From: Inference of gene regulatory subnetworks from time course gene expression data
Algorithm 1: The NCI algorithm | |
---|---|
Input: X; | |
Output: | matrix A and communities of the GRN; |
Step 0. | (Initiation) W : = 0 ∈ ℝn × n. Select μ > 0, γ τ > 0, λ1∈ (0, λ2). |
Step 1. | (N-step: identify possible N etworks) Solve (8) to find an approximate matrix A. |
Step 2. | (C-step: estimate C ommunity structure) Calculate weighted matrix W 1 by Eq. (13), then solve the proposed block PCA model (12) to calculate L*. |
Step 3. | (Update weight matrix) Update W by Eq. (9). If stop criteria are not satisfied, go to Step 1. |
Step 4. | (GRN identification) Identify the communities of the computed GRN by SSVD. |