In our final chapter, we discussed all the necessary concepts required for you to get started with molecular deep learning through DeepChem. We also saw multiple ways of installing and configuring DeepChem locally or on the cloud on a tensor core-based GPU. You learned the basic steps to set up your PyCharm environment. Finally, you read about a simple hands-on approach to get started with developing your own deep learning framework.
From now on, you can practically apply GPU-enabled deep learning with Python for helping society in several scientific ways. You can now learn, work, and develop your own models with DeepChem through Colab, Anaconda, or Docker, and also locally validate an existing DeepChem Conda environment on PyCharm to develop learning models. You now know how drug prediction works as a combination of graph convolutional neural networks and one-shot learning...
