What file formats does matchms support within Claude Code?

Matchms supports a wide range of mass spectrometry formats including mzML, mzXML, MGF, MSP, and GNPS-compatible JSON files.

Is matchms suitable for large-scale library matching?

Absolutely. Matchms is designed to efficiently calculate similarity scores between large sets of query and reference spectra using optimized algorithms and reproducible pipelines.

Can I use matchms for chemical structure derivation?

Yes, it includes specialized filters to derive InChI and InChIKey from SMILES, add molecular fingerprints, and repair structural mismatches in metadata.

What spectral similarity metrics are available in this skill?

It provides several metrics including CosineGreedy, Modified Cosine (which accounts for precursor mass differences), NeutralLossesCosine, and FingerprintSimilarity.

Matchms Mass Spectrometry Analysis

Name: Matchms Mass Spectrometry Analysis
Author: jimmc414

byjimmc414

•

324

データサイエンスとML

Processes and analyzes mass spectrometry data using Python-based spectral similarity, metadata harmonization, and data filtering tools.

概要

Matchms is a specialized capability for Claude Code designed for scientists and researchers working with mass spectrometry data. It provides a comprehensive suite of tools to import, filter, and analyze spectra from various formats like mzML, MGF, and MSP. The skill excels at metadata harmonization, peak normalization, and calculating complex spectral similarities such as Modified Cosine or Neutral Losses, enabling the creation of automated and reproducible metabolomics pipelines and autonomous chemical discovery workflows within the Claude environment.

主な機能

Integrated visualization for spectrum plotting and library matching
Extensible processing pipelines with 40+ built-in spectrum filters
Automated metadata harmonization and chemical annotation (SMILES/InChI)
324 GitHub stars
Advanced spectral similarity metrics including Cosine and Modified Cosine
Support for mzML, MGF, MSP, and JSON file formats

ユースケース

Building automated metabolomics data processing and cleaning pipelines
Identifying unknown compounds by matching query spectra against reference libraries
Large-scale spectral clustering and network-based chemical analysis

概要

主な機能

Integrated visualization for spectrum plotting and library matching
Extensible processing pipelines with 40+ built-in spectrum filters
Automated metadata harmonization and chemical annotation (SMILES/InChI)
324 GitHub stars
Advanced spectral similarity metrics including Cosine and Modified Cosine
Support for mzML, MGF, MSP, and JSON file formats

ユースケース

Building automated metabolomics data processing and cleaning pipelines
Identifying unknown compounds by matching query spectra against reference libraries
Large-scale spectral clustering and network-based chemical analysis