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 Experiment Videos

Question Answering System for Chemistry.

Xiaochi Zhou1, Daniel Nurkowski2, Sebastian Mosbach1

  • 1Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, Cambridge CB3 0AS, U.K.

Journal of Chemical Information and Modeling
|August 2, 2021
PubMed
Summary
This summary is machine-generated.

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

Computational modelling workflows for metal-organic polyhedra in The World Avatar.

Physical chemistry chemical physics : PCCP·2026
Same author

Inverse Design of Metal-Organic Polyhedra through Molecular Fragmentation and Evolutionary Optimisation.

Journal of chemical information and modeling·2026
Same author

Single-Atom Pt with Significantly Boosted Performance by Mesoporous Hollow Ceria Support for Dehydrogenation of Methylcyclohexane.

Angewandte Chemie (International ed. in English)·2026
Same author

Reasoning-agent-driven process simulation, optimization, carbon accounting and decarbonization of distillation.

Communications engineering·2026
Same author

Vapor/Vapor-Solid Interfacial Growth of Covalent Organic Framework Membranes on Alumina Hollow Fiber for Advanced Molecular Separation.

Angewandte Chemie (International ed. in English)·2024
Same author

Leveraging Text-to-Text Pretrained Language Models for Question Answering in Chemistry.

ACS omega·2024
Same journal

Mapping Evolution of Molecules across Biochemistry with Assembly Theory.

Journal of chemical information and modeling·2026
Same journal

Structural Proteomics-Based Deciphering of Hydrophobic Packing Fingerprints Informing Protein Thermostability in TIM Barrels.

Journal of chemical information and modeling·2026
Same journal

Bridging between Structure-Based and Data-Driven Affinity Prediction.

Journal of chemical information and modeling·2026
Same journal

Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data.

Journal of chemical information and modeling·2026
Same journal

EnsembleCycPerm: Interpretable Modeling of Cyclic Peptide Permeability through Solvent-Dependent Conformational Ensembles.

Journal of chemical information and modeling·2026
Same journal

Resolving Conformational Preferences of Monosaccharides from <sup>1</sup>H and <sup>13</sup>C NMR Chemical Shifts Using an Integrated MD and QM Approach.

Journal of chemical information and modeling·2026
See all related articles

A new question answering (QA) system accesses chemical data from knowledge graphs (KGs). This system outperforms existing KGQA systems and search engines for chemistry-related queries.

Area of Science:

  • Chemistry
  • Computer Science
  • Data Science

Background:

  • Knowledge graphs (KGs) offer diverse chemical data.
  • Accessing specific chemical information from KGs can be challenging.
  • Existing question answering (QA) systems may not be optimized for chemical data.

Purpose of the Study:

  • To develop and evaluate a proof-of-concept QA system for chemical data retrieval from KGs.
  • To enhance the accuracy and quality of answers for chemistry-related questions.
  • To compare the system's performance against existing KGQA systems and search engines.

Main Methods:

  • Training specialized question classification and named entity recognition models for chemistry.
  • Implementing a novel topic model for question-to-ontology affiliation.

Related Experiment Videos

  • Developing an automated method for generating training questions from ontologies.
  • Evaluating the QA system against baseline KGQA systems, Google, and WolframAlpha.

    • Main Results:

    • The QA system demonstrates superior performance in answering chemistry-related questions compared to a baseline KGQA system.
    • The system's novel topic model improves answer quality and handles diverse ontology structures.
    • An automatically generated training set of 432,989 questions proved effective for model training.
    • The QA system outperforms Google and WolframAlpha for specific types of chemical queries.

    Conclusions:

    • The developed QA system provides an effective method for accessing chemical data from knowledge graphs.
    • The system's specialized models and novel topic modeling approach enhance retrieval accuracy.
    • This research contributes to more efficient and accurate chemical information discovery.