Machine Learning-Based Identification of Colon Cancer Candidate Diagnostics Genes

Abstract

Background: Colorectal cancer (CRC) is the third leading cause of cancer-related death and the fourth most commonly diagnosed cancer worldwide. Due to a lack of diagnostic biomarkers and understanding of the underlying molecular mechanisms, CRC’s mortality rate continues to grow. CRC occurrence and progression are dynamic processes. The expression levels of specific molecules vary at various stages of CRC, rendering its early detection and diagnosis challenging and the need for identifying accurate and meaningful CRC biomarkers more pressing. The advances in high-throughput sequencing technologies have been used to explore novel gene expression, targeted treatments, and colon cancer pathogenesis. Such approaches are routinely being applied and result in large datasets whose analysis is increasingly becoming dependent on machine learning (ML) algorithms that have been demonstrated to be computationally efficient platforms for the identification of variables across such high-dimensional datasets. Methods: We developed a novel ML-based experimental design to study CRC gene associations. Six different machine learning methods were employed as classifiers to identify genes that can be used as diagnostics for CRC using gene expression and clinical datasets. The accuracy, sensitivity, specificity, F1 score, and area under receiver operating characteristic (AUROC) curve were derived to explore the differentially expressed genes (DEGs) for CRC diagnosis. Gene ontology enrichment analyses of these DEGs were performed and predicted gene signatures were linked with miRNAs. Results: We evaluated six machine learning classification methods (Adaboost, ExtraTrees, logistic regression, naïve Bayes classifier, random forest, and XGBoost) across different combinations of training and test datasets over GEO datasets. The accuracy and the AUROC of each combination of training and test data with different algorithms were used as comparison metrics. Random forest (RF) models consistently performed better than other models. In total, 34 genes were identified and used for pathway and gene set enrichment analysis. Further mapping of the 34 genes with miRNA identified interesting miRNA hubs genes. Conclusions: We identified 34 genes with high accuracy that can be used as a diagnostics panel for CRC.

The Clinical Value of Blood miR-654-5p, miR-126, miR-10b, and miR-144 in the Diagnosis of Colorectal Cancer

“…At present, there are also some studies on constructing CRC diagnostic classifiers based on machine learning algorithms. Koppad et al [ 21 ] screened CRC diagnosis-related genes by the random forest algorithm, which has the advantage of avoiding data overfitting and reducing the computational load of the model. We aimed to filter biomarkers that could diagnose cancer.…”

“…Lian et al [ 20 ] trained medulloblastoma stemness index based on a machine learning method of one-class logistic regression to obtain gene expression-based stemness index and methylation-based stemness index and further identified their corresponding potential drugs, which provides new ideas for the survival of medulloblastoma patients or targeting stem cells. Koppad et al [ 21 ] screened diagnostic candidate genes for CRC based on six methods of machine learning classification including Adaboost, ExtraTrees, logistic regression, Naive Bayes classifier, random forest, and XGBoost. Thus, there is potential for wider application of novel bioinformatics methods to identify novel diagnostic biomarkers based on public databases.…”

Development of a 32-gene signature using machine learning for accurate prediction of inflammatory bowel disease

“…This algorithm shows a balance between prediction performance and explainability, which indicates the ability of machine learning algorithms to explain or justify the results in terms that are understandable by humans (Al' Aref et al 2020, Chen andGuestrin 2016). XGBoost is a common choice for dealing with the classification problem of multiple diseases, such as Parkinson's disease (Gao et al 2018), colon cancer (Koppad et al 2022), and breast cancer (Thalor et al 2022). Due to its simplicity, interpretability, and ability to handle imbalanced datasets, we chose the XGBoost algorithm to construct our IBD classifier (Shorthouse et al 2018).…”

Polarimetric imaging for cervical pre-cancer screening aided by machine learning: ex vivo studies

“…40 An example of this is quantifying biomarkers for disease states in tissues. [41][42][43] In the aforementioned diagnostics context, each of the masked pixels taken from the 4 × 4 MM is treated as an instance in our dataset. Each instance has 16 features, with each feature corresponding to one of the 16 channels of the MM.…”