUSION

AI can be applied to all stages during drug development, and some excellent reviews detailing the applications of AI in specific stages are available.

Fragment-based drug discovery: opportunities for organic synthesis

This Review describes the increasing demand for organic synthesis to facilitate fragment-based drug discovery (FBDD), focusing on polar, unprotected fragments. In FBDD, X-ray crystal structures are used to design target molecules for synthesis with new groups added onto a fragment via specific growth vectors. This requires challenging synthesis which slows down drug discovery, and some fragments are not progressed into optimisation due to synthetic intractability. We have evaluated the output from Astex's fragment screenings for a number of programs, including urokinase-type plasminogen activator, hematopoietic prostaglandin D2 synthase, and hepatitis C virus NS3 protease-helicase, and identified fragments that were not elaborated due, in part, to a lack of commercially available analogues and/or suitable synthetic methodology. This represents an opportunity for the development of new synthetic research to enable rapid access to novel chemical space and fragment optimisation.

More Twins in the Scientific Literature of the 21st Century

This Essay highlights the complex issue of twinning in science publications. Historical accounts present cases where two scientists focused on the same problem and came up with the same solution following different paths. This has changed in the present day. The concurrent publication of rather similar research papers from different groups has increased in frequency since 2010. In the past, twinning in research publications was serendipitous, and there was a healthy competition among teams working on similar projects. Today, twinning has become more frequent. This can be attributed to the urge of researchers to have publications on popular topics, the tendency to base research programs on popular keywords, and funding agencies preferentially supporting certain areas of research. With vast amounts of literature being generated, editorial offices and referees may not be able to find these twins very easily. As we inch away from human ingenuity towards artificial intelligence, twinning may become even more frequent.

A public-private partnership for the express development of antiviral leads: a perspective view

INTRODUCTION

The COVID-19 pandemic raises the question of strategic readiness for emergent pathogens. The current case illustrates that the cost of inaction can be higher in the future. The perspective article proposes a dedicated, government-sponsored agency developing anti-viral leads against all potentially dangerous pathogen species.

AREAS COVERED

The author explores the methods of computational drug screening and in-silico synthesis and proposes a specialized government-sponsored agency focusing on leads and functioning in collaboration with a network of labs, pharma, biotech firms, and academia, in order to test each lead against multiple viral species. The agency will employ artificial intelligence and machine learning tools to cut the costs further. The algorithms are expected to receive continuous feedback from the network of partners conducting the tests.

EXPERT OPINION

The author proposes a bionic principle, emulating antibody response by producing a combinatorial diversity of high q uality generic antiviral leads, suitable for multiple potentially emerging species. The availability of multiple pre-tested agents and an even greater number of combinations would reduce the impact of the next outbreak. The methodologies developed in this effort are likely to find utility in the design of chronic disease therapeutics.

Continuous Flow Upgrading of Selected C2-C6 Platform Chemicals Derived from Biomass

The ever increasing industrial production of commodity and specialty chemicals inexorably depletes the finite primary fossil resources available on Earth. The forecast of population growth over the next 3 decades is a very strong incentive for the identification of alternative primary resources other than petro-based ones. In contrast with fossil resources, renewable biomass is a virtually inexhaustible reservoir of chemical building blocks. Shifting the current industrial paradigm from almost exclusively petro-based resources to alternative bio-based raw materials requires more than vibrant political messages; it requires a profound revision of the concepts and technologies on which industrial chemical processes rely. Only a small fraction of molecules extracted from biomass bears significant chemical and commercial potentials to be considered as ubiquitous chemical platforms upon which a new, bio-based industry can thrive. Owing to its inherent assets in terms of unique process experience, scalability, and reduced environmental footprint, flow chemistry arguably has a major role to play in this context. This review covers a selection of C₂ to C₆ bio-based chemical platforms with existing commercial markets including polyols (ethylene glycol, 1,2-propanediol, 1,3-propanediol, glycerol, 1,4-butanediol, xylitol, and sorbitol), furanoids (furfural and 5-hydroxymethylfurfural) and carboxylic acids (lactic acid, succinic acid, fumaric acid, malic acid, itaconic acid, and levulinic acid). The aim of this review is to illustrate the various aspects of upgrading bio-based platform molecules toward commodity or specialty chemicals using new process concepts that fall under the umbrella of continuous flow technology and that could change the future perspectives of biorefineries.

Flow Chemistry in Contemporary Chemical Sciences: A Real Variety of Its Applications

Flow chemistry is an area of contemporary chemistry exploiting the hydrodynamic conditions of flowing liquids to provide particular environments for chemical reactions. These particular conditions of enhanced and strictly regulated transport of reagents, improved interface contacts, intensification of heat transfer, and safe operation with hazardous chemicals can be utilized in chemical synthesis, both for mechanization and automation of analytical procedures, and for the investigation of the kinetics of ultrafast reactions. Such methods are developed for more than half a century. In the field of chemical synthesis, they are used mostly in pharmaceutical chemistry for efficient syntheses of small amounts of active substances. In analytical chemistry, flow measuring systems are designed for environmental applications and industrial monitoring, as well as medical and pharmaceutical analysis, providing essential enhancement of the yield of analyses and precision of analytical determinations. The main concept of this review is to show the overlapping of development trends in the design of instrumentation and various ways of the utilization of specificity of chemical operations under flow conditions, especially for synthetic and analytical purposes, with a simultaneous presentation of the still rather limited correspondence between these two main areas of flow chemistry.