High throughput assessment of biomarkers in tissue microarrays using artificial intelligence: PTEN loss as a proof-of-principle in multi-center prostate cancer cohorts

Author(s):  
Stephanie A. Harmon ◽  
Palak G. Patel ◽  
Thomas H. Sanford ◽  
Isabelle Caven ◽  
Rachael Iseman ◽  
...  
2018 ◽  
Vol 36 (6_suppl) ◽  
pp. 15-15 ◽  
Author(s):  
Anis Hamid ◽  
Kathryn P. Gray ◽  
Ying Huang ◽  
Michaela Bowden ◽  
Massimo Loda ◽  
...  

15 Background: Loss of PTEN expression correlates with poorer clinical outcomes after definitive therapy for non-metastatic (M0) PrCa. While most studies have used biochemical-based end points, there is limited data regarding PTEN loss by IHC and risk of lethal disease after surgery. Methods: A retrospective cohort of patients who underwent radical prostatectomy (RP) was identified from the Dana-Farber Prostate Clinical Research Information Systems (CRIS) database. Formalin-fixed, paraffin-embedded RP specimens were used to construct tissue microarrays and F-IHC for PTEN was performed. Using multispectral imaging analysis, tumor-only PTEN expression was quantified. PTEN expression was analyzed continuously and dichotomously (low [ < lower quartile] vs other [≥lower quartile]). Kaplan-Meier method estimated the distribution of time from RP to metastatic disease and overall survival (OS). Cox model assessed association of PTEN status and the disease outcomes, with adjustment of age, Gleason score and pathological stage in multivariate analyses (MVA). Prognostic ability of PTEN was also explored using a logistic regression model. Results: The analysis cohort comprised 91 patients with either non-lethal (no metastatic or biochemical relapse) or lethal disease (metastasis post-RP). The median follow-up was 12.4 years. PTEN low was significantly associated with lethal disease as both a continuous (HR 1.82, 95% CI 1.35-2.44) and dichotomous (HR 2.94, 95% CI 1.52-5.56) variable. Significant association of PTEN-low expression and poorer OS was observed (cont: HR 2.22, 95% CI 1.54-3.23; low vs other: HR 4.00, 95% CI 1.89-8.33). MVA models yielded consistent results. A prognostic model assessing 10-year disease outcomes showed incremental prognostic improvement with PTEN status added to age/Gleason/stage (lethal disease: area under curve (AUC) 0.79 vs 0.84 [+PTEN status]; death: AUC 0.71 vs 0.76 [+PTEN status]). Conclusions: Low PTEN expression by F-IHC in primary prostate cancer is an independent prognostic biomarker of lethal disease and death after surgery. Quantitative F-IHC for PTEN is a viable diagnostic assay in this context.


2021 ◽  
Author(s):  
Janielle P. Maynard ◽  
Jiayun Lu ◽  
Igor Vidal ◽  
Jessica Hicks ◽  
Luke Mummert ◽  
...  

Prostate cancer (PCa) remains a leading cause of cancer-related deaths in American men and treatment options for metastatic PCa are limited. There is a critical need to identify new mechanisms that contribute to PCa progression, that distinguish benign from lethal disease, and that have potential for therapeutic targeting. P2X4 belongs to the P2 purinergic receptor family that is commonly upregulated in cancer and is associated with poorer outcomes. Herein, we report that the P2X4 purinergic receptor is overexpressed in PCa, associated with PCa metastasis, and a driver of tumor development in vivo. We observed P2X4 protein expression primarily in epithelial cells of the prostate, a subset of CD66+ neutrophils, and most CD68+ macrophages. Our analysis of tissue microarrays representing 491 PCa cases demonstrated significantly elevated P2X4 expression in cancer compared to benign tissue spots, in prostatic intraepithelial neoplasia, in cancer from White compared to Black men, and in PCa with ERG positivity or with PTEN loss. High P2X4 expression in benign tissues was likewise associated with the development of metastasis after radical prostatectomy. Treatment with P2X4-specific agonist CTP increased transwell migration and invasion of PC3, DU145, and CWR22Rv1 PCa cells. P2X4 antagonist 5-BDBD treatment resulted in a dose-dependent decrease in viability of PC3, DU145, LNCaP, CWR22Rv1, TRAMP-C2, Myc-CaP, BMPC1, and BMPC2 cells and decreased DU145 cell migration and invasion. Knockdown of P2X4 attenuated growth, migration, and invasion of PCa cells. Finally, knockdown of P2X4 in Myc-CaP cells resulted in significantly attenuated subcutaneous allograft growth in FVB/NJ mice. Collectively, these data strongly support a role for the P2X4 purinergic receptor in PCa aggressiveness and identifies P2X4 as a candidate for therapeutic targeting.


2007 ◽  
Vol 177 (4S) ◽  
pp. 52-53
Author(s):  
Stefano Ongarello ◽  
Eberhard Steiner ◽  
Regina Achleitner ◽  
Isabel Feuerstein ◽  
Birgit Stenzel ◽  
...  

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Eddie Luidy Imada ◽  
Diego Fernando Sanchez ◽  
Wikum Dinalankara ◽  
Thiago Vidotto ◽  
Ericka M. Ebot ◽  
...  

Abstract Background PTEN is the most frequently lost tumor suppressor in primary prostate cancer (PCa) and its loss is associated with aggressive disease. However, the transcriptional changes associated with PTEN loss in PCa have not been described in detail. In this study, we highlight the transcriptional changes associated with PTEN loss in PCa. Methods Using a meta-analysis approach, we leveraged two large PCa cohorts with experimentally validated PTEN and ERG status by Immunohistochemistry (IHC), to derive a transcriptomic signature of PTEN loss, while also accounting for potential confounders due to ERG rearrangements. This signature was expanded to lncRNAs using the TCGA quantifications from the FC-R2 expression atlas. Results The signatures indicate a strong activation of both innate and adaptive immune systems upon PTEN loss, as well as an expected activation of cell-cycle genes. Moreover, we made use of our recently developed FC-R2 expression atlas to expand this signature to include many non-coding RNAs recently annotated by the FANTOM consortium. Highlighting potential novel lncRNAs associated with PTEN loss and PCa progression. Conclusion We created a PCa specific signature of the transcriptional landscape of PTEN loss that comprises both the coding and an extensive non-coding counterpart, highlighting potential new players in PCa progression. We also show that contrary to what is observed in other cancers, PTEN loss in PCa leads to increased activation of the immune system. These findings can help the development of new biomarkers and help guide therapy choices.


Biomolecules ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 264
Author(s):  
Kaisa Liimatainen ◽  
Riku Huttunen ◽  
Leena Latonen ◽  
Pekka Ruusuvuori

Identifying localization of proteins and their specific subpopulations associated with certain cellular compartments is crucial for understanding protein function and interactions with other macromolecules. Fluorescence microscopy is a powerful method to assess protein localizations, with increasing demand of automated high throughput analysis methods to supplement the technical advancements in high throughput imaging. Here, we study the applicability of deep neural network-based artificial intelligence in classification of protein localization in 13 cellular subcompartments. We use deep learning-based on convolutional neural network and fully convolutional network with similar architectures for the classification task, aiming at achieving accurate classification, but importantly, also comparison of the networks. Our results show that both types of convolutional neural networks perform well in protein localization classification tasks for major cellular organelles. Yet, in this study, the fully convolutional network outperforms the convolutional neural network in classification of images with multiple simultaneous protein localizations. We find that the fully convolutional network, using output visualizing the identified localizations, is a very useful tool for systematic protein localization assessment.


2002 ◽  
Vol 161 (5) ◽  
pp. 1557-1565 ◽  
Author(s):  
Chih Long Liu ◽  
Wijan Prapong ◽  
Yasodha Natkunam ◽  
Ash Alizadeh ◽  
Kelli Montgomery ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document