for insight discovery
Polly delivers biomedical molecular data enriched with metadata and processed for machine learning applications
Providing access to analysis-ready data from multiple sources in one place
Our curation infrastructure processes public as well as proprietary data through a standard pipeline, producing analysis-ready data suitable for machine learning applications.
How does Polly make data ML-ready?
A plethora of rich metadata annotations with scientific context enable you to find the data most relevant to your research.
Our ML-based curation infrastructure maps metadata with accuracy matching that of human experts.
Raw data is normalized into a standard and consistent format, allowing you to focus on data analysis and interpretation.
Leverage code-first approaches to extract deeper insights from data
Perform advanced querying on data through code
- Polly Libraries facilitates powerful querying capabilities through code, allowing in-depth data exploration.
Take Polly where you work
- Access data on your preferred computational infrastructure through Libraries.
- Integrate data on Polly with analytical platforms including AWS Sagemaker and Databricks.
How it works
Keen to know how we help data-driven drug discovery teams get to faster actionable insights?