In this final chapter, we are going to apply all that we have learned throughout this book so far from an application perspective. DeepChem is a perfect example that combines the power of GPUs, Python, and deep learning toward solving computational problems in science.
To understand its usage as simply as possible, we will start with a brief introduction to basic scientific concepts related to the example that will follow. You will learn about molecular machine learning by revisiting some elementary terminologies in science, such as atoms, molecules, proteins, and enzymes.
A hands-on guide to install and configure DeepChem as an open-ended and closed environment will be included before testing the live example for medicinal drug prediction through deep learning. As a final thought, readers will be encouraged to develop their own deep learning frameworks such as DeepChem.
This chapter is divided into the following sections to facilitate the learning process:
- Knowledge of the practical applicability of GPU-enabled deep learning with Python
- Installing and configuring DeepChem through Colab, Anaconda, or Docker
- Validating an existing DeepChem Conda environment on PyCharm for developing deep learning models
- Testing an AI-based scientific library
- Getting started with the development of a new machine learning framework such as DeepChem