A teaching platform providing interactive Jupyter Notebooks for learning computer-aided drug design (CADD) using open-source tools.
TeachOpenCADD is an open-source educational platform that provides interactive tutorials for learning computer-aided drug design (CADD). It offers Jupyter Notebooks covering key CADD topics like cheminformatics and structural bioinformatics, using popular Python packages to teach both theory and practical implementation. The platform solves the problem of limited freely accessible, hands-on CADD learning materials for students and researchers new to the field.
Students and researchers in computational chemistry, bioinformatics, and drug discovery who want to learn CADD concepts through practical examples. It serves both those with biological/chemical backgrounds needing computational skills and computational scientists seeking domain-specific applications.
Developers choose TeachOpenCADD because it provides ready-to-use, community-maintained tutorials that combine theoretical explanations with executable code. Unlike generic documentation, it offers CADD-focused examples using established open-source tools, lowering the barrier to entry for this specialized field.
TeachOpenCADD: a teaching platform for computer-aided drug design (CADD) using open source packages and data
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Each topic is covered in executable notebooks, allowing learners to run code and experiment directly, making CADD concepts tangible and hands-on.
Includes cheminformatics, structural bioinformatics, and deep learning applications, providing a broad foundation in key CADD areas as shown in the topics figure.
Notebooks can be run online without local setup, lowering barriers to entry and enabling immediate access, though Binder can take around 10 minutes to load.
Offers both Jupyter Notebooks and KNIME workflows for select topics, catering to different learning preferences and skill sets, as highlighted in the KNIME section.
Focuses on foundational topics and introductory deep learning, so it may not cover advanced or niche CADD techniques needed for specialized research, as admitted in its educational focus.
Relies on open-source tools like RDKit and MDAnalysis that may not handle large datasets efficiently compared to commercial solutions, limiting use in high-throughput scenarios.
Online execution via Binder can be slow and unreliable, and local installation requires managing conda environments, which can be complex for some users, as noted in the setup instructions.