We introduce NetREX_CF -- Regulatory Network Reconstruction using EXpression and Collaborative Filtering -- a GRN reconstruction approach that brings together a modern machine learning strategy (Collaborative Filtering) to address the incompleteness of the prior knowledge and a biologically justified model of gene expression (sparse Network Component Analysis based model).
In this GitHub page, we provide the python source codes of our NetREX_CF.
NetREX_CF needs two inputs: expression data and prior data. One example of NetREX_CF's input can be found in Notebook/NetREXCF_S2Cell.ipynb
NetREX_CF outputs a genes by TFs matrix. The row and column names are the same as the prior data. The larger the element in the matrix, the more confident we have for the corresponing TF-gene regulation.