PLRC Genomics & Systems Biology Core directors Jianhua Luo MD, PhD, and Silvia Liu, PhD along with assistant director Yanping Yu, MD, PhD and Pathology Chairman George Michalopoulos, MD, PhD published an article in the American Journal of Pathology entitled,
“Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi- institutional Analysis“
Yu YP, Liu S, Ren BG, Nelson J, Jarrard D, Brooks JD, Michalopoulos G, Tseng G, Luo JH. Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi-Institutional Analysis. Am J Pathol. 2023 Jan 18:S0002-9440(23)00029-9. doi: 10.1016/j.ajpath.2022.12.013. Epub ahead of print. PMID: 36681188.
The study was funded partly by NIH National Cancer Institute grant 1R56CA229262-01, US Department of Defense grant W81XWH-16-1-0541, and NIH National Institute of Diabetes and Digestive and Kidney Diseases grant P30-DK120531-01
Prostate cancer remains one of the most fatal malignancies in men in the United States. Predicting the course of prostate cancer is challenging given that only a fraction of prostate cancer patients experience cancer recurrence after radical prostatectomy or radiation therapy. This study examined the expressions of 14 fusion genes in 607 prostate cancer samples from the University of Pittsburgh, Stanford University, and the University of Wisconsin–Madison. The profiling of 14 fusion genes was integrated with Gleason score of the primary prostate cancer and serum prostate-specific antigen level to develop machine-learning models to predict the recurrence of prostate cancer after radical prostatectomy. Machine-learning algorithms were developed by analysis of the data from the University of Pittsburgh cohort as a training set using the leave-one-out cross-validation method. These algorithms were then applied to the data set from the combined Stanford/Wisconsin cohort (testing set). The results showed that the addition of fusion gene profiling consistently improved the prediction accuracy rate of prostate cancer recurrence by Gleason score, serum prostate-specific antigen level, or a combination of both. These improvements occurred in both the training and testing cohorts and were corroborated by multiple models.
Prostate cancer remains a leading cause of cancer-related death in men in the United States. In 2021, 34,500 US men died from prostate cancer, while 268,490 new cases were diagnosed.1 Most prostate cancers develop slowly. Surgical treatments such as radical prostatectomy are effective in curing cancer. However, patients present with distal metastasis or recurrence after surgical resection.
Some analyses of data from the Surveillance, Epidemiology, and End Results database, maintained by the National Cancer Institute, have shown that patients having prostate cancer with distal metastasis had a high risk for prostate cancer–related death.2,3 Thus, patients at a high risk for prostate cancer recurrence at the time of diagnosis may benefit from early radiotherapy or anti-androgen or other adjunctive chemotherapy and thereby have a reduced risk for mortality.
Currently, the Gleason score of the primary prostate cancer at the time of diagnosis is the main criterion used for predicting the outcomes of patients with prostate cancer. A high Gleason score (eg, 8 to 10) has been associated with an increased risk for prostate cancer recurrence after radical prostatectomy, while a Gleason score of 6 has been associated with a low risk for recurrence.4 The contemporary initial management of patients with a Gleason score of 6 is observation (active surveillance and watchful waiting). Using a combination of Gleason score, prostate-specific antigen (PSA) level, age, and other clinical factors, several nomograms have been developed to gauge the risk for prostate cancer recurrence. These tools have been used with variable success in the predicting clinical outcomes in patients with prostate cancer.5, 6, 7 However, these tools provide little insight into the mechanisms of the disease.
Numerous mutations,8 gene fusions,9, 10, 11, 12 chromosome alterations,13,14 and epigenetic abnormalities15, 16, 17, 18 have been discovered in patients with prostate cancer. In particular, gene fusion events appear widespread and frequent in patients with prostate cancer. Even though some fusion genes such as TMPRSS2-ETS/ERG have been extensively studied, the relationship between gene fusion events and clinical outcomes in patients with prostate cancer remains unclear. In previous studies, 14 fusion genes were detected in prostate cancer samples, with various frequencies ranging from 6% to 80%.10,11,19, 20, 21 Many of these fusion transcripts were shed into the bloodstream and were readily detectable in the blood or serum samples from patients.20,22 Among these fusion genes, MAN2A1-FER, PTEN-NOLC1, and SLC45A2-AMACR induce spontaneous liver cancer in a short period of time when coupled with somatic Pten knockout in mice.10,19,21Yet their potential in predicting the course of prostate cancer is not known. This study determined whether the presence of these fusion genes in prostate cancer samples can be used for predicting the recurrence of prostate cancer.
