Probing the chemical ‘reactome’ with high-throughput experimentation data

Nature Chemistry, Journal Year: 2024, Volume and Issue: 16(4), P. 633 - 643

Published: Jan. 2, 2024

High-throughput experimentation (HTE) has the potential to improve our understanding of organic chemistry by systematically interrogating reactivity across diverse chemical spaces. Notable bottlenecks include few publicly available large-scale datasets and need for facile interpretation these data's hidden insights. Here we report development a high-throughput analyser, robust statistically rigorous framework, which is applicable any HTE dataset regardless size, scope or target reaction outcome, yields interpretable correlations between starting material(s), reagents outcomes. We data landscape with disclosure 39,000+ previously proprietary reactions that cover breadth chemistry, including cross-coupling chiral salt resolutions. The analyser was validated on hydrogenation datasets, showcasing elucidation significant relationships components outcomes, as well highlighting areas bias specific spaces necessitate further investigation.

Language: Английский

---

The case for data science in experimental chemistry: examples and recommendations

Nature Reviews Chemistry, Journal Year: 2022, Volume and Issue: 6(5), P. 357 - 370

Published: April 21, 2022

Language: Английский

---

Machine Learning Yield Prediction from NiCOlit, a Small-Size Literature Data Set of Nickel Catalyzed C–O Couplings

Journal of the American Chemical Society, Journal Year: 2022, Volume and Issue: 144(32), P. 14722 - 14730

Published: Aug. 8, 2022

Synthetic yield prediction using machine learning is intensively studied. Previous work has focused on two categories of data sets: high-throughput experimentation data, as an ideal case study, and sets extracted from proprietary databases, which are known to have a strong reporting bias toward high yields. However, predicting yields published reaction remains elusive. To fill the gap, we built set nickel-catalyzed cross-couplings organic publications, including scope optimization information. We demonstrate importance source failed experiments emphasize how publication constraints shape exploration chemical space by synthetic community. While models still fail perform out-of-sample predictions, this shows that adding knowledge enables fair predictions in low-data regime. Eventually, hope unique public database will foster further improvements methods for more realistic context.

Language: Английский

---

Single-atom heterogeneous catalysts for sustainable organic synthesis

Trends in Chemistry, Journal Year: 2022, Volume and Issue: 4(4), P. 264 - 276

Published: Feb. 21, 2022

Language: Английский

---

Comparative Evaluation of Light‐Driven Catalysis: A Framework for Standardized Reporting of Data**

Angewandte Chemie International Edition, Journal Year: 2022, Volume and Issue: 61(28)

Published: June 13, 2022

Light-driven homogeneous and heterogeneous catalysis require a complex interplay between light absorption, charge separation, transfer, catalytic turnover. Optical irradiation parameters as well reaction engineering aspects play major roles in controlling performance. This multitude of factors makes it difficult to objectively compare light-driven catalysts provide an unbiased performance assessment. Scientific Perspective highlights the importance collecting reporting experimental data catalysis. A critical analysis benefits limitations commonly used indicators is provided. Data collection according FAIR principles discussed context future automated analysis. The authors propose minimum dataset basis for unified community encouraged support development this parameter list through open online repository.

Language: Английский

---