Numerous cancer studies have combined different datasets for the prognosis of patients. This study incorporated four networks for significant directed random walk (sDRW) to predict cancerous genes and risk pathways. The study investigated the feasibility of cancer prediction via different networks. In this study, multiple micro array data were analysed and used in the experiment. Six gene expression datasets were applied in four networks to study the effectiveness of the networks in sDRW in terms of cancer prediction. The experimental results showed that one of the proposed networks is outstanding compared to other networks. The network is then proposed to be implemented in sDRW as a walker network. This study provides a foundation for further studies and research on other networks. We hope these finding will improve the prognostic methods of cancer patients.
Investigations in 30 healthy control subjects of Indian, Chinese and Malay ethnic origin, revealed that all the Chinese and about two thirds of the Indians and Malays had a normal capacity to absorb D—xylose, Vitamin A, Co58 labelled Vitamin B12 and dietary fat. About a third of the Indians and Malays were unable to absorb one or two of the four test substances used in the absorption studies. Jejunal biopsies did not differ in the 3 ethnic groups and were normal or mildly abnormal. 27 patients presenting with anorexia, a sore tongue and pallor were also investigated. Indians formed the majority of the patients. Diarrhoea occurred in only 51 % of the patients. All had a megaloblastic anaemia. Absorption studies revealed malabsorption of xylose, Vitamin A and Vitamin B12 in the majority but steatorrhoea occurred in only 26% of the patients. Jejunal biopsies were mildly abnormal in 8% and moderately or severely abnormal in 92 % of the patients. All responded to folic acid or Vitamin B12 therapy. 16 patients were restudied after 5 to 24 months therapy and the majority were found to have improved. Results of investigations and response to therapy indicate that these patients were suffering from tropical sprue. These studies indicate that tropical sprue in Singapore affects Indians mainly and can often present without diarrhoea and steatorrhoea.
Microarray technology has become one of the elementary tools for researchers to study the genome of organisms. As the complexity and heterogeneity of cancer is being increasingly appreciated through genomic analysis, cancerous classification is an emerging important trend. Significant directed random walk is proposed as one of the cancerous classification approach which have higher sensitivity of risk gene prediction and higher accuracy of cancer classification. In this paper, the methodology and material used for the experiment are presented. Tuning parameter selection method and weight as parameter are applied in proposed approach. Gene expression dataset is used as the input datasets while pathway dataset is used to build a directed graph, as reference datasets, to complete the bias process in random walk approach. In addition, we demonstrate that our approach can improve sensitive predictions with higher accuracy and biological meaningful classification result. Comparison result takes place between significant directed random walk and directed random walk to show the improvement in term of sensitivity of prediction and accuracy of cancer classification.