John Blischak 3/27/2020

How to efficiently calculate pairwise overlaps of many sets

Read Original

The article details the author's process of optimizing a function to calculate pairwise overlaps (e.g., Jaccard index, overlap coefficient) for many sets, motivated by analyzing redundant biological annotation terms from gene set enrichment analysis. It explains the problem, initial slow brute-force approach, and steps taken for significant speed improvements, while inviting knowledge of more clever algorithms.

How to efficiently calculate pairwise overlaps of many sets

Comments

No comments yet

Be the first to share your thoughts!