首页|Justus-Liebig-University Reports Findings in Machine Learning (Leveraging Limite d Experimental Data with Machine Learning: Differentiating a Methyl from an Ethy l Group in the Corey-Bakshi-Shibata Reduction)
Justus-Liebig-University Reports Findings in Machine Learning (Leveraging Limite d Experimental Data with Machine Learning: Differentiating a Methyl from an Ethy l Group in the Corey-Bakshi-Shibata Reduction)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating from Giessen, Ger many, by NewsRx correspondents, research stated, "We present a case study on how to improve an existing metal-free catalyst for a particularly difficult reactio n, namely, the Corey-Bakshi-Shibata (CBS) reduction of butanone, which constitut es the classic and prototypical challenge of being able to differentiate a methy l from an ethyl group. As there are no known strategies on how to address this c hallenge, we leveraged the power of machine learning by constructing a realistic (for a typical laboratory) small, albeit high-quality, data set of about 100 re actions (run in triplicate) that we used to train a model in combination with a key-intermediate graph (of substrate and catalyst) to predict the differences in Gibbs activation energies DD of the enantiomeric reaction paths." Our news editors obtained a quote from the research from Justus-Liebig-Universit y, "With the help of this model, we were able to select and subsequently screen a small selection of catalysts and increase the selectivity for the CBS reductio n of butanone to 80% enantiomeric excess (ee), the highest possibl e value achieved to date for this substrate with a metal-free catalyst, thereby also exceeding the best available enzymatic systems (64% ee) and t he selectivity with Corey's original catalyst (60% ee). This trans lates into a>50% improvement in relative D from 0.9 to 1.4 kcal mol. We underscore the transformative potential of machine learning in accelerating catalyst design because we rely on a manageable small data set and a key-intermediate graph representing a combination of catalyst and substrate graphs in lieu of a transition-state model."
GiessenGermanyEuropeCyborgsEmerg ing TechnologiesMachine Learning
NETL
NSTL
