Fuzzy mutual information based grouping and new fitness function for PSO in selection of miRNAs in cancer

MicroRNAs (miRNA) are one of the important regulators of cell division and also responsible for cancer development. Among the discovered miRNAs, not all are important for cancer detection. In this regard a fuzzy mutual information (FMI) based grouping and miRNA selection method (FMIGS) is developed to identify the miRNAs responsible for a particular cancer. First, the miRNAs are ranked and divided into several groups. Then the most important group is selected among the generated groups. Both the steps viz., ranking of miRNAs and selection of the most relevant group of miRNAs, are performed using FMI. Here the number of groups is automatically determined by the grouping method. After the selection process, redundant miRNAs are removed from the selected set of miRNAs as per user's necessity. In a part of the investigation we proposed a FMI based particle swarm optimization (PSO) method for selecting relevant miRNAs, where FMI is used as a fitness function to determine the fitness of the particles. The effectiveness of FMIGS and FMI based PSO is tested on five data sets and their efficiency in selecting relevant miRNAs are demonstrated. The superior performance of FMIGS to some existing methods are established and the biological significance of the selected miRNAs is observed by the findings of the biological investigation and publicly available pathway analysis tools. The source code related to our investigation is available at http://www.jayanta.droppages.com/FMIGS.html.

[1]  D. Kavanagh,et al.  Is overexpression of HER-2 a predictor of prognosis in colorectal cancer? , 2009, BMC Cancer.

[2]  Deng Cai,et al.  Laplacian Score for Feature Selection , 2005, NIPS.

[3]  Sankar K. Pal,et al.  Fuzzy–Rough Sets for Information Measures and Selection of Relevant Genes From Microarray Data , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Satoru Miyano,et al.  A between-Class Overlapping Filter-Based Method for transcriptome Data Analysis , 2012, J. Bioinform. Comput. Biol..

[5]  Shubhra Sankar Ray,et al.  Computational approaches for identifying cancer miRNA expressions. , 2013, Gene expression.

[6]  Israel Steinfeld,et al.  Novel Rank-Based Statistical Methods Reveal MicroRNAs with Differential Expression in Multiple Cancer Types , 2009, PloS one.

[7]  J. Hoheisel,et al.  Diagnosis of Pancreatic Ductal Adenocarcinoma and Chronic Pancreatitis by Measurement of microRNA Abundance in Blood and Tissue , 2012, PloS one.

[8]  H. Horvitz,et al.  MicroRNA expression profiles classify human cancers , 2005, Nature.

[9]  Xiao-Hui Zheng,et al.  Plasma microRNA profiling in nasopharyngeal carcinoma patients reveals miR-548q and miR-483-5p as potential biomarkers , 2014, Chinese journal of cancer.

[10]  Eckart Meese,et al.  miRNAs in lung cancer - Studying complex fingerprints in patient's blood cells by microarray experiments , 2009, BMC Cancer.

[11]  Wei Gong,et al.  Candidate microRNA biomarkers of pancreatic ductal adenocarcinoma: meta-analysis, experimental validation and clinical significance , 2013, Journal of experimental & clinical cancer research : CR.

[12]  Deng Cai,et al.  Unsupervised feature selection for multi-cluster data , 2010, KDD.

[13]  Huan Liu,et al.  Spectral feature selection for supervised and unsupervised learning , 2007, ICML '07.

[14]  Sankar K. Pal,et al.  A Weighted Threshold for Detection of Cancerous miRNA Expressions , 2013, Fundam. Informaticae.

[15]  A. Shelton,et al.  Changes in neuronal activation patterns in response to androgen deprivation therapy: a pilot study , 2010, BMC Cancer.

[16]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Hui Zhou,et al.  starBase v2.0: decoding miRNA-ceRNA, miRNA-ncRNA and protein–RNA interaction networks from large-scale CLIP-Seq data , 2013, Nucleic Acids Res..

[18]  Artemis G. Hatzigeorgiou,et al.  DIANA-miRPath v3.0: deciphering microRNA function with experimental support , 2015, Nucleic Acids Res..

[19]  Sankar K. Pal,et al.  Identifying relevant group of miRNAs in cancer using fuzzy mutual information , 2015, Medical & Biological Engineering & Computing.

[20]  Eckart Meese,et al.  High-throughput miRNA profiling of human melanoma blood samples , 2010, BMC Cancer.

[21]  J.C. Rajapakse,et al.  SVM-RFE With MRMR Filter for Gene Selection , 2010, IEEE Transactions on NanoBioscience.

[22]  C. A. Murthy,et al.  Unsupervised Feature Selection Using Feature Similarity , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[24]  Evelyn Wenkel,et al.  Circulating Micro-RNAs as Potential Blood-Based Markers for Early Stage Breast Cancer Detection , 2012, PloS one.

[25]  A. Bittner,et al.  Characterization of global microRNA expression reveals oncogenic potential of miR-145 in metastatic colorectal cancer , 2009, BMC Cancer.

[26]  Elizabeth Guruceaga,et al.  Functional interpretation of microRNA-mRNA association in biological systems using R , 2014, Comput. Biol. Medicine.