Automated self-optimization, intensification, and scale-up of photocatalysis in flow

Science, Год журнала: 2024, Номер 383(6681)

Опубликована: Янв. 25, 2024

The optimization, intensification, and scale-up of photochemical processes constitute a particular challenge in manufacturing environment geared primarily toward thermal chemistry. In this work, we present versatile flow-based robotic platform to address these challenges through the integration readily available hardware custom software. Our open-source combines liquid handler, syringe pumps, tunable continuous-flow photoreactor, inexpensive Internet Things devices, an in-line benchtop nuclear magnetic resonance spectrometer enable automated, data-rich optimization with closed-loop Bayesian strategy. A user-friendly graphical interface allows chemists without programming or machine learning expertise easily monitor, analyze, improve photocatalytic reactions respect both continuous discrete variables. system's effectiveness was demonstrated by increasing overall reaction yields improving space-time compared those previously reported processes.

Язык: Английский

---

Applying statistical modeling strategies to sparse datasets in synthetic chemistry

Science Advances, Год журнала: 2025, Номер 11(1)

Опубликована: Янв. 1, 2025

The application of statistical modeling in organic chemistry is emerging as a standard practice for probing structure-activity relationships and predictive tool many optimization objectives. This review aimed tutorial those entering the area chemistry. We provide case studies to highlight considerations approaches that can be used successfully analyze datasets low data regimes, common situation encountered given experimental demands Statistical hinges on (what being modeled), descriptors (how are represented), algorithms modeled). Herein, we focus how various reaction outputs (e.g., yield, rate, selectivity, solubility, stability, turnover number) structures binned, heavily skewed, distributed) influence choice algorithm constructing chemically insightful models.

Язык: Английский

---

The continuing importance of chemical intuition for the medicinal chemist in the era of artificial intelligence

Expert Opinion on Drug Discovery, Год журнала: 2025, Номер unknown

Опубликована: Янв. 14, 2025

Язык: Английский

---

Dataset Design for Building Models of Chemical Reactivity

ACS Central Science, Год журнала: 2023, Номер 9(12), С. 2196 - 2204

Опубликована: Дек. 8, 2023

Models can codify our understanding of chemical reactivity and serve a useful purpose in the development new synthetic processes via, for example, evaluating hypothetical reaction conditions or silico substrate tolerance. Perhaps most determining factor is composition training data whether it sufficient to train model that make accurate predictions over full domain interest. Here, we discuss design datasets ways are conducive data-driven modeling, emphasizing idea set diversity generalizability rely on choice molecular representation. We additionally experimental constraints associated with generating common types chemistry how these considerations should influence dataset building.

Язык: Английский

---

Enhancing chemical synthesis: a two-stage deep neural network for predicting feasible reaction conditions

Journal of Cheminformatics, Год журнала: 2024, Номер 16(1)

Опубликована: Янв. 24, 2024

Abstract In the field of chemical synthesis planning, accurate recommendation reaction conditions is essential for achieving successful outcomes. This work introduces an innovative deep learning approach designed to address complex task predicting appropriate reagents, solvents, and temperatures reactions. Our proposed methodology combines a multi-label classification model with ranking offer tailored condition recommendations based on relevance scores derived from anticipated product yields. To tackle challenge limited data unfavorable contexts, we employed technique hard negative sampling generate that might be mistakenly classified as suitable, forcing refine its decision boundaries, especially in challenging cases. developed excels proposing where exact match recorded solvents reagents found within top-10 predictions 73% time. It also predicts ± 20 ° C temperature 89% test Notably, demonstrates capacity recommend multiple viable conditions, accuracy varying availability records associated each reaction. What sets this apart ability suggest alternative beyond constraints dataset. underscores potential inspire approaches research, presenting compelling opportunity advancing planning elevating engineering. Scientific contribution The combination models provides A novel presented issue scarcity through augmentation. Graphical

Язык: Английский

---

FAIR Data and Software: Improving Efficiency and Quality of Biocatalytic Science

ACS Catalysis, Год журнала: 2024, Номер 14(4), С. 2709 - 2718

Опубликована: Фев. 7, 2024

Biocatalysis is entering a promising era as data-driven science. High-throughput experimentation generates rapidly increasing stream of biocatalytic data, which the raw material for mechanistic and modeling to design improved biocatalysts bioprocesses. However, our laboratory routines scientific practice communicating results are insufficient ensure reproducibility scalability experiments, data management has become bottleneck progress in biocatalysis. In order take full advantage rapid experimental computational technologies, should be findable, accessible, interoperable, reusable (FAIR). FAIRification software achieved by developing standardized exchange formats ontologies, electronic lab notebooks acquisition documentation experimentation, collaborative platforms analyzing repositories publishing together with data. The EnzymeML platform provides extensible tools FAIR scalable digitalization biocatalysis expected improve efficiency research automation guarantee quality science reproducibility. Most all, they foster reasoning creating hypotheses enabling reanalysis previously published thus promote disruptive innovation.

Язык: Английский

---

Accelerating the Development of Sustainable Catalytic Processes through Data Science

Organic Process Research & Development, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

Язык: Английский

---

Opportunities for Machine Learning and Artificial Intelligence to Advance Synthetic Drug Substance Process Development

Organic Process Research & Development, Год журнала: 2023, Номер 27(11), С. 1868 - 1879

Опубликована: Сен. 25, 2023

The goals of this Perspective are threefold: (1) to inform a broad audience, including machine learning (ML) and artificial intelligence (AI) academics professionals, about synthetic drug substance process development, (2) break down the general development task into more tractable subtasks, (3) highlight areas in which might be beneficially developed applied. Application chemical synthesis medicinal compounds has long been discussed resulted number computer-aided planning tools by both academic groups commercial enterprises. focus these efforts primarily centered on retrosynthetic analysis, as seen from perspective chemist. This left significant unrealized opportunities application aid chemist or engineer development.

Язык: Английский

---

Interplay of Computation and Experiment in Enantioselective Catalysis: Rationalization, Prediction, and─Correction?

ACS Catalysis, Год журнала: 2023, Номер 13(21), С. 14285 - 14299

Опубликована: Окт. 26, 2023

The application of computational methods in enantioselective catalysis has evolved from the rationalization observed stereochemical outcome to their prediction and design chiral ligands. This Perspective provides an overview current used, ranging atomistic modeling transition structures involved correlation-based with particular emphasis placed on Q2MM/CatVS method. Using three palladium-catalyzed reactions, namely, conjugate addition arylboronic acids enones, redox relay Heck reaction, Tsuji–Trost allylic amination as case studies, we argue that have become truly equal partners experimental studies that, some cases, they are able correct published assignments. Finally, consequences this approach data-driven discussed.

Язык: Английский

---

Mechanism to model: a physical organic chemistry approach to reaction prediction

Chemical Communications, Год журнала: 2023, Номер 59(72), С. 10711 - 10721

Опубликована: Янв. 1, 2023

Combining a working knowledge of reaction mechanism with statistical modelling is powerful approach to prediction.

Язык: Английский

---