Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

El Agente Cuántico: Automating quantum simulations.

Reports on progress in physics. Physical Society (Great Britain)·2026
Same author

Determination of niobium and tantalum in niobium-tantalum ores by closed acid digestion-inductively coupled plasma optical emission spectrometry.

RSC advances·2026
Same author

Radiogenomic modeling of EGFR mutation status in brain metastases from lung adenocarcinoma: a multicenter study with biological interpretability.

NPJ digital medicine·2026
Same author

Hierarchical microtopology and phase-specific delivery functionally restore ultralong nerve continuity across species.

Science advances·2026
Same author

Calceolarioside B alleviates airway barrier dysfunction and inflammation via targeting P2Y<sub>6</sub>R in OVA-triggered asthma.

Biochemical pharmacology·2026
Same author

Mapping the crystallization landscape of rare earth MOFs: a high-throughput investigation of structure, kinetics, and selectivity.

Chemical science·2026

Related Experiment Video

Updated: Jun 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

508

Automated electrosynthesis reaction mining with multimodal large language models (MLLMs).

Shi Xuan Leong1,2, Sergio Pablo-García1,3,4, Zijian Zhang3,4

  • 1Department of Chemistry, University of Toronto, Lash Miller Chemical Laboratories 80 St. George Street ON M5S 3H6 Toronto Canada alan@aspuru.com.

Chemical Science
|October 14, 2024
PubMed
Summary

Multimodal large language models (MLLMs) can now mine electrosynthesis reactions from diverse data formats, overcoming limitations of previous tools. This breakthrough accelerates chemical knowledge discovery and data-driven research.

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.6K
Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms
08:28

Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms

Published on: March 3, 2023

959

Related Experiment Videos

Last Updated: Jun 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

508
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.6K
Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms
08:28

Automated Multimodal Stimulation and Simultaneous Neuronal Recording from Multiple Small Organisms

Published on: March 3, 2023

959

Area of Science:

  • Chemistry
  • Materials Science
  • Artificial Intelligence

Background:

  • Extracting chemical knowledge from legacy formats like publications and patents is challenging.
  • Existing reaction mining tools struggle with heterogeneous data (text, tables, figures).
  • Automated reaction mining is crucial for accelerating materials and reaction discovery.

Purpose of the Study:

  • To explore multimodal large language models (MLLMs) for automated electrosynthesis reaction mining.
  • To overcome the limitations of single-modality reaction mining toolkits.
  • To develop a pipeline for integrating diverse data inputs for chemical knowledge extraction.

Main Methods:

  • Compiled a dataset (MERMES-T24) of 65 articles for benchmarking.
  • Evaluated five prominent MLLMs on reaction diagram parsing and cross-modality data interdependencies.
  • Integrated successful MLLM capabilities into the MERMES toolkit.
  • Utilized single-shot visual prompts and image pre-processing techniques.

Main Results:

  • The leading MLLM achieved ≥96% accuracy in both reaction diagram parsing and cross-modality analysis.
  • The MERMES toolkit demonstrated effective end-to-end MLLM-powered pipeline for knowledge extraction.
  • Successfully integrated article retrieval, information extraction, and multimodal analysis.

Conclusions:

  • MLLMs offer a powerful solution for analyzing diverse data inputs in electrosynthesis reaction mining.
  • The MERMES toolkit streamlines and automates the extraction of chemical knowledge.
  • This work advances the digitization of chemistry knowledge for data-driven research.