Atlas: A Brain for Self-driving Laboratories

Abstract

Self-driving laboratories (SDLs) are next-generation research and development platforms for closed-loop, autonomous experimentation that combine ideas from artificial intelligence, robotics, and high-performance computing. A critical component of SDLs is the decision-making algorithm used to prioritize experiments to be performed. This SDL “brain” often relies on optimization strategies that are guided by machine learning models, such as Bayesian optimization. However, the diversity of hardware constraints and scientific questions being tackled by SDLs require the availability of a set of flexible algorithms that have yet to be implemented in a single software tool. Here, we report Atlas, an application-agnostic Python library for Bayesian optimization that is specifically tailored to the needs of SDLs. Atlas provides facile access to state-of-the-art, model-based optimization algorithms—including mixed-parameter, multi-objective, constrained, robust, multi-fidelity, meta-learning, and molecular optimization—as an all-in-one tool that is expected to suit the majority of specialized SDL needs. After a brief description of its core capabilities, we demonstrate Atlas’ utility by optimizing the oxidation potential of metal complexes with an autonomous electrochemical experimentation platform. We expect Atlas to expand the breadth of design and discovery problems in the natural sciences that are immediately addressable with SDLs.

Accelerated chemical science with AI

“…Additionally, there was a signicant focus on the necessity and development of multi-objective optimizations for new materials discovery. 102,103 Considering these fundamental AI advancements for enabling chemical discovery, it was noted that most multiobjective, multi-delity constrained problems addressed in self-driving labs today tend to prioritize higher performance based on predened objectives. However, to advance chemistry knowledge, algorithms need to be further tailored for interpretability, extrapolation to learn new science, and hypothesis testing, which fundamentally require different approaches.…”

An affordable platform for automated synthesis and electrochemical characterization

“…These areas include tuning DPV parameters, dynamic characterization techniques, and intricate experimental planning targeting speci c observables. 7 Incorporating such techniques would undoubtedly elevate our framework's quality and e ciency.…”

“…Self-driving laboratories [1][2][3] (SDLs) represent a paradigm shift in chemical research, integrating three key components: 4 (i) automated laboratory equipment, 5 (ii) experimental planners, 6,7 and (iii) orchestration software, 8,9 with seamless communication among these elements. Automated procedures enhance throughput and, once established, easily lend themselves to parallelization in a reproducible fashion, provided instrument choices and operational know-how are in place.…”

“…Previously, taking the advances in automating organic chemistry established by the Burke group 41 while further implementing modular design principles and open-source software, we introduced an extendable multipurpose platform, MEDUSA, as the next generation of "The Machine". 7,42 Speci cally, it has full potential to incorporate both post-synthesis/processing analysis in automation work ows, therefore is ideal for establishing end-to-end automated electrochemistry platforms. Further elaborating our proof-of-concept prototype for open and a ordable SDL, 7 this work integrates an automated laboratory framework that combines an in-house designed, compact potentiostat device with a basic version of MEDUSA ( Figure 1 ).…”

“…7,42 Speci cally, it has full potential to incorporate both post-synthesis/processing analysis in automation work ows, therefore is ideal for establishing end-to-end automated electrochemistry platforms. Further elaborating our proof-of-concept prototype for open and a ordable SDL, 7 this work integrates an automated laboratory framework that combines an in-house designed, compact potentiostat device with a basic version of MEDUSA ( Figure 1 ). The primary goal is to demonstrate the capabilities of this integrated setup by streamlining the generation of a comprehensive database containing metal/ligand complexes of electrochemical interest.…”