Leveraging RCSB PDB APIs for Bioinformatics Analyses and Machine Learning

Virtual Crash Course | October 12, 2023 and October 19/October 25, 2023

This course introduces users to the two main APIs that power the RCSB.org website: Data API and Search API. The live course consisted of two parts: Part 1 featured lectures that introduced the APIs (October 12), while Part 2 featured hands-on sessions held twice (October 19 and Otober 24). The hands-on session consisted of two coding examples demonstrations followed by hands-on coding in break out rooms. Only the coding demonstrations from Part 2 are available in this online course.

After watching the videos featured in this course, you will be able to:

• Understand the data structure in Data API and its relation to the PDBx/mmCIF dictionary and external data
• Become familiarized with the two available interfaces in the Data API: GraphQL and REST
• Write search queries for the Search API with one or multiple search conditions to find PDB identifiers
• Be familiar with search services beyond text: sequence, seqmotif, structure, chemical, strucmotif
• Become acquainted with the Python client for Search API

Additional materials for this course are available:

• Presentation Slides
• Part 1: Talk synopses and Q&A
• Part 2: Session summary and Q&A
• Part 2: Google Colab Notebook for coding example Accessing RCSB PDB APIs via Python
• Part 2: Google Colab Notebook for coding example Preparing a dataset for ML/AI-based prediction of heterodimer binding sites

Click on the image below to play the video.