High-Throughput Omics and Statistical Learning Integration for the Discovery and Validation of Novel Diagnostic Signatures in Colorectal Cancer

Abstract

The advancement of bioinformatics and machine learning has facilitated the discovery and validation of omics-based biomarkers. This study employed a novel approach combining multi-platform transcriptomics and cutting-edge algorithms to introduce novel signatures for accurate diagnosis of colorectal cancer (CRC). Different random forests (RF)-based feature selection methods including the area under the curve (AUC)-RF, Boruta, and Vita were used and the diagnostic performance of the proposed biosignatures was benchmarked using RF, logistic regression, naïve Bayes, and k-nearest neighbors models. All models showed satisfactory performance in which RF appeared to be the best. For instance, regarding the RF model, the following were observed: mean accuracy 0.998 (standard deviation (SD) < 0.003), mean specificity 0.999 (SD < 0.003), and mean sensitivity 0.998 (SD < 0.004). Moreover, proposed biomarker signatures were highly associated with multifaceted hallmarks in cancer. Some biomarkers were found to be enriched in epithelial cell signaling in Helicobacter pylori infection and inflammatory processes. The overexpression of TGFBI and S100A2 was associated with poor disease-free survival while the down-regulation of NR5A2, SLC4A4, and CD177 was linked to worse overall survival of the patients. In conclusion, novel transcriptome signatures to improve the diagnostic accuracy in CRC are introduced for further validations in various clinical settings.

Exploring the Predictors of Rapid Eye Movement Sleep Behavior Disorder for Parkinson’s Disease Patients Using Classifier Ensemble

“…It is a representative ensemble-based machine learning technique that improves prediction accuracy and stability by using multiple decision trees. Even though it is known that the prediction performance of RF is higher than that of decision tree [ 20 ], prediction studies using biomarkers [ 21 ] and those using images [ 22 ] have been mainly conducted for evaluating diseases so far. Moreover, only a few RF-based studies utilize sociodemographic factors, questionnaire data such as health habits, or neuropsychological examination data [ 23 ].…”

Review:Helicobacter pyloriand extragastric diseases

“…But et al, in an interesting study conducted on 4063 incident cases of CRC and 4063 matched controls, reported a significant association between VacA positivity and increased risk of CRC (OR 1.11: CI 95%: 1.01‐1.22), which was stronger in Afro‐Americans (OR 1.45: CI 95%: 1.08‐1.95) . Finally, Long et al, in a sophisticated study employing a novel approach combining multi‐platform transcriptomics and cutting‐edge algorithms in CRC, reported that H pylori may increase the expression of specific signaling biomarkers in epithelial cells …”

Food Intake REstriction for Health OUtcome Support and Education (FIREHOUSE) Protocol: A Randomized Clinical Trial

“…MetSyn afflicts more than 30 percent of adults (>47 million Americans) and is associated with impaired lung function [ 2 , 3 ]. Our group has focused on defining the development of World Trade Center-particulate matter (WTC-PM) associated lung disease in the context of MetSyn in the well-phenotyped Fire Department of New York (FDNY) Cohort [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 ].…”

“…Although one major contributor to poor lung mechanics is from mechanical load-induced stress secondary to abdominal obesity, our prior work shows near equivalent contribution from dyslipidemia in those with WTC-LI [ 2 , 10 , 11 ]. Inflammatory profiles from serum samples collected within three months of 9/11 showed that dyslipidemia predicted WTC-LI even after adjusting for body mass index (BMI), and was in fact a stronger predictor than obesity [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 15 , 20 , 21 ]. In light of these findings, we focused our work on the inflammatory effects of lipids in the development of particulate matter (PM)-induced lung injury [ 22 ]…”

“…In the context of our prior findings, as well as the previously discussed literature linking nutritional modification to health benefits, we have chosen to explore the therapeutic potential of ameliorating MetSyn phenotype in our WTC-exposed cohort [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 21 ]. In the current study, we are implementing a technology-supported, low calorie Mediterranean (LoCalMed) dietary intervention to improve metabolic risk factors in subjects with WTC-LI.…”