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

Search research articles

Related Experiment Videos

A new approach to predicting protein folding types

K C Chou¹, C T Zhang

¹Upjohn Research Laboratories, Kalamazoo, Michigan 49001.

Journal of Protein Chemistry

|April 1, 1993

Summary

A novel method predicts protein folding types using amino acid composition and vector correlation. This approach offers higher accuracy and a more intuitive physical model for protein structure prediction.

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

[An analysis of clinical and genetic feature in pulmonary artery sarcoma].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2025

Same author

[The preliminary application of mNGS in the diagnosis of invasive fungal sinusitis].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2024

Same author

[Mechanical circulatory support combined with immunomodulation treatment for patients with fulminant myocarditis: a single-center real-world study].

Zhonghua xin xue guan bing za zhi·2022

Same author

Overexpression of miR-101-2 in donor cells improves the early development of Holstein cow somatic cell nuclear transfer embryos.

Journal of dairy science·2019

Same author

Protective effects of trehalose on frozen-thawed ovarian granulosa cells of cattle.

Animal reproduction science·2018

Same author

[Molecular detection and genotyping of human papillomavirus].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2018

Area of Science:

Biophysics
Computational Biology
Structural Biology

Background:

Protein folding is crucial for biological function.
Accurate prediction of protein folding types remains a challenge.
Existing methods have limitations in accuracy and interpretability.

Purpose of the Study:

To introduce a new method for predicting protein folding types based on amino acid composition.
To provide a more intuitive physical model for protein structure classification.
To improve the accuracy and applicability of protein folding type prediction.

Main Methods:

Representing proteins as 20-dimensional vectors based on amino acid composition.
Calculating protein similarity using the mutual projection of these vectors (correlation angle).
Predicting folding types by comparing protein vectors to standard vectors for four types (all alpha, all beta, alpha + beta, alpha/beta).

Main Results:

Achieved an 83.6% average accuracy on a development set of 64 proteins.
Attained a 91.4% average accuracy on an independent set of 35 proteins with known X-ray structures.
Demonstrated superior performance compared to existing methods in both self-consistency and extrapolating effectiveness.

Conclusions:

The proposed vector-based method provides a highly accurate and intuitive approach to predicting protein folding types.
This method offers significant improvements over existing techniques, showing great value in practical applications.
The enhanced accuracy and physical interpretability highlight the method's potential for advancing structural biology research.

Related Experiment Videos