Phoenics: A Bayesian Optimizer for Chemistry

Häse, Florian; Roch, Loı̈c M.; Kreisbeck, Christoph

doi:10.1021/acscentsci.8b00307

Cited by 310 publications

(248 citation statements)

References 64 publications

Supporting

Mentioning

242

Contrasting

Unclassified

Order By: Relevance

“…Phoenics also streamlines the throughput of automated solutions via a sampling parameter, which explicitly controls the sampling behavior of the algorithm, gradually exploring and exploiting. Alternating the sampling behavior during the experimental campaign has been shown to accelerate the optimization process and reduce the number of samples 34. In this experiment, ChemOS leveraged Phoenics to suggest four blends per closed‐loop event, and increases the experimentation throughput by simultaneously coordinating the self‐driving approach for the two studied blend systems.…”

Section: Figurementioning

confidence: 99%

Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Fundamental advances to increase the efficiency as well as stability of organic photovoltaics (OPVs) are achieved by designing ternary blends, which represents a clear trend toward multicomponent active layer blends. The development of high‐throughput and autonomous experimentation methods is reported for the effective optimization of multicomponent polymer blends for OPVs. A method for automated film formation enabling the fabrication of up to 6048 films per day is introduced. Equipping this automated experimentation platform with a Bayesian optimization, a self‐driving laboratory is constructed that autonomously evaluates measurements to design and execute the next experiments. To demonstrate the potential of these methods, a 4D parameter space of quaternary OPV blends is mapped and optimized for photostability. While with conventional approaches, roughly 100 mg of material would be necessary, the robot‐based platform can screen 2000 combinations with less than 10 mg, and machine‐learning‐enabled autonomous experimentation identifies stable compositions with less than 1 mg.

show abstract

Section: Figurementioning

confidence: 99%

Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, Nielsen and colleagues applied random forest to map the yield landscape of intricate deoxyfluorination with sulfonyl fluoride allowing improved prediction of high-yielding conditions for untested substrates [19]. More recently, Phoenics was developed, which combines a concept from Bayesian optimization with ideas from Bayesian kernel density estimation to solve optimization problems and afford efficient exploitation of the search space [20]. Meanwhile, our emphasis is on automation of discovery, which is controlled by robots/computers rather than by humans.…”

Section: Machine Learning Towards Chemical Space Explorationmentioning

confidence: 99%

Universal Chemical Synthesis and Discovery with ‘The Chemputer’

Gromski

Granda

Cronin

2020

Trends in Chemistry

117

View full text Add to dashboard Cite

There is a growing drive in the chemistry community to exploit rapidly growing robotic technologies along with artificial intelligence-based approaches. Applying this to chemistry requires a holistic approach to chemical synthesis design and execution. Here, we outline a universal approach to this problem beginning with an abstract representation of the practice of chemical synthesis that then informs the programming and automation required for its practical realization. Using this foundation to construct closed-loop robotic chemical search engines, we can generate new discoveries that may be verified, optimized, and repeated entirely automatically. These robots can perform chemical reactions and analyses much faster than can be done manually. As such, this leads to a road map whereby molecules can be discovered, optimized, and made on demand from a digital code. Automation in Chemical SynthesisMethodologies for the automation of chemical synthesis, optimization, and discovery have not generally been designed for the realities of laboratory-based research, tending instead to focus on engineering solutions to practical problems. We argue that the potential of rapidly developing technologies (e.g., machine learning and robotics) are more fully realized by operating seamlessly with the way that synthetic chemists currently work ( Figure 1) [1]. This is because the organic chemist often works by thinking backwards as much as they do forwards when planning a synthetic procedure. To reproduce this fundamental mode of operation, a new universal approach to the automated exploration of chemical space is needed that combines an abstraction of chemical synthesis with robotic hardware and closed-loop programming [2,3]. However, this leads chemists to constantly test the reactions with different synthetic parameters and conditions. The alternative to this problem, as shown in this opinion article, is the development of an approach to universal chemistry using a programming language with automation in combination with machine learning and artificial intelligence (AI).Chemists already benefit from algorithms in the field of chemometrics and, therefore, automation is one step forward that might help chemists to navigate and search chemical space more quickly, efficiently, and importantly, without bias. Chemometrics is a field that employs a broad range of algorithms to solve chemistry-related problems and has been well established over the past 50 years [4]. Figure 2 presents a standard chemometrics workflow for processing data. The process begins with data that may be of various formats that depend upon the experiment type and/or posed question. The next step is data preprocessing, which covers a variety of procedures depending on the type of data analyzed (e.g., peak detection, input of missing data, and/or normalization). This process is followed by statistical modeling, which is divided into supervised and unsupervised approaches. Probably one of the most well-known unsupervised approaches is principal component analysis (s...

show abstract

“…Aiming for the generation of self‐driving chemistry laboratories, Aspuru‐Guzik and co‐workers showed the use of Phoenics and Chimera in the context of chemistry and experimentation. Phoenics, a probabilistic global optimization algorithm, was used to identify the set of conditions of an experimental chemical reaction by proposing conditions and updating of those proposed conditions after the experimental feedback to Phoenics . Chimera was used as a multitarget optimization method for automation techniques like the autocalibration of a virtual robotic sampling sequence for direct injection .…”

Section: Automated Autonomous Synthesis For Organic Chemistrymentioning

confidence: 99%

Miniaturized and Automated Synthesis of Biomolecules—Overview and Perspectives

et al. 2019

View full text Add to dashboard Cite

Chemical synthesis is performed by reacting different chemical building blocks with defined stoichiometry, while meeting additional conditions, such as temperature and reaction time. Such a procedure is especially suited for automation and miniaturization. Life sciences lead the way to synthesizing millions of different oligonucleotides in extremely miniaturized reaction sites, e.g., pinpointing active genes in whole genomes, while chemistry advances different types of automation. Recent progress in matrix‐assisted laser desorption/ionization mass spectrometry (MALDI‐MS) imaging could match miniaturized chemical synthesis with a powerful analytical tool to validate the outcome of many different synthesis pathways beyond applications in the life sciences. Thereby, due to the radical miniaturization of chemical synthesis, thousands of molecules can be synthesized. This in turn should allow ambitious research, e.g., finding novel synthesis routes or directly screening for photocatalysts. Herein, different technologies are discussed that might be involved in this endeavor. A special emphasis is given to the obstacles that need to be tackled when depositing tiny amounts of materials to many different extremely miniaturized reaction sites.

show abstract

Phoenics: A Bayesian Optimizer for Chemistry

Cited by 310 publications

References 64 publications

Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems

Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems

Universal Chemical Synthesis and Discovery with ‘The Chemputer’

Miniaturized and Automated Synthesis of Biomolecules—Overview and Perspectives

Contact Info

Product

Resources

About