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

Predicting membrane proteins and their types by extracting various sequence features into Chou's general PseAAC.

Ahmad Hassan Butt1, Nouman Rasool2, Yaser Daanial Khan3

  • 1Department of Computer Science, School of Systems and Technology, University of Management and Technology, C-II, Johar Town, P.O. Box 10033, Lahore, 54770, Pakistan. ahmad.hassan@umt.edu.pk.

Molecular Biology Reports
|September 22, 2018
PubMed
Summary

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

predALZ: An Ensemble Learning Framework for Identifying Genetic Biomarkers in Familial Alzheimer's Disease.

Current drug targets·2026
Same author

XCPP: A Multi-model Explainable Deep Learning Framework for Accurate Identification of Cell-Penetrating Peptides from Structured Sequence Features.

Current drug targets·2026
Same author

Deep learning based prediction of RNA 5hmC modifications using composite feature representations and comparative benchmarking with transformer models.

BioData mining·2026
Same author

The Adaptive Lab Mentor (ALM): An AI-Driven IoT Framework for Real-Time Personalized Guidance in Hands-On Engineering Education.

Sensors (Basel, Switzerland)·2025
Same author

A Solar Cell Compatible Super-Wideband Flexible Transparent Antenna with Enhanced Axial Ratio.

Micromachines·2025
Same author

An ensemble strategy for piRNA identification through hybrid moment-based feature modeling.

Scientific reports·2025

This study introduces an enhanced computational model for predicting membrane proteins (MPs), crucial for drug discovery. The new framework improves accuracy by integrating statistical moments and updated datasets, offering a more efficient alternative to lab-based methods.

Area of Science:

  • Biochemistry
  • Computational Biology
  • Bioinformatics

Background:

  • Membrane proteins (MPs) are vital for numerous biological functions and are key targets for pharmaceutical agents.
  • Experimental annotation of MPs is often costly, time-consuming, and sometimes infeasible.
  • Computational models (CMs) offer an efficient alternative for MP prediction and annotation.

Purpose of the Study:

  • To develop and validate an improved computational framework for the accurate prediction of membrane proteins.
  • To enhance existing datasets with the latest membrane protein information from UniProtKB.
  • To evaluate the efficacy of statistical moments combined with neural networks for MP prediction.

Main Methods:

  • A novel MP prediction framework utilizing computational intelligence and a statistical moments-based feature set.
Keywords:
Amino acidsConfusion matrixJackknife testsMathew’s correlation coefficientMembrane proteinsNeural networks

Related Experiment Videos

  • Enhancement of the existing dataset by incorporating new membrane proteins from the UniProtKB database.
  • Training a multilayer neural network using back-propagation techniques for prediction.

    • Main Results:

    • The proposed framework demonstrates improved accuracy in predicting membrane proteins.
    • The integration of statistical moments significantly contributes to prediction performance.
    • The enhanced dataset provides a more comprehensive basis for model training and validation.

    Conclusions:

    • The developed computational model, leveraging statistical moments and neural networks, offers a highly effective and efficient method for membrane protein prediction.
    • This approach provides a valuable tool for accelerating drug discovery and understanding protein functions.
    • The study highlights the potential of advanced computational techniques in overcoming limitations of experimental annotation methods.