Premium
Cover Image, Volume 38, Issue 21
Publication year - 2017
Publication title -
journal of computational chemistry
Language(s) - English
Resource type - Reports
SCImago Journal Rank - 0.907
H-Index - 188
eISSN - 1096-987X
pISSN - 0192-8651
DOI - 10.1002/jcc.24872
Subject(s) - lasso (programming language) , elastic net regularization , cover (algebra) , computer science , volume (thermodynamics) , artificial intelligence , information retrieval , algorithm , data mining , world wide web , engineering , thermodynamics , physics , mechanical engineering , feature selection
LASSO/Elastic Net regressions are representative modern statistical/machine learning techniques that allow extraction of important information from a large amount of data. However, use of these techniques for organic reaction analysis is rare. On page 1825, Shigeru Yamaguchi and colleagues perform CoMFA (Comparative Molecular Field Analysis) using LASSO/Elastic Net regressions, thereby extracting and visualizing important steric effects in organic reactions. Specifically, regression analysis between digitized molecular structures (0,1 vectors calculated from 3D‐molecular structures) and reaction outcomes has been performed using LASSO/Elastic Net. (DOI: 10.1002/jcc.24791 )