Loss of CHGA protein as a potential biomarker for colon cancer diagnosis: a study on biomarker discovery by machine learning and confirmation by immunohistochemistry in colorectal cancer tissue microarrays

Abstract

AbstractBackgroundIncidences of colon and rectal cancers have been parallelly and constantly increased, however, the mortality has been slightly decreased due to early diagnosis and better therapies during the last decades. Precise early diagnosis for colorectal cancer has been a great challenge in order to win chances for the best choices of cancer therapies.Patients and methodsWe have started with searching protein biomarkers based on our colorectal biomarker database (CBD), finding differential expressed genes (GEGs) and non-DEGs from RNA sequencing (RNA-seq) data, and further predicted new biomarkers on protein-protein interaction (PPI) networks by machine learning (ML) methods. The best-selected biomarker was further verified by receiver operating characteristic (ROC) test from microarray and RNA-seq data, biological network and functional analysis, and immunohistochemistry in the tissue arrays from 198 specimens.ResultsThere were twelve proteins (MYO5A, CHGA, MAPK13, VDAC1, CCNA2, YWHAZ, CDK5, GNB3, CAMK2G, MAPK10, SDC2, and ADCY5) which were predicted by ML as colon cancer candidate diagnosis biomarkers. These predicted biomarkers showed close relationships with reported biomarkers on PPI network and shared some pathways. ROC test showed CHGA protein with the best diagnostic accuracy (AUC=0.9 in microarray data and 0.995 in RNA-seq data) among these candidate protein biomarkers. Furthermore, CHGA performed well in the immunohistochemistry test.ConclusionsProtein expression of CHGA in the normal colorectal mucosa was lost in the colorectal cancers and the lose of CHGA protein might be a potential candidate biomarker for colon or even colorectal cancer diagnosis.TopicCHGA expression, colon cancer diagnosisKey MessageThe results of this study suggest that lose of CHGA expression from the normal colon and adjacent mucosa to colon cancer may be used as a valuable biomarker for early diagnosis of colon adenocarcinoma