Claude Skills by HolobiomicsLab

Use when you have a curated training dataset of molecular structures with known CCS values, a target set of ≤10,000 molecules requiring CCS predictions, and need to apply a pre-configured Sklearn-based machine learning model within a reproducible, browser-accessible environment.

Use when you have a collection of molecular structures (as SMILES or SDF files) and need to generate pre-computed CCS values for fast retrieval in downstream mass spectrometry workflows.

Use when you have imaging mass spectrometry (IMS) data preprocessed into an h5py-backed feature matrix, and a trained graph-attention autoencoder has already extracted latent low-dimensional peak features.

Use when you have imaging mass spectrometry (IMS) datasets where peak intensities are high-dimensional and sparse, and you need to extract compressed latent features that preserve spatial adjacency relationships and enable iterative automatic peak picking to identify marker ions.

Use when you have loaded mzML.gz or HDF5-formatted raw LC-IMS-MS/MS data and need to identify discrete peaks before feature alignment. Use it if your goal is to reduce noise, increase signal-to-noise ratio, and prepare multi-dimensional data for cross-sample feature matching and CCS calibration.

Use when you have raw nontargeted LCMS feature tables from one or more analytical methods in tabular format (with m/z, RT, and intensity columns) that need to be aligned or clustered, or when integrating multiple feature tables into a shared BMXP processing pipeline that requires standardized.

Use when when you have acquired a CCS reference library (such as DTCCSN2 for U13C labeled lipids) and need to verify that it contains the expected lipid classes, CCS values are physically plausible for ion mobility data, and coverage matches the library's advertised documentation before using it.

Use when you have IM-MS lipidomics data with measured CCS values, samples spiked with U13C-labeled lipid internal standards (e.

Use when you have parsed MRM transition data (m/z values, retention times, transition parameters) from mass spectrometry experiments and need to map each detected transition to a known lipid identity.

Use when you have N-methyl-derivatized unsaturated sterol lipid structures (as SMILES or molecular formula) and need to predict their MS/MS fragmentation behavior before experimental acquisition, or to build a reference spectral library for isomer-level sterol identification in tissue samples.

Use when you have MS/MS spectra with initial lipid annotations from spectral library matching (e.g., from XCMS + CAMERA or LipidIN's Expeditious Querying module) and seek to improve recall, precision, and annotation coverage.

Use when you have MS-DIAL lipid identification results (alignment exports in msp/txt format) and need to distinguish correct from incorrect lipid IDs before downstream analysis.

Use when you have obtained MobiLipid or a similar IM-MS lipidomics package that bundles a CCS reference library for labeled lipids, and you need to verify library integrity, validate that all expected lipid species are present with plausible numeric CCS values, and prepare a canonical curated.

Use when when you have raw mzML or mzXML mass spectrometry files with uncompressed numeric arrays (not pre-compressed with zlib or msnumpress) and need to reduce file size for archival or transfer while guaranteeing that decompressed data is byte-identical to the original.

Use when after generating an ensemble of 3D conformers via RDKit conformation sampling, when you need to reduce the conformer set size before expensive quantum-chemical calculations (e.g., QUICK).

Use when when you have detected features with m/z, drift time, and retention time dimensions and need to associate peaks into isotopic groups (e.g., monoisotopes with C13 substitutions) or align features across multiple LC-IMS-MS/MS samples.

Use when when you have generated multiple 3D conformations for a molecule or set of ionized adducts (e.g., via RDKit) and need to retain only the most energetically favorable structures before expensive quantum calculations.

Use when you have MS-DIAL lipid identifications from an Orbitrap or TOF mass spectrometer and need to remove spurious or low-confidence assignments before downstream metabolomics analysis.

Use when your metabolomics analysis pipeline requires CCS value prediction for ion-mobility mass spectrometry data, you have access to a curated training set of known metabolites with experimentally validated CCS values, and you plan to predict CCS values on target datasets containing 10,000+.

Use when you have a labeled dataset of DIA raw files (.raw, .d, .wiff) with known quality annotations and have extracted the 15 iDIA-QC metrics (raw file characteristics from timsTOF, TripleTOF, or Orbitrap instruments).

Use when you have extracted latent low-dimensional peak features from imaging mass spectrometry (IMS) data using a graph-attention autoencoder and need to identify a ranked subset of marker ions that represent spatial metabolomic patterns.

Use when after parsing MRM transition tables (m/z values, retention times, transition parameters) from mzML data, before statistical analysis or visualization. Use this skill when you have detected but unannotated transitions and need to map them to lipid species with quantified confidence.

Use when you receive raw MS data files from LC-MS, LC-IMS-MS, direct infusion, or DDA/DIA experiments and need to extract ion chromatograms, mobility heatmaps, quality metrics, or perform spectral matching.

Use when you have raw MS data files from supported instruments (Agilent, Thermo, Bruker, or mzML format) and need to ingest them into IonToolPack for visualization, quality control, targeted extraction, or spectral library matching.

Use when you have raw mass spectrometry data in CSV or mzML format and need to visualize it using pyOpenMS-viz, or you are working with MS data that contains retention time (rt), m/z, intensity, and optionally ion mobility dimensions that must be structured as a Pandas DataFrame before plotting.

Use when you have converted multidimensional MS data (from Agilent .d, Bruker ion mobility .d, Thermo .

Use when when you have raw or processed TWIM-MS data (arrival time and m/z values) from a mass spectrometry instrument and need to organize it into a feature table before biomolecular class assignment or CCS calculations.

Use when when you have mass spectrometry data (mzML, Bruker .d, or CSV) loaded into a Pandas DataFrame with columns for m/z, retention time, ion mobility, or intensity values, and you need to render spectrum plots, chromatograms, mobilograms, or 2D peak maps.

Use when when you have raw ion mobility-mass spectrometry data (drift times, m/z values, and frame metadata) from DTIMS-MS, TWIMS-MS, or SLIM-based instruments and need to compute CCS values for structural characterization or database matching.

Use when you have raw MS/MS spectral data in one or more standard mass spectrometry file formats (.mgf, .msp, or .mzML) and need to convert them into a standardized bag-of-fragments representation for unsupervised topic modeling or substructure discovery workflows.

Use when you have mzML or mzXML mass spectrometry data files and need to extract and validate spectral records (m/z and intensity arrays) for lossless compression, lossy transformation, or format conversion.

Use when after loading a pixel array (NumPy format) and its associated metadata JSON file from MSIGen, when you need to account for pixel-to-pixel variations in total ion signal or when comparing relative abundances of multiple ions within or across samples.

Use when you have raw line-scan MSI data from a vendor instrument (Agilent, Bruker, Thermo, or open-source .mzML format) and need to extract ion images for specified m/z targets with spatial binning and tolerance-based filtering.

Use when your input mass spectrometry imaging data is in a proprietary vendor format (Bruker .d/.baf, or other binary formats not natively supported by MSIGen) and you need to convert it to an open, readable format (mzML or processed binary) compatible with MSIGen's msigen() function.

Use when you plan to perform repeated queries or filtering on MS metadata attributes (e.g., extract all MS2 spectra with collision energy > 30 eV, or collect all scans in a retention time window) across a large MZA HDF5 file.

Use when you have raw DIA mass spectrometry files (.raw, .d, .wiff formats) from timsTOF, TripleTOF, or Orbitrap instruments and need to quantify file quality for automated quality control, longitudinal instrument monitoring, or training a quality prediction classifier.

Use when you have multi-sample MS1 data (LC-MS, LC-IMS-MS, or direct infusion across any omics domain) and need to detect samples with abnormal global ion intensity patterns or unusual per-ion metric behavior (intensity distribution, signal-to-noise, retention time stability) that may indicate.

Use when working with imaging mass spectrometry (IMS) datasets where you need to (1) automatically identify marker ions without manual annotation, (2) reduce peak intensity dimensionality while preserving spatial relationships between measurement points, or (3) apply iterative peak picking.

Use when you are building a visualization library that must support multiple plot kinds (chromatogram, spectrum, mobilogram, peakmap) across multiple rendering backends (matplotlib, bokeh, plotly) and want to avoid code duplication.

Use when when you have raw DIA mass spectrometry data files (.raw, .d, .

Use when you have positive- or negative-mode tunemix reference data (with known CCS values, m/z, and measured drift times) and need to establish a calibration model for converting observed drift times into CCS values for downstream feature annotation.

Use when you have acquired tunemix data (positive or negative ion mode, in .h5 format) with known CCS reference values and need to construct a calibration function that will later predict CCS values for unknown analytes.

Use when when you have high-resolution LC-MS or GC-MS data from environmental samples and need to simultaneously screen for both known suspect chemicals and their transformation products, rather than targeting single compounds.

Use when you have positive- or negative-mode tune reference compound data stored in HDF5 format (e.g., example_tune_pos.h5) and need to extract the tune mass spectrum for CCS calibration. This skill is the entry point before applying deimos.calibration.

Use when when you have a collection of mzML.gz files from a multidimensional MS instrument (e.

Use when you have a collection of mzML or mzML.gz files from LC-IMS-MS/MS experiments and need to apply a consistent, reproducible sequence of feature detection, alignment, CCS calibration, isotope detection, and MS/MS deconvolution operations across multiple samples.

Use when when working with multidimensional MS data (LC–IM–MS/MS) converted to MZA format where spectra are stored in jagged arrays with m/z values distributed across individual HDF5 datasets per scan, and you need to ensure m/z consistency for downstream peak detection, isotope analysis, or.

Use when when you have extracted m/z and intensity arrays from an MZA file (or similar HDF5-backed MS data structure) and need to visually inspect a single MS1 or MS2 spectrum, verify peak characteristics, or diagnose data quality issues before downstream analysis (peak fitting, isotope pattern.

Use when when converting raw line-scan mass spectrometry imaging data (Agilent .d, Bruker .tsf/.baf/.tdf, Thermo .raw, or .mzML formats) and must decide which m/z values from a reference mass list correspond to peaks in the raw spectra.

Use when when you have mass spectrometry data (chromatograms, spectra, mobilograms, or peak maps) in a Pandas DataFrame and need to generate the same visualization in multiple formats—e.