GWAS Algorithm Optimization
In the fight against deadly deseases, fast and accurate algorithmic solutions are helping pharmaceutical companies get new medications to market sooner.
One powerful weapon in this fight is genome-wide association studies (GWAS), which analyze large sets of genetic markers across large cohorts of individuals to locate genetic variants contributing to the heritability of specific phenotypes (i.e., traits). However, GWAS analysis is computationally challenging because of the scale of the data involved and the modeling algorithms required.
A pharma company's GWAS analysis solution had proven to be accurate, yet it hampered researches due to the long run time on each experiment they administered. They wanted to speed up the logistic regression modeling — the most computationally demanding component of many GWAS analyses — that determines which markers explain specific phenotypes.
With an Analytics Starter Pack from Topcoder, the pharma company got on-demand access to more than 50 data scientists who worked to tackle the problem. Topcoder optimized the research algorithm in just 10 days, increasing the computational speed of the solution by a staggering 1200x.
This extreme value solution enabled the pharma company to expand research by completing more experiments faster, putting them one giant step closer to solving some of the world's most pressing healthcare challenges.