The goal of this 2015 challenge, conducted in collaboration with the Scripps Research Institute on Topcoder, was to optimize and speed up an existing algorithm for clustering antibody sequences (see the problem statement). Clustering these sequences allows researchers to understand the lineage structure of all human antibodies. Researchers can then monitor the global changes of the human antibody repertoire in response to different medical conditions. In this challenge, 40 competitors submitted 214 solutions and competed for $8,500 in prizes. The speed of the algorithm was increased by more than 4 orders of magnitude from 300 seconds down to 30 milliseconds on a dataset of 10,000. The winning algorithm also successfully completed a 2.3 million dataset in 30 seconds on a laptop.
