Deep Learning for Biology: Harness AI to Solve Real-World Biology Problems

by Charles Ravarani, Natasha Latysheva

Overview

Bridge the gap between biology and cutting-edge machine learning techniques with this essential guide. Train and interpret deep learning models and answer fundamental biological questions. Whether your background is in biology, machine learning, or software engineering, this book empowers you with the practical skills needed for your deep learning journey.

Through step-by-step recipes, authors Natasha Latysheva and Charles Ravarani teach you to train models for tasks like understanding gene regulatory logic, uncovering insights about protein families, and exploring subcellular localization. Each chapter provides self-contained mini-projects that serve as templates for approaching complex biological problems.

By the end of this book, you'll be able to:

• Approach biological problems with a deep learning perspective
• Train and interpret deep learning models to explore complex biological data
• Leverage Python code and iPython notebooks to extend your projects
• Transform your insights into actionable solutions in medicine, genomics, and biotechnology

Product Details

ISBN-13:	9781098168032
Publisher:	O'Reilly Media, Incorporated
Publication date:	08/26/2025
Pages:	300
Product dimensions:	7.00(w) x 9.19(h) x 0.89(d)

About the Author

Charles Ravarani is a biologist and software engineer who is currently Chief Technology Officer at biotx.ai, a computational drug discovery startup. He completed his PhD and post-doc in computational biology at the University of Cambridge, and in addition to his outstanding academic contributions, Charles is a software development veteran, has consulted various organizations, and has a passion for teaching programming and machine learning topics.

Natasha Latysheva is a biologist and machine learning practitioner who is currently a Senior Research Engineer at Google DeepMind, specializing in deep learning for genomics. With a PhD in computational biology from the University of Cambridge and experience across several machine learning domains, her expertise is in bridging the gap between biology and machine learning. She is passionate about machine learning education and making complex technical topics accessible and exciting.