Skip to content
DraconiticResearch
Search Sources API
186,546 studies31 sourcesUpdated 54 min ago
Peer-reviewedCC BY-NC-ND 4.0JACS Au

Mapping the Molecular Universe

  • Daniel Hannah1,2
  • Yumin Zhang1,2
  • Stanley Whittingham3
  • Martin Winter4,5
  • Y. Shirley Meng6,7
  • Qichao Hu1,2
  • Kang Xu1,2,8
8 affiliations
  1. 1SES AI Corp. , , ,
  2. 2Molecular Universe Pte , ,
  3. 3Binghamton University , , , ,
  4. 4Forschungszentrum Jülich , , ,
  5. 5University of Münster , , ,
  6. 6University of Chicago , , , ,
  7. 7Argonne National Laboratory , , , ,
  8. 8The Ohio State University , , , ,
Read full textPDFDOICite

Abstract

The success of large-language-models highlighted the importance of datasets, whose quantity, quality, and diversity dictate the accuracy and creativity of artificial intelligence (AI) systems in learning and inferring. However, in scientific domains, such datasets required for domain-specific AI/machine-learning (ML) models do not exist most of the time. In this perspective, by examining the logics and rationales behind the construction and mapping of a universe for small organic molecules (108–1012), we explore what new capabilities AI can bring to the materials discoveries. We identify the elusive structure–property relationship as a core challenge for new materials design and explore the possibility AI tools could enable us to design based on targeted properties instead of the structural derivation. In a broader context, we further discuss what challenges and limitations AI-driven material sciences still face and envision possible avenues into the future of AI4Materials.

Versions

Related

  1. Molecular Mapping of Atherosclerotic Plaques with MALDI Mass Spectrometry Imaging
    Dawid Leksa, Dorota Bartusik-Aebisher, Daniel Roshan Justin Raj +6
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0Full textPhysical chemistryCrossrefEurope PMC
  2. Mapping the limits of equilibrium in sheared granular liquid crystals
    Jacopo Bilotto, Martin Trulsson, Jean-François Molinari
    Physical Review ResearchPeer-reviewedPublisher termsMaterials & polymersCrossref
  3. Machine learning based distribution mapping of gold in soil samples using aqua regia digestion and solid phase extraction
    Maryam Rezazadeh, Dariush Esmaeily
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textAnalytical chemistryCrossref
  4. Systematic mapping of bimetallic catalyst combinations for floating catalyst chemical vapor deposition growth of single-walled carbon nanotubes
    Anastasios Karakassides, Lauri Suominen, Hirotaka Inoue +2
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  5. A Generalized Theory for the Structural and Spatial Mapping of Energy, Entropy, and Free Energy
    Michael K. Gilson, Joe Cruz, Kunhuan Liu +4
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{hannah2026mapping,
  title = {{Mapping the Molecular Universe}},
  author = {Daniel Hannah and Yumin Zhang and Stanley Whittingham and Martin Winter and Y. Shirley Meng and Qichao Hu and Kang Xu},
  journal = {JACS Au},
  year = {2026},
  month = oct,
  doi = {10.1021/jacsau.6c01250},
  url = {https://pubs.acs.org/jaaucr/article/6/10/5531/5449020/Mapping-the-Molecular-Universe},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Mapping the Molecular Universe
AU  - Daniel Hannah
AU  - Yumin Zhang
AU  - Stanley Whittingham
AU  - Martin Winter
AU  - Y. Shirley Meng
AU  - Qichao Hu
AU  - Kang Xu
PY  - 2026
DA  - 2026/10/12
JO  - JACS Au
DO  - 10.1021/jacsau.6c01250
UR  - https://pubs.acs.org/jaaucr/article/6/10/5531/5449020/Mapping-the-Molecular-Universe
AB  - The success of large-language-models highlighted the importance of datasets, whose quantity, quality, and diversity dictate the accuracy and creativity of artificial intelligence (AI) systems in learning and inferring. However, in scientific domains, such datasets required for domain-specific AI/machine-learning (ML) models do not exist most of the time. In this perspective, by examining the logics and rationales behind the construction and mapping of a universe for small organic molecules (108–1012), we explore what new capabilities AI can bring to the materials discoveries. We identify the elusive structure–property relationship as a core challenge for new materials design and explore the possibility AI tools could enable us to design based on targeted properties instead of the structural derivation. In a broader context, we further discuss what challenges and limitations AI-driven material sciences still face and envision possible avenues into the future of AI4Materials.
SN  - 2691-3704
ER  -