Muhammad Faiz Misman

A multi-objective strategy in genetic algorithms for gene selection of gene expression data

A microarray machine offers the capacity to measure the expression levels of thousands of genes simultaneously. It is used to collect information from tissue and cell samples regarding gene expression differences that could be useful for cancer classification. However, the urgent problems in the use of gene expression data are the availability of a huge number of genes relative to the small number of available samples, and the fact that many of the genes are not relevant to the classification. It has been shown that selecting a small subset of genes can lead to improved accuracy in the classification. Hence, this paper proposes a solution to the problems by using a multiobjective strategy in a genetic algorithm. This approach was tried on two benchmark gene expression data sets. It obtained encouraging results on those data sets as compared with an approach that used a single-objective strategy in a genetic algorithm.

Selecting informative genes from microarray data by using hybrid methods for cancer classification

Gene expression technology, namely microarrays, offers the ability to measure the expression levels of thousands of genes simultaneously in biological organisms. Microarray data are expected to be of significant help in the development of an efficient cancer diagnosis and classification platform. A major problem in these data is that the number of genes greatly exceeds the number of tissue samples. These data also have noisy genes. It has been shown in literature reviews that selecting a small subset of informative genes can lead to improved classification accuracy. Therefore, this paper aims to select a small subset of informative genes that are most relevant for cancer classification. To achieve this aim, an approach using two hybrid methods has been proposed. This approach is assessed and evaluated on two well-known microarray data sets, showing competitive results.

A group-specific tuning parameter for hybrid of SVM and SCAD in identification of informative genes and pathways

The pathway-based microarray classification approach leads to a new era of genomic research. However, this approach is limited by the issues in quality of pathway data. Usually the pathway data are curated from biological literatures and in specific biological experiment (e.g., lung cancer experiment), context free pathway information collection process takes place leading to the presence of uninformative genes in the pathways. Many methods in this approach neglect these limitations by treating all genes in a pathway as significant. In this paper, we proposed a hybrid of support vector machine and smoothly clipped absolute deviation with group-specific tuning parameters (gSVM-SCAD) to select informative genes within pathways before the pathway evaluation process. Our experiment on canine, gender and lung cancer datasets shows that gSVM-SCAD obtains significant results in identifying significant genes and pathways and in classification accuracy.

An improved hybrid of SVM and SCAD for pathway analysis

Pathway analysis has lead to a new era in genomic research by providing further biological process information compared to traditional single gene analysis. Beside the advantage, pathway analysis provides some challenges to the researchers, one of which is the quality of pathway data itself. The pathway data usually defined from biological context free, when it comes to a specific biological context (e.g. lung cancer disease), typically only several genes within pathways are responsible for the corresponding cellular process. It also can be that some pathways may be included with uninformative genes or perhaps informative genes were excluded. Moreover, many algorithms in pathway analysis neglect these limitations by treating all the genes within pathways as significant. In previous study, a hybrid of support vector machines and smoothly clipped absolute deviation with groups-specific tuning parameters (gSVM-SCAD) was proposed in order to identify and select the informative genes before the pathway evaluation process. However, gSVM-SCAD had showed a limitation in terms of the performance of classification accuracy. In order to deal with this limitation, we made an enhancement to the tuning parameter method for gSVM-SCAD by applying the B-Type generalized approximate cross validation (BGACV). Experimental analyses using one simulated data and two gene expression data have shown that the proposed method obtains significant results in identifying biologically significant genes and pathways, and in classification accuracy.

A Study of Network-based Approach for Cancer Classification

The advent of high-throughput techniques such as microarray data enabled researchers to elucidate process in a cell that fruitfully useful for pathological and medical. For such opportunities, microarray gene expression data have been explored and applied for various types of studies e.g. gene association, gene classification and construction of gene network. Unfortunately, since gene expression data naturally have a few of samples and thousands of genes, this leads to a biological and technical problems. Thus, the availability of artificial intelligence techniques couples with statistical methods can give promising results for addressing the problems. These approaches derive two well known methods: supervised and unsupervised. Whenever possible, these two superior methods can work well in classification and clustering in term of class discovery and class prediction. Significantly, in this paper we will review the benefit of network-based in term of interaction data for classification in identification of class cancer.

A hybrid of SVM and SCAD with group-specific tuning parameter for pathway-based microarray analysis

The incorporation of pathway data into the microarray analysis had lead to a new era in advance understanding of biological processes. However, this advancement is limited by the two issues in quality of pathway data. First, the pathway data are usually made from the biological context free, when it comes to a specific cellular process (e.g. lung cancer development), it can be that only several genes within pathways are responsible for the corresponding cellular process. Second, pathway data commonly curated from the literatures, it can be that some pathway may be included with the uninformative genes while the informative genes may be excluded. In this paper, we proposed a hybrid of support vector machine and smoothly clipped absolute deviation with group-specific tuning parameters (gSVM-SCAD) to select informative genes within pathways before the pathway evaluation process. Our experiments on lung cancer and gender data sets show that gSVM-SCAD obtains significant results in classification accuracy and in selecting the informative genes and pathways.