News

New machine learning approach speeds up search for molecular conformers

CEST researchers developed a new procedure based on active-learning Bayesian optimization (BO) and quantum chemistry methods to search for molecular conformers
A graphic showing a front cover describing the conformer search method
Photo showing CEST doctoral candidate Lincan Fang
CEST doctoral candidate Lincan Fang

Conformer search continues to be a topic of great interest in computational chemistry, drug design and material science. It is a challenging endeavor due to the high dimensionality of the search space and the computational cost of accurate quantum chemical methods needed to determine the molecular structure and energy. Previously, searching for molecular conformers meant that thousands of structures needed to be relaxed first. Therefore, this process took up considerable time and computational resources even when applied to small molecules.

A recent paper authored by Lincan Fang, Esko Makkonen, Milica Todorovic, Patrick Rinke, and Xi Chen proposes a molecular conformer search procedure that combines an active learning Bayesian optimization (BO) algorithm with quantum chemistry methods to address this challenge. BO active learning smartly samples the structures with low energies or high energy uncertainties, thus minimizing the required data points.

In this paper, the authors tested the procedure on four amino acids (cysteine, serine, tryptophan and aspartic acid).  After only 1000 single-point calculations and approximately 80 structure relaxations, which is less than 10% of the computational cost of the current fastest method, the team found the low-energy conformers in good agreement with experimental measurements and reference calculations.

First author Fang now plans to extend the method to search for structures of molecules that are bonded to nanoclusters.

This research paper is published in the Journal of Chemical Theory and Computation and has been selected as a supplementary cover of the issue.

doi.org/10.1021/acs.jctc.0c00648

  • Published:
  • Updated:
Share
URL copied!

Read more news

Games Now!
Research & Art Published:

Games Now! – Open lectures on game development

Games Now! is an open lecture series on the dominant topics and emerging trends in games.
Future Digital Mobility Management
Research & Art Published:

Do you drive a car in metropolitan area? Come and test how to make motoring routes smoother and safer.

During the autumn, an international Code the Streets pilot will be implemented in metropolitan area, where motorists will be offered alternative driving routes with a navigator. We are now looking for testers for the navigation app who have an Android phone.
Ths picture shows Assistant Professor Ciprian Domnisoru and Professor, Nobel Laureate David Card.
Research & Art Published:

Research co-operation with a Nobel Laureate

According to Assistant Professor Ciprian Domnisoru, David Card is a meticulous, hard-working, kind, and fun co-author who often uses a Finnish painting as his Zoom background.
Speaker photos of How to win with platform strategy with Tero Ojanperä, Bengt Holmström, Timo Vuori, Maija Hovila, Matias Järnefelt, Michael Tushman
Research & Art Published:

Recording and Q&A now available from the Platform Strategy Seminar 5 October, 2021

The Aalto University seminar "How to Win with Platform Strategy" with top experts from MIT, Harvard, Aalto University, and industry took place on 5 October, 2021 both online and onsite at Aalto campus in Espoo. On this page you can find the recording of the event and Q&A.