Skip to main content
Fig. 5 | Journal of Translational Medicine

Fig. 5

From: Incorporating knowledge of disease-defining hub genes and regulatory network into a machine learning-based model for predicting treatment response in lupus nephritis after the first renal flare

Fig. 5

Searching for top-regulatory genes for determining the responders in sub-networks. A Binomial deviance plot with lambda as the tuning parameter for DDC-6 (left panel). The red dots are the values of binomial deviance. The gray lines represent the standard error (SE). The vertical dashed lines are the optimal values by the minimum criteria and 1-SE criteria. LASSO coefficient profile of the 33 selected genes in DDC-6 (right panel). B Horizontal dot plot demonstrates the coefficients of the 33 selected genes. Red triangle indicates DEGs with |logFC ≥ 1| between responders and non-responders after treatment for LN with the first RF in GSE200306. Green triangle indicates DEGs with |logFC < 1|. C Top 10 regulatory gene nodes selected by MNC, MCC, EPC, DMNC, and Degree. Color bar indicates the ranking among the ten selected genes

Back to article page

Journal of Translational Medicine

ISSN: 1479-5876

Contact us