Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Multiple Regression

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...

You might also read

Related Articles

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

Sort by

Same author

SPMFE-UNet: shape perception and multi-scale features enhancement UNet for robust abdominal organ and skin lesion segmentation.

Biomedical physics & engineering express·2026

Same author

Identification of genes associated with liver ischemia-reperfusion injury after liver transplantation by WGCNA and PPI network analyses.

Transplant immunology·2025

Same author

Development of a medication literacy assessment scale for patients with mental disorders in recovery in China: a mixed-methods Delphi study.

Frontiers in psychiatry·2025

Same author

Genetic Spectrum and Genotype-Phenotype Correlations in a Chinese Cohort With Nanophthalmos With Secondary Angle-Closure Glaucoma.

Investigative ophthalmology & visual science·2025

Same author

Hepatitis C virus NS5A protein promotes the lysosomal degradation of diacylglycerol O-acyltransferase 1 (DGAT1) via endosomal microautophagy.

Autophagy reports·2025

Same author

Real estate valuation with multi-source image fusion and enhanced machine learning pipeline.

PloS one·2025

Search research articles

Related Experiment Video

Updated: Nov 1, 2025

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Predicting antifreeze proteins with weighted generalized dipeptide composition and multi-regression feature selection

Shunfang Wang¹, Lin Deng², Xinnan Xia³

¹Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming, 650504, China. sfwang_66@ynu.edu.cn.

BMC Bioinformatics

|June 24, 2021

Summary

This study introduces a new method combining weighted generalized dipeptide composition (W-GDipC) and a two-stage regression feature selection (LRMR-Ri) for predicting antifreeze proteins. The approach significantly enhances classification accuracy, demonstrating its effectiveness for biological antifreeze ability prediction.

Keywords:

Antifreeze proteins prediction Ensemble feature selection Lasso regression Ridge regression Two-stage multiple regressions Weighted general dipeptide composition

More Related Videos

Identification of Plant Ice-binding Proteins Through Assessment of Ice-recrystallization Inhibition and Isolation Using Ice-affinity Purification

Identification of Plant Ice-binding Proteins Through Assessment of Ice-recrystallization Inhibition and Isolation Using Ice-affinity Purification

Published on: May 5, 2017

Determining the Ice-binding Planes of Antifreeze Proteins by Fluorescence-based Ice Plane Affinity

Determining the Ice-binding Planes of Antifreeze Proteins by Fluorescence-based Ice Plane Affinity

Published on: January 15, 2014

Related Experiment Videos

Last Updated: Nov 1, 2025

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Identification of Plant Ice-binding Proteins Through Assessment of Ice-recrystallization Inhibition and Isolation Using Ice-affinity Purification

Identification of Plant Ice-binding Proteins Through Assessment of Ice-recrystallization Inhibition and Isolation Using Ice-affinity Purification

Published on: May 5, 2017

Determining the Ice-binding Planes of Antifreeze Proteins by Fluorescence-based Ice Plane Affinity

Determining the Ice-binding Planes of Antifreeze Proteins by Fluorescence-based Ice Plane Affinity

Published on: January 15, 2014

Area of Science:

Biochemistry and Molecular Biology
Structural Biology
Bioinformatics

Background:

Antifreeze proteins (AFPs) are crucial for organisms surviving in cold environments by inhibiting ice crystal formation.
Accurate prediction of AFP structure and function is vital but underexplored due to challenges in sequence feature extraction and selection.
Current research lacks comprehensive methods for identifying key features that determine AFP classification.

Purpose of the Study:

To develop and validate a novel feature representation and selection method for improved antifreeze protein classification.
To enhance the accuracy of predicting antifreeze proteins using sequence-derived features.
To assess the generalizability of the proposed method for other protein classification tasks, such as membrane proteins.

Main Methods:

Proposed a weighted generalized dipeptide composition (W-GDipC) for feature representation.
Introduced an ensemble feature selection method, LRMR-Ri, employing a two-stage regression approach.
Utilized Lasso, Ridge regression, Maximal Information Coefficient, and Relief for initial feature subset identification.

Main Results:

The LRMR-Ri and W-GDipC method achieved high accuracy (ACC: 95.56%, RE: 97.06%, MCC: 0.9105) with SVM on the antifreeze protein dataset.
The proposed method significantly outperformed individual feature selection algorithms like Lasso, Ridge, Mic, and Relief.
Demonstrated robust performance in both binary (antifreeze proteins) and multiple (membrane proteins) classification tasks.

Conclusions:

The combined LRMR-Ri and W-GDipC approach substantially improves antifreeze protein prediction accuracy.
The method shows broad applicability and reliability, achieving good results in membrane protein classification.
This work provides a significant advancement in computational approaches for protein function and structure prediction.