A transcriptomics-based meta-analysis combined with machine learning approach identifies a secretory biomarker panel for diagnosis of pancreatic adenocarcinoma

medRxiv

Abstract

Abstract Pancreatic ductal adenocarcinoma (PDAC) is largely incurable due to late diagnosis and absence of markers that are concordant with expression in several sample sources (i.e. tissue, blood, plasma) and platform (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 specificity in discriminating PDAC from non-tumor samples in five training-sets on cross-validation. This classifier accurately discriminated PDAC from chronic-pancreatitis (AUC=0.95), early stages of progression (Stage I and II (AUC=0.82), IPMA and IPMN (AUC=1), 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 facilitate early blood-diagnosis and risk stratification upon validation in prospective clinical-trials. Furthermore, the validation of these markers in proteomics and single-cell transcriptomics studies suggest their prognostic role in the diagnosis of PDAC.

Authors 2

1. Indu Khatri Aachen Division of Immunohematology and Blood transfusion

   Harvard University · Leiden University Medical Center

   Affiliation as printed

   Division of IMBIO, Department of Medicine, Beth Israel Lahey Health, Harvard Medical School, Boston MA 02215

   Division of Immunohematology and Blood transfusion, Leiden University Medical Center, Leiden, The Netherlands, 2333ZA

   Division of IMBIO, Department of Medicine, Beth Israel Lahey Health, Harvard Medical School, Boston MA 0225

   Division of Immunohematology and Blood transfusion, Leiden University Medical Center, Leiden, The Netherlands, 2ZA

2. Manoj Bhasin corresponding

   Harvard University · Emory University · Children's Healthcare of Atlanta

   Affiliation as printed

   Department of Pediatrics and Biomedical Informatics, Children Healthcare of Atlanta, Emory School of Medicine, Atlanta, GA 30322

   Division of IMBIO, Department of Medicine, Beth Israel Lahey Health, Harvard Medical School, Boston MA 02215

   Department of Pediatrics and Biomedical Informatics, Children Healthcare of Atlanta, Emory School of Medicine, Atlanta, GA 303

   Division of IMBIO, Department of Medicine, Beth Israel Lahey Health, Harvard Medical School, Boston MA 0225