In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.

Recent advances in end-to-end continuous-flow synthesis are rapidly expanding the capabilities of automated customized syntheses of small-molecule pharmacophores, resulting in considerable industrial and societal impacts; however, many hurdles persist that limit the number of sequential steps that can be achieved in such systems, including solvent and reagent incompatibility between individual steps, cumulated by-product formation, risk of clogging and mismatch of timescales between steps in a processing chain. To address these limitations, herein we report a strategy that merges solid-phase synthesis and continuous-flow operation, enabling push-button automated multistep syntheses of active pharmaceutical ingredients. We demonstrate our platform with a six-step synthesis of prexasertib in 65% isolated yield after 32 h of continuous execution. As there are no interactions between individual synthetic steps in the sequence, the established chemical recipe file was directly adopted or slightly modified for the synthesis of twenty-three prexasertib derivatives, enabling both automated early and late-stage diversification.

Combining high‐throughput experiments with machine learning accelerates materials and process optimization toward user‐specified target properties. In this study, a rapid machine learning‐driven automated flow mixing setup with a high‐throughput drop‐casting system is introduced for thin film preparation, followed by fast characterization of proxy optical and target electrical properties that completes one cycle of learning with 160 unique samples in a single day, a >10× improvement relative to quantified, manual‐controlled baseline. Regio‐regular poly‐3‐hexylthiophene is combined with various types of carbon nanotubes, to identify the optimum composition and synthesis conditions to realize electrical conductivities as high as state‐of‐the‐art 1000 S cm−1. The results are subsequently verified and explained using offline high‐fidelity experiments. Graph‐based model selection strategies with classical regression that optimize among multi‐fidelity noisy input‐output measurements are introduced. These strategies present a robust machine‐learning driven high‐throughput experimental scheme that can be effectively applied to understand, optimize, and design new materials and composites.

<p>In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with a desired absorbance spectrum. Combining a Gaussian Process based Bayesian Optimization (BO) with a Deep Neural Network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable<i> </i>by humans, the proposed framework efficiently optimizes the nanomaterial synthesis, and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.</p>

No abstract