Optimizing molecular signatures for predicting prostate cancer recurrence.
Ontology highlight
ABSTRACT:
SUBMITTER: Sun Y
PROVIDER: S-EPMC3425355 | biostudies-literature | 2009 Jul
REPOSITORIES: biostudies-literature
Publications
Optimizing molecular signatures for predicting prostate cancer recurrence.
The Prostate 20090701 10
<h4>Background</h4>The derivation of molecular signatures indicative of disease status and predictive of subsequent behavior could facilitate the optimal choice of treatment for prostate cancer patients.<h4>Methods</h4>In this study, we conducted a computational analysis of gene expression profile data obtained from 79 cases, 39 of which were classified as having disease recurrence, to investigate whether advanced computational algorithms can derive more accurate prognostic signatures for prosta ...[more]
Similar Datasets
Project description:The derivation of molecular signatures indicative of disease status and predictive of subsequent behavior could facilitate the optimal choice of treatment for prostate cancer patients. In this study, we conducted a computational analysis of gene expression profile data obtained from 79 cases, 39 of which were classified as having disease recurrence, to investigate whether advanced computational algorithms can derive more accurate prognostic signatures for prostate cancer. At the 90% sensitivity level, a newly derived prognostic genetic signature achieved 85% specificity. This is the first reported genetic signature to outperform a clinically used postoperative nomogram. Furthermore, a hybrid prognostic signature derived by combination of the nomogram and gene expression data significantly outperformed both genetic and clinical signatures, and achieved a specificity of 95%. Our study demonstrates the feasibility of utilizing gene expression information for highly accurate prostate cancer prognosis beyond the current clinical systems, and shows that more advanced computational modeling of tissue-derived microarray data is warranted before clinical application of molecular signatures is considered. mRNA profiling was performed using 79 cases of prostate cancer of known disease recurrence status
2010-11-05 | E-GEOD-25136 | biostudies-arrayexpress
Project description:The derivation of molecular signatures indicative of disease status and predictive of subsequent behavior could facilitate the optimal choice of treatment for prostate cancer patients. In this study, we conducted a computational analysis of gene expression profile data obtained from 79 cases, 39 of which were classified as having disease recurrence, to investigate whether advanced computational algorithms can derive more accurate prognostic signatures for prostate cancer. At the 90% sensitivity level, a newly derived prognostic genetic signature achieved 85% specificity. This is the first reported genetic signature to outperform a clinically used postoperative nomogram. Furthermore, a hybrid prognostic signature derived by combination of the nomogram and gene expression data significantly outperformed both genetic and clinical signatures, and achieved a specificity of 95%. Our study demonstrates the feasibility of utilizing gene expression information for highly accurate prostate cancer prognosis beyond the current clinical systems, and shows that more advanced computational modeling of tissue-derived microarray data is warranted before clinical application of molecular signatures is considered.
2010-11-05 | GSE25136 | GEO
Project description: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 < 2e-16), and advanced tumor stages (OR 1.33, P = 4.37e-13). SigMuc1NW remains an independent risk factor of BCR (HR 2.44, 95% CI 1.53-3.87, P = 1.62e-4) after adjusting for age at diagnosis, Gleason score, surgical margin, and tumor stage. In an independent PC (MSKCC) cohort (n = 140), these 15 genes were altered in PC vs normal tissue, metastatic PCs vs primary PCs, and recurrent PCs vs nonrecurrent PCs. Importantly, a 10-gene subsignature SigMuc1NW1 predicts BCR in MSKCC (P = 3.11e-15) and TCGA (P = 3.13e-12); SigMuc1NW1 discriminates BCR at 18.4 m with tAUC as 82.5%. Collectively, our analyses support SigMuc1NW as a novel and robust signature in predicting BCR of PC.
| S-EPMC6120243 | biostudies-literature
Project description:Background: Prostate cancer (PCa) is the second most frequent cause of cancer-related death in men worldwide. It is a heterogeneous disease at molecular and clinical levels which makes its prognosis and treatment outcome hard to predict. The epithelial-to-mesenchymal transition (EMT) marks a key step in the invasion and malignant progression of PCa. We sought to assess the co-expression of epithelial cytokeratin 8 (CK8) and mesenchymal vimentin (Vim) in locally-advanced PCa as indicators of EMT and consequently predictors of the progression status of the disease. Methods: Co-expression of CK8 and Vim was evaluated by immunofluorescence (IF) on paraffin-embedded tissue sections of 122 patients with PCa who underwent radical prostatectomies between 1998 and 2016 at the American University of Beirut Medical Center (AUBMC). EMT score was calculated accordingly and then correlated with the patients' clinicopathological parameters and PSA failure. Results: The co-expression of CK8/Vim (EMT score), was associated with increasing Gleason group. A highly significant linear association was detected wherein higher Gleason group was associated with higher mean EMT score. In addition, the median estimated biochemical recurrence-free survival for patients with < 25% EMT score was almost double that of patients with more than 25%. The validity of this score for prediction of prognosis was further demonstrated using cox regression model. Our data also confirmed that the EMT score can predict PSA failure irrespective of Gleason group, pathological stage, or surgical margins. Conclusion: This study suggests that assessment of molecular markers of EMT, particularly CK8 and Vim, in radical prostatectomy specimens, in addition to conventional clinicopathological prognostic parameters, can aid in the development of a novel system for predicting the prognosis of locally-advanced PCa.
| S-EPMC6421270 | biostudies-literature
Project description:Background The first sign of metastatic prostate cancer after radical prostatectomy is rising PSA levels in the blood, termed biochemical recurrence. The prediction of recurrence relies mainly on the morphological assessment of prostate cancer using the Gleason grading system. However, in this system, within-grade morphological patterns and subtle histopathological features are currently omitted, leaving a significant amount of prognostic potential unexplored. Methods To discover additional prognostic information using artificial intelligence, we trained a deep learning system to predict biochemical recurrence from tissue in H&E-stained microarray cores directly. We developed a morphological biomarker using convolutional neural networks leveraging a nested case-control study of 685 patients and validated on an independent cohort of 204 patients. We use concept-based explainability methods to interpret the learned tissue patterns. Results The biomarker provides a strong correlation with biochemical recurrence in two sets (n = 182 and n = 204) from separate institutions. Concept-based explanations provided tissue patterns interpretable by pathologists. Conclusions These results show that the model finds predictive power in the tissue beyond the morphological ISUP grading. Plain language summary To determine the prognosis of patients with prostate cancer, several clinical factors are taken into account. One of these is the cancer grade, assigned by a pathologist based on the cancer’s appearance under a microscope. The grade ranges from 1 to 5, where 5 is the most aggressive tumour type. This study explored whether deep learning—a technique in which computer software learns patterns from multiple examples—can learn to predict the risk of patients’ cancers recurring from microscopic images of the tumours. We show, on two clinical datasets from different institutions, that such a system can help to better predict prognosis, beyond the information provided by grade alone. In the future, this type of method could help clinicians to predict the prognosis of individual prostate cancer patients. Pinckaers et al. develop a deep learning system to predict biochemical recurrence in prostate cancer patients treated with radical prostatectomy. The authors’ morphological biomarker provides predictive power beyond traditional Gleason grading, based on analysis of two clinical datasets from different institutions.
| S-EPMC9177591 | biostudies-literature
Project description:BackgroundProstate cancer (PCa) is one of the leading causes of cancer death in men. About 30% of PCa will develop a biochemical recurrence (BCR) following initial treatment, which significantly contributes to prostate cancer-related deaths. In clinical practice, accurate prediction of PCa recurrence is crucial for making informed treatment decisions. However, the development of reliable models and biomarkers for predicting PCa recurrence remains a challenge. In this study, the aim is to establish an effective and reliable tool for predicting the recurrence of PCa.MethodsWe systematically screened and analyzed potential datasets to predict PCa recurrence. Through quality control analysis, low-quality datasets were removed. Using meta-analysis, differential expression analysis, and feature selection, we identified key genes associated with recurrence. We also evaluated 22 previously published signatures for PCa recurrence prediction. To assess prediction performance, we employed nine machine learning algorithms. We compared the predictive capabilities of models constructed using clinical variables, expression data, and their combinations. Subsequently, we implemented these machine learning models into a user-friendly web server freely accessible to all researchers.ResultsBased on transcriptomic data derived from eight multicenter studies consisting of 733 PCa patients, we screened 23 highly influential genes for predicting prostate cancer recurrence. These genes were used to construct the Prostate Cancer Recurrence Prediction Signature (PCRPS). By comparing with 22 published signatures and four important clinicopathological features, the PCRPS exhibited a robust and significantly improved predictive capability. Among the tested algorithms, Random Forest demonstrated the highest AUC value of 0.72 in predicting PCa recurrence in the testing dataset. To facilitate access and usage of these machine learning models by all researchers and clinicians, we also developed an online web server (https://urology1926.shinyapps.io/PCRPS/) where the PCRPS model can be freely utilized. The tool can also be used to (1) predict the PCa recurrence by clinical information or expression data with high accuracy. (2) provide the possibility of PCa recurrence by nine machine learning algorithms. Furthermore, using the PCRPS scores, we predicted the sensitivity of 22 drugs from GDSC2 and 95 drugs from CTRP2 to the samples. These predictions provide valuable insights into potential drug sensitivities related to the PCRPS score groups.ConclusionOverall, our study provides an attractive tool to further guide the clinical management and individualized treatment for PCa.
| S-EPMC11016622 | biostudies-literature
Project description:Prostate cancer (PCa) is a common malignant type of urogenital tract tumor with poor prognosis. Despite therapeutic advances, the recurrence and mortality rates of PCa have continued to increase with poor prognoses. Pyroptosis, also known as inflammatory cell necrosis, is a recently identified type of programmed cell death that can regulate the invasiveness, differentiation, proliferation, and metastasis of tumor cells; thus, it has a profound effect on the prognosis of patients with tumors. However, the relationship between pyroptosis and PCa remains unclear. We first identified 25 pyroptosis-related genes (PRGs) that were differentially expressed between PCa tissues and matched normal tissues in The Cancer Genome Atlas (TCGA) cohort. Based on the expression levels of 25 PRGs, PCa patients were clearly divided into two clusters and 17 PRGs were found to be significantly different between the two clusters, suggesting probable roles for these genes in the progression and recurrence of PCa. Therefore, the GSE40272 dataset with recurrence follow-up information was used to verify their value. Univariate analysis suggested that 5/17 genes were associated with recurrence, the number of genes did not decrease after least absolute shrinkage and selection operator (LASSO) regression analysis, and 5 PRGs constituted the risk score formula. Low-risk and high-risk subgroups identified using the recurrence model showed different disease-free survival (DFS) times (P<0.001) and the risk score of five PRGs was a factor of independence for recurrence in patients with PCa. In addition, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses suggested that these pathways, and comprising PRGs might be closely related to carcinogenesis and invasion of tumors, tumor microenvironment, and immune response. In conclusion, the expression signatures of PRGs play an important role in predicting PCa recurrence.
| S-EPMC9163412 | biostudies-literature
Project description:Currently, seven molecular subtypes of prostate cancer (PCa) are known, the most common of which being the subtype characterized by the presence of the TMPRSS2-ERG fusion transcript. While there is a considerable amount of work devoted to the influence of this transcript on the prognosis of the disease, data on its role in the progression and prognosis of PCa remain controversial. The present study is devoted to the analysis of the association between the TMPRSS2-ERG transcript and the biochemical recurrence of PCa. The study included two cohorts: the RNA-Seq sample of Russian patients with PCa (n = 72) and the TCGA-PRAD data (n = 203). The results of the analysis of the association between the TMPRSS2-ERG transcript and biochemical recurrence were contradictory. The differential expression analysis (biochemical recurrence cases versus biochemical recurrence-free) and the gene set enrichment analysis revealed a list of genes involved in major cellular pathways. The GNL3, QSOX2, SSPO, and SYS1 genes were selected as predictors of the potential prognostic model (AUC = 1.000 for a cohort of Russian patients with PCa and AUC = 0.779 for a TCGA-PRAD cohort).
| S-EPMC8234735 | biostudies-literature
Project description:Prostate cancer (PCa) is a high morbidity malignancy in males, and biochemical recurrence (BCR) may appear after the surgery. Our study is designed to build up a risk score model using circular RNA sequencing data for PCa. The dataset is from the GEO database, using a cohort of 144 patients in Canada. We removed the low abundance circRNAs (FPKM < 1) and obtained 546 circRNAs for the next step. BCR-related circRNAs were selected by Logistic regression using the "survival" and "survminer" R package. Least absolute shrinkage and selector operation (LASSO) regression with 10-fold cross-validation and penalty was used to construct a risk score model by "glmnet" R software package. In total, eight circRNAs (including circ_30029, circ_117300, circ_176436, circ_112897, circ_112897, circ_178252, circ_115617, circ_14736, and circ_17720) were involved in our risk score model. Further, we employed differentially expressed mRNAs between high and low risk score groups. The following Gene Ontology (GO) analysis were visualized by Omicshare Online tools. As per the GO analysis results, tumor immune microenvironment related pathways are significantly enriched. "CIBERSORT" and "ESTIMATE" R package were used to detect tumor-infiltrating immune cells and compare the level of microenvironment scores between high and low risk score groups. What's more, we verified two of eight circRNA's (circ_14736 and circ_17720) circular characteristics and tested their biological function with qPCR and CCK8 in vitro. circ_14736 and circ_17720 were detected in exosomes of PCa patients' plasma. This is the first bioinformatics study to establish a prognosis model for prostate cancer using circRNA. These circRNAs were associated with CD8+ T cell activities and may serve as a circRNA-based liquid biopsy panel for disease prognosis.
| S-EPMC7758402 | biostudies-literature
Project description:ObjectivesTo develop a model to predict biochemical recurrence (BCR) after radical prostatectomy (RP), using artificial intelligence (AI) techniques.Patients and methodsThis study collected data from 7,128 patients with prostate cancer (PCa) who received RP at 3 tertiary hospitals. After preprocessing, we used the data of 6,755 cases to generate the BCR prediction model. There were 16 input variables with BCR as the outcome variable. We used a random forest to develop the model. Several sampling techniques were used to address class imbalances.ResultsWe achieved good performance using a random forest with synthetic minority oversampling technique (SMOTE) using Tomek links, edited nearest neighbors (ENN), and random oversampling: accuracy = 96.59%, recall = 95.49%, precision = 97.66%, F1 score = 96.59%, and ROC AUC = 98.83%.ConclusionWe developed a BCR prediction model for RP. The Dr. Answer AI project, which was developed based on our BCR prediction model, helps physicians and patients to make treatment decisions in the clinical follow-up process as a clinical decision support system.
| S-EPMC8243093 | biostudies-literature