skills.rest
K-Dense-AI
K-Dense-AIOFFICIAL
Explore all skills by this author →
Website𝕏@k_dense_aiGitHub

lamindb

Manage biological datasets with lineage tracking, validation, and ontology-backed annotation.

46.6k|4.2k|Updated Oct 19, 2025
Search Tags:#ontology#data validation#bioinformatics#data lineage#single-cell#lakehouse#lamindb
One-click install
npx skills add https://github.com/K-Dense-AI/claude-scientific-skills --skill lamindb-k-dense-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lamindb
Source: https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/skills/lamindb
Command: npx skills add https://github.com/K-Dense-AI/claude-scientific-skills --skill lamindb-k-dense-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lamindb, bionty, and includes references (resource) components.

What problem does it solve? Biological research teams struggle to keep datasets queryable, traceable, and reproducible across notebooks, pipelines, and storage systems. This Skill guides AI agents through LaminDB, the open-source lineage-native lakehouse, so artifacts, runs, and annotations stay versioned, validated, and FAIR-compliant. ## Core Features & Use Cases - Artifact and lineage management: Register versioned datasets (DataFrame, AnnData, SpatialData, Parquet, Zarr), track notebook and pipeline execution with ln.track(), and visualize provenance graphs. - Querying and validation: Filter registries with feature-based and logical queries, stream large files, and curate data against flexible or strict schemas using DataFrameCurator and AnnDataCurator. - Ontology-backed annotation: Standardize genes, cell types, tissues, and diseases with Bionty ontologies, and integrate with Nextflow, Snakemake, W&B, MLflow, S3, and GCS. - Use Case: A researcher curating scRNA-seq batches can validate cell types against the Cell Ontology, annotate artifacts with typed features, and later query all treated PBMC datasets across experiments in one command. ## Quick Start Ask the agent to set up a LaminDB instance and register your first AnnData artifact with lineage tracking enabled.

Frequently Asked Questions about lamindb

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track data lineage in LaminDB?▼

Call ln.track() at the start of a notebook or script and ln.finish() at the end to capture source code, environment, inputs, and outputs automatically. For function workflows, use the @ln.flow() and @ln.step() decorators, then inspect results with artifact.view_lineage().

How to validate AnnData files against a schema in LaminDB?▼

Define Feature records, build a Schema with slots for obs and var.T, then run ln.curators.AnnDataCurator(adata, schema).validate(). Fix issues with curator.cat.standardize() or ontology mapping, and save the result with curator.save_artifact().

What biological ontologies does Bionty support?▼

Bionty provides over 20 curated ontologies including Ensembl genes, UniProt proteins, Cell Ontology cell types, Uberon tissues, Mondo and DOID diseases, HPO phenotypes, GO pathways, EFO experimental factors, and NCBItaxon organisms.

Does LaminDB work with S3 and Google Cloud Storage?▼

Yes, LaminDB supports AWS S3, Google Cloud Storage, S3-compatible endpoints like MinIO and Cloudflare R2, local filesystems, and read-only HTTP sources. Initialize an instance with lamin init --storage pointing to the bucket, paired with SQLite or PostgreSQL.

Can LaminDB integrate with Nextflow or Snakemake pipelines?▼

Yes, LaminDB integrates with Nextflow, Snakemake, and Redun by calling ln.track() inside process scripts or rules to register inputs and outputs. For native Nextflow projects, the nf-lamin plugin with nextflow.config is the preferred pattern.

When should I use PostgreSQL instead of SQLite with LaminDB?▼

Use SQLite for local development and single-user work, since it requires no separate server. Switch to PostgreSQL for production deployments that need concurrent writes, multi-user access control, and better performance at scale.

Related Skills

Explore More Education & Research Skills→
aristoteleoaristoteleo
478

OpenST Skills Index

Map Open-ST data processing into an end-to-end pipeline from BCL/FASTQ to h5ad objects.

Official
Advanced
Cnext-euCnext-eu
1

kairos-projection-generation

Generate dbt models, graph schemas, search indexes, and UI schemas from ontologies.

Official
Advanced
hung-phanhung-phan
1

experiment-tracking

Track machine learning experiments and manage model lifecycles with MLflow, Weights & Biases, and Trackio.

Community
Advanced
HermeticOrmusHermeticOrmus

data-versioning-patterns

Implement reproducible ML data management with DVC, Delta Lake, and OpenLineage.

Community
Advanced