Claude Skills by HolobiomicsLab

Use when when you receive a mass spectrometry imaging dataset in unknown or mixed vendor formats and need to apply format-specific preprocessing before generating ion images.

Use when you have m/z values from mass spectrometry imaging (or similar MSI experiments) and need to assign molecular formulae to them. This is especially valuable when working with spatially-resolved metabolomics data where annotation precision lags behind traditional LC-MS approaches.

Use when you have an observed m/z value from spatially-resolved mass spectrometry imaging and need to assign one or more plausible molecular formulae with confidence metrics.

Use when when you need to reproduce a computational workflow described in a GitHub repository, validate CI/CD pipeline definitions (e.g., GitHub Actions workflows), inspect source code structure, or execute local versions of automated tests.

Use when you have retrieved and deduplicated chemical formulae and metadata from multiple heterogeneous sources (HMDB, ChEMBL, PubChem) and extracted both structural relationships (DBEdges) and biological reactant pairs (BioEdges from KEGG), and now need to merge them into a single queryable.

Use when when comparing GNPS chemical annotations across two or more groups of samples (defined by ReDU sample-information categories such as sample type, extraction method, or ionization source) where the groups contain different numbers of files.

Use when after performing isotopic correction, quantitation, or other pixel-level transformations on a feature-by-pixel intensity matrix imported from an imzML file via Cardinal's HDF5 layout.

Use when you have isotope-corrected or raw ion-image intensity matrices from LipidQMap or similar MSI software and need to: (1) export them as persistent HDF5 containers for archival or sharing, (2) programmatically read an existing Cardinal::HDF5 export to extract intensity matrices and feature.

Use when when exporting quantified MSI data (feature-by-pixel intensity matrices with associated ion m/z, lipid annotations, and pixel spatial coordinates) from LipidQMap and you need to produce a standards-compliant HDF5 container that can be read by Cardinal and other MSI analysis tools.

Use when when you have raw or preprocessed mass spectrometry imaging (MSI) data with limited spatial resolution, high noise, or incomplete molecular coverage, and you want to enhance signal fidelity to support multiscale tissue–single-cell mapping or brain biochemical profiling.

Use when you have two spatial omics datasets (e.g., spatial transcriptome and metabolome spot matrices) collected from the same or adjacent tissue sections, with both feature matrices (X: np.ndarray) and spatial coordinates (D: np.ndarray containing location information in .

Use when after you have computed a histogram of pairwise mass differences from MSI peak data and want to identify which mass shifts occur most frequently and whether they correspond to known chemical adducts.

Use when when preparing ion images (single-channel 2D arrays or multi-channel spectral images) from mass spectrometry imaging for contrastive learning in DeepION's COL or ISO modes.

Use when you have loaded a normalized or raw pixel array (NumPy format) with associated metadata from MSI line-scan data, and need to generate publication-quality ion images with controlled intensity scaling, smoothing, and optional ratio or fractional abundance comparisons across multiple m/z.

Use when you have paired cdf files (raw mass spectrometry imaging data) and Matlab workspace (.mat) files for the same root sample, and you need to reproduce published linear-axis imaging analysis results (e.g., per-root mass spectrometry imaging metrics along a developmental or spatial axis).

Use when you have raw mass spectrometry data files (mzML, NetCDF, or vendor formats) with unknown or mixed acquisition modalities, and you need to automatically determine whether the input is LC-MS, GC-MS, IMS (ion mobility spectrometry), or MS imaging (e.

Use when you have imaging mass spectrometry data from spatial metabolomics experiments and need to reduce the high-dimensional peak space to a ranked set of marker ions for downstream spatial analysis (e.g., tissue region annotation or biomarker discovery).

Use when after mzML-to-imzML conversion has produced barebones imzML files with pixel alignment but no experimental metadata.

Use when you have acquired raw mass spectrometry imaging data in imzML continuous format (e.g., from CardinalIO or other MSI instruments) and need to load it into R as a structured MSImagingExperiment object to perform statistical analysis, normalization, or visualization.

Use when you have acquired imaging mass spectrometry (IMS) data stored in imzML format (accompanied by an .ibd ion binary data file) and need to load it into a Python-based spatial metabolomics workflow.

Use when when you have one or more imzML files containing mass spectrometry imaging data and need to import them into LipidQMap for ion image extraction, isotopic correction, and quantitative analysis.

Use when you have received paired .imzML (XML metadata) and .ibd (binary data) files from an Imaging Mass Spectrometry instrument and need to discover the imaging geometry, m/z calibration, and scan coordinate system before extracting mass images or computing total ion chromatograms (TIC).

Use when you have aligned, imputed time-resolved mass spectrometric data from direct-injection plasma ionization (e.g., DBDI, DESI) without chromatographic separation, and you suspect multiple m/z features belong to the same neutral analyte as in-source fragments or oxygen-bound adducts.

Use when you have a preprocessed peak table with statistically significant or differentially abundant metabolites (e.g., from ANCOVA or PLS/PLS-DA), and you want to move beyond individual peak-level interpretation to understand which biological pathways or metabolic networks are perturbed.

Use when augmenting mass spectrometry ion images in ISO mode (isotope ions from the same molecule) and you need to simulate intensity-dependent data loss that reflects real detector behavior where lower-intensity pixels are more likely to be missed or undetected.

Use when after noise reduction when working with imported imzML MSI data where pixel-to-pixel or sample-to-sample intensity variations due to instrumental sensitivity or sample loading differences must be corrected before mean intensity calculation, ROI analysis, or metabolite annotation.

Use when when you have computed PCA coordinates from chemical annotation matrices (e.

Use when you have added a known internal standard compound to your nano-DESI MSI sample and want to correct for pixel-to-pixel variation in ionization efficiency or sample deposition.

Use when after isotope correction has been applied to MSI ion images, when you have sprayed or identified a reference lipid standard of known amount (pmol/mm²) and need to normalize target lipid intensities against this standard to remove matrix effects and enable cross-pixel and cross-sample.

Use when you have peak data from MSI experiments (stored as .zip peak matrix files) where matrix ions (e.g., silver adducts in AgLDI-MSI) dominate the spectrum and obscure analyte signals.

Use when when you have preprocessed mass spectrometry ion images (single-channel 2D arrays or multi-channel spectral images) and need to train a self-supervised encoder to learn low-dimensional representations for downstream tasks such as co-localized ion discovery (COL mode) or isotope ion.

Use when when preparing ion image data from mass spectrometry imaging for contrastive self-supervised representation learning, and you need to generate augmented image pairs that reflect either co-localization relationships between different molecular ions (COL mode) or isotopic relationships.

Use when training a contrastive encoder on mass spectrometry imaging (MSI) data in ISO mode (isotope ions from the same molecule).

Use when you have 512-dimensional representation vectors output from ResNet18 encoders processing paired augmented ion images, and you need to prevent trivial solutions (representation collapse) during contrastive learning—specifically when optimizing for maximized similarity between augmentations.

Use when when you have imzML mass spectrometry imaging data files and need to convert raw ion image intensities into quantitative lipid abundance (pmol/mm²) using known internal standards.

Use when your raw MSI dataset is acquired on an ion-mobility-enabled instrument (e.g., Bruker .baf, .tsf, or .tdf formats) and your analyte of interest has a known or experimentally determined ion mobility value (1/K0 or drift time μs).

Use when you have loaded MSI data with an extracted peak list and need to annotate matrix-related signals, particularly when the dataset may contain isobaric ions or peaks with overlapping spatial distributions that could be misclassified during downstream annotation filtering.

Use when after matrix annotation has been performed on mass spectrometry imaging (MSI) data when you need to identify and document ions whose m/z values overlap with or are isobaric to other peaks, creating risk of false positive or false negative matrix assignments.

Use when after isotopic correction has been performed on MSI ion images and you need to convert normalized intensities into absolute quantitative values.

Use when you have latent low-dimension peak features extracted by a Graph-attention autoencoder from imaging mass spectrometry (IMS) datasets, and you need to automatically identify a ranked subset of marker ions without manual inspection.

Use when when you need to verify that a Java project's automated build pipeline (GitHub Actions workflow) executes without errors and generates distributable artifacts (e.g., .deb installers, portable binaries, or .jar files).

Use when you have defined a Keras model architecture (convolutional and dense layers) accepting raw mass spectrometry imaging data tensors and need to prepare it for training on tumor/non-tumor probabilistic classification without prior peak picking.

Use when when integrating two spatial omics modalities (ST and SM) measured on the same tissue sample but at different spatial resolutions or spot coordinates.

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 deposited mass spectrometry imaging datasets in NetCDF (CDF) format with accompanying MATLAB workspace files (.

Use when when processing mass spectrometry imaging data with multiple adduct forms of the same lipid species, and you need to correct one adduct form (e.g. [M+H]+) for isotopic interference from a co-occurring adduct (e.g. [M+Na]+).

Use when a spatial metabolomics dataset contains semicolon-delimited isomer name annotations (e.g., 'all_IsomerNames' column in SpaMTP Seurat objects) and you need to collapse multiple lipid nomenclature variants into their parent lipid categories and classes.

Use when you have acquired full-scan mass spectrometry imaging data (e.g., from a mouse bladder or tissue section) with detected m/z features and want to assign chemical identities to those features by querying a structured lipid database.

Use when after quantifying ion images in LipidQMap and before exporting to HDF5 format, when you need to organize per-feature metadata (lipid ID, class, adduct, m/z, internal standard flag) into aligned datasets that can be linked to intensity data via dimension scales and sorted for reproducible.