RDKit: Cheminformatics & Drug Discovery in Python
Learn RDKit via systematic introduction & real projects for drug design applications, machine learning modeling, etc.
RDKit: Cheminformatics & Drug Discovery in Python udemy course
Learn RDKit via systematic introduction & real projects for drug design applications, machine learning modeling, etc.
In this course, you will learn the RDKit toolkit in two ways: first by systematically exploring the toolkit’s common modules and functionalities, and second by working on meaningful real-life projects. The content is explained step by step with details in Jupyter Notebook, which is a user-friendly code editor.
In the Reading & Writing Molecules section, the process of reading different formats and writing them will be explained, in addition to important RDKit concepts such as molecular sanitization.
In the Molecules section, the Molecule object in RDKit will be explained alongside related objects (Atom, Bond, and Conformer). This section will make you familiar with how RDKit represents and handles molecules.
In the Molecule Operations section, the common operations on molecules will be explained, including adding & removing hydrogens, programmatically modifying molecules, and performing substructure matching.
In the Descriptors & Fingerprints section, you will learn how to use RDKit to calculate molecular descriptors and fingerprints, the different methods for calculation, and the available types of fingerprints.
In the Drawing Molecules section, you will learn how to draw molecules, the different methods for drawing, how to customize drawing options, how to highlight atoms & bonds, and when to use each drawing method.
In the Projects section, you will learn how to combine different RDKit concepts to perform real and meaningful projects and workflows in cheminformatics and drug discovery. You will also learn how to integrate RDKit with other Python packages—for example, how to build machine learning models with RDKit and scikit-learn for virtual screening, and how to use RDKit with the Pandas package for advanced data analysis. The projects will also demonstrate how to use RDKit’s algorithms, such as MCS (Maximum Common Substructure) analysis, 3D conformer generation, and similarity analysis. The projects will also cover more advanced topics, such as fragment-based drug design with RDKit, which involves handling and connecting fragments conditionally.
