A machine learning framework develops a DNA replication stress model for predicting clinical outcomes and therapeutic vulnerability in primary prostate cancer.

Recent studies have identified DNA replication stress as an important feature of advanced prostate cancer (PCa). The identification of biomarkers for DNA replication stress could therefore facilitate risk stratification and help inform treatment options for PCa. Here, we designed a robust machine learning-based framework to comprehensively explore the impact of DNA replication stress on prognosis and treatment in 5 PCa bulk transcriptomic cohorts with a total of 905 patients. Bootstrap resampling-based univariate Cox regression and Boruta algorithm were applied to select a subset of DNA replication stress genes that were more clinically relevant. Next, we benchmarked 7 survival-related machine-learning algorithms for PCa recurrence using nested cross-validation. Multi-omic and drug sensitivity data were also utilized to characterize PCa with various DNA replication stress. We found that the hyperparameter-tuned eXtreme Gradient Boosting model outperformed other tuned models and was therefore used to establish a robust replication stress signature (RSS). RSS demonstrated superior performance over most clinical features and other PCa signatures in predicting PCa recurrence across cohorts. Lower RSS was characterized by enriched metabolism pathways, high androgen activity, and a favorable prognosis. In contrast, higher RSS was significantly associated with TP53, RB1, and PTEN deletion, exhibited increased proliferation and DNA replication stress, and was more immune-suppressive with a higher chance of immunotherapy response. In silico screening identified 13 potential targets (e.g. TOP2A, CDK9, and RRM2) from 2249 druggable targets, and 2 therapeutic agents (irinotecan and topotecan) for RSS-high patients. Additionally, RSS-high patients were more responsive to taxane-based chemotherapy and Poly (ADP-ribose) polymerase inhibitors, whereas RSS-low patients were more sensitive to androgen deprivation therapy. In conclusion, a robust machine-learning framework was used to reveal the great potential of RSS for personalized risk stratification and therapeutic implications in PCa.

Associations between nephrolithiasis and diabetes mellitus, hypertension and gallstones: A meta-analysis of cohort studies.

AIM: To review and clarify the strengths and directions of associations between nephrolithiasis and hypertension (HTN), diabetes mellitus (DM) and gallstones (GS) given the inconsistent results reported in cohort studies. METHODS: Relevant literature was searched in PubMed and EMBASE from inception to July 2019, for cohort studies that examined the relationships between kidney stones and these three diseases among adults. Pooled relative risks (RRs) were calculated by maximally adjusted risk estimates using a random effect model. Subgroup analysis, meta-regression and sensitivity analysis were conducted whenever appropriate. RESULTS: Of 3537 papers, 21 articles with each including 1 to 3 cohorts were identified. In this meta-analysis, nephrolithiasis was reciprocally linked to HTN, DM and GS. Kidney stones were significantly associated with 31%, 33% and 46% higher risks of incident HTN, DM and GS whereas GS was associated with a significantly higher risk of nephrolithiasis (RR: 1.49; 95% CI, 1.28-1.73), followed by HTN (RR: 1.30; 95% CI, 1.11-1.52) and DM (RR: 1.18; 95% CI, 1.07-1.29). Also, females with DM (RR: 1.29; 95% CI, 1.08-1.55) were more likely to develop kidney stones than diabetic male patients (RR: 0.91; 95% CI, 0.75-1.10). CONCLUSION: Although additional studies are needed to confirm these findings and elucidate the mechanisms, this study revealed possible bidirectional associations between nephrolithiasis and HTN, diabetes and GS, which reinforced the notion of nephrolithiasis as a systemic disease that requires comprehensive investigations.

Dietary and lifestyle factors for primary prevention of nephrolithiasis: a systematic review and meta-analysis.

BACKGROUND: Dietary and lifestyle factors may play an important role in the increasing prevalence of nephrolithiasis. We aimed to review and quantify the associations between lifestyle factors and incident nephrolithiasis and suggest lifestyle changes for the primary prevention of nephrolithiasis. METHODS: PubMed, EMBASE, and Cochrane Library were searched up to May 2019, for observational studies and randomized controlled trials (RCTs) that assessed modifiable lifestyle factors and risk of nephrolithiasis in adults. Pooled relative risks (RRs) and 95% confidence intervals (CIs) were computed using a random effects model. The I2 statistic was employed to evaluate heterogeneity. Subgroup analysis, sensitivity analysis and meta-regression were also conducted whenever possible. RESULTS: Fifty relevant articles with 1,322,133 participants and 21,030 cases in total were identified. Prominent risk factors for incident stones were body mass index (1.39,1.27-1.52), dietary sodium (1.38, 1.21-1.56), fructose, meat, animal protein, and soda. In contrast, protective factors included fluid intake (0.55, 0.51-0.60), a Dietary Approaches to Stop Hypertension (DASH) style diet (0.69, 0.64-0.75), alcohol (0.69, 0.56-0.85), water, coffee, tea, vegetables, fruits, dietary fiber, dietary calcium (0.83, 0.76-0.90), and potassium. Vitamin D (1.22, 1.01-1.49) and calcium (1.16, 1.00-1.35) supplementation alone increased the risk of stones in meta-analyses of observational studies, but not in RCTs, where the cosupplementation conferred significant risk. CONCLUSIONS: Several modifiable factors, notably fluid intake, dietary patterns, and obesity, were significantly associated with nephrolithiasis. Long-term RCTs are required to investigate the cost-effectiveness of dietary patterns for stone prevention. The independent and combined effects of vitamin D and calcium supplementation on nephrolithiasis need further elucidation.