Autonomous chemical research with large language models

Nature, Journal Year: 2023, Volume and Issue: 624(7992), P. 570 - 578

Published: Dec. 20, 2023

Transformer-based large language models are making significant strides in various fields, such as natural processing

Language: Английский

---

A Brief Introduction to Chemical Reaction Optimization

Chemical Reviews, Journal Year: 2023, Volume and Issue: 123(6), P. 3089 - 3126

Published: Feb. 23, 2023

From the start of a synthetic chemist's training, experiments are conducted based on recipes from textbooks and manuscripts that achieve clean reaction outcomes, allowing scientist to develop practical skills some chemical intuition. This procedure is often kept long into researcher's career, as new developed similar protocols, intuition-guided deviations through learning failed experiments. However, when attempting understand systems interest, it has been shown model-based, algorithm-based, miniaturized high-throughput techniques outperform human intuition optimization in much more time- material-efficient manner; this covered detail paper. As many chemists not exposed these undergraduate teaching, leads disproportionate number scientists wish optimize their reactions but unable use methodologies or simply unaware existence. review highlights basics, cutting-edge, modern well its relation process scale-up can thereby serve reference for inspired each techniques, detailing several respective applications.

Language: Английский

---

A field guide to flow chemistry for synthetic organic chemists

Chemical Science, Journal Year: 2023, Volume and Issue: 14(16), P. 4230 - 4247

Published: Jan. 1, 2023

This review explores the benefits of flow chemistry and dispels notion that it is a mysterious “black box”, demonstrating how can push boundaries organic synthesis through understanding its governing principles.

Language: Английский

---

Closed-loop optimization of general reaction conditions for heteroaryl Suzuki-Miyaura coupling

Science, Journal Year: 2022, Volume and Issue: 378(6618), P. 399 - 405

Published: Oct. 27, 2022

General conditions for organic reactions are important but rare, and efforts to identify them usually consider only narrow regions of chemical space. Discovering more general reaction requires considering vast space derived from a large matrix substrates crossed with high-dimensional conditions, rendering exhaustive experimentation impractical. Here, we report simple closed-loop workflow that leverages data-guided down-selection, uncertainty-minimizing machine learning, robotic discover conditions. Application the challenging consequential problem heteroaryl Suzuki-Miyaura cross-coupling identified double average yield relative widely used benchmark was previously developed using traditional approaches. This study provides practical road map solving multidimensional optimization problems search spaces.

Language: Английский

---

Accelerated Chemical Reaction Optimization Using Multi-Task Learning

ACS Central Science, Journal Year: 2023, Volume and Issue: 9(5), P. 957 - 968

Published: April 13, 2023

Functionalization of C-H bonds is a key challenge in medicinal chemistry, particularly for fragment-based drug discovery (FBDD) where such transformations require execution the presence polar functionality necessary protein binding. Recent work has shown effectiveness Bayesian optimization (BO) self-optimization chemical reactions; however, all previous cases these algorithmic procedures have started with no prior information about reaction interest. In this work, we explore use multitask (MTBO) several silico case studies by leveraging data collected from historical campaigns to accelerate new reactions. This methodology was then translated real-world, chemistry applications yield pharmaceutical intermediates using an autonomous flow-based reactor platform. The MTBO algorithm be successful determining optimal conditions unseen experimental activation reactions differing substrates, demonstrating efficient strategy large potential cost reductions when compared industry-standard process techniques. Our findings highlight as enabling tool workflows, representing step-change utilization and machine learning goal accelerated optimization.

Language: Английский

---

Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back

Science, Journal Year: 2023, Volume and Issue: 382(6677)

Published: Dec. 21, 2023

A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In first study, experimentally realized 294 unreported across three automatic iterations design-make-test-analyze cycles while exploring structure-function space four rarely reported scaffolds. each iteration, property prediction models that guided exploration learned structure-property diverse scaffold derivatives, which were multistep syntheses a variety reactions. The second study exploited trained explored chemical previously discover nine top-performing within lightly space.

Language: Английский

---

A machine-learning tool to predict substrate-adaptive conditions for Pd-catalyzed C–N couplings

Science, Journal Year: 2023, Volume and Issue: 381(6661), P. 965 - 972

Published: Aug. 31, 2023

Machine-learning methods have great potential to accelerate the identification of reaction conditions for chemical transformations. A tool that gives substrate-adaptive palladium (Pd)-catalyzed carbon-nitrogen (C-N) couplings is presented. The design and construction this required generation an experimental dataset explores a diverse network reactant pairings across set conditions. large scope C-N was actively learned by neural models using systematic process experiments. showed good performance in validation: Ten products were isolated more than 85% yield from range with out-of-sample reactants designed challenge models. Importantly, developed workflow continually improves prediction capability as corpus data grows.

Language: Английский

---

Active learning guides discovery of a champion four-metal perovskite oxide for oxygen evolution electrocatalysis

Nature Materials, Journal Year: 2023, Volume and Issue: 23(1), P. 108 - 115

Published: Nov. 2, 2023

Language: Английский

---

Self-Driving Laboratory for Polymer Electronics

Chemistry of Materials, Journal Year: 2023, Volume and Issue: 35(8), P. 3046 - 3056

Published: March 9, 2023

Owing to the chemical pluripotency and viscoelastic nature of electronic polymers, polymer electronics have shown unique advances in many emerging applications such as skin-like electronics, large-area printed energy devices, neuromorphic computing but their development period is years-long. Recent advancements automation, robotics, learning algorithms led a growing number self-driving (autonomous) laboratories that begun revolutionize accelerated discovery materials. In this perspective, we first introduce current state autonomous laboratories. Then analyze why it challenging conduct research by an laboratory highlight needs. We further discuss our efforts building laboratory, namely Polybot, for automated synthesis characterization polymers processing fabrication into devices. Finally, share vision using different types research.

Language: Английский

---

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(40), P. 21699 - 21716

Published: Sept. 27, 2023

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable fundamentally interesting, because they often involve new physical phenomena compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) automated experimentation have widely proposed to accelerate target identification synthesis planning. In this Perspective, we argue the data-driven methods commonly used today well-suited for optimization not realization of exceptional molecules. Finding such outliers should be possible using ML, only by shifting away from traditional ML approaches tweak composition, crystal structure, reaction pathway. We highlight case studies high-Tc oxide superconductors superhard demonstrate challenges ML-guided discovery discuss limitations automation task. then provide six recommendations development capable discovery: (i) Avoid tyranny middle focus on extrema; (ii) When data limited, qualitative predictions direction than interpolative accuracy; (iii) Sample what can made how make it defer optimization; (iv) Create room (and look) unexpected while pursuing your goal; (v) Try fill-in-the-blanks input output space; (vi) Do confuse human understanding model interpretability. conclude a description these integrated into workflows, which enable materials.

Language: Английский

---