scholarly journals Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

Science ◽  
2018 ◽  
Vol 362 (6416) ◽  
pp. eaat8603 ◽  
Author(s):  
Kangway V. Chuang ◽  
Michael J. Keiser
Keyword(s):  
Machine Learning ◽  
Experimental Design ◽  
Coupling Reaction ◽  
Cross Coupling ◽  
Learning Models ◽  
Applied Machine Learning ◽  
Cross Coupling Reaction ◽  
Reaction Performance ◽  
Test Scenarios ◽  
Machine Learning Models

Ahneman et al. (Reports, 13 April 2018) applied machine learning models to predict C–N cross-coupling reaction yields. The models use atomic, electronic, and vibrational descriptors as input features. However, the experimental design is insufficient to distinguish models trained on chemical features from those trained solely on random-valued features in retrospective and prospective test scenarios, thus failing classical controls in machine learning.

scholarly journals Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

Science ◽  
2018 ◽  
Vol 362 (6416) ◽  
pp. eaat8763 ◽  
Author(s):  
Jesús G. Estrada ◽  
Derek T. Ahneman ◽  
Robert P. Sheridan ◽  
Spencer D. Dreher ◽  
Abigail G. Doyle
Keyword(s):  
Machine Learning ◽  
Cross Coupling ◽  
Feature Model ◽  
Learning Models ◽  
Chemical Feature ◽  
Out Of Sample ◽  
Reaction Performance ◽  
Machine Learning Models

We demonstrate that the chemical-feature model described in our original paper is distinguishable from the nongeneralizable models introduced by Chuang and Keiser. Furthermore, the chemical-feature model significantly outperforms these models in out-of-sample predictions, justifying the use of chemical featurization from which machine learning models can extract meaningful patterns in the dataset, as originally described.

scholarly journals Directly probing the effect of the solvent on a catalyst electronic environment using X-ray photoelectron spectroscopy

RSC Advances ◽  
2015 ◽  
Vol 5 (45) ◽  
pp. 35958-35965 ◽  
Author(s):  
Shuang Men ◽  
Kevin R. J. Lovelock ◽  
Peter Licence
Keyword(s):  
Ionic Liquid ◽  
Photoelectron Spectroscopy ◽  
Coupling Reaction ◽  
Cross Coupling ◽  
Metal Centre ◽  
X Ray ◽  
Electronic Environment ◽  
Cross Coupling Reaction ◽  
Reaction Performance

The anion of an ionic liquid can significantly influence the electronic environment of a metal centre, and thus impact upon reaction performance in a model Suzuki cross coupling reaction.

Improving XGBoost with Imagination Sampling

2020 ◽  
Vol 2 (1) ◽  
pp. 3-6
Author(s):  
Eric Holloway
Keyword(s):  
Machine Learning ◽  
General System ◽  
Learning Models ◽  
Starting Point ◽  
Machine Learning Models

Imagination Sampling is the usage of a person as an oracle for generating or improving machine learning models. Previous work demonstrated a general system for using Imagination Sampling for obtaining multibox models. Here, the possibility of importing such models as the starting point for further automatic enhancement is explored.

Ferromagnetic Chain Based on Verdazyl-Nitroxide Diradical

2020 ◽  
Author(s):  
Evgeny Tretyakov ◽  
Svetlana Zhivetyeva ◽  
Pavel Petunin ◽  
Dmitry Gorbunov ◽  
Nina Gritsan ◽  
...  
Keyword(s):  
Coupling Reaction ◽  
Cross Coupling ◽  
Ferromagnetic Coupling ◽  
Nitronyl Nitroxide ◽  
Triplet Ground State ◽  
One Dimensional ◽  
Cross Coupling Reaction ◽  
Palladium Catalyzed ◽  
Ferromagnetic Chain ◽  
High Yields

<p>Verdazyl-nitroxide diradicals were synthesized using the palladium-catalyzed cross-coupling reaction of the corresponding iodoverdazyls with a nitronyl nitroxide-2-ide gold(I) complex with high yields (up to 82%). The synthesized diradicals were found to be highly thermally stable and have a singlet (D<i>E</i><sub>ST</sub> » -64 cm<sup>–1</sup>) or triplet ground state (D<i>E</i><sub>ST</sub> ³ 25 and 100 cm<sup>–1</sup>), depending on which canonical hydrocarbon diradical type they belong to. Upon crystallization, triplet diradicals form unique one-dimensional (1D) spin <i>S</i> = 1 chains of organic diradicals with intrachain ferromagnetic coupling of <i>J</i>′/<i>k</i><sub>B</sub> from 3 to 6 K.</p>

An Iron-Based Catalyst Enables The Enantioconvergent Synthesis of Chiral 1,1-Diarylalkanes Through a Suzuki-Miyaura Cross-Coupling Reaction

2020 ◽  
Author(s):  
Chet Tyrol ◽  
Nang Yone ◽  
Connor Gallin ◽  
Jeffery Byers
Keyword(s):  
Coupling Reaction ◽  
Cross Coupling ◽  
Coupling Reactions ◽  
Radical Intermediates ◽  
Cross Coupling Reactions ◽  
Cross Coupling Reaction ◽  
Boronic Esters ◽  
Carbon Centered Radical ◽  
Iron Based ◽  
High Yields

By using an iron-based catalyst, access to enantioenriched 1,1-diarylakanes was enabled through an enantioselective Suzuki-Miyaura crosscoupling reaction. The combination of a chiral cyanobis(oxazoline) ligand framework and 1,3,5-trimethoxybenzene additive were essential to afford high yields and enantioselectivities in cross-coupling reactions between unactivated aryl boronic esters and a variety of benzylic chlorides, including challenging ortho-substituted benzylic chloride substrates. Mechanistic investigations implicate a stereoconvergent pathway involving carbon-centered radical intermediates.

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Ni(0)-Catalyzed α-Allylic Alkylation of Regular Ketones with 1,3-Dienes under pH and Redox-neutral Conditions

2019 ◽  
Author(s):  
Tiantian Chen ◽  
Yang Yang ◽  
Liyu Xie ◽  
Haijian Yang ◽  
Guangbin Dong ◽  
...  
Keyword(s):  
Oxidative Addition ◽  
Coupling Reaction ◽  
Cross Coupling ◽  
Dual Role ◽  
Allylic Alkylation ◽  
Cross Coupling Reaction ◽  
Neutral Conditions

<p>We report a Ni(0)-catalyzed cross coupling reaction between simple ketones and 1,3-dienes. A variety of a-allylic alkylation products were formed in an 1,2-addition manner with excellent regioselectivity. Water was found to significantly accelerate this transformation. A HO-Ni-H species generated from oxidative addition of Ni(0) to H<sub>2</sub>O is proposed to play a “dual role” in activating both the ketone and the diene substrate.</p>

Sign in / Sign up

Export Citation Format

Share Document