Deep Learning Methodologies for Genomic Data Prediction: Review

Abstract

The last few years have seen an advancement in genomic research in bioinformatics. With the introduction of high-throughput sequencing techniques, researchers now can analyze and produce a large amount of genomic datasets and this has aided the classification of genomic studies as a "big data" discipline. There is a need to develop a robust and powerful algorithm and deep learning methodologies can provide better performance accuracy than other computational methodologies. In this review, we captured the most frequently used deep learning architectures for the genomic domain. We outline the limitations of deep learning methodologies when dealing with genomic data and we conclude that advancement in deep learning methodologies will help rejuvenate genomic research and build a better architecture that will promote a genomic task.

Heuristic Analysis of Genomic Sequence Processing Models for High Efficiency Prediction: A Statistical Perspective

“…With the massive generation of data, the era known as ‘big’ data, deep learning (DL) approaches have appeared as a discipline of machine learning (ML) that are considered to be more efficient and effective when we deal with a big amount of data. The DL methodologies have helped provide high computation power to resolve complex research hypotheses in genomics [ 8 ]. Genomic data sequences are capable of representing a wide variety of information about the underlying species.…”