Data-science driven autonomous process optimization

Abstract

<p>Autonomous process optimization involves the human intervention-free exploration of a range of pre-defined process parameters in order to improve responses such as reaction yield and product selectivity. Utilizing off-the-shelf components, we developed a closed-loop system capable of carrying out parallel autonomous process optimization experiments in batch with significantly reduced cycle times. Upon implementation of our system in the autonomous optimization of a palladium-catalyzed stereoselective Suzuki-Miyaura coupling, we found that the definition of a set of meaningful, broad, and unbiased process parameters was the most critical aspect of a successful optimization. In addition, we found that categorical parameters such as phosphine ligand were vital to determining the reaction outcome. To date, categorical parameter selection has relied on chemical intuition, potentially introducing an element of bias into the experimental design. In seeking a systematic method for the selection of a diverse set of phosphine ligands fully representative of the chemical space, we developed a strategy that leveraged computed molecular descriptor clustering analysis. This strategy allowed for the successful autonomous optimization of a stereoselective Suzuki-Miyaura coupling between a vinyl sulfonate and an arylboronic acid to selectively generate the <i>E</i>-product isomer in high yield. </p>

Automation isn't automatic

“…20). 41 Over a four-day optimization campaign that was free of human intervention, this system developed an optimized stereoselective Suzuki cross-coupling protocol with a 76% yield. While there is still much to learn about the interpretation of data stemming from experimental planning algorithms, it is evident that the application of autonomous technologies is the next frontier in chemistry automation.…”

“…The same scenario can be envisioned with ML algorithms, where the interpretation of analytical outcomes will determine the next set of actions. We have highlighted two examples that demonstrate the utility of such systems here, 16,41 but are looking forward to a new era in which intelligent automation becomes the norm, and not the exception. Only with this feedback control will automation platforms be able to master the art of synthesis.…”

Implications of the BATTERY 2030+ AI‐Assisted Toolkit on Future Low‐TRL Battery Discoveries and Chemistries

“…Viewed from a top-down perspective, such interactions can be seen as the tight interconnection of different research groups and the accelerated research tasks [10] therein. The seamless integration of research tasks automatically triggering the next pertinent task is then considered so-called closed-loop [79,80] or, on a larger scale, a self-driving lab [81][82][83][84][85][86] when fully interconnected, even a materials acceleration platform. Similar to the levels of autonomous driving, Stein and Gregoire [10] tried to assess different early-stage closed-loop discovery cycles in chemistry.…”

Genetic Optimization of Homogeneous Catalysts

“…In the spirit of inverse design, [4][5][6][7][8] NaviCatGA uses a Genetic Algorithm (GA) [9][10][11][12] to find optimal catalysts (Figure 1). This pipeline represents a complementary approach to highthroughput screening [13][14][15][16][17] that becomes comparatively more efficient as the dimensionality of the combinatorial space of catalyst components grows.…”