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

Artificial neural network model for predicting membrane protein types.

Y D Cai1, X J Liu, K C Chou

  • 1Shanghai Research Centre of Biotechnology, Chinese Academy of Sciences. yac@aber.ac.uk

Journal of Biomolecular Structure & Dynamics
|March 14, 2001
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

[Relationship between small vessel disease load and cerebral blood flow and white matter integrity in patients with subcortical ischemic vascular dementia].

Zhonghua yi xue za zhi·2026
Same author

[Aggressive NK-cell leukemia with CD5(+)CD10(-) monoclonal B cell lymphocytosis and hemophagocytic lymphohistiocytosis: a case report and literature review].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2026
Same author

Digestible indispensable amino acid score of energy-providing ingredients commonly used in diets.

The British journal of nutrition·2026
Same author

[Performance simulation study of a modified root canal irrigation needle based on computational fluid dynamics].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2025
Same author

[Co-incidence of sexually transmitted diseases in female sex workers in Yunnan Province, 2023].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

Splicing of a core clock gene regulates seasonal adaptations by a winter gating mechanism.

bioRxiv : the preprint server for biology·2025
Same journal

Anti-mycobacterial activity of phytocompounds from <i>Ricinus communis</i> L. - an integrated <i>in-vitro</i> and <i>in-silico</i> approach.

Journal of biomolecular structure & dynamics·2026
Same journal

Binding studies of the X-ray characterized [SnMe<sub>2</sub>Cl<sub>2</sub>(Me<sub>2</sub>phen)] complex with human serum albumin: experimental and molecular docking approaches.

Journal of biomolecular structure & dynamics·2026
Same journal

Computational design and experimental validation of peptide inhibitors to disrupt urease enzyme maturation in pathogenic bacteria <i>Proteus mirabilis</i>.

Journal of biomolecular structure & dynamics·2026
Same journal

Wavelet-domain multiway spectral separation of free drug, DNA, and drug-DNA complex profiles for quantitative binding analysis based on fractional occupancy (<i>θ</i>).

Journal of biomolecular structure & dynamics·2026
Same journal

Gene expression and microsecond scale conformational dynamics suggest potential regulatory mechanisms for the expanded subtilase family of <i>T. rubrum</i>.

Journal of biomolecular structure & dynamics·2026
Same journal

Deciphering the Role of Sugar Osmolytes in Free and Nano forms to Mitigate Protein Aggregation: Insights from Biophysical and Microscopic Studies.

Journal of biomolecular structure & dynamics·2026
See all related articles

This study classifies membrane proteins using amino acid composition. A neural network model accurately predicts protein types, demonstrating high self-consistency and cross-validation rates.

Area of Science:

  • Biochemistry
  • Bioinformatics
  • Computational Biology

Background:

  • Membrane proteins are crucial cellular components with diverse functions.
  • Classifying membrane proteins into types (Type I, Type II, multipass, lipid-anchored, GPI-anchored) is essential for understanding their roles.
  • Accurate prediction of membrane protein types aids in biological research.

Purpose of the Study:

  • To develop a computational method for classifying membrane proteins into five distinct types.
  • To utilize T. Kohonen's self-organization model (a neural network) for this classification task.
  • To evaluate the model's performance based on amino acid composition.

Main Methods:

  • Amino acid composition analysis of membrane proteins.
  • Application of T. Kohonen's self-organization model, a type of neural network.

Related Experiment Videos

  • Performance evaluation using self-consistency and cross-validation metrics.

    • Main Results:

    • The self-organization model achieved a high self-consistency rate of 94.80%.
    • The model demonstrated a cross-validation accuracy of 77.76%.
    • The neural network exhibited robust fault-tolerant abilities in predicting membrane protein types.

    Conclusions:

    • T. Kohonen's self-organization model is effective for predicting membrane protein types based on amino acid composition.
    • The model's high accuracy and fault tolerance make it a valuable tool in membrane protein research.
    • This computational approach facilitates the classification and study of diverse membrane proteins.