Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks
Abstract Reconstruction of Gene Regulatory Networks (GRNs) of gene expression data with Probabilistic Network Models (PNMs) is an open problem. Gene expression datasets consist of thousand of genes with relatively small sample sizes (i.e. are large-p-small-n). Moreover, dependencies of various order...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-21957-z |
| _version_ | 1828309968804118528 |
|---|---|
| author | Catharina E. Graafland José M. Gutiérrez |
| author_facet | Catharina E. Graafland José M. Gutiérrez |
| author_sort | Catharina E. Graafland |
| collection | DOAJ |
| description | Abstract Reconstruction of Gene Regulatory Networks (GRNs) of gene expression data with Probabilistic Network Models (PNMs) is an open problem. Gene expression datasets consist of thousand of genes with relatively small sample sizes (i.e. are large-p-small-n). Moreover, dependencies of various orders coexist in the datasets. On the one hand transcription factor encoding genes act like hubs and regulate target genes, on the other hand target genes show local dependencies. In the field of Undirected Network Models (UNMs)—a subclass of PNMs—the Glasso algorithm has been proposed to deal with high dimensional microarray datasets forcing sparsity. To overcome the problem of the complex structure of interactions, modifications of the default Glasso algorithm have been developed that integrate the expected dependency structure in the UNMs beforehand. In this work we advocate the use of a simple score-based Hill Climbing algorithm (HC) that learns Gaussian Bayesian networks leaning on directed acyclic graphs. We compare HC with Glasso and variants in the UNM framework based on their capability to reconstruct GRNs from microarray data from the benchmarking synthetic dataset from the DREAM5 challenge and from real-world data from the Escherichia coli genome. We conclude that dependencies in complex data are learned best by the HC algorithm, presenting them most accurately and efficiently, simultaneously modelling strong local and weaker but significant global connections coexisting in the gene expression dataset. The HC algorithm adapts intrinsically to the complex dependency structure of the dataset, without forcing a specific structure in advance. |
| first_indexed | 2024-04-13T15:36:51Z |
| format | Article |
| id | doaj.art-942083521442428b818cceb28e88b060 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-13T15:36:51Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-942083521442428b818cceb28e88b0602022-12-22T02:41:15ZengNature PortfolioScientific Reports2045-23222022-11-0112111810.1038/s41598-022-21957-zLearning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networksCatharina E. Graafland0José M. Gutiérrez1Instituto de Física de Cantabria, CSIC-Universidad de CantabriaInstituto de Física de Cantabria, CSIC-Universidad de CantabriaAbstract Reconstruction of Gene Regulatory Networks (GRNs) of gene expression data with Probabilistic Network Models (PNMs) is an open problem. Gene expression datasets consist of thousand of genes with relatively small sample sizes (i.e. are large-p-small-n). Moreover, dependencies of various orders coexist in the datasets. On the one hand transcription factor encoding genes act like hubs and regulate target genes, on the other hand target genes show local dependencies. In the field of Undirected Network Models (UNMs)—a subclass of PNMs—the Glasso algorithm has been proposed to deal with high dimensional microarray datasets forcing sparsity. To overcome the problem of the complex structure of interactions, modifications of the default Glasso algorithm have been developed that integrate the expected dependency structure in the UNMs beforehand. In this work we advocate the use of a simple score-based Hill Climbing algorithm (HC) that learns Gaussian Bayesian networks leaning on directed acyclic graphs. We compare HC with Glasso and variants in the UNM framework based on their capability to reconstruct GRNs from microarray data from the benchmarking synthetic dataset from the DREAM5 challenge and from real-world data from the Escherichia coli genome. We conclude that dependencies in complex data are learned best by the HC algorithm, presenting them most accurately and efficiently, simultaneously modelling strong local and weaker but significant global connections coexisting in the gene expression dataset. The HC algorithm adapts intrinsically to the complex dependency structure of the dataset, without forcing a specific structure in advance.https://doi.org/10.1038/s41598-022-21957-z |
| spellingShingle | Catharina E. Graafland José M. Gutiérrez Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks Scientific Reports |
| title | Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks |
| title_full | Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks |
| title_fullStr | Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks |
| title_full_unstemmed | Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks |
| title_short | Learning complex dependency structure of gene regulatory networks from high dimensional microarray data with Gaussian Bayesian networks |
| title_sort | learning complex dependency structure of gene regulatory networks from high dimensional microarray data with gaussian bayesian networks |
| url | https://doi.org/10.1038/s41598-022-21957-z |
| work_keys_str_mv | AT catharinaegraafland learningcomplexdependencystructureofgeneregulatorynetworksfromhighdimensionalmicroarraydatawithgaussianbayesiannetworks AT josemgutierrez learningcomplexdependencystructureofgeneregulatorynetworksfromhighdimensionalmicroarraydatawithgaussianbayesiannetworks |