KMeans Greedy Search Hybrid Algorithm for Biclustering Gene Expression Data

Das, Sagnik; Idicula, Sumam Mary

doi:10.1007/978-1-4419-5913-3_21

Cited by 6 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seed growing starts from condition list followed by gene list until the hscore value reaches the given threshold. This is a greedy method since our aim is to select the next element which produces bicluster with minimum hscore value [6] [7].…”

Section: Greedy Search Algorithmmentioning

confidence: 99%

“…Table 2 lists a comparison of results of various algorithms on Yeast data. Performance of greedy search-Binary PSO hybrid with that of SEBI [12], Cheng and Church's algorithm (CC) [3], and the algorithm FLOC by Yang et al [13], DBF [14] and Modified greedy [6] are given. Here biclusters with MSR less than 100 obtained from greedy search is used as initial population of PSO.…”

Section: Datasets Usedmentioning

confidence: 99%

See 1 more Smart Citation

Greedy Search-Binary PSO Hybrid for Biclustering Gene Expression Data

Das¹,

Idicula²

2010

IJCA

Self Cite

View full text Add to dashboard Cite

As a useful data mining technique biclustering identifies local patterns from gene expression data. A bicluster of a gene expression dataset is a subset of genes which exhibit similar expression patterns along a subset of conditions. In this paper a new method is introduced based on greedy search algorithm combined with the evolutionary technique particle swarm optimization for the identification of biclusters. Greedy methods have the possibility of getting trapped in local minima. Metaheuristic methods like particle swarm optimization have features for escaping from local minima and can find global optimal solutions. In this algorithm biclusters are identified in three steps. In the first step small disjoint tightly coregulated submatrices are generated using K-Means clustering algorithm. Then greedy search algorithm is used to enlarge the seeds. Output of greedy search algorithm is used as initial population of binary PSO. The result obtained on Yeast dataset shows that this method can generate high quality biclusters.

show abstract

Section: Greedy Search Algorithmmentioning

confidence: 99%

Section: Datasets Usedmentioning

confidence: 99%

Greedy Search-Binary PSO Hybrid for Biclustering Gene Expression Data

Das¹,

Idicula²

2010

IJCA

Self Cite

View full text Add to dashboard Cite

show abstract

“…This bicluster has strikingly similar up-regulation and down regulation and is with a structural appearance which is hitherto unseen in any of the literature published so far. In the case of novel greedy search algorithm [6] the added node is removed only when the MSR of the bicluster exceeds δ (MSR threshold). But when MSR difference threshold is applied there is more restriction on the incremental value of hscore or MSR which means that the elements in the biclusters are more tightly packed.…”

Section: Biclustering Using Iterative Search With Incremental Msr Difmentioning

confidence: 99%

“…Thus the value of δ is set to 200 in this study. The performance of BISIMT algorithm in comparison with that of Novel Greedy [6], SEBI [11], Cheng and Church's algorithm (CC) [3], and the algorithm FLOC by Yang et al [12] and DBF [13] etc. for the Yeast dataset are given.…”

Section: Comparisonmentioning

confidence: 99%

Iterative Search with Incremental MSR Difference Threshold for Biclustering Gene Expression Data

Das¹,

Idicula²

2010

IJCA

Self Cite

View full text Add to dashboard Cite

The goal of biclustering in a gene expression data matrix is to find a submatrix such that the genes in the submatrix show highly correlated activities across all conditions in the submatrix. A measure called Mean Squared Residue (MSR) is used to simultaneously evaluate the coherence of rows and columns within a submatrix. In this paper a new method for biclustering gene expression data is developed. In the first step high quality bicluster seeds are generated using K-Means clustering algorithm. Then more genes and conditions (node) are added to the bicluster. Before adding a node the MSR X of the bicluster is calculated. After adding the node again the MSR Y is calculated. The added node is deleted if Y minus X is greater than MSR difference threshold or if Y is greater than δ (MSR threshold) which depends on the dataset. The MSR difference threshold is different for gene list and condition list and it depends on the dataset also. Proper values should be identified through experimentation in order to obtain biclusters of large size. Since it is very difficult to calculate the value of MSR difference threshold, in this algorithm an iterative search is used where MSR difference threshold is initialized with a small value and it is incremented after each iteration. A bicluster is obtained from Yeast dataset with a unique structural appearance. This proves that the newly introduced concept of MSR difference threshold will result in high quality biclusters. The results obtained on bench mark datasets prove that this algorithm is better than many of the existing biclustering algorithms.

show abstract

“…The focus of our analysis is on the K-means algorithm, because of its widespread use in a variety of settings and applications ranging from image segmentation [1] to co-clustering [2], and even analysis of bio-logical datasets [3]. Recently, many alternative clustering algorithms with more desirable stability properties (e.g., spectral methods [4]) have been derived.…”

Section: Introductionmentioning

confidence: 99%

Cluster-Aware Compression with Provable K-means Preservation

Freris¹,

Vlachos²,

Turaga³

2012

Proceedings of the 2012 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

This work rigorously explores the design of clusterpreserving compression schemes for high-dimensional data. We focus on the K-means algorithm and identify conditions under which running the algorithm on the compressed data yields the same clustering outcome as on the original. The compression is performed using single and multi-bit minimum mean square error quantization schemes as well as a given clustering assignment of the original data. We provide theoretical guarantees on post-quantization cluster preservation under certain conditions on the cluster structure, and propose an additional data transformation that can ensure cluster preservation unconditionally; this transformation is invertible and thus induces virtually no distortion on the compressed data. In addition, we provide an efficient scheme for multi-bit allocation, per cluster and data dimension, which enables a trade-off between high compression efficiency and low data distortion. Our experimental studies highlight that the suggested scheme accurately preserved the clusters formed in all cases, while incurring minimal distortion on the data shapes.Our results can find many applications, e.g., in a) clustering, analysis and distribution of massive datasets, where the proposed data compression can boost performance while providing provable guarantees on the clustering result, as well as, in b) cloud computing services, as the optional transformation provides a data-hiding functionality in addition to preserving the K-means clustering outcome.

show abstract

KMeans Greedy Search Hybrid Algorithm for Biclustering Gene Expression Data

Cited by 6 publications

References 6 publications

Greedy Search-Binary PSO Hybrid for Biclustering Gene Expression Data

Greedy Search-Binary PSO Hybrid for Biclustering Gene Expression Data

Iterative Search with Incremental MSR Difference Threshold for Biclustering Gene Expression Data

Cluster-Aware Compression with Provable K-means Preservation

Contact Info

Product

Resources

About