Polly Delivers STAR Quality Data at High Throughput, 5x Lower Cost
Key Highlights
A global AI Biotech company utilizes machine learning (ML) model(s) to identify new treatments, de-risk, and accelerate clinical trials. It needed a high throughput of consistently processed bulk RNA-seq data at high throughput and low costs to train its model(s).
The company faced challenges in integrating public data with in-house data, dealing with the high costs of processing data at scale through STAR pipelines, and ensuring consistent high data quality throughout the process.
Elucidata's team deployed a custom STAR pipeline on Polly, enabling the company to harness public data and meet the stringent data requirements for training their ML model(s).
We delivered consistently processed bulk RNA-seq datasets 9X faster and at 5X lower costs than industry averages resulting in a cost saving of $1.4 million for the company.
.svg)
.svg)
%201%20(1).svg)
.svg)
%201.svg){kind=icon}
.svg)
%20(1).svg)
