Improving classification accuracy of cancer types using parallel hybrid feature selection on microarray gene expression data

다국어 초록 (Multilingual Abstract)

Background Data mining techniques are used to mine unknown knowledge from huge data. Microarray gene expression (MGE) data plays a major role in predicting type of cancer. But as MGE data is huge in volume, applying traditional data mining approaches is time consuming. Hence parallel programming frameworks like Hadoop, Spark and Mahout are necessary to ease the task of computation.
Objective Not all the gene expressions are necessary in prediction, it is very essential to select important genes for improving classification accuracy. So feature selection algorithms are parallelized and executed on Spark framework to eliminate unnecessary genes and identify only predictive genes in very less time without affecting prediction accuracy.
Methods Parallelized hybrid feature selection (HFS) method is proposed to serve the purpose. This method includes parallelized correlation feature subset selection followed by rank-based feature selection methods. The selected subset of genes is evaluated using parallel classification algorithms. The accuracy values obtained are compared with existing rank-weight feature selection, parallelized recursive feature selection methods and also with the values obtained by executing parallelized HFS on DistributedWekaSpark.
Results The classification accuracy obtained with the proposed parallelized HFS method is 97% and 79% for gastric cancer and childhood leukemia respectively. The proposed parallelized HFS method produced ~ 4% to ~ 15% improvement in classification accuracy when compared with previous methods.
Conclusion The results reveal the fact that the proposed parallelized feature selection algorithm is scalable to growing medical data and predicts cancer sub-types in lesser time with higher accuracy.

참고문헌 (Reference)

1 "Waikato Environment for Knowledge Analysis (WEKA)"

2 방만석, "Transcriptome analysis of non-small cell lung cancer and genetically matched adjacent normal tissues identifies novel prognostic marker genes" 한국유전학회 39 (39): 277-284, 2017

3 Hall M, "The WEKA data mining software : an update" 11 (11): 10-18, 2009

4 "Spark Release 2.2.1—Apache Spark"

5 강성만, "Prediction of personalized drugs based on genetic variations provided by DNA sequencing technologies" 한국유전학회 33 (33): 591-603, 2011

6 Venkataramana L, "Parallelized classification of cancer sub-types from gene expression profiles using recursive gene selection" 27 (27): 215-224, 2018

7 Eiras-Franco C, "Multithreaded and Spark parallelization of feature selection filters" 17 : 609-619, 2016

8 Golub TR, "Molecular classification of cancer : class discovery and class prediction by gene expression monitoring" 286 (286): 531-537, 1999

9 Zhang H, "Informative gene selection and direct classification of tumor based on chi square test of pairwise gene interactions" 2014 (2014): 1-9, 2014

10 Singh RK, "Feature selection of gene expression data for cancer classification : a review" 50 : 52-57, 2015

11 Yuan M, "Feature selection by maximizing correlation information for integrated high-dimensional protein data" 92 : 17-24, 2017

12 Peralta D, "Evolutionary feature selection for big data classification : a Mapreduce approach" 2015 (2015): 1-11, 2015

13 Bolón-CanedoV V, "Distributed feature selection : an application to microarray data classification" 30 : 136-150, 2015

14 허정훈, "Distinct gene expression signatures during development of distant metastasis" 한국유전학회 35 (35): 511-522, 2013

15 Gracia Jacob S, "Discovery of novel oncogenic patterns using hybrid feature selection and rule mining" Anna University 2015

16 Hall MA, "Correlation-based feature selection for discrete and numeric class machine learning" 359-366, 2000

17 Li J, "Challenges of feature selection for big data analytics" 32 (32): 9-15, 2017

18 "Bioinformatics Laboratory"

19 Ramani RG, "Benchmarking classification models for cancer prediction from gene expression data : a novel approach and new findings" 22 (22): 134-143, 2013

20 Wang Z, "Application of ReliefF algorithm to selecting feature sets for classification of high resolution remote sensing image" 755-758, 2016

21 Lokeswari YV, "Advances in big data and cloud computing" Springer 529-538, 2019

22 Ryza S, "Advanced analytics with Spark: patterns for learning from data at scale" O’Reilly Media Inc. 2017

23 Alshamlan HM, "A study of cancer microarray gene expression prole : objectives and approaches" 2 : 1-6, 2013

24 Wang X, "A robust gene selection method for microarray-based cancer classification" 9 : CIN-S3794-, 2010

25 Lee CP, "A novel hybrid feature selection method for microarray data analysis" 11 (11): 208-213, 2017

26 Das AK, "A new hybrid feature selection approach using feature association map for supervised and unsupervised classification" 88 : 81-94, 2017

27 Jia-Feng Yu, "A hybrid strategy for comprehensive annotation of the protein coding genes in prokaryotic genome" 한국유전학회 37 (37): 347-355, 2015

28 Chuang LY, "A hybrid feature selection method for DNA microarray data" 41 (41): 228-237, 2011

29 Lu H, "A hybrid feature selection algorithm for gene expression data classification" 256 : 56-62, 2017

30 Ali SI, "A feature subset selection method based on symmetric uncertainty and ant colony optimization" 1-6, 2012