Bayesian Optimization of Computer-Proposed Multistep Synthetic Routes on an Automated Robotic Flow Platform

Abstract

Computer-aided synthesis planning (CASP) tools can propose retrosynthetic pathways and forward reaction conditions for the synthesis of organic compounds, but the limited availability of context-specific data currently necessitates experimental development to fully specify process details. We plan and optimize a CASP-proposed and human-refined multistep synthesis route toward an exemplary small molecule, sonidegib, on a modular, robotic flow synthesis platform with integrated process analytical technology (PAT) for data-rich experimentation. Human insights address catalyst deactivation and improve yield by strategic choices of order of addition. Multi-objective Bayesian optimization identifies optimal values for categorical and continuous process variables in the multistep route involving 3 reactions (including heterogeneous hydrogenation) and 1 separation. The platform's modularity, robotic reconfigurability, and flexibility for convergent synthesis are shown to be essential for allowing variation of downstream residence time in multistep flow processes and controlling the order of addition to minimize undesired reactivity. Overall, the work demonstrates how automation, machine learning, and robotics enhance manual experimentation through assistance with idea generation, experimental design, execution, and optimization.

Photochemical Synthesis of the Bioactive Fragment of Salbutamol and Derivatives in a Self‐Optimizing Flow Chemistry Platform

“…The hardware of the SOFCP used in this study (Figure 2 and Supporting Information) is detailed in previous papers [12c,15] . Briefly, four feedstock solutions (substrate, reactant, catalyst and pure solvent) were pumped using VICI M6HP pumps into a 0.125 mL active mixing chamber equipped with a stir bar, before entering a 1 mL coiled tubular reactor (PFA tubing, 1/32′′ ID, 1/16” OD) where irradiation occurred.…”

Re-envisioning the Design of Nanomedicines: Harnessing Automation and Artificial Intelligence

“…As the name suggests, these systems accelerate scientific discovery through a self-guided process that employs automation and ML models [61,84,85]. Seminal works in this area have focused on the optimization of chemical reactions [86][87][88][89] and design of functional materials [90][91][92][93]. In recent years, self-driving laboratories have helped elucidate information that could have otherwise been overlooked and revealed areas of further investigation for materials discovery [94].…”

A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

“…The same group, in collaboration with Hein, Sigman, and Merck, later demonstrated its utility in autonomous process optimization of stereoselective Suzuki–Miyaura coupling . The group of Jensen and Jamison also applied multi-objective BO to a computer-proposed multistep synthesis of small molecule sonidegib on an automated robotic flow platform . However, these tool are less accessible to nonexperts and lack valuable functionality such as the ability to visualize output predictions and modify condition space during the course of an optimization campaign.…”