Research Paper Volume 16, Issue 7 pp 6455—6477
Machine learning for identifying tumor stemness genes and developing prognostic model in gastric cancer
Figure 4. Construction of prognostic model. (A) LASSO coefficient profiles of the genes obtained from the SVM machine learning algorithm. (B) Partial likelihood deviance was plotted versus log (Lambda). The vertical dotted line indicates the lambda value with the minimum error and the largest lambda value. (C) The distribution of survival status in TCGA cohorts based on TSRS. (D) The distribution of survival status in GEO cohorts based on TSRS. (E) The patient samples from TCGA were divided into high and low TSRS groups and the OS of the groups were analyzed. (F) OS analysis of high and low TSRS groups from the GEO samples. Abbreviation: LASSO: least absolute shrinkage and selection operator.