Skip to main content

Metadata assistant agent for Lobster AI - sample metadata and harmonization operations

Project description

lobster-metadata

Sample metadata management and harmonization for multi-omics datasets.

Installation

pip install lobster-metadata

Agents

Agent Description
metadata_assistant Metadata operations specialist. Sample ID mapping, schema standardization, dataset validation, and disease annotation enrichment.

Services

Service Purpose
SampleMappingService Map sample IDs between datasets using multiple strategies
MetadataStandardizationService Standardize metadata fields to Pydantic schemas
MetadataFilteringService Filter datasets by metadata criteria
DiseaseStandardizationService Standardize disease names to controlled vocabularies
DiseaseOntologyService Map diseases to ontology terms (MONDO, DO)
ClinicalMetadataService Extract and validate clinical metadata fields
SampleGroupingService Group samples by metadata attributes
MicrobiomeFilteringService Microbiome-specific metadata filtering

Features

Sample ID Mapping

  • Exact match between matrix and metadata identifiers
  • Fuzzy matching with configurable similarity thresholds
  • Pattern-based matching using regular expressions
  • Metadata-based correlation for complex mapping scenarios

Metadata Standardization

  • Transcriptomics schema (cell type, tissue, organism, disease)
  • Proteomics schema (platform, quantification method, normalization)
  • Microbiome schema (16S vs shotgun, taxonomic level, diversity)

Dataset Validation

  • Sample count consistency between matrix and metadata
  • Condition coverage verification for experimental design
  • Control sample identification and validation
  • Biological and technical replicate detection
  • Platform consistency checks across samples

Disease Enrichment

Four-phase hierarchy for missing disease annotations:

  1. Column re-scan for disease-related field names
  2. LLM-based abstract extraction from publication context
  3. LLM-based methods section parsing
  4. Manual mapping fallback for known datasets

Multi-Omics Integration

  • Cross-modality sample alignment
  • Shared sample identification across data types
  • Metadata merging with conflict resolution

Requirements

  • Python 3.12+
  • lobster-ai >= 1.0.0

Testing

To run the test suite for this package:

# Install in editable mode with dev dependencies
pip install -e ".[dev]"

# Run all tests
pytest tests/ -v

# Run specific test categories
pytest tests/services/metadata/ -v  # Service tests only
pytest tests/agents/ -v             # Agent tests only

Documentation

Full documentation: docs.omics-os.com/docs/agents/metadata

License

AGPL-3.0-or-later

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lobster_metadata-1.1.418.tar.gz (100.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lobster_metadata-1.1.418-py3-none-any.whl (111.2 kB view details)

Uploaded Python 3

File details

Details for the file lobster_metadata-1.1.418.tar.gz.

File metadata

  • Download URL: lobster_metadata-1.1.418.tar.gz
  • Upload date:
  • Size: 100.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for lobster_metadata-1.1.418.tar.gz
Algorithm Hash digest
SHA256 9f94997bcee0b8d0ba52e913419de028102d0b8104cae96ae43528dd46dadd51
MD5 8ebec25e1e9e2b55f8e57ece4bcf02c1
BLAKE2b-256 4cd5b2c204338e33e24627e8863245cf39dfdd0c3b2fdb6878547de425d74bd2

See more details on using hashes here.

Provenance

The following attestation bundles were made for lobster_metadata-1.1.418.tar.gz:

Publisher: publish-packages.yml on the-omics-os/lobster

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file lobster_metadata-1.1.418-py3-none-any.whl.

File metadata

File hashes

Hashes for lobster_metadata-1.1.418-py3-none-any.whl
Algorithm Hash digest
SHA256 a2b0b56cdbce51bea1df2ce23b8e17055962855b2a6748537f91479311d43068
MD5 f32eb3a430757a8734f3abea04ea968b
BLAKE2b-256 bbb962eca0fcb5f7bae10209537a4a6edccd7e90fcd35b43b4090e334994df52

See more details on using hashes here.

Provenance

The following attestation bundles were made for lobster_metadata-1.1.418-py3-none-any.whl:

Publisher: publish-packages.yml on the-omics-os/lobster

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page