A bio-inspired computing model for ovarian carcinoma classification and oncogene detection

MOTIVATION Ovarian cancer is the fifth leading cause of cancer deaths in women in the western world for 2013. In ovarian cancer, benign tumors turn malignant, but the point of transition is difficult to predict and diagnose. The 5-year survival rate of all types of ovarian cancer is 44%, but this can be improved to 92% if the cancer is found and treated before it spreads beyond the ovary. However, only 15% of all ovarian cancers are found at this early stage. Therefore, the ability to automatically identify and diagnose ovarian cancer precisely and efficiently as the tissue changes from benign to invasive is important for clinical treatment and for increasing the cure rate. This study proposes a new ovarian carcinoma classification model using two algorithms: a novel discretization of food sources for an artificial bee colony (DfABC), and a support vector machine (SVM). For the first time in the literature, oncogene detection using this method is also investigated. RESULTS A novel bio-inspired computing model and hybrid algorithms combining DfABC and SVM was applied to ovarian carcinoma and oncogene classification. This study used the human ovarian cDNA expression database to collect 41 patient samples and 9600 genes in each pathological stage. Feature selection methods were used to detect and extract 15 notable oncogenes. We then used the DfABC-SVM model to examine these 15 oncogenes, dividing them into eight different classifications according to their gene expressions of various pathological stages. The average accuracyof the eight classification experiments was 94.76%. This research also found some oncogenes that had not been discovered or indicated in previous scientific studies. The main contribution of this research is the proof that these newly discovered oncogenes are highly related to ovarian or other cancers. AVAILABILITY AND IMPLEMENTATION http://mht.mis.nchu.edu.tw/moodle/course/view.php?id=7.

[1]  Dervis Karaboga,et al.  A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm , 2007, J. Glob. Optim..

[2]  D. Busam,et al.  Molecular and Cellular Pathobiology SMAD 2 , SMAD 3 and SMAD 4 Mutations in Colorectal Cancer , 2013 .

[3]  F. Hao,et al.  Mutations in POFUT1, encoding protein O-fucosyltransferase 1, cause generalized Dowling-Degos disease. , 2013, American journal of human genetics.

[4]  Ya Cao,et al.  Detection of STAT2 in early stage of cervical premalignancy and in cervical cancer. , 2012, Asian Pacific journal of tropical medicine.

[5]  R. Bartrons,et al.  PFKFB3 gene silencing decreases glycolysis, induces cell‐cycle delay and inhibits anchorage‐independent growth in HeLa cells , 2006, FEBS letters.

[6]  C. Conover,et al.  Overexpression of pregnancy-associated plasma protein-A in ovarian cancer cells promotes tumor growth in vivo. , 2011, Endocrinology.

[7]  Xiaoyan Xie,et al.  MicroRNA-125b induces cancer cell apoptosis through suppression of Bcl-2 expression. , 2012, Journal of genetics and genomics = Yi chuan xue bao.

[8]  Chia-Chen Chen,et al.  Credit Rating Analysis with Support Vector Machines and Artificial Bee Colony Algorithm , 2013, IEA/AIE.

[9]  D. Busam,et al.  SMAD2, SMAD3 and SMAD4 mutations in colorectal cancer. , 2013, Cancer research.

[10]  Mu-Yen Chen Using a hybrid evolution approach to forecast financial failures for Taiwan-listed companies , 2014 .

[11]  Ahmedin Jemal,et al.  Cancer Statistics, 2002 , 2002, CA: a cancer journal for clinicians.

[12]  K. Odunsi,et al.  PGE(2)-induced CXCL12 production and CXCR4 expression controls the accumulation of human MDSCs in ovarian cancer environment. , 2011, Cancer research.

[13]  蔡孟勳,et al.  STATISTICAL AND SVM-BASED ONCOGENE DETECTION OF HUMAN CDNA EXPRESSIONS FOR OVARIAN CARCINOMA , 2009 .

[14]  P. Rolland,et al.  The chemokine, CXCL12, is an independent predictor of poor survival in ovarian cancer , 2012, British Journal of Cancer.

[15]  R. Montironi,et al.  Fluorescence in situ hybridization analysis of CCND3 gene as marker of progression in bladder carcinoma. , 2013, Journal of biological regulators and homeostatic agents.

[16]  Y. Takai,et al.  RA-RhoGAP, Rap-activated Rho GTPase-activating Protein Implicated in Neurite Outgrowth through Rho*♦ , 2005, Journal of Biological Chemistry.

[17]  Andrew Kusiak,et al.  Cancer gene search with data-mining and genetic algorithms , 2007, Comput. Biol. Medicine.

[18]  Tzong-Der Way,et al.  EGCG inhibits transforming growth factor-β-mediated epithelial-to-mesenchymal transition via the inhibition of Smad2 and Erk1/2 signaling pathways in nonsmall cell lung cancer cells. , 2012, Journal of agricultural and food chemistry.

[19]  Xifeng Wu,et al.  Genetic variants in the fibroblast growth factor pathway as potential markers of ovarian cancer risk, therapeutic response, and clinical outcome. , 2014, Clinical chemistry.

[20]  W. Jiang,et al.  Guanine nucleotide binding protein β 1: a novel transduction protein with a possible role in human breast cancer. , 2013, Cancer genomics & proteomics.

[21]  Jie Sun,et al.  Financial distress prediction using support vector machines: Ensemble vs. individual , 2012 .

[22]  Donna K. Slonim,et al.  Getting Started in Gene Expression Microarray Analysis , 2009, PLoS Comput. Biol..

[23]  A. Bacolla,et al.  DHX9 helicase is involved in preventing genomic instability induced by alternatively structured DNA in human cells , 2013, Nucleic acids research.

[24]  Mu-Yen Chen,et al.  Visualization and dynamic evaluation model of corporate financial structure with self-organizing map and support vector regression , 2012, Appl. Soft Comput..

[25]  Hua Han,et al.  Notch signaling pathway and cancer metastasis. , 2012, Advances in experimental medicine and biology.

[26]  Cuntai Guan,et al.  SoHyFIS-Yager: A self-organizing Yager based Hybrid neural Fuzzy Inference System , 2012, Expert Syst. Appl..

[27]  Jason E. Stewart,et al.  Minimum information about a microarray experiment (MIAME)—toward standards for microarray data , 2001, Nature Genetics.

[28]  Yong‐jun Liu,et al.  DHX9 Pairs with IPS-1 To Sense Double-Stranded RNA in Myeloid Dendritic Cells , 2011, The Journal of Immunology.

[29]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[30]  B. Beutler,et al.  The BTB-ZF transcription factors , 2012, Cell cycle.

[31]  S. Inan,et al.  Effects of 5-fluorouracil and gemcitabine on a breast cancer cell line (MCF-7) via the JAK/STAT pathway. , 2012, Acta histochemica.

[32]  K. Cibulskis,et al.  Prognostically relevant gene signatures of high-grade serous ovarian carcinoma. , 2012, The Journal of clinical investigation.

[33]  J. Dimmock,et al.  Potential role of N-myristoyltransferase in cancer. , 2007, Progress in lipid research.

[34]  Shyr-Shen Yu,et al.  A statistical and learning based oncogene detection and classification scheme using human cDNA expressions for ovarian carcinoma , 2011, Expert Syst. Appl..

[35]  Shyam Visweswaran,et al.  Bayesian rule learning for biomedical data mining , 2010, Bioinform..

[36]  P. Sujka-Kordowska,et al.  MDR Gene Expression Analysis of Six Drug-Resistant Ovarian Cancer Cell Lines , 2012, BioMed research international.

[37]  Guoqiang Li,et al.  Development and investigation of efficient artificial bee colony algorithm for numerical function optimization , 2012, Appl. Soft Comput..

[38]  L. Staudt,et al.  Oncogenic mechanisms in Burkitt lymphoma. , 2014, Cold Spring Harbor perspectives in medicine.

[39]  Edmond J. Breen,et al.  Identification of ovarian cancer associated genes using an integrated approach in a Boolean framework , 2013, BMC Systems Biology.

[40]  Arindam Chaudhuri,et al.  Fuzzy Support Vector Machine for bankruptcy prediction , 2011, Appl. Soft Comput..

[41]  Ali Husseinzadeh Kashan,et al.  DisABC: A new artificial bee colony algorithm for binary optimization , 2012, Appl. Soft Comput..

[42]  Zne-Jung Lee,et al.  An integrated algorithm for gene selection and classification applied to microarray data of ovarian cancer , 2008, Artif. Intell. Medicine.

[43]  Bahram Parvin,et al.  Prediction of epigenetically regulated genes in breast cancer cell lines , 2010, BMC Bioinformatics.

[44]  A. Bolino,et al.  A novel homozygous mutation in the MTMR2 gene in two siblings with ‘hypermyelinating neuropathy’ , 2013, Journal of the peripheral nervous system : JPNS.

[45]  M. Lai,et al.  MiR-148a promotes apoptosis by targeting Bcl-2 in colorectal cancer , 2011, Cell Death and Differentiation.

[46]  Mahdi Shabani,et al.  Adenosine induces cell cycle arrest and apoptosis via cyclinD1/Cdk4 and Bcl-2/Bax pathways in human ovarian cancer cell line OVCAR-3 , 2013, Tumor Biology.

[47]  J. Trent,et al.  Targeting 6-Phosphofructo-2-Kinase (PFKFB3) as a Therapeutic Strategy against Cancer , 2013, Molecular Cancer Therapeutics.

[48]  W. Hiddemann,et al.  Expression analysis of genes located in the minimally deleted regions of 13q14 and 11q22‐23 in chronic lymphocytic leukemia—unexpected expression pattern of the RHO GTPase activator ARHGAP20 , 2011, Genes, chromosomes & cancer.

[49]  K. Uzawa,et al.  Protein O-fucosyltransferase 1: a potential diagnostic marker and therapeutic target for human oral cancer. , 2013, International journal of oncology.

[50]  Sebastian M. Armasu,et al.  Methylation of leukocyte DNA and ovarian cancer: relationships with disease status and outcome , 2014, BMC Medical Genomics.

[51]  Alvis Brazma,et al.  Minimum Information About a Microarray Experiment (MIAME) – Successes, Failures, Challenges , 2009, TheScientificWorldJournal.

[52]  L. Mao,et al.  Protein Secretion Is Required for Pregnancy-Associated Plasma Protein-A to Promote Lung Cancer Growth In Vivo , 2012, PloS one.

[53]  Feng Su,et al.  The early detection of ovarian cancer: from traditional methods to proteomics. Can we really do better than serum CA-125? , 2008, American journal of obstetrics and gynecology.

[54]  F CooperGregory,et al.  Bayesian rule learning for biomedical data mining , 2010 .

[55]  N. Dubrawsky Cancer statistics , 1989, CA: a cancer journal for clinicians.

[56]  Hui Li,et al.  Financial distress prediction using support vector machines: Ensemble vs. individual , 2012, Appl. Soft Comput..

[57]  D. Harrington,et al.  Stem Cell-Like Gene Expression in Ovarian Cancer Predicts Type II Subtype and Prognosis , 2013, PloS one.