Random Walking on Functional Interaction Networks to Rank Genes Involved in Cancer

Ré, Matteo; Valentini, Giorgio

doi:10.1007/978-3-642-33412-2_7

Cited by 5 publications

(5 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fully unsupervised clustering techniques (e.g., intelligent k-means and kernel k-means) are applied to analyze genes in colorectal carcinoma [117]. Other than that, random walk-based clustering, GCHL, and CLIQUE clustering techniques are also used in unsupervised manners [26,41,[46][47][48]61,67].…”

Section: Discussionmentioning

confidence: 99%

“…However, density-based clustering has a high runtime analysis to detect clusters [64]. DBSCAN, random walk, and Relative Core Merge (RECOME) are examples of density-based clustering [44][45][46][47][48]. Historically, a random walk uses the theory of Markov chain [48,65].…”

Section: Category 4: Density-based Clusteringmentioning

confidence: 99%

“…DBSCAN, random walk, and Relative Core Merge (RECOME) are examples of density-based clustering [44][45][46][47][48]. Historically, a random walk uses the theory of Markov chain [48,65]. In most studies, the random walk has been used to infer and to optimize the structural properties of networks [65,66].…”

Section: Category 4: Density-based Clusteringmentioning

confidence: 99%

See 2 more Smart Citations

A Review of Computational Methods for Clustering Genes with Similar Biological Functions

et al. 2019

View full text Add to dashboard Cite

Clustering techniques can group genes based on similarity in biological functions. However, the drawback of using clustering techniques is the inability to identify an optimal number of potential clusters beforehand. Several existing optimization techniques can address the issue. Besides, clustering validation can predict the possible number of potential clusters and hence increase the chances of identifying biologically informative genes. This paper reviews and provides examples of existing methods for clustering genes, optimization of the objective function, and clustering validation. Clustering techniques can be categorized into partitioning, hierarchical, grid-based, and density-based techniques. We also highlight the advantages and the disadvantages of each category. To optimize the objective function, here we introduce the swarm intelligence technique and compare the performances of other methods. Moreover, we discuss the differences of measurements between internal and external criteria to validate a cluster quality. We also investigate the performance of several clustering techniques by applying them on a leukemia dataset. The results show that grid-based clustering techniques provide better classification accuracy; however, partitioning clustering techniques are superior in identifying prognostic markers of leukemia. Therefore, this review suggests combining clustering techniques such as CLIQUE and k-means to yield high-quality gene clusters.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Category 4: Density-based Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Computational Methods for Clustering Genes with Similar Biological Functions

et al. 2019

View full text Add to dashboard Cite

show abstract

“…We evaluated also another variant of RW, i.e. the random walk with restart (RWR) algorithm, just successfully applied in gene prioritization problems [22]: at each step of the random walk in the graph the random walker can move to one of its neighbours or can restart from its initial condition with probability 0 < θ < 1. We considered also a classical inductive method, i.e.…”

Section: Compared Methodsmentioning

confidence: 99%

A Fast Ranking Algorithm for Predicting Gene Functions in Biomolecular Networks

Ré

Mesiti

Valentini

2012

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

Self Cite

View full text Add to dashboard Cite

Ranking genes in functional networks according to a specific biological function is a challenging task raising relevant performance and computational complexity problems. To cope with both these problems we developed a transductive gene ranking method based on kernelized score functions able to fully exploit the topology and the graph structure of biomolecular networks and to capture significant functional relationships between genes. We run the method on a network constructed by integrating multiple biomolecular data sources in the yeast model organism, achieving significantly better results than the compared state-of-the-art network-based algorithms for gene function prediction, and with relevant savings in computational time. The proposed approach is general and fast enough to be in perspective applied to other relevant node ranking problems in large and complex biological networks.

show abstract

“…In [1], Re and Valentini utilize random walk and random walk with restart to rank genes with respect to their likelihood of belonging to each cancer module by exploiting the global topology of the functional interaction network, and local connections between genes close to genes in each cancer module. In [3], Erten, Bebek and Koyuturk come forward with a random walk based algorithm which postulates that genes which are associated with similar diseases exhibit patterns of topological similarity in PPI networks.…”

Section: Related Workmentioning

confidence: 99%

Ranking of cancer genes in Markov chain model through integration of heterogeneous sources of data

Chen

Wilkins

2014

2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Cancer is a disease driven largely by the accumulation of somatic mutations during the lifetime of a patient. Distinguishing driver mutations from passenger mutations had posed a challenge in modern cancer research. With the widespread use of microarray experiments and clinical studies, a large numbers of candidate cancer genes are produced and extracting informative genes out of them is essential. In our project we aim to find the informative genes for cancer by using mutation data from ovarian cancers. In our model we utilized the patient gene mutation profile, gene expression data and gene gene interactions network to build a graphical representation of genes and patients and construct Markov processes for mutation and patients separately. After this process, we can prioritize cancers genes automatically by looking into their scores at their stationary distributions. Comprehensive experiments show that the utilization of heterogeneous sources of information is very helpful in finding important cancer genes.

show abstract

Random Walking on Functional Interaction Networks to Rank Genes Involved in Cancer

Cited by 5 publications

References 23 publications

A Review of Computational Methods for Clustering Genes with Similar Biological Functions

A Review of Computational Methods for Clustering Genes with Similar Biological Functions

A Fast Ranking Algorithm for Predicting Gene Functions in Biomolecular Networks

Ranking of cancer genes in Markov chain model through integration of heterogeneous sources of data

Contact Info

Product

Resources

About