Discovery of dominant and dormant genes from expression data using a novel generalization of SNR for multi-class problems

Tsai, Yu‐Shuen; Lin, Chin‐Teng; Tseng, George C.; Chung, I‐Fang; Pal, Nikhil R.

doi:10.1186/1471-2105-9-425

Cited by 26 publications

(25 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly for RHAB tumour class D63878_at, X54673_at genes are reported in Pomeroy et al (2002). In literature (Pomeroy et al, 2002;Tsai et al, 2008), D85418_at, D30755_at and D31888_at genes are reported to belong to NCER class as we obtained in our work. Gene U79288_at is reported in Tsai et al (008) to belong to PNET class.…”

Section: Gene Markers For Brain Tumour Datasetsupporting

confidence: 66%

See 1 more Smart Citation

Cancer tissue sample classification using point symmetry-based clustering algorithm

Acharya¹,

Saha²

2018

IJHT

View full text Add to dashboard Cite

Clustering or unsupervised classification techniques can be used to solve different types of classification problems of different domains. Symmetry is an important property for any real life object. Therefore, symmetry-based distance measurements play some important roles in identifying some patterns or clusters of real life datasets. In this paper, inspired by the symmetric property, we have proposed a point symmetry-based clustering algorithm which has been used to identify clusters of tissue samples from some real life cancer datasets. Our proposed algorithm is also multi-objective-optimisation (MOO) based, i.e., optimises more than one objectives simultaneously. We have also shown the superiority of our proposed algorithm with respect to some state-of-the-art clustering algorithms.

show abstract

Section: Gene Markers For Brain Tumour Datasetsupporting

confidence: 66%

“…Gene U79288_at is reported in Tsai et al (008) to belong to PNET class. Z31560_s and U50648_s_at genes are reported to belong to MD class in Wang et al (2008) and Tsai et al (2008), respectively. These findings are similar to the observations derived from our present study.…”

Section: Gene Markers For Brain Tumour Datasetmentioning

confidence: 99%

Cancer tissue sample classification using point symmetry-based clustering algorithm

Acharya¹,

Saha²

2018

IJHT

View full text Add to dashboard Cite

show abstract

“…In [13] Y.-S. Tsai presents an innovative generalizations of SNR for multiclass cancer discrimination is proposed through the beginning of two indices, one is called Gene Dominant Index and another one is called Gene Dormant Index (GDIs) . These two indices lead to the concepts of dominant and dormant genes with biological significance.…”

Section: Generalization Approachmentioning

confidence: 99%

“…Tsai et al [13] Propose an innovative generalizations of SNR for multiclass cancer discrimination is proposed through the beginning of two indices, one is called Gene Dominant Index and another one is called Gene Dormant Index (GDIs).…”

Section: Redundancy Removalmentioning

confidence: 99%

A Survey on Improved Filtering Techniques for Multiclass Gene Selection

Manoharan¹,

Shanmugalakshmi²

2014

IJCA

View full text Add to dashboard Cite

In the field of bioinformatics, selection of genes in multiclass sample classification can be done by filtering methods using microarray data. Such approaches usually contribute to bias towards a few classes that are easily recognizable from other classes due to imbalances of strong features and sample sizes of distinct classes in a microarray data. Many methods have been used for the filter methods, as they are very commonly used in gene ranking from microarray data in multiclass problems. In this research, we discuss various methods to decompose multiclass ranking statistics into class specific statistics and then need of Pareto-front analysis for selection of genes. This mitigates the bias induced by class intrinsic characteristics of dominating classes. The need of Pareto-front analysis is to indicate on two filter criteria commonly used for gene selection: F-score and KW-score. A significant development in classification performance and reduction in redundancy among top ranked genes were achieved in experiments with both synthetic and real-benchmark data sets. The following work is analysis over the traditional and improved filter methods used for gene selection of various classes through various mechanisms available in the literature.

show abstract

“…A centroid-based ranking score was proposed as a multiplication of the difference between class and overall mean, with the disparity between between-class sum of squares to withinclass sum of squares [11]. A generalization of signal-to-noise ratio for multiclass gene selection was developed by defining gene dominant index and gene dormant index [12]. Final classification was thus performed using a few top-ranked dominant and dormant genes.…”

Section: Introductionmentioning

confidence: 99%

Multiclass Gene Selection Using Pareto-Fronts

Rajapakse

Mundra

2013

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Filter methods are often used for selection of genes in multiclass sample classification by using microarray data. Such techniques usually tend to bias toward a few classes that are easily distinguishable from other classes due to imbalances of strong features and sample sizes of different classes. It could therefore lead to selection of redundant genes while missing the relevant genes, leading to poor classification of tissue samples. In this manuscript, we propose to decompose multiclass ranking statistics into class-specific statistics and then use Pareto-front analysis for selection of genes. This alleviates the bias induced by class intrinsic characteristics of dominating classes. The use of Pareto-front analysis is demonstrated on two filter criteria commonly used for gene selection: F-score and KW-score. A significant improvement in classification performance and reduction in redundancy among top-ranked genes were achieved in experiments with both synthetic and real-benchmark data sets.

show abstract

Discovery of dominant and dormant genes from expression data using a novel generalization of SNR for multi-class problems

Cited by 26 publications

References 63 publications

Cancer tissue sample classification using point symmetry-based clustering algorithm

Cancer tissue sample classification using point symmetry-based clustering algorithm

A Survey on Improved Filtering Techniques for Multiclass Gene Selection

Multiclass Gene Selection Using Pareto-Fronts

Contact Info

Product

Resources

About