No abstract

Summary Background COVID-19 has the potential to cause substantial disruptions to health services, due to cases overburdening the health system or response measures limiting usual programmatic activities. We aimed to quantify the extent to which disruptions to services for HIV, tuberculosis, and malaria in low-income and middle-income countries with high burdens of these diseases could lead to additional loss of life over the next 5 years. Methods Assuming a basic reproduction number of 3·0, we constructed four scenarios for possible responses to the COVID-19 pandemic: no action, mitigation for 6 months, suppression for 2 months, or suppression for 1 year. We used established transmission models of HIV, tuberculosis, and malaria to estimate the additional impact on health that could be caused in selected settings, either due to COVID-19 interventions limiting activities, or due to the high demand on the health system due to the COVID-19 pandemic. Findings In high-burden settings, deaths due to HIV, tuberculosis, and malaria over 5 years could increase by up to 10%, 20%, and 36%, respectively, compared with if there was no COVID-19 pandemic. The greatest impact on HIV was estimated to be from interruption to antiretroviral therapy, which could occur during a period of high health system demand. For tuberculosis, the greatest impact would be from reductions in timely diagnosis and treatment of new cases, which could result from any prolonged period of COVID-19 suppression interventions. The greatest impact on malaria burden could be as a result of interruption of planned net campaigns. These disruptions could lead to a loss of life-years over 5 years that is of the same order of magnitude as the direct impact from COVID-19 in places with a high burden of malaria and large HIV and tuberculosis epidemics. Interpretation Maintaining the most critical prevention activities and health-care services for HIV, tuberculosis, and malaria could substantially reduce the overall impact of the COVID-19 pandemic. Funding Bill & Melinda Gates Foundation, Wellcome Trust, UK Department for International Development, and Medical Research Council.

The synthesis of complex organic molecules requires several stages, from ideation to execution, that require time and effort investment from expert chemists. Here, we report a step toward a paradigm of chemical synthesis that relieves chemists from routine tasks, combining artificial intelligence–driven synthesis planning and a robotically controlled experimental platform. Synthetic routes are proposed through generalization of millions of published chemical reactions and validated in silico to maximize their likelihood of success. Additional implementation details are determined by expert chemists and recorded in reusable recipe files, which are executed by a modular continuous-flow platform that is automatically reconfigured by a robotic arm to set up the required unit operations and carry out the reaction. This strategy for computer-augmented chemical synthesis is demonstrated for 15 drug or drug-like substances.

Computer assistance in synthesis design has existed for over 40 years, yet retrosynthesis planning software has struggled to achieve widespread adoption. One critical challenge in developing high-quality pathway suggestions is that proposed reaction steps often fail when attempted in the laboratory, despite initially seeming viable. The true measure of success for any synthesis program is whether the predicted outcome matches what is observed experimentally. We report a model framework for anticipating reaction outcomes that combines the traditional use of reaction templates with the flexibility in pattern recognition afforded by neural networks. Using 15 000 experimental reaction records from granted United States patents, a model is trained to select the major (recorded) product by ranking a self-generated list of candidates where one candidate is known to be the major product. Candidate reactions are represented using a unique edit-based representation that emphasizes the fundamental transformation from reactants to products, rather than the constituent molecules’ overall structures. In a 5-fold cross-validation, the trained model assigns the major product rank 1 in 71.8% of cases, rank ≤3 in 86.7% of cases, and rank ≤5 in 90.8% of cases.

Computer-aided synthesis planning (CASP) is focused on the goal of accelerating the process by which chemists decide how to synthesize small molecule compounds. The ideal CASP program would take a molecular structure as input and output a sorted list of detailed reaction schemes that each connect that target to purchasable starting materials via a series of chemically feasible reaction steps. Early work in this field relied on expert-crafted reaction rules and heuristics to describe possible retrosynthetic disconnections and selectivity rules but suffered from incompleteness, infeasible suggestions, and human bias. With the relatively recent availability of large reaction corpora (such as the United States Patent and Trademark Office (USPTO), Reaxys, and SciFinder databases), consisting of millions of tabulated reaction examples, it is now possible to construct and validate purely data-driven approaches to synthesis planning. As a result, synthesis planning has been opened to machine learning techniques, and the field is advancing rapidly. In this Account, we focus on two critical aspects of CASP and recent machine learning approaches to both challenges. First, we discuss the problem of retrosynthetic planning, which requires a recommender system to propose synthetic disconnections starting from a target molecule. We describe how the search strategy, necessary to overcome the exponential growth of the search space with increasing number of reaction steps, can be assisted through a learned synthetic complexity metric. We also describe how the recursive expansion can be performed by a straightforward nearest neighbor model that makes clever use of reaction data to generate high quality retrosynthetic disconnections. Second, we discuss the problem of anticipating the products of chemical reactions, which can be used to validate proposed reactions in a computer-generated synthesis plan (i.e., reduce false positives) to increase the likelihood of experimental success. While we introduce this task in the context of reaction validation, its utility extends to the prediction of side products and impurities, among other applications. We describe neural network-based approaches that we and others have developed for this forward prediction task that can be trained on previously published experimental data. Machine learning and artificial intelligence have revolutionized a number of disciplines, not limited to image recognition, dictation, translation, content recommendation, advertising, and autonomous driving. While there is a rich history of using machine learning for structure-activity models in chemistry, it is only now that it is being successfully applied more broadly to organic synthesis and synthesis design. As reported in this Account, machine learning is rapidly transforming CASP, but there are several remaining challenges and opportunities, many pertaining to the availability and standardization of both data and evaluation metrics, which must be addressed by the community at large.