Related Experiment Video
Updated: Nov 5, 2025
MicroRNA In situ Hybridization for Formalin Fixed Kidney Tissues
Published on: November 30, 2013
A self-organizing deep neuro-fuzzy system approach for classification of kidney cancer subtypes using miRNA genomics
Saeed Pirmoradi1, Mohammad Teshnehlab2, Nosratollah Zarghami3
1Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Abstract:
Kidney cancer is a dangerous disease affecting many patients all over the world. Early-stage diagnosis and correct identification of kidney cancer subtypes play an essential role in the patient's survival; therefore, its subtypes diagnosis and classification are the main challenges in kidney cancer treatment. Medical studies have proved that miRNA dysregulation can increase the risk of cancer. Thus, in this paper, we propose a new machine learning approach for significant miRNAs identification and kidney cancer subtype classification to design an automatic diagnostic tool. The proposed method contains two main steps: feature selection and classification. First, we apply the feature selection algorithm to choose the candidate miRNAs for each subtype. The feature selection algorithm utilizes the AMGM measure to select significant miRNAs with high discriminant power. Next, the candidate miRNAs are fed to a classifier to evaluate the candidate features. In the classification step, the proposed self-organizing deep neuro-fuzzy system is employed to classify kidney cancer subgroups. The new deep neuro-fuzzy system consists of a deep structure in the rule layer and novel architecture in the fuzzifier layer. The proposed self-organizing deep neuro-fuzzy system can help us to overcome the main obstacles in the field of neuro-fuzzy system applications, such as the curse of dimensionality. The goal of this paper is to illustrate that the neuro-fuzzy system can very useful in high dimensional data, such as genomics data, using the proposed deep neuro-fuzzy system. The obtained results illustrated that our proposed method has succeeded in classifying kidney cancer subtypes with high accuracy based on the selected miRNAs.
Insights
This study introduces a novel machine learning approach for identifying significant microRNAs (miRNAs) and classifying kidney cancer subtypes. The method accurately distinguishes kidney cancer subtypes using selected miRNAs, aiding in early diagnosis.
Area of Science:
- Oncology
- Bioinformatics
- Machine Learning
Background:
- Kidney cancer diagnosis and subtype classification are critical for patient survival.
- MicroRNA (miRNA) dysregulation is linked to increased cancer risk.
- Accurate identification of kidney cancer subtypes remains a significant clinical challenge.
Purpose of the Study:
- To develop a machine learning approach for identifying significant miRNAs and classifying kidney cancer subtypes.
- To design an automated diagnostic tool for kidney cancer.
- To demonstrate the utility of a novel neuro-fuzzy system for high-dimensional genomic data analysis.
Main Methods:
- A two-step approach involving feature selection and classification.
- Utilized the AMGM measure for selecting significant miRNAs with high discriminant power.
- Employed a self-organizing deep neuro-fuzzy system with a deep structure in the rule layer and a novel fuzzifier layer for classification.
Main Results:
- Successfully identified significant miRNAs for each kidney cancer subtype.
- The proposed deep neuro-fuzzy system effectively classified kidney cancer subgroups.
- Achieved high accuracy in classifying kidney cancer subtypes based on selected miRNAs.
Conclusions:
- The developed machine learning approach accurately classifies kidney cancer subtypes using selected miRNAs.
- The novel self-organizing deep neuro-fuzzy system overcomes challenges like the curse of dimensionality in genomic data.
- This method offers a promising automated diagnostic tool for kidney cancer.
