Big Data Analytics in Bioinformatics: A Machine Learning Perspective

Abstract

Bioinformatics research is characterized by voluminous and incremental datasets and complex data analytics methods. The machine learning methods used in bioinformatics are iterative and parallel. These methods can be scaled to handle big data using the distributed and parallel computing technologies.Usually big data tools perform computation in batch-mode and are not optimized for iterative processing and high data dependency among operations. In the recent years, parallel, incremental, and multi-view machine learning algorithms have been proposed. Similarly, graph-based architectures and in-memory big data tools have been developed to minimize I/O cost and optimize iterative processing.However, there lack standard big data architectures and tools for many important bioinformatics problems, such as fast construction of co-expression and regulatory networks and salient module identification, detection of complexes over growing protein-protein interaction data, fast analysis of massive DNA, RNA, and protein sequence data, and fast querying on incremental and heterogeneous disease networks. This paper addresses the issues and challenges posed by several big data problems in bioinformatics, and gives an overview of the state of the art and the future research opportunities.

Comparing Worldwide, National, and Independent Notifications about Adverse Drug Reactions Due to COVID-19 Vaccines

“…Such data, commonly referred to as big data, contain valuable information about users' activities, interests, and behaviors, making it inherently suitable for an extensive range of applications [1]. For example, in bioinformatics applications [2], big data analytics provides appropriate techniques for storing, organizing, understanding, and interpreting the exponential amount of biological data that aims at solving problems in medicine and biology (e.g., fast analysis of massive DNA, RNA, and protein sequence data, fast querying on incremental and heterogeneous disease networks, and detection of complexes over growing protein-protein interaction data [3]).…”

Revisiting Large Scale Distributed Machine Learning

“…The potential of machine learning to healthcare application has been recognized from some time [35,57] and also the benefit of multi-agent systems [44], but in recent years the diversity of sources and the amount of available information, more than 420 million radiological images are generated in US alone [7], have created the need to adopt distributed machine learning techniques [34,56]. Furthermore, with the rise of health-tracking apps for mobile phones, user activity and sensor data are becoming widely available, but the data is mostly used to generate simple statistics and visual attractive activity history plots.…”