Deep Learning for Genomics

Deep learning for genomics introduces the concepts, methodologies, and applications with aim of building predictive models for solving real-world problems in genomics.

Key Features

• Learn how to apply deep learning algorithms to solve real-world problems in genomics
• Extract biological insights from deep learning models built from genomic datasets
• Train, tune, and deploy deep learning models for enabling predictions

Book Description

Recently, deep learning has shown impressive promise in many disciplines including genomics. However, there is a lack of skilled deep learning workforce to apply methodologies in genomics. For researchers to stand out from the rest of the crowd and solve real-world problems in genomics, they must have the necessary skill set.

The book introduces the fundamental concepts and highlights the power of deep learning approaches in handling genomics big data. It provides a hands-on approach and associated methodologies to researchers, data scientists, and any other research professionals working in genomics. The book will take a whirlwind tour by first introducing the readers to conventional genomic analysis, then transitioning into state-of-the-art machine learning-based genomic applications, and finally diving deep into deep learning approaches for genomics. The book covers all of the important deep learning algorithms that are commonly used by the research community and go into the details of what they are, how they work, and practical applications of those algorithms to genomics. Additionally, the book has a complete section on operationalizing deep learning models that will provide practical hands-on tutorials for them to build, tune, interpret, deploy and monitor the deep learning models from genomics big datasets.

Finally, the book ends with challenges, best practices, and pitfalls of deep learning for genomics.

What you will learn

• Introduction and techniques to genomic data analysis
• Basic introduction to state-of-the-art machine learning applications for genomics
• Deep learning concepts and methodologies for genomic applications
• Understanding supervised DL algorithms (FNN, CNN, RNN) for genomics applications
• Unsupervised deep learning with Autoencoders
• Improving deep learning models using generative models
• Build, tune, and evaluate deep learning predictive models from genomics datasets
• Visualize and interpret machine learning and deep learning models
• Understand challenges, pitfalls, and best practices for leveraging deep learning for genomics

Who This Book Is For

Data Scientists in genomics/Biotechnology/Life Sciences disciplines who want to leverage machine learning and deep learning technologies in genomic applications to extract insights from big data sets. This book can be beneficial to managers and leaders looking to adopt machine learning and deep learning methodologies for analyzing high throughput sequencing genomics big data to identify patterns, come up with predictions and thereby accelerate data-driven decision making

Table of Contents

1. Introducing Machine Learning for Genomics
2. Genomics Data Analysis
3. Machine Learning Methods for Genomic Applications
4. Deep Learning for Genomics
5. Introducing Convolutional Neural Networks for Genomics
6. Recurrent Neural Networks in Genomics
7. Unsupervised Deep Learning with Autoencoders
8. GANs for Improving Models in Genomics
9. Building and Tuning Deep Learning models
10. Model interpretability methods
11. Model Deployment and Monitoring
12. Challenges, Pitfalls, and Best Practices for Deep Learning in Genomics