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

Visual management of large scale data mining projects.

I Shah1, L Hunter

  • 1American Type Culture Collection, Manassas, VA 20110, USA. ishah@atcc.org

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|July 21, 2000
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

Flow-Xl: a new facility for the analysis of crystallization in flow systems.

Journal of applied crystallography·2024
Same author

A systematic analysis of read-across within REACH registration dossiers.

Computational toxicology (Amsterdam, Netherlands)·2024
Same author

Impact of maternal body mass index (BMI) and the challenges of fetal echocardiography.

Public health·2024
Same author

SMaRT-PCR: sampling using masks and RT-PCR, a non-invasive diagnostic tool for paediatric pulmonary TB.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2024
Same author

Pulmonary hypertension in adults completing tuberculosis treatment.

African journal of thoracic and critical care medicine·2023
Same author

Evaluating structure-based activity in a high-throughput assay for steroid biosynthesis.

Computational toxicology (Amsterdam, Netherlands)·2023
Same journal

Trust, Reproducibility, and Progress: The Roles of Independent Blind Prediction and Assessment and Benchmarking in Computational Biology.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

The Evolving Cyberinfrastructure at the National Institutes of Health to Support Data and AI in Biomedical Research.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

Applications of AI & ML in Biomanufacturing of Cell and Gene Therapies.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

AI for Health: Leveraging Artificial Intelligence to Revolutionize Healthcare.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

Workshop Introduction: Advances of AI Methods in Single Cell Spatial Omics.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

DRIVE-KG: Enhancing variant-phenotype association discovery in understudied complex diseases using heterogeneous knowledge graphs.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
See all related articles

This study introduces a visualization framework to enhance machine learning for enzyme function prediction. The tools improve accuracy by aiding in dataset exploration and result analysis, leading to better learning strategies.

Area of Science:

  • Bioinformatics
  • Machine Learning
  • Data Visualization

Background:

  • Enzyme functional prediction from protein sequence data is crucial.
  • Existing methods based on sequence similarity alone incorrectly assign functions to approximately 6% of enzyme sequences.
  • Machine learning and modular domain representations offer potential to improve prediction accuracy.

Purpose of the Study:

  • To develop and present a unified framework for visualizing machine learning experiments in enzyme function prediction.
  • To improve the accuracy of predicting enzyme function from sequence data.
  • To aid in understanding and identifying weaknesses in sequence representations and learning algorithms.

Main Methods:

  • Designed and conducted over 250 machine learning experiments using information-theoretic decision tree induction and naive Bayesian learning.

Related Experiment Videos

  • Utilized local sequence domain representations for enzyme function classes.
  • Developed graphical user interfaces for data exploration, hypothesis inspection, and result visualization.

    • Main Results:

    • The developed visualization tools significantly aided in understanding experiment successes and failures.
    • Identified weaknesses in modular sequence representations and induction algorithms, suggesting improved learning strategies.
    • Achieved perfect discrimination among various functions for similar sequences in over half of the tested cases.

    Conclusions:

    • The unified visualization framework is effective for managing and interpreting complex machine learning experiments.
    • The tools facilitate the identification of biological explanations for prediction accuracy.
    • This approach enhances the development of more efficient and accurate enzyme function prediction models.