Crystal structures classifier for an evolutionary algorithm structure predictor

Mario Valle, Artem R. Oganov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Citations (Scopus)

Abstract

USPEX is a crystal structure predictor based on an evolutionary algorithm. Every USPEX run produces hundreds or thousands of crystal structures, some of which may be identical. To ease the extraction of unique and potentially interesting structures we applied usual high-dimensional classification concepts to the unusual field of crystallography. We experimented with various crystal structure descriptors, distinct distance measures and tried different clustering methods to identify groups of similar structures. These methods are already applied in combinatorial chemistry to organic molecules for a different goal and in somewhat different forms, but are not widely used for crystal structures classification. We adopted a visual design and validation method in the development of a library (CrystalFp) and an end-user application to select and validate method choices, to gain users' acceptance and to tap into their domain expertise. The use of the classifier has already accelerated the analysis of US-PEX output by at least one order of magnitude, promoting some new crystallographic insight and discovery. Furthermore the visual display of key algorithm indicators has led to diverse, unexpected discoveries that will improve the USPEX algorithms.

Original languageEnglish
Title of host publicationVAST'08 - IEEE Symposium on Visual Analytics Science and Technology, Proceedings
Pages11-18
Number of pages8
DOIs
Publication statusPublished - 2008
Externally publishedYes
EventIEEE Symposium on Visual Analytics Science and Technology, VAST'08 - Columbus, OH, United States
Duration: 21 Oct 200823 Oct 2008

Publication series

NameVAST'08 - IEEE Symposium on Visual Analytics Science and Technology, Proceedings

Conference

ConferenceIEEE Symposium on Visual Analytics Science and Technology, VAST'08
Country/TerritoryUnited States
CityColumbus, OH
Period21/10/0823/10/08

Keywords

  • I.5.2 [pattern recognition]: Design methodology - classifier design and evaluation
  • J.2 [physical sciences and engineering]: Chemistry

Fingerprint

Dive into the research topics of 'Crystal structures classifier for an evolutionary algorithm structure predictor'. Together they form a unique fingerprint.

Cite this