This startup provides a Cohort API that harmonizes multi-omics data from diverse sources without local transformation, enabling rapid SQL queries for patient cohorts based on OMOP standards. By automating data integration with a human-in-the-loop machine learning algorithm, it reduces the time required for data preparation from months to minutes, facilitating efficient drug discovery and clinical trial participant selection.
Funding
Funding not disclosed
Founders
Product
Problem
Researchers and clinicians face significant challenges in integrating and harmonizing multi-omics data from disparate sources, hindering the creation of comprehensive patient cohorts. Traditional data integration methods require extensive local transformation, a time-consuming process that can delay drug discovery and clinical trial participant selection.
Solution
This startup offers a Cohort API that enables rapid SQL queries for patient cohorts based on OMOP standards without requiring local data transformation. The API federates multi-omics data from diverse sources, streamlining data harmonization. A human-in-the-loop machine learning algorithm automates the integration process, reducing data preparation time from months to minutes on a query-by-query basis. This allows researchers to efficiently create decentralized patient cohorts for accurate stratification in drug discovery, diagnostics development, and clinical trials. The platform ensures data protection while enabling federated workflows for GWAS, ML, and custom bioinformatics analyses.
Target Audience
The primary target audience includes researchers, bioinformaticians, and clinicians involved in drug discovery, diagnostics development, and clinical trials who require efficient access to harmonized multi-omics data.
Features
- Harmonizes multi-omics data from heterogeneous sources without local transformation.
- Supports SQL queries for patient cohorts based on OMOP standards.
- Employs a human-in-the-loop machine learning algorithm to automate data integration.
- Enables federated workflows for GWAS, ML, and custom bioinformatics analyses.
- Facilitates the creation of decentralized patient cohorts for accurate stratification.
- Provides a unified multi-omics data layer leveraging insights from genomic population-scale datasets to bespoke proteome and RNA studies.