Construction of a set of novel and robust gene expression signatures predicting prostate cancer recurrence

We report here numerous novel genes and multiple new signatures which robustly predict prostate cancer (PC) recurrence. We extracted 696 differentially expressed genes relative to a reported PC signature from the TCGA dataset (n = 492) and built a 15‐gene signature (SigMuc1NW) using Elastic‐net with 10‐fold cross‐validation through analyzing their expressions at 1.5 standard deviation/SD below and 2 SD above a population mean. SigMuc1NW predicts biochemical recurrence (BCR) following surgery with 56.4% sensitivity, 72.6% specificity, and 63.24 median months disease free (MMDF) (P = 1.12e‐12). The prediction accuracy is improved with the use of SigMuc1NW's cutpoint (P = 3e‐15) and is further enhanced (sensitivity 67%, specificity 75.7%, MMDF 45.2, P = 0) when all 15 genes were analyzed through their cutpoints instead of their SDs. These genes individually associate with BCR using either SD or cutpoint as the cutoff points. Eight of 15 genes are individual risk factors after adjusting for age at diagnosis, Gleason score, surgical margin, and tumor stage. Eleven of 15 genes are novel to PC. SigMuc1NW discriminates BCR with time‐dependent AUC (tAUC) values of 76.6% at 11.5 months (76.6%–11.5 m), 73.8%‐22.3 m, 78.5%‐32.1 m, and 76.4%–48.4 m. SigMuc1NW is correlated with adverse features of PC, high Gleason scores (odds ratio/OR 1.48, P