# Generating eco-friendly ionic liquids with enhanced CO2 solubility using language models

https://mdr.nims.go.jp/datasets/3360fc4f-3a09-4bfb-97ee-f5b71c3d3a86

## File

- [1-s2.0-S2949747725000065-main (3).pdf](https://mdr.nims.go.jp/filesets/00462734-53b8-4b9c-a4c7-0b351ce6db11/download) ([Detail](https://mdr.nims.go.jp/filesets/00462734-53b8-4b9c-a4c7-0b351ce6db11.md))
- [1-s2.0-S2949747725000065-mmc1 (1).pdf](https://mdr.nims.go.jp/filesets/e07d3a8e-655e-43a9-8bde-e1a50c754bf9/download) ([Detail](https://mdr.nims.go.jp/filesets/e07d3a8e-655e-43a9-8bde-e1a50c754bf9.md))
- [datasets.xlsx](https://mdr.nims.go.jp/filesets/d707a537-1de1-48c0-aecc-7452ea410b12/download) ([Detail](https://mdr.nims.go.jp/filesets/d707a537-1de1-48c0-aecc-7452ea410b12.md))

## Id

3360fc4f-3a09-4bfb-97ee-f5b71c3d3a86

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-12-09T05:29:17.130812Z

## Updated at

2025-12-09T23:30:26.436086Z

## Published at

2025-12-09T23:23:46.528522Z

## Doi



## First published url

https://doi.org/10.1016/j.aichem.2025.100089

## Date published

2025-05-22

## Recorded date published

2025-6

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Generating eco-friendly ionic liquids with enhanced CO2 solubility using
    language models
  title_type: original
  lang: en

## Description

- description: This study presents a viable approach for designing eco-friendly ionic
    liquids (ILs) with enhanced CO2 solubility using language models, specifically
    GPT-2 in conjunction with SMILES-X. The GPT-2 model was fine-tuned on a relatively
    small, unlabeled IL dataset and subsequently used to generate diverse IL structures.
    SMILES-X models, trained on IL datasets labeled with CO2 solubility and eco-toxicity
    values, were employed to predict the properties of the generated ILs. Trends observed
    in the predicted IL properties were validated using density functional theory
    (DFT) and COSMO-RS calculations. The GPT-2 model was then fine-tuned iteratively,
    with the training data updated by including the top generated ILs from previous
    cycles. This iterative process led to a gradual improvement in the properties
    of the generated ILs. It was also observed, however, that continuously adding
    curated generated ILs to the training data eventually caused the model to produce
    correct but unrealistic IL structures. These findings highlight both the potential
    and limitations of language models in designing novel chemicals. Additionally,
    the CO2 adsorption capacity of a surrogate IL was experimentally measured, demonstrating
    the potential of this approach in advancing decarbonization technologies.
  description_type: abstract
  lang: und

## Creator

- name: Adroit T.N. Fajar
  role: author
- name: Guillaume Lambard
  role: author
  orcid: https://orcid.org/0000-0003-0275-4079
  organization: National Institute for Materials Science
- name: Md. Amirul Islam
  role: author
- name: Bidyut B. Saha
  role: author
- name: Zakiah D. Nurfajrin
  role: author
- name: Kevin Septioga
  role: author

## Contact agent



## Publisher

organization: Elsevier BV

## Managing organization



## Keyword

- subject: Generative model
  schema: not_defined
- subject: GPT
  schema: not_defined
- subject: Prediction
  schema: not_defined
- subject: SMILES
  schema: not_defined
- subject: Decarbonization
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Artificial Intelligence Chemistry
  issn: '29497477'
  volume: '3'
  issue: '1'
  article_number: '100089'

## Conference



## Related item



## Funding

- identifier: WPI-I2CNER
  funder_name: International Institute for Carbon-Neutral Energy Research, Kyushu
    University
- identifier: 251FP-22667
  funder_name: Ministry of Education, Culture, Sports, Science and Technology

## 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: 00462734-53b8-4b9c-a4c7-0b351ce6db11
  filename: 1-s2.0-S2949747725000065-main (3).pdf
  content_type: application/pdf
  size: 3404669
  md5: 216cd064290cc131f737299a0c42b3fa
- id: e07d3a8e-655e-43a9-8bde-e1a50c754bf9
  filename: 1-s2.0-S2949747725000065-mmc1 (1).pdf
  content_type: application/pdf
  size: 858226
  md5: 9f0184a44159e4c01fc423cc1411642f
- id: d707a537-1de1-48c0-aecc-7452ea410b12
  filename: datasets.xlsx
  content_type: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  size: 2294315
  md5: f43ec755bf6c838df0c364411b97fea0

## Thumbnail

fileset_id: 00462734-53b8-4b9c-a4c7-0b351ce6db11
filename: 1-s2.0-S2949747725000065-main (3).pdf