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

Molecular Models02:00

Molecular Models

Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries
Classification and Mechanical Properties of Synthetic Polymers01:28

Classification and Mechanical Properties of Synthetic Polymers

Synthetic polymers are classified as elastomers, fibers, or plastics based on their crystallinity. Crystallinity, the degree of long-range order in the solid state, influences the mechanical properties (stretching or contracting) of elastomers. Elastomers are flexible polymers that can expand or contract easily upon the application of an external force. They have numerous crosslinks that pull them back into their original shape when stress is removed. Silicones, for instance, are highly elastic...
Experimental Determination of Chemical Formula02:37

Experimental Determination of Chemical Formula

The elemental makeup of a compound defines its chemical identity, and chemical formulas are the most concise way of representing this elemental makeup. When a compound’s formula is unknown, measuring the mass of its constituent elements is often the first step in determining the formula experimentally.

You might also read

Related Articles

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

Sort by
Same author

A novel glioma prognosis marker CAMK2A is related to immune microenvironment and may be involved in Ras/Raf/MEK/ERK signaling.

Scientific reports·2026
Same author

Biomimetic Wavy-Crimped Porous Structure Enhances Tendon Attachment Reconstruction via Integrin-FAK/Src-MAPK Signaling Axis.

Advanced healthcare materials·2026
Same author

Exosomes derived from human umbilical cord mesenchymal stem cells attenuate neuroinflammation in intracerebral hemorrhage rats by modulating lactylation modification.

Journal of translational medicine·2026
Same author

Recent advances in immunoregulatory biomaterials for tendon healing: From immune remodeling to functional regeneration.

Materials today. Bio·2026
Same author

Macrophage Polarization-Targeted Hydrogels for Bone Regeneration.

Tissue engineering. Part B, Reviews·2026
Same author

Transfer factor alleviates bovine mastitis and protects mammary epithelial barrier via the TAK1/NF-κB/MLCK signaling axis.

Journal of animal science·2026

Related Experiment Video

Updated: May 26, 2026

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
14:34

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

A chemically-aware validation framework for benchmarking large language models in materials synthesis planning.

Aobo Zhang1

  • 1Department of Chemistry, Tsinghua University, Beijing, 100084, China. aobozhang2020@hotmail.com.

Journal of Cheminformatics
|May 24, 2026
PubMed
Summary
This summary is machine-generated.

We developed a new framework to assess AI-generated chemistry protocols, ensuring scientific accuracy beyond generic language models. This benchmark quantifies AI

Keywords:
Automated synthesisCheminformaticsEvaluation metricsGenerative AILLM benchmarkingScientific NLP

More Related Videos

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics
10:52

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Published on: April 12, 2019

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

Related Experiment Videos

Last Updated: May 26, 2026

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
14:34

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics
10:52

Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics

Published on: April 12, 2019

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

Area of Science:

  • Artificial Intelligence in Chemistry
  • Chemical Synthesis Protocol Verification
  • Natural Language Processing for Scientific Applications

Background:

  • Current benchmarks for AI-generated text often overlook the specific, rigorous requirements of scientific domains like chemistry.
  • Evaluating the scientific validity of AI-generated synthesis protocols necessitates domain-specific metrics that go beyond general language understanding.

Purpose of the Study:

  • To introduce a domain-tailored verification framework for assessing the scientific quality of AI-generated chemical synthesis protocols.
  • To establish a quantitative benchmark for automated protocol generation, addressing limitations of generic NLP evaluations.
  • To measure the discrepancy between conceptual synthesis pathways and precise experimental parameters in AI outputs.

Main Methods:

  • Development of a verification framework incorporating two quantitative metrics: a framework score for logical coherence and a weighted detail score for experimental parameter precision.
  • Application of a curated dataset of Self-Amplifying Circuits (SAC) as a testbed for fine-tuning mainstream open-source Large Language Models (LLMs).
  • Generalization of the developed benchmark methodology to encompass broader material synthesis protocols.

Main Results:

  • Demonstration of a domain-specific approach that effectively evaluates AI-generated synthesis protocols for scientific rigor.
  • Quantification of the gap between the conceptual feasibility and parametric exactness of LLM-generated protocols.
  • Successful fine-tuning of open-source LLMs using a specialized dataset, leading to improved protocol generation.

Conclusions:

  • The proposed framework provides a robust method for evaluating the scientific quality of AI-generated synthesis protocols.
  • This work establishes a crucial benchmark for advancing automated protocol generation in chemistry and related fields.
  • The methodology is adaptable and can be extended to assess protocols for various material synthesis applications.