Preface

Deep learning is the subset of machine learning based on artificial neural networks with representative learning using vast amounts of data. Machine learning is a subcomponent of artificial intelligence, which includes sophisticated algorithms that enable machines to mimic human intelligence to perform human tasks automatically. Both deep learning and machine learning help automatically detect meaningful patterns from data without explicit programming. Machine learning and deep learning have completely changed the way that we live these days. We rely on these so much that it’s hard to imagine a day without using any of these in some way or another, whether it is via the spam filtering of emails, product recommendations, or speech recognition. Both machine learning and specifically deep learning have been adopted by the scientific community in areas such as biology, genomics, bioinformatics, and computational biology. High-throughput technologies (HTS) such as next-generation sequencing (NGS) have made a significant contribution to genomics to study complex biological phenomena at a single-base-pair resolution on an unprecedented scale, facilitating an era of big data genomics. To get meaningful and novel biological insights from this big data, most of the algorithms are currently based on machine learning and, lately, deep learning methodologies to provide higher levels of accuracy in specific tasks related to genomics than state-of-the-art rule-based algorithms. Given the growing trend in the perception and application of machine learning and deep learning in genomics, research professionals, scientists, and managers require a good understanding of this exciting field to equip them with the necessary tools, technologies, and general guidelines to assist them in the selection of machine learning and deep learning methods for handling genomics data and accelerating data-driven decision-making in industries related to life sciences and biotechnology.

Throughout this book, we will learn how to apply deep learning approaches to solve real-world problems in genomics, interpret biological insights from deep learning models built from genomic datasets, and finally, operationalize deep learning models using open source tools to enable predictions for end users.