Abstract
Pancreatic ductal adenocarcinoma (PDAC) is generally incurable due to the late diagnosis and absence of markers that are concordant with expression in several sample sources (i.e., tissue, blood, plasma) and platforms (i.e., Microarray, sequencing). We optimized meta-analysis of 19 PDAC (tissue and blood) transcriptome studies from multiple platforms. The key biomarkers for PDAC diagnosis with secretory potential were identified and validated in different cohorts. Machine learning approach i.e., support vector machine supported by leave-one-out cross-validation was used to build and test the classifier. We identified a 9-gene panel (IFI27, ITGB5, CTSD, EFNA4, GGH, PLBD1, HTATIP2, IL1R2, CTSA) that achieved ∼0.92 average sensitivity and ∼0.90 average specificity in distinguishing PDAC from healthy samples in five training sets using cross-validation. These markers were also validated in proteomics and single-cell transcriptomics studies suggesting their prognostic role in the diagnosis of PDAC. Our 9-gene classifier can not only clearly discriminate between better and poor survivors but can also precisely discriminate PDAC from chronic pancreatitis (AUC = 0.95), early stages of progression [Stage I and II (AUC = 0.82), IPMA and IPMN (AUC = 1), and IPMC (AUC = 0.81)]. The 9-gene marker outperformed the previously known markers in blood studies particularly (AUC = 0.84). The discrimination of PDAC from early precursor lesions in non-malignant tissue (AUC > 0.81) and peripheral blood (AUC > 0.80) may assist in an early diagnosis of PDAC in blood samples and thus will also facilitate risk stratification upon validation in clinical trials.
Highlights
Pancreatic ductal adenocarcinoma (PDAC) is the most common type of pancreatic cancer (PC), which is one of the fatal cancers in the world with 5-year survival rate of
To develop a gene based minimally invasive biomarker for differentiating PDAC from normal/pancreatitis, we identified 19 microarray and RNA sequencing studies containing PDAC and normal samples
We applied a data mining approach to a large number of publicly available transcriptome datasets derived from pancreatic cancer and healthy blood and tissues, followed by class prediction analysis using machine learning and validation of the classifier in the independent datasets to discover candidate PDAC biomarkers (Harsha et al, 2009; Ranganathan et al, 2009)
Summary
Pancreatic ductal adenocarcinoma (PDAC) is the most common type of pancreatic cancer (PC), which is one of the fatal cancers in the world with 5-year survival rate of 50% cases. Our group discovered a novel five-genes-based tissue biomarker for the diagnosis of PDAC using innovative meta-analysis approach on multiple transcriptome studies This biomarker panel could distinguish PDAC from healthy controls with 94% sensitivity and 89% specificity and was able to distinguish PDAC from CP, other cancers, and non-tumor from PDAC precursors at tissue level (Bhasin et al, 2016). Provided the erratic nature of PC, the major unmet requirement is to have reliable blood-based biomarkers for early diagnosis of PDAC
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
