Machine-learning-based Analysis Identifies miRNA Expression Profile for Diagnosis and Prediction of Colorectal Cancer: A Preliminary Study

Abstract

Background: The stage of colorectal cancer (CRC) at the day of diagnosis has the greatest influence on survival rate. Thus, for CRC, which is mainly identified as advanced disease, non-invasive, molecular blood or stool tests could boost the diagnosis and lower mortality. Evaluation of miRNA expression levels in serum of patients diagnosed with CRC is a potential tool in early screening. Screening can be supported by machine learning (ML) as a tool for developing a cancer risk predictive model based on genetic data. Materials and Methods: miRNA was isolated from the serum of 8 patients diagnosed with CRC and 10 patients from a control group matched for age and sex. The expression of 179 miRNAs was determined using a serum/plasma panel (Exiqon). Determinations were conducted using real-time PCR technique on an Applied Biosystems QuantStudio3 device in 96-well plates. A predictive model was developed through the Azure Machine Learning platform. Results: A wide panel of 29 up-regulated miRNAs in CRC were identified and divided into two subgroups: 1) miRNAs with significantly higher serum level in cancer patients vs. controls (24 miRNAs) and 2) miRNAs detected only in cancer patients and not in controls ( 5 miRNAs). Re-analysis of published miRNA profiles of CRC tumours or CRC exosomes revealed that only 2 out of 29 miRNAs were up-regulated in all datasets including ours (miR-34a and miR-25-3p). Conclusion: Our research suggests the potential role of overexpressed miRNAs as diagnostic or prognostic biomarkers among CRC patients. Such clustering of miRNAs may be a potential direction for discovering new diagnostic panels of cancer (including CRC), especially using ML. The low correspondence between deregulation of miRNAs in serum and tumour tissue revealed in our study confirms previously published reports.Colorectal cancer (CRC) is one of the most common cancers and the third leading cause of cancer-related deaths, especially in developed countries (1). Morbidity from CRC is strongly related to certain environmental factors, such as low-fibre diet, addictions (alcohol consumption and smoking) and lack of physical activity (2, 3). Because of the high frequency and impact of CRC on general public health, the studies on its genetic background include searching early genetic markers of this cancer at the chromosomal, molecular, and epigenetic levels (4, 5). Although some noninvasive techniques for CRC screening exist, colonoscopy still remains the gold standard (6). As some patients avoid or refuse this procedure, establishing a new genetic screening test from blood would be greatly beneficial for CRC prevention and early diagnosis.The stage of CRC at the day of diagnosis plays the largest role in survival rates. Notably, when CRC is diagnosed at a localized stage, the 5-year survival rate ranges between 89% 503 # These Authors contributed equally to this study.

CXCL10Expression in Human Colorectal Cancer Tissue and its Correlation With Serum Levels of CXCL10

“…Hematological examinations have been reported as validated for the screening of CRC patients (23). Thus, we hypothesized that the serum level of CXCL10 reflects its expression in colorectal cancer tissues and tested this correlation.…”

Blood Biomarkers Panels for Screening of Colorectal Cancer and Adenoma on a Machine Learning-Assisted Detection Platform

“… 32 Pawelka D et al found that a two-class Bayes Point Machine based on miRNA expression profiles has the potential to diagnose and prognosis. 33 Wan et al predicted early CRC using 2 classification methods (LR and SVM) and secured good results. 34 A comparison with existing models accentuates our model's cost-effectiveness utilizing routinely accessible blood indicators, while maintaining remarkable sensitivity and accuracy.…”

Genomic and Transcriptomic Research in the Discovery and Application of Colorectal Cancer Circulating Markers

“…The EXIQON miRCURY LNA-based PCR platform (Qiagen, Hilden, Germany) was used to analyze the expression of 179 hsa-miRs in the serum samples of eight CRC subjects and ten controls [156]. Machine learning was used to develop a model for cancer risk prediction.…”

“…A panel of 29 hsa-miRs upregulated in CRC was obtained; these miRNAs were regularly observable in the examined CRC samples. Repeated analysis of the publicly available hsa-miR profiles of CRC tumors or CRC exosomes demonstrated that two of the selected 29 hsa-miRs were upregulated in all datasets, hsa-miR-34a and hsa-miR-25-3p included [156].…”