The Efficacy of Various Machine Learning Models for Multi-class Classification of RNA-Seq Expression Data

Abstract

Late diagnosis and high costs are key factors that negatively impact the care of cancer patients worldwide. Although the availability of biological markers for the diagnosis of cancer type is increasing, costs and reliability of tests currently present a barrier to the adoption of their routine use. There is a pressing need for accurate methods that enable early diagnosis and cover a broad range of cancers. The use of machine learning and RNA-seq expression analysis has shown promise in the classification of cancer type. However, research is inconclusive about which type of machine learning models are optimal. The suitability of five algorithms were assessed for the classification of 17 different cancer types. Each algorithm was fine-tuned and trained on the full array of 18,015 genes per sample, for 4,221 samples (75 % of the dataset). They were then tested with 1,408 samples (25 % of the dataset) for which cancer types were withheld to determine the accuracy of prediction. The results show that ensemble algorithms achieve 100% accuracy in the classification of 14 out of 17 types of cancer. The clustering and classification models, while faster than the ensembles, performed poorly due to the high level of noise in the dataset. When the features were reduced to a list of 20 genes, the ensemble algorithms maintained an accuracy above 95% as opposed to the clustering and classification models.

A comparative assessment on gene expression classification methods of RNA-seq data generated using next-generation sequencing (NGS)

“…In general, in all simulated datasets, the classification performance of RF outperforms the CART, LR and SVM. It is in line with the previous studies [31,32,33]. RF algorithm had been previously shown to perform outstanding in several bioinformatics tasks [34].…”

“…In addition, RF can handle the overdispersion relatively better than the other algorithms. RF is one of ensemble methods which aggregates multiple machine learning models with the aim of decreasing both bias and variance [32,33]. Hence, the result from an ensemble method such as RF will be better than any of individual machine learning model.…”

Analyzing RNA-Seq Gene Expression Data for Cancer Classification Through ML Approach

“…First, to categorise cancer, Sterling Ramroach et al used various machine learning techniques [18]. A dataset for several cancer kinds was downloaded for their study from the online data portal COSMIC.…”

“…First, Cascade forests are built using decision treebased random forests trained to find relevant characteristics in raw data. Next, this result was placed against state-of-the-art classifiers like SVM, KNN, LR, RF, and the original gcforest [18]. The authors claimed that their suggested approach produced more precise results.…”

Design of a Novel Ensemble Model of Classification Technique for Gene-Expression Data of Lung Cancer with Modified Genetic Algorithm

“…The state of a cell communicated by the layout of RNA will thusly serve to be of great help to check whether a cell might be a normal or a variation one [15]. The use of machine learning in cancer diagnosis is becoming more feasible as algorithms become less prone to error and noise, and as the volume of training data increases [16]. The proposed SVM and KNN methods are tested and the accuracy of both the approaches are recorded as 71.52% and 94.74%, respectively.…”