{"id":11309,"date":"2023-03-28T12:51:28","date_gmt":"2023-03-28T10:51:28","guid":{"rendered":"https:\/\/sano.science\/?p=11309"},"modified":"2025-03-17T14:52:34","modified_gmt":"2025-03-17T13:52:34","slug":"neardata-a-new-ambitious-project-for-sano","status":"publish","type":"post","link":"https:\/\/sano.science\/neardata-a-new-ambitious-project-for-sano\/","title":{"rendered":"NEARDATA: a new ambitious project for Sano\u00a0\u00a0\u00a0\u00a0"},"content":{"rendered":"\n

The goal of NEARDATA is to create an extreme data platform which will mediate data flows between Object Storage technology and Data Analytics platforms across the Compute Continuum. The platform will serve as an intermediary data service that intercepts and optimises data flows (S3 API, stream APIs) with high performance near-data connectors (Cloud\/Edge). 

The need for a such mediating platform is caused by the fact that up to 90% of medical data is stored in unsearchable formats, as a consequence, huge pools of unstructured data are nowadays locked away in Object stores as bulk data and are very difficult to mine and analyse. Additionally, medical data is highly dispersed and has tough privacy and security requirements. Because of that, there is a strong challenge in ingestion data from Object Storage to computing analytics services. 

The Extreme near-data platform will enable consumption, mining and processing of distributed and federated data without need to master the logistics of data access across heterogeneous data locations and pools. 

The project is focusing on three health data domains, which contain large unstructured data: metabolomics (images), genomics (text), and surgery data (video). The Extreme near-data platform will leverage effects of advanced AI technologies in those domains. 

Sano is responsible for two subprojects in the genomics domain:      <\/strong><\/p>\n\n\n