Cancer diagnosis marker extraction for soft tissue sarcomas based on gene expression profiling data by using projective adaptive resonance theory (PART) filtering method

BackgroundRecent advances in genome technologies have provided an excellent opportunity to determine the complete biological characteristics of neoplastic tissues, resulting in improved diagnosis and selection of treatment. To accomplish this objective, it is important to establish a sophisticated algorithm that can deal with large quantities of data such as gene expression profiles obtained by DNA microarray analysis.ResultsPreviously, we developed the projective adaptive resonance theory (PART) filtering method as a gene filtering method. This is one of the clustering methods that can select specific genes for each subtype. In this study, we applied the PART filtering method to analyze microarray data that were obtained from soft tissue sarcoma (STS) patients for the extraction of subtype-specific genes. The performance of the filtering method was evaluated by comparison with other widely used methods, such as signal-to-noise, significance analysis of microarrays, and nearest shrunken centroids. In addition, various combinations of filtering and modeling methods were used to extract essential subtype-specific genes. The combination of the PART filtering method and boosting – the PART-BFCS method – showed the highest accuracy. Seven genes among the 15 genes that are frequently selected by this method – MIF, CYFIP2, HSPCB, TIMP3, LDHA, ABR, and RGS3 – are known prognostic marker genes for other tumors. These genes are candidate marker genes for the diagnosis of STS. Correlation analysis was performed to extract marker genes that were not selected by PART-BFCS. Sixteen genes among those extracted are also known prognostic marker genes for other tumors, and they could be candidate marker genes for the diagnosis of STS.ConclusionThe procedure that consisted of two steps, such as the PART-BFCS and the correlation analysis, was proposed. The results suggest that novel diagnostic and therapeutic targets for STS can be extracted by a procedure that includes the PART filtering method.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[2]  Serhiy Souchelnytskyi,et al.  TGFβ1/Smad3 counteracts BRCA1-dependent repair of DNA damage , 2005, Oncogene.

[3]  D Haussler,et al.  Knowledge-based analysis of microarray gene expression data by using support vector machines. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Hiroyuki Honda,et al.  Lymphoma Prognostication from Expression Profiling Using a Combination Method of Boosting and Projective Adaptive Resonance Theory , 2006 .

[5]  David E. Misek,et al.  Characterization of gene expression profiles associated with glioma progression using oligonucleotide-based microarray analysis and real-time reverse transcription-polymerase chain reaction. , 2003, The American journal of pathology.

[6]  Werner Paulus,et al.  Regulators of G‐Protein Signaling 3 and 4 (RGS3, RGS4) Are Associated with Glioma Cell Motility , 2004, Journal of neuropathology and experimental neurology.

[7]  C. Wild,et al.  Tissue inhibitor of metalloproteinase‐3 (TIMP‐3) gene is methylated in the development of esophageal adenocarcinoma: Loss of expression correlates with poor prognosis , 2005, International journal of cancer.

[8]  Claire L Weston,et al.  beta-Catenin status predicts a favorable outcome in childhood medulloblastoma: the United Kingdom Children's Cancer Study Group Brain Tumour Committee. , 2005, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[9]  John Anastasi,et al.  Acute lymphoblastic leukaemia: diagnosis and classification. , 2002, Best practice & research. Clinical haematology.

[10]  Jin Gu,et al.  Matrix Metalloproteinases Expression Correlates with Survival in Patients with Esophageal Squamous Cell Carcinoma , 2005, The American Journal of Gastroenterology.

[11]  Taizo Hanai,et al.  Model Construction for Quality of Beer and Brewing Process using FNN. , 1999 .

[12]  P. Bonnier,et al.  Long-term prognostic significance of neoangiogenesis in breast carcinomas: comparison of Tie-2/Tek, CD105, and CD31 immunocytochemical expression. , 2004, Human pathology.

[13]  Y. Doki,et al.  Clinical significance of class III beta-tubulin expression and its predictive value for resistance to docetaxel-based chemotherapy in gastric cancer. , 2006, International journal of oncology.

[14]  Hiroyuki Honda,et al.  Classification of intramural metastases and lymph node metastases of esophageal cancer from gene expression based on boosting and projective adaptive resonance theory. , 2006, Journal of bioscience and bioengineering.

[15]  Trevor Hastie,et al.  Gene Expression Programs in Response to Hypoxia: Cell Type Specificity and Prognostic Significance in Human Cancers , 2006, PLoS medicine.

[16]  Taizo Hanai,et al.  Analysis of expression profile using fuzzy adaptive resonance theory , 2002, Bioinform..

[17]  L C Harrison,et al.  Fuzzy neural network-based prediction of the motif for MHC class II binding peptides. , 2001, Journal of bioscience and bioengineering.

[18]  F. Berthold,et al.  Retention of imprinting of the human apoptosis-related gene TSSC3 in human brain tumors. , 2000, Human molecular genetics.

[19]  Yoshiki Uchikawa,et al.  On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm , 1992, IEEE Trans. Neural Networks.

[20]  Taizo Hanai,et al.  Fuzzy Neural Network Applied to Gene Expression Profiling for Predicting the Prognosis of Diffuse Large B‐cell Lymphoma , 2002, Japanese journal of cancer research : Gann.

[21]  Shishir Shah,et al.  Genome-wide array comparative genomic hybridization analysis reveals distinct amplifications in osteosarcoma , 2004, BMC Cancer.

[22]  Javier León,et al.  Inhibitory effect of c-Myc on p53-induced apoptosis in leukemia cells. Microarray analysis reveals defective induction of p53 target genes and upregulation of chaperone genes , 2005, Oncogene.

[23]  Henri Porte,et al.  Tissue inhibitor of metalloproteinase 1 is an independent predictor of prognosis in patients with nonsmall cell lung carcinoma who undergo resection with curative intent , 2005, Cancer.

[24]  H. Kirikoshi,et al.  Expression of WNT7A in human normal tissues and cancer, and regulation of WNT7A and WNT7B in human cancer. , 2002, International journal of oncology.

[25]  Philippe Moreau,et al.  CD130 rather than CD126 expression is associated with disease activity in multiple myeloma , 1999, British journal of haematology.

[26]  Meera Mathur,et al.  Stromelysin‐3 expression is an early event in human oral tumorigenesis , 2003, International journal of cancer.

[27]  Mary Miu Yee Waye,et al.  Paeoniae Radix, a Chinese herbal extract, inhibit hepatoma cells growth by inducing apoptosis in a p53 independent pathway. , 2002, Life sciences.

[28]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[29]  P. Nowell,et al.  Detection of leukemia-associated MLL-GAS7 translocation early during chemotherapy with DNA topoisomerase II inhibitors. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[30]  R. Tibshirani,et al.  Significance analysis of microarrays applied to the ionizing radiation response , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[31]  Hiroyuki Honda,et al.  A New Reliable Cancer Diagnosis Method Using Boosted Fuzzy Classifier with a SWEEP Operator Method , 2005 .

[32]  Juan P Albar,et al.  An anti-ICAM-2 (CD102) monoclonal antibody induces immune-mediated regressions of transplanted ICAM-2-negative colon carcinomas. , 2002, Cancer research.

[33]  Gajendra P. S. Raghava,et al.  SVM based method for predicting HLA-DRB1*0401 binding peptides in an antigen sequence , 2004, Bioinform..

[34]  Hiroyuki Honda,et al.  Prediction of peptide binding to major histocompatibility complex class II molecules through use of boosted fuzzy classifier with SWEEP operator method. , 2006, Journal of bioscience and bioengineering.

[35]  G M Bokoch,et al.  Abr and Bcr are multifunctional regulators of the Rho GTP-binding protein family. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[36]  Serhiy Souchelnytskyi,et al.  TGFbeta1/Smad3 counteracts BRCA1-dependent repair of DNA damage. , 2005, Oncogene.

[37]  V. Vapnik,et al.  A note one class of perceptrons , 1964 .

[38]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[39]  Youhei Saito,et al.  Enhancement of oxidative stress-induced apoptosis by Hsp105alpha in mouse embryonal F9 cells. , 2002, European journal of biochemistry.

[40]  Jianhong Wu,et al.  Projective ART for clustering data sets in high dimensional spaces , 2002, Neural Networks.

[41]  Jianhong Wu,et al.  Dynamics of projective adaptive resonance theory model: the foundation of PART algorithm , 2004, IEEE Transactions on Neural Networks.

[42]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[43]  Hiroyuki Honda,et al.  Construction of robust prognostic predictors by using projective adaptive resonance theory as a gene filtering method , 2005, Bioinform..

[44]  R. Tibshirani,et al.  Diagnosis of multiple cancer types by shrunken centroids of gene expression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[45]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.

[46]  Fumiaki Sasaki,et al.  Macrophage migration inhibitory factor promotes tumor invasion and metastasis via the Rho-dependent pathway. , 2005, Clinical cancer research : an official journal of the American Association for Cancer Research.

[47]  Stuart K. Calderwood,et al.  Heat shock proteins in cancer: diagnostic, prognostic, predictive, and treatment implications , 2005, Cell stress & chaperones.

[49]  Carlos Rubio,et al.  COL11A1 in FAP polyps and in sporadic colorectal tumors , 2001, BMC Cancer.