Machine Learning Based Computational Gene Selection Models: A Survey, Performance Evaluation, Open Issues, and Future Research Directions

Abstract

Gene Expression is the process of determining the physical characteristics of living beings by generating the necessary proteins. Gene Expression takes place in two steps, translation and transcription. It is the flow of information from DNA to RNA with enzymes’ help, and the end product is proteins and other biochemical molecules. Many technologies can capture Gene Expression from the DNA or RNA. One such technique is Microarray DNA. Other than being expensive, the main issue with Microarray DNA is that it generates high-dimensional data with minimal sample size. The issue in handling such a heavyweight dataset is that the learning model will be over-fitted. This problem should be addressed by reducing the dimension of the data source to a considerable amount. In recent years, Machine Learning has gained popularity in the field of genomic studies. In the literature, many Machine Learning-based Gene Selection approaches have been discussed, which were proposed to improve dimensionality reduction precision. This paper does an extensive review of the various works done on Machine Learning-based gene selection in recent years, along with its performance analysis. The study categorizes various feature selection algorithms under Supervised, Unsupervised, and Semi-supervised learning. The works done in recent years to reduce the features for diagnosing tumors are discussed in detail. Furthermore, the performance of several discussed methods in the literature is analyzed. This study also lists out and briefly discusses the open issues in handling the high-dimension and less sample size data.

Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning

“…RBMs are energy-based generative models with two layers, visible and hidden. Both the layers have nodes connected to each other ( Mahendran et al, 2020 ; Sureshkumar et al, 2020 ). The major components in RBMs are bias, weight, and activation function ( Le Roux and Bengio, 2008 ; Sekaran and Sudha, 2020 ).…”

“…Artificial Intelligent models have been widely deployed in genetics research ( Mahendran et al, 2020 ). Deep learning approaches remove certain data pre-processing, which is usually deployed in machine learning ( Srinivasan et al, 2017 ; Agarwal et al, 2018 ; Chakriswaran et al, 2019 ; Khan et al, 2021a ; Khan et al, 2021b ; Khan et al, 2021c ) ( Sanchez-Riera et al, 2018 ; Srinivasan et al, 2020 ; Afza et al, 2021 ; Ashwini et al, 2021 ; Attique Khan et al, 2021 ; Khan et al, 2021d ; Mamdiwar et al, 2021 ; Srinivasan et al, 2021 ).…”

Mutational Slime Mould Algorithm for Gene Selection

“…At the same time, lasso, elastic net, and other sparse regression methods were introduced for cancer classification and gene selection. Mahendran et al [ 52 ] conducted an extensive review of recent work on machine learning-based selection and its performance analysis, classified various feature selection algorithms under supervised, unsupervised and semi-supervised learning, and discussed the problems in dealing with high and low sample data. Tan et al [ 53 ] proposed an integrated machine learning approach to analyze multiple gene expression profiles of cervical cancer to find the genomes associated with it, with the expectation that it could help in diagnosis and prognosis.…”

A novel biomarker selection method combining graph neural network and gene relationships applied to microarray data

“…Feature selection is different from feature extraction, which obtains a set of representation information of low-dimensional space from high-dimensional space. Feature extraction can not explain the meaning of the representation of low-dimensional space and can not be well connected with downstream tasks [ 2 ]. Traditional feature selection tasks can be divided into filter, wrapper, and embedded methods.…”