Metadata-Version: 2.4
Name: lobster-proteomics
Version: 1.1.418
Summary: Proteomics agent for Lobster AI (DDA/DIA mass spectrometry, affinity platforms)
Author-email: Omics-OS <info@omics-os.com>
License-Expression: AGPL-3.0-or-later
Project-URL: Homepage, https://omics-os.com
Project-URL: Documentation, https://docs.omics-os.com
Project-URL: Repository, https://github.com/the-omics-os/lobster
Keywords: bioinformatics,proteomics,mass-spectrometry,DDA,DIA,Olink,SomaScan,lobster-ai
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Requires-Python: <3.14,>=3.12
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: lobster-ai~=1.1.0
Requires-Dist: anndata>=0.9.0
Requires-Dist: numpy>=1.23.0
Requires-Dist: pandas>=1.5.0
Requires-Dist: plotly>=5.0.0
Requires-Dist: scipy>=1.10.0
Requires-Dist: scikit-learn>=1.3.0
Requires-Dist: statsmodels>=0.14.0
Requires-Dist: lifelines>=0.27.0
Requires-Dist: peptides>=0.3
Provides-Extra: network-analysis
Requires-Dist: networkx>=3.0; extra == "network-analysis"
Dynamic: license-file

# lobster-proteomics

Unified proteomics analysis for mass spectrometry (DDA/DIA) and affinity platforms (Olink, SomaScan).

## Installation

```bash
pip install lobster-proteomics
```

## Agents

| Agent | Description |
|-------|-------------|
| `proteomics_expert` | Full proteomics workflow orchestration with auto-detection of platform type and appropriate preprocessing. |

## Services

| Service | Purpose |
|---------|---------|
| ProteomicsAnalysisService | Core analysis workflows for protein quantification |
| ProteomicsDifferentialService | Differential protein expression between conditions |
| ProteomicsSurvivalService | Survival analysis with protein biomarkers |
| ProteomicsNetworkService | Protein-protein interaction network analysis |
| ProteomicsQualityService | Quality control and missing value assessment |
| ProteomicsPreprocessingService | MNAR/MAR-aware imputation and normalization |
| ProteomicsVisualizationService | Volcano plots, heatmaps, and network graphs |
| MaxQuantParser | Parse MaxQuant proteinGroups.txt output |
| DIANNParser | Parse DIA-NN report.tsv output |
| SpectronautParser | Parse Spectronaut report output |
| OlinkParser | Parse Olink NPX export files |

## Features

- Auto-detection of platform type from data characteristics
- Missing value handling optimized for MNAR (mass spec) vs MAR (affinity) patterns
- Platform-appropriate quality control with batch effect detection
- Median and quantile normalization with log2 transformation
- Multiple imputation strategies (MinDet, KNN, zero, median)
- Differential protein analysis with multiple testing correction
- Volcano plots and MA plots for results visualization
- Protein-protein interaction network construction and visualization
- Survival analysis integration for clinical proteomics studies
- Support for multi-plex affinity platforms (Olink, SomaScan, Luminex)

## Platform Support

| Platform | Missing Values | Normalization | Notes |
|----------|---------------|---------------|-------|
| Mass Spectrometry (DDA/DIA) | 30-70% (MNAR) | Median + log2 | Peptide mapping support |
| Affinity (Olink) | <30% (MAR) | Quantile | Plate effect correction |
| Affinity (SomaScan) | <30% (MAR) | Quantile | Antibody validation |

## Requirements

- Python 3.12+
- lobster-ai >= 1.0.0

## Tier Requirement

This is a **free** agent. Access is controlled at runtime via Lobster AI's tier system.

## Documentation

Full documentation: [docs.omics-os.com/docs/agents/proteomics](https://docs.omics-os.com/docs/agents/proteomics)

## License

MIT
