BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Memento EPFL// BEGIN:VEVENT SUMMARY:Swiss Chemical Society (SCS) Lectureship - Prof. Scott Denmark (Un iversity of Illinois) DTSTART:20230920T161500 DTEND:20230920T171500 DTSTAMP:20260427T201435Z UID:54f2b07889d81e12336ae44129d0d0eb09b8575400279ac8abc3bed3 CATEGORIES:Conferences - Seminars DESCRIPTION:Prof. Scott Denmark\, University of Illinois at Urbana-Champai gn (UIUC)\, USA\nLink to poster\n\nTitle: Application of Chemoinformatics and Machine Learning to Enantioselective Catalysis\n\nAbstract:\nThe devel opment of synthetic methods in organic chemistry has historically been dri ven by Edisonian empiricism. Catalyst design is no exception wherein exper imentalists attempt to qualitatively recognize patterns in catalyst struct ures to improve catalyst selectivity and efficiency. However\, this approa ch is hindered by the inherent limitations of the human brain to find patt erns in large collections of data\, and the lack of quantitative guideline s to aid catalyst selection. Chemoinformatics provides an attractive alter native for several reasons: no mechanistic information is needed\; catalys t structures can be characterized by 3D-descriptors which quantify the ste ric and electronic properties of thousands of candidate molecules\; and th e suitability of a given catalyst candidate can be quantified by comparing its properties to a computationally derived model on the basis of experim ental data. The ability to accurately predict a selective catalyst using a set of non-optimal data remains a Grand Challenge of machine learning wit h respect to asymmetric catalysis. \n\nThis lecture will describe a newly developed\, chemoinformatic workflow that consists of the following compo nents: (A) construction of an in silico library of a large collection of c onceivable\, synthetically accessible catalysts of a particular scaffold\; (B) calculation of robust chemical descriptors for each scaffold (C) sele ction of a representative subset of the catalysts in this space. This subs et is termed the Universal Training Set (UTS)\, so named because it is agn ostic to reaction or mechanism. (D) Collection of the training data\, and (E) application of modern machine learning methods to generate models that predict the enantioselectivity of each member of the in silico library. T hese models are evaluated with an external test set of catalysts. The vali dated models can then be used to select the optimal catalyst for a given r eaction. Recent illustrations include enantioselective addition of thiols to acyl imines\, atropselective iodination of pyridines and enantioselecti ve vinylogous Mukaiyama aldol reactions. Solutions to challenges presented by small data sets and failed regression analysis will be presented.\n\n\ nSpeaker's biography:\nScott E. Denmark was born in Lynbrook\, NY in 1953. He obtained a S. B. from the Massachusetts Institute of Technology in 197 5 and a D.Sc. Tech. from the ETH-Zürich under the direction of Albert Esc henmoser in 1980. That same year he was appointed as assistant professor a t the University of Illinois and since 1991 has been the Reynold C. Fuson Professor of Chemistry.\nProfessor Denmark has won a number of honors incl uding the Pedler and Robert Robinson Medals (RSC)\, the Aldrich Award for Creative Work in Synthetic Organic Chemistry\, Brown Award for Creative Re search in Synthetic Methods\, the F. S. Kipping Award in Silicon Chemistry (ACS)\, the Prelog Medal\, Noyori Prize and the Paracelsus Prize.  He is currently on the Board of Directors of Organic Reactions and Organic Syn theses and serves on the Editorial Advisory Boards of the Journal of the  American Chemical Society\, the Journal of Organic Chemistry and Organ ic Letters.\n\nLab website: https://denmarkgroup.illinois.edu/ \n\n\n  LOCATION:BCH 2201 https://plan.epfl.ch/?room==BCH%202201 STATUS:CONFIRMED END:VEVENT END:VCALENDAR