Features
Automatic lineage capture for notebooks, scripts, functions, pipelines
Unified query interface across Parquet, Zarr, AnnData, SpatialData
Schema management and validation for biological datasets
Bio-registries and ontology support (Cell Ontology, Gene Ontology)
LIMS and ELN capabilities with markdown notes
Git-like branching and merging for change management
Zero-copy data sharing across databases and storage
Integration with Nextflow, Redun, Snakemake, Weights & Biases, MLFlow
Built-in role-based access control and audit logs
Support for local, S3, GCP, Azure, and R2 storage backends
Record.from_dataframe() ~2x speedup (db 2.7.0)
Excel support for sheet imports (hub 1.44.0)
Native SpatialData support
LaminR package for R traceability
Database mirror for Arc Virtual Cell Atlas (600M cells, 41TB)
Real-world data from millions of oncology patients globally
Flatiron Telescope AI platform for rapid oncology insights
LLM-based thematic analysis of clinical trial discussions
ML models predicting rapid progression in HR+/HER2- metastatic breast cancer
Real-world biomarker testing and outcomes studies
Point-of-care clinical decision support
Regulatory-grade real-world evidence generation
Cancer-specific data abstraction and curation
Custom study design and analytics services
Data quality assurance and validation processes
Multi-cancer type cohort identification
Publication support – over 2,000 peer-reviewed papers
49+ research acceptances at ASCO 2026
Integration with life sciences workflows
Professional services for research collaborations
Integrations
Electronic Health Record (EHR) systems
Laboratory information systems
Clinical trial management systems
Research data repositories
Genomic sequencing platforms
