Microarray-Based Cancer Prediction Using Soft Computing Approach

Abstract

One of the difficulties in using gene expression profiles to predict cancer is how to effectively select a few informative genes to construct accurate prediction models from thousands or ten thousands of genes. We screen highly discriminative genes and gene pairs to create simple prediction models involved in single genes or gene pairs on the basis of soft computing approach and rough set theory. Accurate cancerous prediction is obtained when we apply the simple prediction models for four cancerous gene expression datasets: CNS tumor, colon tumor, lung cancer and DLBCL. Some genes closely correlated with the pathogenesis of specific or general cancers are identified. In contrast with other models, our models are simple, effective and robust. Meanwhile, our models are interpretable for they are based on decision rules. Our results demonstrate that very simple models may perform well on cancerous molecular prediction and important gene markers of cancer can be detected if the gene selection approach is chosen reasonably.

A Robust Gene selection Method for Microarray-based Cancer Classification

“…However, our recent studies have revealed that for the microarray-based cancer classification problem, the application of the depended degree was severely limited because of its overly rigor definition. In contrast, its generalized form-α depended degree, had essentially improved utility 2. To explore how the classification quality was improved by using the α depended degree relative to the depended degree, we compared the classification results obtained under different α values while based on the identical classifiers.…”

“…Hence, in,2 we defined the α depended degree, a generalization form of the depended degree, and utilized the α depended degree as the basis for choosing genes. The α depended degree of an attribute subset P by the decision attribute D was defined as ${\gamma }_{P}false(D,\hspace{0.17em}\alpha false)=\frac{false|{\text{POS}}_{P}false(D,\hspace{0.17em}\alpha false)false|}{\left|U\right|}$, where 0 ≤ α ≤ 1, $false|{\text{POS}}_{P}false(D,\hspace{0.17em}\alpha false)false|=false|\underset{X\in U/Rfalse(Dfalse)}{\cup }\mathit{\text{pos}}(P,\hspace{0.17em}X,\hspace{0.17em}\alpha )false|$ and pos ( P , X , α ) = ∪ { Y ∈ U/R ( P )| | Y ∩ X |/| Y | ≥ α }.…”

Network-based identification of reliable bio-markers for cancers

“…In the literature, several methods and concepts have been used to propose candidates of bio-markers, including support vector machine (Guyon et al, 2000), floating sequential search algorithm (Zhang et al, 2011), software "Gotoh" (Wang and Gotoh, 2009), independent principal component analysis , top score pair (Geman et al, 2004;Tan et al, 2005;Leek, 2009;Li et al, 2009), k-means IIC (Zhang et al, 2008), and so on. A total of 40 candidates are collected in the present work, among which 6 genes are not included in the considered set of 314 genes.…”

Cancer Classification Using Single Genes

“…In addition, because there are microarray intensity discrepancies between the training set and the test set in the prostate cancer dataset caused by two different experiments, we normalize both the training and the test data. Each original expression level ( , ) g x y is normalized to It is noted that the confidence of every classification rule produced by the way is no less than α [19]. Thus, we can ensure sufficient reliability of the derived classification rules by setting high threshold of α value.…”

“…Recently, we proposed a rough sets based soft computing method to conduct cancer classification using single or double genes [19]. In this article, we reevaluate the method by exploring the classification of cancer on the basis of single genes with three distinct datasets.…”