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

MsDBP: Exploring DNA-Binding Proteins by Integrating Multiscale Sequence Information via Chou's Five-Step Rule.

Xiuquan Du1, Yanyu Diao1, Heng Liu2

  • 1The School of Computer Science and Technology , Anhui University , Hefei , Anhui , China.

Journal of Proteome Research
|July 4, 2019
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

A Double-Teacher Model Capable of Exploiting Isomorphic and Heterogeneous Discrepancy Information for Medical Image Segmentation.

Diagnostics (Basel, Switzerland)·2023
Same author

[Pharmacokinetic study of Polydopamine Guttate Pills loaded with active components of Sarcandrae Herba in rats].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2022
Same author

Ginsenoside Rg5 allosterically interacts with P2RY<sub>12</sub> and ameliorates deep venous thrombosis by counteracting neutrophil NETosis and inflammatory response.

Frontiers in immunology·2022
Same author

Over-Expression of an R2R3 MYB Gene, <i>MdMYB108L</i>, Enhances Tolerance to Salt Stress in Transgenic Plants.

International journal of molecular sciences·2022
Same author

Structural Design and Testing of a Micromechanical Resonant Accelerometer.

Micromachines·2022
Same author

Closed-Loop Control and Output Stability Analysis of a Micromechanical Resonant Accelerometer.

Micromachines·2022

A new computational method, MsDBP, accurately predicts DNA-binding proteins using multiscale sequence features and deep neural networks. This sequence-based approach offers a faster and more efficient alternative to experimental identification methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Molecular Biology

Background:

  • DNA-binding proteins play critical roles in fundamental cellular processes like DNA replication, transcription, and repair.
  • Current experimental methods for identifying DNA-binding proteins are often costly and labor-intensive.
  • There is a need for rapid and accurate computational tools to predict DNA-binding proteins.

Purpose of the Study:

  • To develop a novel, sequence-based computational method for predicting DNA-binding proteins.
  • To introduce MsDBP, a predictor that utilizes multiscale sequence features and deep learning.
  • To provide an efficient and accurate tool for identifying DNA-binding proteins.

Main Methods:

  • Developed MsDBP, a sequence-based predictor, avoiding structure-based limitations.
Keywords:
DNA-binding proteinsdense layersmultiscale features

Related Experiment Videos

  • Extracted multiscale sequence features by dividing proteins into subsequences of varying lengths and encoding them.
  • Employed a deep neural network with dense layers to learn abstract features for classification.

    • Main Results:

    • MsDBP achieved an overall accuracy of 66.99% and 70.69% sensitivity (SE) on the independent PDB2272 dataset.
    • Comparative experiments demonstrated MsDBP's effectiveness against existing prediction methods.
    • The predictor shows promise as a valuable tool for DNA-binding protein identification.

    Conclusions:

    • MsDBP represents a significant advancement in computational prediction of DNA-binding proteins.
    • The multiscale feature extraction and deep learning approach enhance prediction accuracy.
    • MsDBP is accessible via a web server, facilitating its use in research.