Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry

by   Prema Dhorma Lama, et al.

The mechanistic underpinnings of asymmetric catalysis at atomic levels provide shortcuts for developing the potential value of chiral catalysts beyond the current state-of-the-art. In the enantioselective redox transformations, the present intuition-driven studies require a systematic approach to support their intuitive idea. Arguably, the most systematic approach would be based on the reliable quantitative structure-selectivity relationship of diverse and dissimilar chiral scaffolds in an optimal feature space that is universally applied to reactions. Here, we introduce a predictive workflow for the extension of the reaction scope of chiral catalysts across name reactions. For this purpose, whole geometry descriptors were encoded from DFT optimized 3D structures of multiple catalyst scaffolds, 113 catalysts in 9 clusters. The molecular descriptors were verified by the statistical comparison of the enantioselective predictive classification models built from each descriptors of chiral iodoarenes. More notably, capturing the whole molecular geometry through one hot encoding of split three-dimensional molecular fingerprints presented reliable enantioselective predictive regression models for three different name reactions by recycling the data and metadata obtained across reactions. The potential use value of this workflow and the advantages of recyclability, compatibility, and generality proved that the workflow can be applied for name reactions other than the aforementioned name reactions (out of samples). Furthermore, for the consensus prediction of ensemble models, this global descriptor can be compared with sterimol parameters and noncovalent interaction vectors. This study is one case showing how to overcome the sparsity of experimental data in organic reactions, especially asymmetric catalysis.


page 7

page 16

page 17

page 23

page 24

page 29

page 31

page 42


QSAR Classification Modeling for Bioactivity of Molecular Structure via SPL-Logsum

Quantitative structure-activity relationship (QSAR) modelling is effecti...

Investigating 3D Atomic Environments for Enhanced QSAR

Predicting bioactivity and physical properties of molecules is a longsta...

Constant Size Molecular Descriptors For Use With Machine Learning

A set of molecular descriptors whose length is independent of molecular ...

Descriptor Selection via Self-Paced Learning for Bioactivity of Molecular Structure in QSAR Classification

Quantitative structure-activity relationship (QSAR) modelling is effecti...

Lipophilicity Prediction with Multitask Learning and Molecular Substructures Representation

Lipophilicity is one of the factors determining the permeability of the ...

WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials

We introduce weighted atom-centered symmetry functions (wACSFs) as descr...

Mol-PECO: a deep learning model to predict human olfactory perception from molecular structures

While visual and auditory information conveyed by wavelength of light an...

Please sign up or login with your details

Forgot password? Click here to reset