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

lncRNA - Long Non-coding RNAs

lncRNA - Long Non-coding RNAs

In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...

You might also read

Related Articles

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

Sort by

Same author

Catalyzing early ovarian cancer detection: Platelet RNA-based precision screening.

iScience·2025

Same author

Tailored chemotherapy: Innovative deep-learning model customizing chemotherapy for high-grade serous ovarian carcinoma.

Clinical and translational medicine·2024

Same author

Enhanced Glutaminolysis Drives Hypoxia-Induced Chemoresistance in Pancreatic Cancer.

Cancer research·2023

Same author

Probiotic Property and Anti-Obesity Effect of <i>Lactiplantibacillus plantarum</i> KC3.

Food science of animal resources·2022

Same author

A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer.

Cancer informatics·2022

Same author

Integrated analysis of ascites and plasma extracellular vesicles identifies a miRNA-based diagnostic signature in ovarian cancer.

Cancer letters·2022

Search research articles

Related Experiment Video

Updated: Oct 13, 2025

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Published on: July 22, 2020

Classification and Functional Analysis between Cancer and Normal Tissues Using Explainable Pathway Deep Learning

Sangick Park¹, Eunchong Huang¹, Taejin Ahn^1,2

¹Department of Advanced Convergence, Handong Global University, Pohang-si 37554, Gyeongbuk, Korea.

International Journal of Molecular Sciences

|November 13, 2021

Summary

This study introduces PathDeep, a novel deep learning model that integrates biological pathways for cancer classification. PathDeep enhances diagnostic accuracy by explaining gene and pathway contributions, improving interpretability in cancer research.

Keywords:

biological function cancer gene expression deep learning neural networks pathway

More Related Videos

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

Analyzing Tumor Gene Expression Factors with the CorExplorer Web Portal

Analyzing Tumor Gene Expression Factors with the CorExplorer Web Portal

Published on: October 11, 2019

Related Experiment Videos

Last Updated: Oct 13, 2025

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Published on: July 22, 2020

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

Analyzing Tumor Gene Expression Factors with the CorExplorer Web Portal

Analyzing Tumor Gene Expression Factors with the CorExplorer Web Portal

Published on: October 11, 2019

Area of Science:

Computational biology
Bioinformatics
Machine learning in oncology

Background:

Deep learning models excel at cancer diagnosis but lack interpretability.
Biological pathways offer structured knowledge of gene functions, valuable for human researchers.
Integrating gene-pathway relationships into deep learning can enhance model comprehension.

Purpose of the Study:

To develop a deep neural network (PathDeep) that incorporates gene-to-pathway relationships.
To create a framework for measuring pathway and gene contributions within deep learning models.
To improve the interpretability of deep learning models in cancer classification.

Main Methods:

Developed PathDeep, a deep neural network integrating gene-to-pathway information.
Implemented a framework to quantify pathway and gene importance in classification tasks.
Applied PathDeep to classify cancer versus normal tissues using gene expression data.

Main Results:

PathDeep achieved high accuracy (0.994) in distinguishing cancer from normal tissues.
Identified 42 key pathways and 57 significant genes associated with cancer tissues.
Highlighted G-protein-coupled receptor signaling and G1/S transition of the mitotic cell cycle as critical cancer-related functions.

Conclusions:

PathDeep effectively integrates biological pathway knowledge into deep learning for cancer classification.
The model provides interpretable insights into the biological underpinnings of cancer.
Identified pathways and functions offer potential biomarkers and therapeutic targets for cancer.