Optimization of molecular characteristics via machine learning based on continuous representation of molecules

Kyosuke Sato, Kenji Tsuruta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We demonstrate an automatic materials design method using continuous representation of molecule and its atomic arrangement via a neural network algorithm. This method is applied to optimizing and predicting the HOMO-LUMO gap within the molecules composed of carbon, oxygen, nitrogen, fluorine, and hydrogen. Adopting the Quantum Machine 9 (QM9) dataset as a training dataset for the molecules, we first established a continuous representation of molecules in a latent space, then predicted molecules that have target values of the HOMO-LUMO gap. In the gap maximization calculation, CF4 with the largest gap value in the QM9 dataset was automatically found despite there is no a priori data for the gap. In the case of a target gap value of 0.10 hartree, we found a new molecule whose gap value is closer to 0.10 hartree than any other molecules in the QM9 dataset.

Original languageEnglish
Title of host publicationTHERMEC 2021 - International Conference on Processing and Manufacturing of Advanced Materials Processing, Fabrication, Properties, Applications
EditorsMihail Ionescu, Christof Sommitsch, Cecilia Poletti, Ernst Kozeschnik, Tara Chandra
PublisherTrans Tech Publications Ltd
Pages1492-1496
Number of pages5
ISBN (Print)9783035736304
DOIs
Publication statusPublished - 2021
EventInternational Conference on Processing and Manufacturing of Advanced Materials Processing, Fabrication, Properties, Applications, THERMEC 2021 - Vienna, Austria
Duration: May 10 2021May 14 2021

Publication series

NameMaterials Science Forum
Volume1016 MSF
ISSN (Print)0255-5476
ISSN (Electronic)1662-9752

Conference

ConferenceInternational Conference on Processing and Manufacturing of Advanced Materials Processing, Fabrication, Properties, Applications, THERMEC 2021
CountryAustria
CityVienna
Period5/10/215/14/21

Keywords

  • HOMO-LUMO gap
  • Machine learning
  • Materials design
  • Neural network
  • SMILES

ASJC Scopus subject areas

  • Materials Science(all)
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Optimization of molecular characteristics via machine learning based on continuous representation of molecules'. Together they form a unique fingerprint.

Cite this