The code-first data platform for bioinformaticians
Empowering bioinformatics scientists with ML-ready data to drive the success of multi-disciplinary drug discovery teams
All the data you need, where you need it
Get access to 350,000+ curated biomedical molecular data in an analysis–ready form. Our code-first platform lets you explore data at depth through code and perform complex querying. Alternatively, you can choose to integrate the data for analysis on your preferred computational infrastructure.
High-quality data for machine learning applications
All of the data on Polly is ready for direct downstream machine learning applications. Our curation pipeline enriches data by adding harmonized metadata annotations with scientific context, helping you find the data you need within seconds. The depth of data curation enables advanced querying through code across datasets, samples, and specific features. Raw data is normalized into a standard, consistent format, letting you focus on data analysis and insight discovery over data wrangling.
Build, scale and discover insights faster with our team of experts
The success of data-driven research depends on the availability of technical expertise, operational bandwidth and computational infrastructure. Our Customer Success team consists of scientists, bioinformaticians and engineers who can work with you to deliver customized solutions to shorten your journey to insight discovery.