Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 20 min ago
PreprintCC BYChemRxiv

AutomaticMolCraft: A Web Interface for 3D Molecular Generation, Dataset Curation, and Structure–Property Analysis

  • Thanapat Worakul1,2
  • Osvaldo Hernandez Cuellar1,2
  • Clémence Corminboeuf1,2,3
  1. 1Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering
  2. 2École Polytechnique Fédérale de Lausanne (EPFL)
  3. 3National Center for Competence in Research-Catalysis (NCCR-Catalysis)
Open at sourceDOICite

Abstract

Here, we present AutomaticMolCraft, a locally deployed browser platform for running and organising 3D molecular discovery campaigns. It is designed to complement MolCraftDiffusion, a 3D molecular-generation platform that provides the computational layer for model training, 3D molecular generation, and analysis, while AutomaticMolCraft serves as the interactive interface for visualising molecular data and generated results. It also supports molecular data management while keeping data, computations, and results connected and traceable. The three applications are selected to showcase distinct capabilities of the interface across data-driven molecular discovery tasks. First, we demonstrate the data management and visualisation components by curating three organocatalyst datasets and comparing their molecular structures and properties to support the selection. Second, we show how these data components connect with the computational layer of MolCraftDiffusion by running and comparing property-directed generation workflows for producing 3D molecules with specified scalar properties. Third, we extend this integration to steric-property-directed generation, where AutomaticMolCraft is used to identify underrepresented regions of property space, generate molecules toward those regions, and incorporate the resulting candidates back into the molecular data for subsequent analysis. The codebases are available at: https://github.com/lcmd-epfl/MolCraftDiffusion and https://github.com/lcmd-epfl/AutomaticMolCraft.

Related

  1. Modeling Reactions on the Solid-Liquid Interface with Next Generation Extended Lagrangian Quantum-Based Molecular Dynamics.
    Rae A Corrigan Grove, Kevin G Kleiner, Joshua Finkelstein +5
    The journal of physical chemistry. C, Nanomaterials and interfacesPeer-reviewedCC BY-NC-NDFull textElectrochemistry & energyEurope PMC
  2. Curvature-Aware Flow Matching for Molecular Structure Generation
    Samir Darouich, Juliane Geisler, Jacob W. Toney +4
    arXivPreprintCC BY 4.0Full textPhysical chemistryarXiv
  3. Advances in enzyme and interface engineering for next-generation biosensors
    Nicolas Mano
    Current Opinion in ElectrochemistryPeer-reviewedCC BY 4.0Full textAnalytical chemistryHAL
  4. Electrospray ion beam deposition of small peptides on solid surfaces: A molecular level description of the glutathione/copper interface
    C. Méthivier, P. Cornette, D. Costa +1
    Applied Surface SciencePeer-reviewedLicence not stated10 citedGeneral chemistryHAL
  5. Charged Interface in Battery Breaks Molecular Chiral Symmetry
    Chao Chen, Dengpan Dong, Yanjin Liu +8
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{worakul2026automaticmolcraft,
  title = {{AutomaticMolCraft: A Web Interface for 3D Molecular Generation, Dataset Curation, and Structure–Property Analysis}},
  author = {Thanapat Worakul and Osvaldo Hernandez Cuellar and Clémence Corminboeuf},
  howpublished = {ChemRxiv},
  year = {2026},
  month = aug,
  doi = {10.26434/chemrxiv.15008080/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008080/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - AutomaticMolCraft: A Web Interface for 3D Molecular Generation, Dataset Curation, and Structure–Property Analysis
AU  - Thanapat Worakul
AU  - Osvaldo Hernandez Cuellar
AU  - Clémence Corminboeuf
PY  - 2026
DA  - 2026/08/31
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15008080/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008080/v1
AB  - Here, we present AutomaticMolCraft, a locally deployed browser platform for running and organising 3D molecular discovery campaigns. It is designed to complement MolCraftDiffusion, a 3D molecular-generation platform that provides the computational layer for model training, 3D molecular generation, and analysis, while AutomaticMolCraft serves as the interactive interface for visualising molecular data and generated results. It also supports molecular data management while keeping data, computations, and results connected and traceable. The three applications are selected to showcase distinct capabilities of the interface across data-driven molecular discovery tasks. First, we demonstrate the data management and visualisation components by curating three organocatalyst datasets and comparing their molecular structures and properties to support the selection. Second, we show how these data components connect with the computational layer of MolCraftDiffusion by running and comparing property-directed generation workflows for producing 3D molecules with specified scalar properties. Third, we extend this integration to steric-property-directed generation, where AutomaticMolCraft is used to identify underrepresented regions of property space, generate molecules toward those regions, and incorporate the resulting candidates back into the molecular data for subsequent analysis. The codebases are available at: https://github.com/lcmd-epfl/MolCraftDiffusion and https://github.com/lcmd-epfl/AutomaticMolCraft.
ER  -