The LASSO Cox regression model analysis was performed in R software (version 3.3.1) using the ‘glmnet’ package, and the DTGs with non‐zero coefficients were selected for further analysis. Weighted gene coexpression network analysis (WGCNA) was performed using the WGCNA module in R software. The appropriate soft threshold power β was 4, and the minimal module size was 15 in our study. Receiver operating curve (ROC) analysis and the area under the ROC (AUC) were used to confirm the predictive ability of the parameters for DFS or for pCR. The overlapping DTGs selected from the LASSO analysis and WGCNA were chosen as targeted genes. The DTG‐score (DTG‐S) was simply plus or minus the normalized selected DTGs according to their predictive ability for DFS. The DTG‐S classification was the DTG‐S high‐risk group (DTG‐SH) and the DTG‐S low‐risk group (DTG‐SL), separated by the Youden index of the ROC curve.

Note: The content above has been extracted from a research article, so it may not display correctly.



Q&A
Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.



We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.