Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 26 min ago
PreprintCC BYChemRxiv

Paper2CIF: An AI Agent for Reconstructing Atomistic Models to Discover Structure-Reactivity Relationships

  • Qixin Zhou1,2
  • Yonghang Yue3,4
  • Wenjie Guo5,6
  • Yongfa Zhu5,6,7,8
  • Yan Guo3,4
8 affiliations
  1. 1Department of Materials Science and Engineering
  2. 2City University of Hong Kong
  3. 3School of Environment
  4. 4University of Science and Technology of China
  5. 5Department of Chemistry
  6. 6Tsinghua University
  7. 7College of Chemistry and Molecular Sciences
  8. 8Anhui Normal University
Open at sourcePDFDOICite

Abstract

Reinterpreting published chemical findings requires explicit atomic structures that connect experimental observations with reactivity. Here we report Paper2CIF, an artificial intelligence (AI) agent that reconstructs sample-specific atomic structures from published chemical evidence for structure-reactivity relationship investigations. Across 171 interdisciplinary articles, Paper2CIF achieves 97.08% phase identification accuracy and 91.23% final structural accuracy, with correct structures satisfying all applicable reported constraints, including composition, site occupancy, and local coordination. Calculations on reconstructed BiVO4 structures reveal distortion-dependent spatial contributions to the transition dipole, guiding targeted synthesis toward enhanced near-edge photon conversion. The resulting BiVO4-based Z-scheme pair exhibits a 3.47-fold increase in apparent quantum yield from 4.51% to 15.64% at 475 nm, compared with a 1.03-fold increase from 18.51% to 19.02% at 365 nm. The solar-to-hydrogen efficiency increases from 0.969% to 1.448% for overall water splitting. Paper2CIF establishes atomic reconstruction as a common basis for deriving chemical mechanisms from published evidence and translating them into experimentally testable principles for materials synthesis.

Related

  1. Precision synthesis and mechanochemical structure–reactivity relationships of mechanophore-bearing polymers with diverse conformations
    Seiyoung Yoon, Javad Tamnanloo, Ling-Jo Wu +6
    Nature CommunicationsPeer-reviewedCC BY-NC-ND 4.0Full textMaterials & polymersCrossref
  2. From Photoswitch to Polycycle: Structure–Reactivity Relationships in the Photoinduced Isomerization–Cyclization of Amino(hetero)arylidene‐thiazolidine‐2,4‐diones
    Vincent Bruneau, Johanne Coutard, Nina Bukhtiiarova +7
    Chemistry - A European JournalPeer-reviewedLicence not statedFull textMaterials & polymersHAL
  3. Structural, supramolecular and computational insights into the ALS inhibitor pyroxsulam: crystal structure, reactivity and bioactivity
    Krishna Murthy Potla, Suneetha Vankayalapati, Cheerlin Mishma Justin Nathaniel +7
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textInorganic & organometallic chemistryCrossref
  4. Nitrous oxide-derived vinyldiazotates: structure and reactivity
    Christeena Mathew, Alexandre Genoux, Damien Chen +4
    Chemical CommunicationsPeer-reviewedCC BYOrganic chemistryHAL
  5. Understanding the Structure and Assembly of Dense, Solvent-Free Cellulose Derivatives through Atomistic Force-Field Comparisons
    Debashish Mukherji, Tiago Espinosa de Oliveira, Marcus Müller
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{zhou2026paper2cif,
  title = {{Paper2CIF: An AI Agent for Reconstructing Atomistic Models to Discover Structure-Reactivity Relationships}},
  author = {Qixin Zhou and Yonghang Yue and Wenjie Guo and Yongfa Zhu and Yan Guo},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15010164/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010164/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Paper2CIF: An AI Agent for Reconstructing Atomistic Models to Discover Structure-Reactivity Relationships
AU  - Qixin Zhou
AU  - Yonghang Yue
AU  - Wenjie Guo
AU  - Yongfa Zhu
AU  - Yan Guo
PY  - 2026
DA  - 2026/10/09
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15010164/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010164/v1
AB  - Reinterpreting published chemical findings requires explicit atomic structures that connect experimental observations with reactivity. Here we report Paper2CIF, an artificial intelligence (AI) agent that reconstructs sample-specific atomic structures from published chemical evidence for structure-reactivity relationship investigations. Across 171 interdisciplinary articles, Paper2CIF achieves 97.08% phase identification accuracy and 91.23% final structural accuracy, with correct structures satisfying all applicable reported constraints, including composition, site occupancy, and local coordination. Calculations on reconstructed BiVO4 structures reveal distortion-dependent spatial contributions to the transition dipole, guiding targeted synthesis toward enhanced near-edge photon conversion. The resulting BiVO4-based Z-scheme pair exhibits a 3.47-fold increase in apparent quantum yield from 4.51% to 15.64% at 475 nm, compared with a 1.03-fold increase from 18.51% to 19.02% at 365 nm. The solar-to-hydrogen efficiency increases from 0.969% to 1.448% for overall water splitting. Paper2CIF establishes atomic reconstruction as a common basis for deriving chemical mechanisms from published evidence and translating them into experimentally testable principles for materials synthesis.
ER  -