A Novel Gene Selection Algorithm for Cancer Classification Using Microarray Datasets

Overview

Journal BMC Med Genomics

Publisher Biomed Central

Specialty Genetics

Date 2019 Jan 17

PMID 30646919

Citations 19

Authors

Russul Alanni

Jingyu Hou

Hasseeb Azzawi

Yong Xiang

Affiliations

Soon will be listed here.

Abstract

Background: Microarray datasets are an important medical diagnostic tool as they represent the states of a cell at the molecular level. Available microarray datasets for classifying cancer types generally have a fairly small sample size compared to the large number of genes involved. This fact is known as a curse of dimensionality, which is a challenging problem. Gene selection is a promising approach that addresses this problem and plays an important role in the development of efficient cancer classification due to the fact that only a small number of genes are related to the classification problem. Gene selection addresses many problems in microarray datasets such as reducing the number of irrelevant and noisy genes, and selecting the most related genes to improve the classification results.

Methods: An innovative Gene Selection Programming (GSP) method is proposed to select relevant genes for effective and efficient cancer classification. GSP is based on Gene Expression Programming (GEP) method with a new defined population initialization algorithm, a new fitness function definition, and improved mutation and recombination operators. . Support Vector Machine (SVM) with a linear kernel serves as a classifier of the GSP.

Results: Experimental results on ten microarray cancer datasets demonstrate that Gene Selection Programming (GSP) is effective and efficient in eliminating irrelevant and redundant genes/features from microarray datasets. The comprehensive evaluations and comparisons with other methods show that GSP gives a better compromise in terms of all three evaluation criteria, i.e., classification accuracy, number of selected genes, and computational cost. The gene set selected by GSP has shown its superior performances in cancer classification compared to those selected by the up-to-date representative gene selection methods.

Conclusion: Gene subset selected by GSP can achieve a higher classification accuracy with less processing time.

Citing Articles

Prediction of in-hospital mortality risk for patients with acute ST-elevation myocardial infarction after primary PCI based on predictors selected by GRACE score and two feature selection methods.

Tang N, Liu S, Li K, Zhou Q, Dai Y, Sun H Front Cardiovasc Med. 2024; 11:1419551.

PMID: 39502196 PMC: 11534735. DOI: 10.3389/fcvm.2024.1419551.

Machine learning for pan-cancer classification based on RNA sequencing data.

Stancl P, Karlic R Front Mol Biosci. 2023; 10:1285795.

PMID: 38028533 PMC: 10667476. DOI: 10.3389/fmolb.2023.1285795.

FSF-GA: A Feature Selection Framework for Phenotype Prediction Using Genetic Algorithms.

Mowlaei M, Shi X Genes (Basel). 2023; 14(5).

PMID: 37239419 PMC: 10218676. DOI: 10.3390/genes14051059.

Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis.

Hu H, Cai J, Qi D, Li B, Yu L, Wang C Int J Mol Sci. 2023; 24(9).

PMID: 37175757 PMC: 10178909. DOI: 10.3390/ijms24098050.

A Novel Hybrid Runge Kutta Optimizer with Support Vector Machine on Gene Expression Data for Cancer Classification.

Houssein E, Hassan H, Samee N, Jamjoom M Diagnostics (Basel). 2023; 13(9).

PMID: 37175012 PMC: 10178557. DOI: 10.3390/diagnostics13091621.

References

Azzawi H, Hou J, Xiang Y, Alanni R . Lung cancer prediction from microarray data by gene expression programming. IET Syst Biol. 2016; 10(5):168-178. PMC: 8687242. DOI: 10.1049/iet-syb.2015.0082. View

Singh D, Febbo P, Ross K, Jackson D, Manola J, Ladd C . Gene expression correlates of clinical prostate cancer behavior. Cancer Cell. 2002; 1(2):203-9. DOI: 10.1016/s1535-6108(02)00030-2. View

Mohamad M, Omatu S, Deris S, Yoshioka M, Abdullah A, Ibrahim Z . An enhancement of binary particle swarm optimization for gene selection in classifying cancer classes. Algorithms Mol Biol. 2013; 8(1):15. PMC: 3847130. DOI: 10.1186/1748-7188-8-15. View

Chuang L, Chang H, Tu C, Yang C . Improved binary PSO for feature selection using gene expression data. Comput Biol Chem. 2007; 32(1):29-37. DOI: 10.1016/j.compbiolchem.2007.09.005. View

Al-Anni R, Hou J, Abdu-Aljabar R, Xiang Y . Prediction of NSCLC recurrence from microarray data with GEP. IET Syst Biol. 2017; 11(3):77-85. PMC: 8687152. DOI: 10.1049/iet-syb.2016.0033. View

Suryamohan K, Halfon M . Identifying transcriptional cis-regulatory modules in animal genomes. Wiley Interdiscip Rev Dev Biol. 2015; 4(2):59-84. PMC: 4339228. DOI: 10.1002/wdev.168. View

Nutt C, Mani D, Betensky R, Tamayo P, Cairncross J, Ladd C . Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. Cancer Res. 2003; 63(7):1602-7. View

Armstrong S, Staunton J, Silverman L, Pieters R, den Boer M, Minden M . MLL translocations specify a distinct gene expression profile that distinguishes a unique leukemia. Nat Genet. 2001; 30(1):41-7. DOI: 10.1038/ng765. View

Golub T, Slonim D, Tamayo P, Huard C, Gaasenbeek M, Mesirov J . Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science. 1999; 286(5439):531-7. DOI: 10.1126/science.286.5439.531. View

10.

Staunton J, Slonim D, Coller H, Tamayo P, Angelo M, Park J . Chemosensitivity prediction by transcriptional profiling. Proc Natl Acad Sci U S A. 2001; 98(19):10787-92. PMC: 58553. DOI: 10.1073/pnas.191368598. View

11.

Chen K, Wang K, Tsai M, Wang K, Adrian A, Cheng W . Gene selection for cancer identification: a decision tree model empowered by particle swarm optimization algorithm. BMC Bioinformatics. 2014; 15:49. PMC: 3944936. DOI: 10.1186/1471-2105-15-49. View

12.

Mohamad M, Omatu S, Deris S, Yoshioka M . A modified binary particle swarm optimization for selecting the small subset of informative genes from gene expression data. IEEE Trans Inf Technol Biomed. 2011; 15(6):813-22. DOI: 10.1109/TITB.2011.2167756. View

13.

Moosa J, Shakur R, Kaykobad M, Rahman M . Gene selection for cancer classification with the help of bees. BMC Med Genomics. 2016; 9 Suppl 2:47. PMC: 4980787. DOI: 10.1186/s12920-016-0204-7. View

14.

Bhattacharjee A, Richards W, Staunton J, Li C, Monti S, Vasa P . Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proc Natl Acad Sci U S A. 2001; 98(24):13790-5. PMC: 61120. DOI: 10.1073/pnas.191502998. View

15.

Kusy M, Obrzut B, Kluska J . Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients. Med Biol Eng Comput. 2013; 51(12):1357-65. PMC: 3825140. DOI: 10.1007/s11517-013-1108-8. View

16.

Yu Z, Chen X, Cui L, Si H, Lu H, Liu S . Prediction of lung cancer based on serum biomarkers by gene expression programming methods. Asian Pac J Cancer Prev. 2014; 15(21):9367-73. DOI: 10.7314/apjcp.2014.15.21.9367. View

17.

Su A, Welsh J, Sapinoso L, Kern S, Dimitrov P, Lapp H . Molecular classification of human carcinomas by use of gene expression signatures. Cancer Res. 2001; 61(20):7388-93. View

18.

Khan J, Wei J, Ringner M, Saal L, Ladanyi M, Westermann F . Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nat Med. 2001; 7(6):673-9. PMC: 1282521. DOI: 10.1038/89044. View

19.

Xie H, Li J, Zhang Q, Wang Y . Comparison among dimensionality reduction techniques based on Random Projection for cancer classification. Comput Biol Chem. 2016; 65:165-172. DOI: 10.1016/j.compbiolchem.2016.09.010. View

20.

Seo M, Oh S . A novel divide-and-merge classification for high dimensional datasets. Comput Biol Chem. 2012; 42:23-34. DOI: 10.1016/j.compbiolchem.2012.10.005. View