Skip to main content
Fig. 4 | Stem Cell Research & Therapy

Fig. 4

From: Plasma proteomics-based biomarkers for predicting response to mesenchymal stem cell therapy in severe COVID-19

Fig. 4

Selection of 10 proteins using LASSO binary logistic regression model between the responders and non-responders from 13 DEPs. A LASSO coefficient profiles of the 13 proteins. Vertical line was drawn at the value selected using fivefold cross-validation, where optimal λ resulted in 10 nonzero coefficients. B Tuning parameter (λ) selection in the LASSO model used fivefold cross-validation via minimum partial likelihood deviance. Abbreviations: LASSO, least absolute shrinkage and selection operator

Back to article page