Elucidata (Polly)

Elucidata (Polly) — Harmonised multi-modal biomedical data lake plus a knowledge graph: public omics and literature sources (gene-expression repositories, publications, supplementary files, figures, regulatory documents) normalised to standard ontologies and enriched with 50+ structured metadata fields covering study design, trial arms, endpoints, eligibility, assay results, toxicology and EHR/EMR-derived data. Critically, this is layered with customer-submitted private omics and clinical data harmonised into the same schema, so the platform holds a federation of proprietary datasets aligned …

Elucidata (Polly) offers (Alternative, Reference, Fundamental) — Not published in aggregate. Scope indicators: harmonisation across major public omics repositories plus 50+ metadata fields per study, a knowledge graph spanning genes, diseases, drugs and pathways, and per-document extraction across full texts, supplements and figures. Underlying public omics content is itself petabyte-scale, but the proprietary portion is the harmonised metadata and curation layer, whose size is not stated.

Target identification and validation; training document-intelligence and multimodal biomedical extraction models on human-verified spans; building and evaluating biomedical knowledge-graph completion models; dataset discovery and prioritisation for computational biology; FAIR-compliant data-lake population; regulatory and literature evidence synthesis; and for a buyer's own AI programme, a labelled corpus of biomedical document-to-schema pairs which is scarce and expensive to reproduce

The data is with 8 years of history.

Coverage spans US; Health Care Technology; alternative, reference, fundamental; equities.

The supplier's own access route is a conversation with the supplier. Request a sample through Brickroad to start.