Connecting the Dots: Using Machine Learning to Forge Gene Regulatory Networks from Large Biological Datasets. At the Intersection of GRNs: Where System Biology Meets Machine Learning

Monga, Isha; Randhawa, Vinay; Dhanda, Sandeep Kumar

doi:10.1007/978-981-16-5993-5_6

Cited by 1 publication

(1 citation statement)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Plants are well-suited experimental systems to study the mechanistic basis of developmental dynamics, given that they are more amenable to in vivo manipulation than, for example, animals. Constructing the Arabidopsis gene regulatory network is currently topical research [31][32][33]. Figure 10 shows that the convergence effect of the MCMC iteration number of 50,000 under the PCCs-ED-DBN model is approximately the same as the convergence effect of the MCMC iteration number of 200,000 under the HMM-DBN model.…”

Section: Gene Regulatory Network In Arabidopsismentioning

confidence: 98%

Constructing a Gene Regulatory Network Based on a Nonhomogeneous Dynamic Bayesian Network

Zhang

2022

Electronics

View full text Add to dashboard Cite

Since the regulatory relationship between genes is usually non-stationary, the homogeneity assumption cannot be satisfied when modeling with dynamic Bayesian networks (DBNs). For this reason, the homogeneity assumption in dynamic Bayesian networks should be relaxed. Various methods of combining multiple changepoint processes and DBNs have been proposed to relax the homogeneity assumption. When using a non-homogeneous dynamic Bayesian network to model a gene regulatory network, it is inevitable to infer the changepoints of the gene data. Based on this analysis, this paper first proposes a data-based birth move (ED-birth move). The ED-birth move makes full use of the potential information of data to infer the changepoints. The greater the Euclidean distance of the mean of the data in the two components, the more likely this data point will be selected as a new changepoint by the ED-birth move. In brief, the selection of the changepoint is proportional to the Euclidean distance of the mean on both sides of the data. Furthermore, an improved Markov chain Monte Carlo (MCMC) method is proposed, and the improved MCMC introduces the Pearson correlation coefficient (PCCs) to sample the parent node-set. The larger the absolute value of the Pearson correlation coefficient between two data points, the easier it is to be sampled. Compared with other classical models on Saccharomyces cerevisiae data, synthetic data, RAF pathway data, and Arabidopsis data, the PCCs-ED-DBN proposed in this paper improves the accuracy of gene network reconstruction and further improves the convergence and stability of the modeling process.

show abstract

Section: Gene Regulatory Network In Arabidopsismentioning

confidence: 98%

Constructing a Gene Regulatory Network Based on a Nonhomogeneous Dynamic Bayesian Network

Zhang

2022

Electronics

View full text Add to dashboard Cite

show abstract

Connecting the Dots: Using Machine Learning to Forge Gene Regulatory Networks from Large Biological Datasets. At the Intersection of GRNs: Where System Biology Meets Machine Learning

Cited by 1 publication

References 75 publications

Constructing a Gene Regulatory Network Based on a Nonhomogeneous Dynamic Bayesian Network

Constructing a Gene Regulatory Network Based on a Nonhomogeneous Dynamic Bayesian Network

Contact Info

Product

Resources

About