Computational Techniques and Tools for Omics Data Analysis: State-of-the-Art, Challenges, and Future Directions

Abstract

The heterogeneous and high-dimensional nature of omics data presents various challenges in gaining insights while analysis. In the era of big data, omics data is available as genome, proteome, transcriptome, and metabolome. Apart from the single omics data type, integrative omics known as multi-omics, and omics imaging data known as radiomics approaching to big data are being used for predictive analysis. The various computational approaches such as data mining, machine learning, deep learning, statistical methods, metaheuristic techniques have gained attention to process, normalize, integrate, analyse omics data. This paper presents the critical review of state-of-the-art techniques for omics, multi-omics, radiomics data analysis themed at disease prediction, disease recurrence, survival analysis, and biomarker discovery. The paper investigates, compares and categorizes various existing tools and technologies based on common characteristics for integration and analysis of omics data. In addition, the significant research challenges and directions are discussed for futuristic omics research. This survey would guide researchers to understand the use of computationally intelligent approaches for efficient omics data analysis.