Skip to main content
Loading

Sponsor Led Poster Presentation: Scaling ingestion and querying in omics data lakes

20 Jun 2024
Salon H
Data Quality , Drug Response Prediction , Lead Generation & Optimization , Target Identification
Sponsor Led Poster Presentation: Scaling ingestion and querying in omics data lakes

Biomarker based ML applications, for ex: classifying responders to certain types of therapy based on genomic variants from sequencing data, show great promise. Biomarker applications rely on data from genomics, transcriptomics, and other omics assays, and can also be augmented by images from pathology or pseudo-images from novel applications such as spatial transcriptomics. To enable ML applications, the following need to be ingested, stored, and queried efficiently:

  • Metadata schema and relevant ontologies for each type of data, for ex., the UBERON ontology for multispecies anatomy
  • Data, for ex. Fastq files for omics data
  • Results, for ex., cell type annotations from spatial transcriptomics
Industry Expert
Radhakrishna Bettadapura, Vice President, Business Development - Strand Life Sciences