# Structure Prediction from Chemical Formula Using Periodic Descriptors

https://mdr.nims.go.jp/datasets/ac7d6c24-6891-49e4-9781-8d66e2f81132

## File

- [2025秋季応用物理学会.pdf](https://mdr.nims.go.jp/filesets/8a9fde09-a966-41d7-9dde-f1394dfb11f4/download) ([Detail](https://mdr.nims.go.jp/filesets/8a9fde09-a966-41d7-9dde-f1394dfb11f4.md))

## Id

ac7d6c24-6891-49e4-9781-8d66e2f81132

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-09-12T02:05:42.244697Z

## Updated at

2025-09-12T23:30:19.467589Z

## Published at

2025-09-12T23:17:25.777086Z

## Doi

https://doi.org/10.48505/nims.5762

## First published url



## Date published



## Recorded date published



## Resource type

conference_presentation

## Manuscript type

na

## Collection



## Title

- title: Structure Prediction from Chemical Formula Using Periodic Descriptors
  title_type: original
  lang: en

## Description

- description: "Recent advances in machine learning and generative models have opened
    new opportunities for exploring novel functional materials. However, many of the
    proposed candidates, especially those generated through formula-based searches,
    lack structural information, posing a bottleneck for simulation and experimental
    design. In this study, we explore the potential of our previously proposed periodic
    descriptors [1], which are low-dimensional and chemically structured features
    derived from the periodic table, for predicting crystal structure directly from
    chemical formulas.\r\nWe construct classification models trained on approximately
    150,000 experimentally reported inorganic compounds from the AtomWork-Adv. (AWA)
    database [2] to predict structures, including space groups and Pearson symbols.
    Our models achieve top-3 accuracies of ~0.70 for space group and ~0.76 for Pearson
    symbol classification. These results demonstrate that compositional patterns captured
    through periodic trends can be effectively linked to structural tendencies, enabling
    prototype structure inference.\r\nWe further compare our models with benchmark
    classification tools and analyze prediction consistency across structure classes.
    This approach addresses the challenge of missing structural data in early-stage
    materials screening and provides a simple, composition-only method to guide structural
    assumptions for novel candidates. Future applications will apply this method to
    newly generated formulas from chemical space exploration algorithms. Structure
    prediction prior to simulation or experimental evaluation will support a more
    integrated inverse design framework in inorganic materials discovery."
  description_type: abstract
  lang: eng

## Creator

- name: Yen-Ju Wu
  role: author
  orcid: https://orcid.org/0000-0003-2647-3407
  organization: National Institute for Materials Science
  department: Center for Basic Research on Materials/Data-driven Materials Research
    Field/Data-driven Inorganic Materials Group
- name: Yibin Xu
  role: author
  orcid: https://orcid.org/0000-0001-8600-8748
  organization: National Institute for Materials Science
  department: Center for Basic Research on Materials/Data-driven Materials Research
    Field/Data-driven Inorganic Materials Group

## Contact agent



## Publisher



## Managing organization



## Keyword

- subject: periodic descriptor
  schema: not_defined
- subject: structure prediction
  schema: not_defined
- subject: machine learning
  schema: not_defined
- subject: template substitution
  schema: not_defined

## Rights

- identifier: http://rightsstatements.org/vocab/InC/1.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal



## Conference

name: 第８6回応用物理学会　秋季学術講演会
start_date: 2025-09-07
end_date: 2025-09-10
identifier: https://meeting.jsap.or.jp/

## Related item



## Funding



## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 8a9fde09-a966-41d7-9dde-f1394dfb11f4
  filename: 2025秋季応用物理学会.pdf
  content_type: application/pdf
  size: 219156
  md5: 19b4301e39880cd139f9a131f47749da

## Thumbnail

fileset_id: 8a9fde09-a966-41d7-9dde-f1394dfb11f4
filename: 2025秋季応用物理学会.pdf