bnlearn

require(GCModeller); #' Bayesian network learning and the in silico gene perturbation toolkit imports "bnlearn" from "biosystem";

Bayesian network learning and the in silico gene perturbation toolkit

This R# package module provides the toolkit for learn the gene regulatory bayesian network from the gene expression data, and then run the in silico gene perturbation experiment based on the learned network model:

prior_network and as.prior_net: create the prior knowledge regulatory network(TF -> target gene) which is used as the whitelist of the network structure learning;

bnlearn: learn the network structure(MMHC algorithm with the whitelist prior) and the network parameters(Gaussian bayesian network MLE);

knockouts, overexpress and knockdown: run the in silico gene perturbation experiment on the learned network model;

make_exports: export the perturbation experiment result as a set of the csv table files;

save_model: save the learned bayesian network model as the tsv table files.

.NET clr type export
struct_learn_params: StructureLearningParams	结构学习参数
knowledges: KeyValuePair`2
modular_network: ModularNetworkPipeline	基于 WGCNA 模块划分的贝叶斯子网络训练 + 全局虚拟扰动流水线
modular_bayesian: BlockBayesianNetwork
bnlearn: BNLearnWorkflow	BNLearn 工作流 —— 基因表达调控网络建模与虚拟干扰分析

.NET clr function exports
bnlearn	learn the gene regulatory bayesian network from the gene expression data
read_module_assignment	read WGCNA module color assignment result table
wildtype_baseline	set wildtype baseline
modular_intervene
export_modular_response
as.prior_net	build prior network object based on a given vector of the knowledge network edges data
prior_network	create prior knowledge netwoek edges from the given vector data
knockouts	run the in silico gene knockout experiment on the given network model
overexpress	run the in silico gene overexpression experiment on the given network model
knockdown	run the in silico gene knockdown experiment on the given network model
make_exports	export the virtual permutation result as csv table files
save_model	save bnlearn model

[Document Index]