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 Video

Updated: Mar 30, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

A comprehensive evaluation of machine learning techniques for cancer class prediction based on microarray data.

Khalid Raza¹, Atif N Hasan²

¹1 Department of Computer Science, Jamia Millia Islamia (Central University), New Delhi 110025, India.

International Journal of Bioinformatics Research and Applications

|November 13, 2015

Summary

This summary is machine-generated.

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

AI-driven transformer-guided fragment-based discovery of Prostaglandin A1 as a multi-target inhibitor of PSAT1, PARP1, and PIK3CA in ovarian cancer.

Computational biology and chemistry·2026

Same author

Multitarget docking and molecular enumeration reveal DdpMPyPEPhU as a potent modulator of cell cycle, glucocorticoid, and estrogen signalling in breast cancer.

PloS one·2026

Same author

In silico discovery of natural compound-derived multi-target inhibitor for Huntington's disease therapy.

Scientific reports·2026

Same author

Multimodal evaluation of mannose engineered poly lactic glycolic acid nanoparticles with granulocyte colony stimulating factor focused delivery to bone marrow for neutropenia.

Scientific reports·2026

Same author

MALAT1 and HIST1H2BC as connecting diagnostic biomarkers in Ebola and its overlapping disease: An integrative approach.

Bioinformation·2025

Same author

Unravelling mutation patterns in Extended-Spectrum β-Lactamases for precision drug design against AMR in Enterobacteriaceae.

Molecular genetics and genomics : MGG·2025

Same journal

In silico analysis, annotation and characterisation of putative ESTs from Sorghum bicolor associated with heat stress.

International journal of bioinformatics research and applications·2015

Same journal

Docking analysis of gallic acid derivatives as HIV-1 protease inhibitors.

International journal of bioinformatics research and applications·2015

Same journal

Automatic segmentation of Potyviridae family polyproteins.

International journal of bioinformatics research and applications·2015

Same journal

Neural network and rough set hybrid scheme for prediction of missing associations.

International journal of bioinformatics research and applications·2015

Same journal

On the interconnection of stable protein complexes: inter-complex hubs and their conservation in Saccharomyces cerevisiae and Homo sapiens networks.

International journal of bioinformatics research and applications·2015

Same journal

Diversity and evolution of the envelope gene of dengue virus type 1 circulating in India in recent times.

International journal of bioinformatics research and applications·2015

See all related articles

This study reduces gene attributes in prostate cancer data using IQR and t-tests. Bayes Network achieved 94.11% accuracy in predicting cancer class, outperforming other machine learning methods.

Area of Science:

Oncology
Bioinformatics
Machine Learning

Background:

Prostate cancer is a common malignancy in males with known heterogeneity.
Gene expression data reveals genomic changes applicable to cancer class prediction.
Microarray data presents challenges due to high dimensionality and limited samples, necessitating attribute reduction.

Purpose of the Study:

To reduce non-significant genes from prostate cancer microarray data.
To evaluate the performance of ten machine learning techniques for cancer class prediction.
To identify the most accurate predictive model for prostate cancer.

Main Methods:

Attribute reduction was performed using a combination of the interquartile range (IQR) and t-test.
Ten state-of-the-art machine learning techniques were applied to the reduced dataset.

Keywords:

Bayes network bioinformatics cancer class prediction machine learning microarray analysis prostate cancer

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Related Experiment Videos

Last Updated: Mar 30, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Performance was evaluated based on prediction accuracy for cancer class.

Main Results:

The combined IQR and t-test effectively reduced attributes in the prostate cancer dataset.
Bayes Network achieved the highest prediction accuracy at 94.11%.
Naïve Bayes followed with an accuracy of 91.17%.

Conclusions:

Attribute reduction is crucial for improving machine learning model performance on high-dimensional gene expression data.
Bayes Network demonstrates superior efficacy in predicting prostate cancer class compared to other evaluated methods.
This approach offers a robust framework for analyzing genomic data in cancer research.