Artificial Neural Network Inference (ANNI): A Study on Gene-Gene Interaction for Biomarkers in Childhood Sarcomas

Objective To model the potential interaction between previously identified biomarkers in children sarcomas using artificial neural network inference (ANNI). Method To concisely demonstrate the biological interactions between correlated genes in an interaction network map, only 2 types of sarcomas in the children small round blue cell tumors (SRBCTs) dataset are discussed in this paper. A backpropagation neural network was used to model the potential interaction between genes. The prediction weights and signal directions were used to model the strengths of the interaction signals and the direction of the interaction link between genes. The ANN model was validated using Monte Carlo cross-validation to minimize the risk of over-fitting and to optimize generalization ability of the model. Results Strong connection links on certain genes (TNNT1 and FNDC5 in rhabdomyosarcoma (RMS); FCGRT and OLFM1 in Ewing’s sarcoma (EWS)) suggested their potency as central hubs in the interconnection of genes with different functionalities. The results showed that the RMS patients in this dataset are likely to be congenital and at low risk of cardiomyopathy development. The EWS patients are likely to be complicated by EWS-FLI fusion and deficiency in various signaling pathways, including Wnt, Fas/Rho and intracellular oxygen. Conclusions The ANN network inference approach and the examination of identified genes in the published literature within the context of the disease highlights the substantial influence of certain genes in sarcomas.

[1]  Clare E. Giacomantonio,et al.  A Boolean Model of the Gene Regulatory Network Underlying Mammalian Cortical Area Development , 2010, PLoS Comput. Biol..

[2]  K. Nishii,et al.  Targeted disruption of the cardiac troponin T gene causes sarcomere disassembly and defects in heartbeat within the early mouse embryo. , 2008, Developmental biology.

[3]  G Deléage,et al.  FVT-1, a novel human transcription unit affected by variant translocation t(2;18)(p11;q21) of follicular lymphoma. , 1993, Blood.

[4]  R. Albert,et al.  Boolean Modelingof Genetic Regulatory Networks , 2004 .

[5]  Dong-Ling Tong,et al.  Hybrid genetic algorithm-neural network: Feature extraction for unpreprocessed microarray data , 2011, Artif. Intell. Medicine.

[6]  M. McGee-Lawrence,et al.  The Ewing's sarcoma fusion protein, EWS‐FLI, binds Runx2 and blocks osteoblast differentiation , 2010, Journal of cellular biochemistry.

[7]  Candidate screening of the bovine and feline spinal muscular atrophy genes reveals no evidence for involvement in human motor neuron disorders , 2008, Neuromuscular Disorders.

[8]  A. Üren,et al.  Wnt/Frizzled signaling in Ewing sarcoma , 2004, Pediatric blood & cancer.

[9]  Trey Ideker,et al.  Cytoscape 2.8: new features for data integration and network visualization , 2010, Bioinform..

[10]  Michael L. Creech,et al.  Integration of biological networks and gene expression data using Cytoscape , 2007, Nature Protocols.

[11]  Karin Bammann,et al.  Neural networks for modeling gene-gene interactions in association studies , 2009, BMC Genetics.

[12]  X. Chen,et al.  DNA Methylation and Gene Expression Profiling of Ewing Sarcoma Primary Tumors Reveal Genes That Are Potential Targets of Epigenetic Inactivation , 2012, Sarcoma.

[13]  V. Notario,et al.  Auto-stimulatory action of secreted caveolin-1 on the proliferation of Ewing's sarcoma cells. , 2011, International journal of oncology.

[14]  Qing-Rong Chen,et al.  Prediction of Clinical Outcome Using Gene Expression Profiling and Artificial Neural Networks for Patients with Neuroblastoma , 2004, Cancer Research.

[15]  Ambuj K. Singh,et al.  Predicting genetic interactions with random walks on biological networks , 2009, BMC Bioinformatics.

[16]  Qing Nie,et al.  Incorporating Existing Network Information into Gene Network Inference , 2009, PloS one.

[17]  Christophe Lemetre,et al.  Artificial Neural Network Based Algorithm for Biomolecular Interactions Modeling , 2009, IWANN.

[18]  Richard Taylor.  Interpretation of the Correlation Coefficient: A Basic Review , 1990 .

[19]  P. Shannon,et al.  Cytoscape: a software environment for integrated models of biomolecular interaction networks. , 2003, Genome research.

[20]  Susan S. Brown,et al.  FHL3 binds MyoD and negatively regulates myotube formation , 2007, Journal of Cell Science.

[21]  E. Cesarman,et al.  Expression of the follicular lymphoma variant translocation 1 gene in diffuse large B-cell lymphoma correlates with subtype and clinical outcome. , 2008, American journal of clinical pathology.

[22]  B. Schwikowski,et al.  A network of protein–protein interactions in yeast , 2000, Nature Biotechnology.

[23]  M. Brown,et al.  Cardiac high‐sensitivity troponin T measurement: A layer of complexity in managing haemodialysis patients , 2012, Nephrology.

[24]  Alvis Brazma,et al.  Current approaches to gene regulatory network modelling , 2007, BMC Bioinformatics.

[25]  Tommi S. Jaakkola,et al.  Bayesian Methods for Elucidating Genetic Regulatory Networks , 2002, IEEE Intell. Syst..

[26]  D. Benayahu,et al.  TSG-6 Regulates Bone Remodeling through Inhibition of Osteoblastogenesis and Osteoclast Activation*S⃞ , 2008, Journal of Biological Chemistry.

[27]  Christian Haass,et al.  Amyloid Precursor-like Protein 1 Influences Endocytosis and Proteolytic Processing of the Amyloid Precursor Protein* , 2006, Journal of Biological Chemistry.

[28]  L. Machesky,et al.  Congenital myopathies: diseases of the actin cytoskeleton , 2004, The Journal of pathology.

[29]  Stephen L. Lessnick,et al.  EWS/FLI Mediates Transcriptional Repression via NKX2.2 during Oncogenic Transformation in Ewing's Sarcoma , 2008, PloS one.

[30]  Aurélien Mazurie,et al.  Gene networks inference using dynamic Bayesian networks , 2003, ECCB.

[31]  Chakresh Kumar Jain,et al.  The Wnt pathway: emerging anticancer strategies. , 2013, Recent patents on endocrine, metabolic & immune drug discovery.

[32]  Victoria A. Higman,et al.  TSG-6: a pluripotent inflammatory mediator? , 2006, Biochemical Society transactions.

[33]  L. Staudt,et al.  Identification of FGFR4-activating mutations in human rhabdomyosarcomas that promote metastasis in xenotransplanted models. , 2009, The Journal of clinical investigation.

[34]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[35]  F. Otto,et al.  Identification of novel genes of the bone-specific transcription factor Runx2. , 2004, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[36]  J. Belleroche,et al.  Heat shock protein 27 rescues motor neurons following nerve injury and preserves muscle function , 2006, Experimental Neurology.

[37]  R. Arena,et al.  Expression of the Irisin Precursor FNDC5 in Skeletal Muscle Correlates With Aerobic Exercise Performance in Patients With Heart Failure , 2012, Circulation. Heart failure.

[38]  R. Albert.  Boolean modeling of genetic regulatory networks , 2004 .

[39]  Susan S. Brown,et al.  FHL3 is an actin-binding protein that regulates alpha-actinin-mediated actin bundling: FHL3 localizes to actin stress fibers and enhances cell spreading and stress fiber disassembly. , 2003, The Journal of biological chemistry.

[40]  S. Bhattacharyya,et al.  Hypoxia Reduces Arylsulfatase B Activity and Silencing Arylsulfatase B Replicates and Mediates the Effects of Hypoxia , 2012, PloS one.

[41]  Donald C. Wunsch,et al.  A Study of Particle Swarm Optimization in Gene Regulatory Networks Inference , 2006, ISNN.

[42]  F. Otto,et al.  Identification of Novel Target Genes of the Bone‐Specific Transcription Factor Runx2 , 2004 .

[43]  A. Blangy,et al.  RhoE controls myoblast alignment prior fusion through RhoA and ROCK , 2008, Cell Death and Differentiation.

[44]  Mesut Remzi,et al.  Novel artificial neural network for early detection of prostate cancer. , 2002, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[45]  S. Krebs,et al.  A missense mutation in the 3-ketodihydrosphingosine reductase FVT1 as candidate causal mutation for bovine spinal muscular atrophy , 2007, Proceedings of the National Academy of Sciences.

[46]  Wenbin Liu.  SEPT4 is regulated by the Notch signaling pathway , 2011, Molecular Biology Reports.

[47]  Zchong‐Zcho Wu,et al.  Knockdown of CITED2 using short‐hairpin RNA sensitizes cancer cells to cisplatin through stabilization of p53 and enhancement of p53‐dependent apoptosis , 2011, Journal of cellular physiology.

[48]  J. R. M. Ramos,et al.  Cardiac Troponin T and Illness Severity in the Very-Low-Birth-Weight Infant , 2012, International journal of pediatrics.

[49]  Christine Nardini,et al.  A Comprehensive Molecular Interaction Map for Rheumatoid Arthritis , 2010, PloS one.

[50]  Alejandro Martínez-Abraín,et al.  Statistical significance and biological relevance: A call for a more cautious interpretation of results in ecology , 2008 .

[51]  Guy Karlebach,et al.  Modelling and analysis of gene regulatory networks , 2008, Nature Reviews Molecular Cell Biology.

[52]  Christophe Lemetre,et al.  Artificial neural network techniques to investigate potential interactions between biomarkers , 2010 .

[53]  Li Song,et al.  Neural network analysis of lymphoma microarray data: prognosis and diagnosis near-perfect , 2003, BMC Bioinformatics.

[54]  H. Tsuda,et al.  NKX2.2 is a Useful Immunohistochemical Marker for Ewing Sarcoma , 2012, The American journal of surgical pathology.

[55]  M. Ringnér,et al.  Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks , 2001, Nature Medicine.

[56]  Graham R. Ball,et al.  Estrogen receptor status prediction for breast cancer using artificial neural network , 2011, 2011 International Conference on Machine Learning and Cybernetics.

[57]  Long Cheng,et al.  Recurrent Neural Network for Non-Smooth Convex Optimization Problems With Application to the Identification of Genetic Regulatory Networks , 2011, IEEE Transactions on Neural Networks.

[58]  Hidde de Jong,et al.  Modeling and Simulation of Genetic Regulatory Systems: A Literature Review , 2002, J. Comput. Biol..

[59]  Andrei Dragomir,et al.  Gene regulatory networks modelling using a dynamic evolutionary hybrid , 2010, BMC Bioinformatics.

[60]  L. Mirny,et al.  Protein complexes and functional modules in molecular networks , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[61]  Mary T. Brinkoetter,et al.  FNDC5 and irisin in humans: I. Predictors of circulating concentrations in serum and plasma and II. mRNA expression and circulating concentrations in response to weight loss and exercise. , 2012, Metabolism: clinical and experimental.

[62]  J. A. Barnes,et al.  Role of troponin T in disease , 2004, Molecular and Cellular Biochemistry.

[63]  J. Monti,et al.  Human atrial myosin light chain 1 expression attenuates heart failure. , 2005, Advances in experimental medicine and biology.

[64]  V. Notario,et al.  Caveolin-1 Modulates the Ability of Ewing's Sarcoma to Metastasize , 2010, Molecular Cancer Research.

[65]  Ramesh Ram,et al.  MCMC Based Bayesian Inference for Modeling Gene Networks , 2009, PRIB.

[66]  C. McIntyre,et al.  Troponin T for the detection of dialysis-induced myocardial stunning in hemodialysis patients. , 2012, Clinical journal of the American Society of Nephrology : CJASN.

[67]  S. L. Wong,et al.  A Map of the Interactome Network of the Metazoan C. elegans , 2004, Science.

[68]  D. Hughes,et al.  Critical signaling pathways in bone sarcoma: Candidates for therapeutic interventions , 2009, Current oncology reports.

[69]  Wei-Po Lee,et al.  Computational methods for discovering gene networks from expression data , 2009, Briefings Bioinform..

[70]  Xu Ma,et al.  CITED2 mutation links congenital heart defects to dysregulation of the cardiac gene VEGF and PITX2C expression. , 2012, Biochemical and biophysical research communications.

[71]  A. Cheung,et al.  Wnt activation downregulates olfactomedin-1 in Fallopian tubal epithelial cells: a microenvironment predisposed to tubal ectopic pregnancy , 2012, Laboratory Investigation.

[72]  A A Schäffer,et al.  A novel nemaline myopathy in the Amish caused by a mutation in troponin T1. , 2000, American journal of human genetics.

[73]  Graham R. Ball,et al.  Identification of gene transcript signatures predictive for estrogen receptor and lymph node status using a stepwise forward selection artificial neural network modelling approach , 2008, Artif. Intell. Medicine.

[74]  Dong-Ling Tong,et al.  Hybridising Genetic Algorithm-Neural Network (GANN) in marker genes detection , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[75]  Dong Ling Tong,et al.  Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection , 2010, Int. J. Mach. Learn. Cybern..

[76]  Christophe Lemetre,et al.  An introduction to artificial neural networks in bioinformatics - application to complex microarray and mass spectrometry datasets in cancer studies , 2008, Briefings Bioinform..

[77]  Keith Phalp,et al.  Innovative Hybridisation of Genetic Algorithms and Neural Networks in Detecting Marker Genes for Leukaemia Cancer , 2009 .

[78]  G. Ball,et al.  A validated gene expression profile for detecting clinical outcome in breast cancer using artificial neural networks , 2010, Breast Cancer Research and Treatment.

[79]  Christophe Lemetre,et al.  MicroRNA signatures predict oestrogen receptor, progesterone receptor and HER2/neu receptor status in breast cancer , 2009, Breast Cancer Research.

[80]  M. Morgan,et al.  The LIM proteins FHL1 and FHL3 are expressed differently in skeletal muscle. , 1999, Biochemical and biophysical research communications.

[81]  A. Barabasi,et al.  Network biology: understanding the cell's functional organization , 2004, Nature Reviews Genetics.

[82]  G. Ball,et al.  Characterization of biomarkers in polycystic ovary syndrome (PCOS) using multiple distinct proteomic platforms. , 2007, Journal of proteome research.

[83]  A. Rajwanshi,et al.  Malignant small round cell tumors , 2009, Journal of cytology.