Machine Learning in Biotechnology and Life Sciences

Book Preface

We have seen major changes in the field of machine learning in the last few years that have impacted our daily lives and the way business decisions are made. If there is one thing that the biotechnology and life sciences industries have in abundance, it is their never-ending sources of data. As we move toward more data-driven models, the intersection of life sciences and machine learning has seen unprecedented growth, uncovering vast quantities of information and hidden patterns giving companies major competitive advantages.
Over the course of this book, we will touch on some of the most important elements of machine learning from both a supervised and unsupervised perspective. We will not only learn to develop and train robust models, but also deploy them in the cloud using AWS and GCP, allowing us to make them immediately available for end users.
Who this book is for
This book specifically caters to scientific professionals in both academia and industry looking to transcend to the data science domain. Individual contributors and managers alike who are already established within the pharmaceutical, life sciences, and biotechnology sectors will find this book not only useful, but immensely applicable
to current-day projects. Although an introduction to Python and machine learning
is provided, a basic understanding of Python programming and a beginner-level background in data science conjunction is recommended to get the most out of this book.
What this book covers
Chapter 1, Introducing Machine Learning for Biotechnology, provides a brief introduction to the field of biotechnology and some of the areas in which machine learning can be applied, in addition to some of the technology this book will use.
Chapter 2, Introducing Python and the Command Line, comprises a summary of some
of the must-know techniques and commands in Bash and the Python programming language, in addition to some of the most common Python libraries.

Chapter 3, Getting Started with SQL and Relational Databases, is where you will gain knowledge of the SQL querying language and learn how to create a remote database using MySQL and AWS RDS.
Chapter 4, Visualizing Data with Python, introduces you to some of the most common methods for visualizing and representing data using the Python programming language.
Chapter 5, Understanding Machine Learning, comprises some of the most important elements of standard machine learning pipelines, introducing you to supervised and unsupervised methods, as well as saving models for future use.
Chapter 6, Unsupervised Machine Learning, is where you will learn about unsupervised models and dive into clustering and dimensionality reduction methods with tutorials relating to breast cancer.
Chapter 7, Supervised Machine Learning, is where you will learn about supervised learning models and dive into classification and regression methods.
Chapter 8, Understanding Deep Learning, provides an overview of the deep learning space, where we will explore the elements of a deep learning model, as well as two tutorials relating to protein classification using Keras and anomaly detection using AWS.
Chapter 9, Natural Language Processing, teaches you some of the most common NLP options as we explore popular libraries and tools, in addition to two tutorials relating to clustering as well as semantic searching using transformers.
Chapter 10, Exploring Time Series Analysis, explores data using a time-based approach in which we break down the components of a time series dataset and develop two forecasting models using Prophet and LSTMs.
Chapter 11, Deploying Models with Flask Applications, provides an introduction to one of the most popular frameworks for deploying models and applications to end users.
Chapter 12, Deploying Applications to the Cloud, provides an introduction to two of the most popular cloud computing platforms, in addition to three tutorials allowing users to deploy their work to AWS LightSail, GCP AppEngine, and GitHub.