Claude Skills by HolobiomicsLab

Use when when you have raw MS/MS mass spectrometry data and need to submit it to the Mass2SMILES Docker inference container for structure and functional group prediction.

Use when you have three distinct mass spectrometry data sources (quantification table, metadata table, and spectral data from an MS library or reference dataset like omsw_pleurotus_ms2deepscore) and need to combine them into a single JSON output that preserves all three modalities for interactive.

Use when when you need to retrieve a specific MS/MS spectrum from a public proteomics repository (PRIDE, MassIVE, PeptideAtlas) by its USI string for annotation, visualization, or comparative analysis, rather than working with locally stored mzML/mzXML files or already-loaded spectrum objects.

Use when you have acquired multiple MS1 spectra over a defined acquisition time range (e.g., 0–30 s in FIA-MS) and need to combine them into a unified spectrum before feature detection.

Use when apply TIC normalization when you have raw, unprocessed mass spectrometry data (Cardinal objects or imaging matrices with 10,000+ m/z features and 1,000+ spectra) where signal intensity varies across spatial locations or samples due to instrumental drift, uneven sample preparation, or.

Use when you have centroided mzML files from LC–MS experiments and need to perform targeted metabolomics or lipidomics analysis. Specifically, use it when you require polarity filtering, QC-sample stratification, or batch-aware peak detection—all of which depend on sampleData$type annotations (e.

Use when you have a set of centroided .mzML LC-MS files from a targeted metabolomics or lipidomics experiment and need to represent them as a structured object that links raw spectra to sample-level metadata (e.

Use when you have raw MS/MS spectral data in MGF format from multiple sources or instruments with inconsistent metadata fields, varying intensity scales, and potential low-quality spectra that need standardization before metadata harmonization or spectral library compilation.

Use when when you have raw LC-MS/MS DDA spectral data (positive and/or negative ionization modes) paired with sample metadata (originating taxon), and you need to detect molecular features, build a molecular network from fragmentation spectra, and annotate those features using both spectral.

Use when when importing raw mass spectrometry data in formats like mzML, mzXML, msp, MGF, or JSON and you need to ensure spectral data quality before proceeding to similarity comparisons or other downstream analyses.

Use when you have a USI string (e.g., mzspec:GNPS:TASK-d93bdbb5cdda40e48975e6e18a45c3ce-f.mwang87/data/... or mzspec:MSV000084951:AH22) and need to extract the corresponding mass spectrum peak list (m/z and intensity pairs) for downstream analysis, visualization, or cross-repository comparison.

Use when after completing MS/MS spectra detection and peak recognition on tandem MS breath samples.

Use when you have completed a GNPS1 (METABOLOMICS-SNETS, METABOLOMICS-SNETS-V2, FEATURE-BASED-MOLECULAR-NETWORKING) or GNPS2 (classical_networking_workflow, feature_based_molecular_networking_workflow) molecular networking job and need to access its output files in a standardized format for.

Use when when raw spectra have been imported from common MS/MS file formats but contain inconsistent, missing, or malformed metadata fields that could compromise spectral similarity comparisons or cause downstream pipeline failures.

Use when you have executed MassQL queries on mzML mass spectrometry data and need to communicate query results visually—particularly when comparing peak shapes across multiple files, assessing retention time distributions, or validating precursor/product ion matches.

Use when you need to generate synthetic LC/GC-MS feature tables or raw mzML files with realistic peak complexity, ion multiplicities, and natural spectral variation—not just theoretical m/z values.

Use when you have executed batch spectral searches against two or more domain-specific MASST tools and received heterogeneous output formats (domain-specific HTML trees, JSON objects, TSV match tables) that need to be reconciled into a single normalized schema for downstream aggregation.

Use when when you have an unknown mass spectrum (query spectrum) and need to search it against a reference database of billions of spectra to find matching or structurally related compounds.

Use when when you have a pre-cleaned spectral library (e.g., GNPS, MoNA, or MTBLS1572) with an existing training/test boundary established by prior work (e.g., MSBERT), and you need to report model performance with uncertainty quantification across multiple random partitions.

Use when you have a noisy MS/MS spectrum and need to identify and remove chemical noise ions (as opposed to electronic noise). You have the precursor compound's SMILES string or molecular formula and its adduct type.

Use when you have untargeted MS2 spectra from environmental or clinical samples that will be used for natural product identification (e.g., linking to BGCs via IOKR or other kernel-based methods), and you have access to a high-quality training library of annotated spectra with known structures.

Use when you have high-resolution tandem MS spectra (in mzML, mzXML, or MGF format) that need to be clustered or searched at scale (millions of spectra).

Use when you have per-sample MS2 spectra (in matchms-compatible formats like mzML, mzXML, MGF, or msp) and need to compare metabolomic samples across different LC methods, mass spectrometers, or retention-time regimes—especially when samples are chemodiverse with poor feature overlap or strong RT.

Use when you have a set of preprocessed MS/MS spectra (binned to 10,000 m/z bins with intensities square-root transformed) and a trained MS2DeepScore Siamese neural network model, and you need to compute 200-dimensional spectral embeddings for dimensionality reduction, clustering, or chemical space.

Use when you have a collection of pre-processed MS/MS spectra (binned, intensity-normalized) and a trained MS2DeepScore base network, and you need to compute structural similarity scores between spectrum pairs or visualize spectra in chemical space via dimensionality reduction (e.g., UMAP).

Use when after training a transformer-encoder-based mass spectrometry embedding model (e.

Use when when you have preprocessed MS/MS spectral peak data (m/z and intensity pairs) and need to compute a complexity metric for individual spectra prior to similarity comparisons, or when benchmarking compound identification performance against dot product–based methods.

Use when after feature detection and alignment in untargeted MS data processing, when you need to filter or rank candidate metabolite annotations by spectral quality before committing to xenobiotic metabolite assignments. Use when combining fragmentation similarity scores (e.

Use when you need to measure the similarity between two MS/MS spectra as a continuous value that reflects both peak presence/absence and intensity patterns, particularly when comparing noisy versus denoised spectrum variants, or when ranking candidate reference library matches during compound.

Use when you have a detected feature table (m/z, drift_time, retention_time, intensity) and need to identify and label C13 isotopic clusters for singly-charged features (z=+1).

Use when you have spectral feature data annotated by both in silico structural tools (e.

Use when after identifying statistically significant LC-MS features (e.

Use when you have an annotated LC-MS feature table with KEGG candidate matches and adduct assignments (output from the matching stage), and you need to disambiguate which features co-elute and correlate in intensity, signaling a common metabolite origin before applying adduct-based filtering.

Use when when you have generated separate MemoMatrix objects from independent sample sets (e.g., sample set A and sample set B) and need to align and combine their MS2 fingerprint data into a single matrix for comparative analysis.

Use when you have raw LC/MS data in mzML format and need to perform non-targeted screening to discover unknown chemical features without a predefined list of target compounds.

Use when when you have raw LC-MS metabolomics data in .mzML or .npy format from multiple disease groups with varying ionization efficiencies or detector sensitivities, and you need to train a deep learning model for disease classification.

Use when when performing large-scale untargeted metabolomics annotations where you need to assess the false discovery rate of metabolite identifications but lack sufficient negative control samples or decoy compound databases.

Use when after peak-picking stage completes on centroided mzML or netCDF raw LC-MS data via any of the three wrapped algorithms (Centwave, FeatureFinderMetabo, ADAP), when you need to pass the detected features to downstream SLAW stages (alignment, isotope/adduct grouping, gap-filling, MS2.

Use when you have raw LC-MS data in mzXML format (or vendor formats convertible via MS-Convert) and need to identify and quantify metabolic features before multi-sample alignment. Use MS1 peak picking for full-scan or DDA data to extract Gaussian and non-Gaussian shaped peaks;

Use when you have generated per-sample MS2 fingerprints (as spec2vec document representations counting MS2 peaks and neutral losses to precursor in each sample) and need to align them into a single matrix for downstream cross-sample comparison, filtering, or visualization (e.

Use when you have a collection of MS/MS spectra in standard formats (mzML, MGF) and need to perform rapid similarity search, clustering, or joint analysis across millions of spectra without repeated peptide database searches.

Use when when you have a GNPS molecular networking job archive (downloaded as a .zip or compressed archive) and need to prepare metabolomics spectra and molecular family data for NPLinker integration.

Use when you have MS2 fragmentation spectra from multiple metabolomics samples and need to compare them in a retention time-agnostic manner, especially when samples are chemically diverse, acquired with different LC methods or mass spectrometer technologies (e.

Use when you have a high-resolution LC-MS/MS spectrum or pre-computed molecular fingerprint from a small-molecule sample and need to retrieve a systematic structural classification (compound class and subclass) with confidence estimates.

Use when after clustering features with RAMClustR and inferring molecular weights via do.findmain, when you need to perform structure elucidation or molecular formula prediction using MSFinder (for .mat format) or Sirius (for .ms format).

Use when when raw spectral data exists in one mass spectrometry file format but downstream analysis requires a different format; when integrating spectra from multiple sources or instruments that produce heterogeneous file formats;

Use when you have raw or unprocessed MS/MS spectral data in standard metabolomics formats (MGF, mzML, mzXML, msp, or JSON) and need to import them into a Python-based workflow for MS2 fingerprint generation, peak counting, or spectral similarity scoring.

Use when when you have an experimental tandem mass spectrum (peaks with m/z and intensity values) and wish to identify which fragments or chemical subformulae each peak corresponds to.

Use when you have an MS/MS spectrum (m/z and intensity arrays) and a known or hypothesized peptide sequence (optionally with post-translational modifications in ProForma 2.

Use when when you have metabolomics intensity data with metabolites grouped by fragmentation spectral similarity (Molecular Families or Mass2Motifs) and need to rank or score these groups by their differential activity across experimental conditions, especially when traditional pathway databases.