IPCA-CMI: An Algorithm for Inferring Gene Regulatory Networks based on a Combination of PCA-CMI and MIT Score

Aghdam, Rosa; Ganjali, Mojtaba; Eslahchi, Changiz

doi:10.1371/journal.pone.0092600

Cited by 23 publications

(16 citation statements)

References 39 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This network includes 9 genes and 9 samples. The second network is Dream100 from Dream3 challenge with 100 genes and 100 samples which consists of 166 edges in real network [26].…”

Section: Resultsmentioning

confidence: 99%

The inference of predictor set in gene regulatory networks using gravitational search algorithm

Jafari

Sattari-Naeini

Ghavami

2016

2016 1st Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)

View full text Add to dashboard Cite

The inference of Gene Regulatory Network (GRN) using the gene expression data is a growing field in bioinformatics and biological systems. As a matter of fact, the inference of GRN is crucial in order to predict the biological processes. In addition, it would be beneficial to determine the behavior of the processes in order to avoid the occurrence of some unplanned processes (disease). Inferring truly GRN requires the accurate inference of the predictor set. The process of predictor set inference consists of realizing the dependency of target genes and their potential predictors. Generally, the main limitations of an accurate inference of predictor set are the large number of genes, the low number of samples and the presence of noise in the gene expression data. This paper presents an accurate framework using Gravitational Search Algorithm (GSA) to infer predictor subset of each target gene in a GRN. In this work, one heuristic algorithm is utilized for each target gene independently. In each population, a mass presents the predictor subset related to the target gene. To generate the initial population per each target gene, instead of choosing predictors randomly, they are chosen using the Pearson correlation coefficient. The Mean Conditional Entropy (MCE) is used to guide GSA (as fitness function). Experimental results on biological data and comparative analysis including a recently method based on Genetic Algorithm (GA) for the same purpose, reveal that the proposed framework achieves superior accuracy.

show abstract

“…This network includes 9 genes and 9 samples. The second network is Dream100 from Dream3 challenge with 100 genes and 100 samples which consists of 166 edges in real network [26].…”

Section: Resultsmentioning

confidence: 99%

The inference of predictor set in gene regulatory networks using gravitational search algorithm

Jafari

Sattari-Naeini

Ghavami

2016

2016 1st Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)

View full text Add to dashboard Cite

show abstract

“…For discrete variables X and Y , MI is defined as [ 31 , 38 , 70 , 71 ]: where p ( x , y ) is the joint probability distribution of X and Y , and p ( x ) and p ( y ) are the marginal probability distributions of X and Y , respectively; H ( X ) and H ( Y ) are the entropies of X and Y , respectively; and H ( X , Y ) is the joint entropy of X and Y .…”

Section: Methodsmentioning

confidence: 99%

Inference of Gene Regulatory Network Based on Local Bayesian Networks

et al. 2016

View full text Add to dashboard Cite

The inference of gene regulatory networks (GRNs) from expression data can mine the direct regulations among genes and gain deep insights into biological processes at a network level. During past decades, numerous computational approaches have been introduced for inferring the GRNs. However, many of them still suffer from various problems, e.g., Bayesian network (BN) methods cannot handle large-scale networks due to their high computational complexity, while information theory-based methods cannot identify the directions of regulatory interactions and also suffer from false positive/negative problems. To overcome the limitations, in this work we present a novel algorithm, namely local Bayesian network (LBN), to infer GRNs from gene expression data by using the network decomposition strategy and false-positive edge elimination scheme. Specifically, LBN algorithm first uses conditional mutual information (CMI) to construct an initial network or GRN, which is decomposed into a number of local networks or GRNs. Then, BN method is employed to generate a series of local BNs by selecting the k-nearest neighbors of each gene as its candidate regulatory genes, which significantly reduces the exponential search space from all possible GRN structures. Integrating these local BNs forms a tentative network or GRN by performing CMI, which reduces redundant regulations in the GRN and thus alleviates the false positive problem. The final network or GRN can be obtained by iteratively performing CMI and local BN on the tentative network. In the iterative process, the false or redundant regulations are gradually removed. When tested on the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in E.coli, our results suggest that LBN outperforms other state-of-the-art methods (ARACNE, GENIE3 and NARROMI) significantly, with more accurate and robust performance. In particular, the decomposition strategy with local Bayesian networks not only effectively reduce the computational cost of BN due to much smaller sizes of local GRNs, but also identify the directions of the regulations.

show abstract

“…In addition, the casual relationship between variables can be detected by BNs. Three well‐known methods to learn the structure of BNs are constraint‐based, score‐based searching, and hybrid approaches . For constraint‐based method, the dependency among nodes in networks are assigned based on the conditional independency tests.…”

Section: Introductionmentioning

confidence: 99%

“…Three well-known methods to learn the structure of BNs are constraint-based, [15][16][17] score-based searching, [18][19][20][21][22] and hybrid approaches. [23][24][25] For constraint-based method, the dependency among nodes in networks are assigned based on the conditional independency tests. The score-based searching method contains two parts: assigning the scoring function and applying search procedure.…”

Section: Introductionmentioning

confidence: 99%

Some node ordering methods for the K2 algorithm

Aghdam

Tabar

Pezeshk

2018

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Inferring Bayesian network structure from data is a challenging issue, and many researchers have been working on this problem. The K2 is a well‐known order‐dependent algorithm to learn Bayesian network. The result of the algorithm is not robust since it achieves different network structure if node orderings are permuted. Consequently, choosing suitable sequential node ordering for the input of the K2 algorithm is a challenging task. In this work, some deterministic methods for selecting a suitable sequential node ordering are introduced. The effectiveness of these methods benchmarked through the Asia, Alarm, Car, and Insurance networks. The results indicate that the methods based on the concept of mutual information and entropy are suitable for finding a sequential node ordering and considerably improves the precision of network inference. The source code and selected data sets are available on http://profiles.bs.ipm.ir/softwares/ordering/.

show abstract

IPCA-CMI: An Algorithm for Inferring Gene Regulatory Networks based on a Combination of PCA-CMI and MIT Score

Cited by 23 publications

References 39 publications

The inference of predictor set in gene regulatory networks using gravitational search algorithm

The inference of predictor set in gene regulatory networks using gravitational search algorithm

Inference of Gene Regulatory Network Based on Local Bayesian Networks

Some node ordering methods for the K2 algorithm

Contact Info

Product

Resources

About