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

MicroarrayCancerNet: Hybrid optimized deep learning with integration of graph CNN with 1D-CNN for cancer

B Shyamala Gowri1, S Anu H Nair2, K P Sanal Kumar3

  • 1Department of Computer Science and Engineering, Annamalai University, Annamalainagar, Chidambaram- 608002, Tamil Nadu, India; Assistant Professor, Department of Computer Science and Engineering, Easwari Engineering college, Ramapuram, Chennai-600089, Tamil Nadu, India.

Computational Biology and Chemistry
|October 19, 2025
PubMed
Summary

Related Concept Videos

DNA Microarrays02:34

DNA Microarrays

16.8K
Microarrays are high-throughput and relatively inexpensive assays that can be automated to analyze large quantities of data at a time. They are used in genome-wide studies to compare gene or protein expression under two varied conditions, such as healthy and diseased states. Microarrays consist of glass or silica slides on which probe molecules are covalently attached through surface functionalization. Most commonly, the slides are prepared through the chemisorption of silanes to silica...
16.8K

You might also read

Related Articles

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

Sort by
Same author

Proposed association rule hiding based privacy preservation model with block chain technology for IoT healthcare sector.

Computer methods in biomechanics and biomedical engineering·2022
Same author

Detection of estrous biomarkers in the body exudates of Kangayam cattle (Bos indicus) from interplay of hormones and behavioral expressions.

Domestic animal endocrinology·2020
Same author

Detection of Skin Cancer Using SVM, Random Forest and kNN Classifiers.

Journal of medical systems·2019
Same author

Modulating role of pheromonal cues from oestrus-specific urine on 3-methylcholanthrene-induced male reproductive toxicity.

Andrologia·2015
Same author

Adriamycin induced spermatogenesis defect is due to the reduction in epididymal adipose tissue mass: a possible hypothesis.

Medical hypotheses·2011
Same author

Spermidine may decrease ER stress in pancreatic beta cells and may reduce apoptosis via activating AMPK dependent autophagy pathway.

Medical hypotheses·2011

This study introduces a novel cancer classification framework using gene expression data. The developed Hybrid Deep Learning Framework (HDLF) achieves 91.78% precision, outperforming existing methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Accurate gene classification is crucial for cancer diagnosis but challenging with high-dimensional microarray data.
  • Existing gene selection methods show limited success in large datasets.

Purpose of the Study:

  • To design a novel cancer classification framework utilizing gene expression data.
  • To improve the accuracy and efficiency of cancer classification through advanced computational methods.

Main Methods:

  • Data preprocessing involved NAN and missing value removal from microarray and seq expression data.
  • The Modified Sandpiper Optimization Algorithm (MSOA) was employed for optimal gene selection.
  • A Hybrid Deep Learning Framework (HDLF), combining Graph Convolutional Neural Networks (GCNN) and 1D Convolutional Neural Networks (1D-CNN), was developed for classification.
Keywords:
Cancer ClassificationHybrid Deep Learning FrameworkMicro-array DataModified Sandpiper Optimization AlgorithmOptimal Gene Selection

Related Experiment Videos

Main Results:

  • The proposed HDLF framework achieved a precision of 91.78% for cancer classification.
  • The MSOA effectively identified optimal genes and tuned parameters for both GCNN and 1D-CNN.
  • The developed model demonstrated superior performance compared to existing machine learning and deep learning approaches.

Conclusions:

  • The novel cancer classification framework integrating MSOA and HDLF shows significant promise.
  • This approach offers an effective solution for accurate cancer classification using gene expression data.
  • The study highlights the potential of hybrid deep learning models in bioinformatics.