Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-12244
For citation please use:
Main Title: Datasets: Machine learning of solvent effects on molecular spectra and reactions
Author(s): Gastegger, Michael
Schütt, Kristof T.
Müller, Klaus-Robert
Type: Generic Research Data
Is Supplement To: 10.1039/D1SC02742E
Language Code: en
Abstract: Fast and accurate simulation of complex chemical systems in environments such as solutions is a long standing challenge in theoretical chemistry. In recent years, machine learning has extended the boundaries of quantum chemistry by providing highly accurate and efficient surrogate models of electronic structure theory, which previously have been out of reach for conventional approaches. Those models have long been restricted to closed molecular systems without accounting for environmental influences, such as external electric and magnetic fields or solvent effects. Here, we introduce the deep neural network FieldSchNet for modeling the interaction of molecules with arbitrary external fields. FieldSchNet offers access to a wealth of molecular response properties, enabling it to simulate a wide range of molecular spectra, such as infrared, Raman and nuclear magnetic resonance. Beyond that, it is able to describe implicit and explicit molecular environments, operating as a polarizable continuum model for solvation or in a quantum mechanics / molecular mechanics setup. We employ FieldSchNet to study the influence of solvent effects on molecular spectra and a Claisen rearrangement reaction. Based on these results, we use FieldSchNet to design an external environment capable of lowering the activation barrier of the rearrangement reaction significantly, demonstrating promising venues for inverse chemical design.
URI: https://depositonce.tu-berlin.de/handle/11303/13458
http://dx.doi.org/10.14279/depositonce-12244
Issue Date: 26-Jul-2021
Date Available: 30-Jul-2021
DDC Class: 500 Naturwissenschaften und Mathematik
Subject(s): machine learning
quantum chemistry
solvent effects
response properties
molecular spectra
Sponsor/Funder: EC/H2020/792572/EU/Machine Learning for Catalytic Carbon Dioxide Activation/MachineCat
BMBF, 01IS18037A, Verbundprojekt BIFOLD-BZML: Berlin Institute for the Foundations of Learning and Data
License: https://choosealicense.com/licenses/mit/
Appears in Collections:FG Maschinelles Lernen » Research Data

Files in This Item:
README.txt

Information on the data format and instructions for accessing the data.

Format: Text | Size: 4.21 kB
Download
ethanol_vacuum.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 8.04 MB
Download
ethanol_continuum_evw.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 24.1 MB
Download
ethanol_continuum_mt.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 16.07 MB
Download
ethanol_qmmm.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 32.1 MB
Download
ethanol_methanol_qmmm.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 1.13 MB
Download
ate_vacuum.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 113.02 MB
Download
ate_qmmm.tgz

Tar Gzip of ASE db-file

Format: TAR GZ | Size: 98.72 MB
Download

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.