Claude Skills by HolobiomicsLab

Use when you have raw or baseline-corrected mass spectra from MSImagingArrays or MSImagingExperiment objects and need to decide between smoothing methods before peak picking or statistical analysis.

Use when after annotating mass-difference pairs with candidate adduct identities, compute correlations to test whether putative parent and adduct ion intensities co-vary across the imaging pixel grid. High positive correlation (with Bonferroni-corrected p-value < 0.

Use when when you have deposited mass spectrometry imaging datasets for plant roots in CDF format paired with pre-computed Matlab workspaces, and you need to reproduce per-root linear-axis metabolite profiling outputs to validate reported genotype-level results (e.

Use when you have raw line-scan mass spectrometry imaging data from nano-DESI or other line-scan acquisition modes and need to produce a georeferenced 3D pixel array.

Use when after normalizing an MSI pixel array to TIC or an internal standard, when the raw pixel intensity distribution spans multiple orders of magnitude and produces images with poor contrast or where extreme outlier intensities would wash out spatial detail.

Use when when preparing augmented variants of ion images (single-channel 2D arrays or multi-channel spectral images) for contrastive learning in mass spectrometry imaging tasks.

Use when augmenting mass spectrometry ion images for contrastive learning, particularly when the model must generalize across different detector conditions or signal-to-noise ratios.

Use when augmenting mass spectrometry ion images for contrastive learning, specifically when you need to simulate the natural Poisson noise that arises from photon-counting detectors in mass spectrometry imaging experiments.

Use when when processing imzML/ibd Imaging Mass Spectrometry datasets and you need to extract ion density maps for specific analytes or isotopes. Apply this skill after importing the .imzML metadata and .

Use when you have extracted a list of candidate molecular formulae for a given m/z value and need to rank them by plausibility.

Use when when you have raw mass spectrometry imaging data tensors and need to build a trainable deep-learning classifier that outputs class probabilities (tumor vs. non-tumor) without preprocessing or manual peak detection.

Use when when you have access to a research repository or README documenting a machine learning implementation (e.g., Keras/TensorFlow-based deep learning model) and need to reproduce the computational environment exactly. Triggers include: (1) README explicitly lists pinned versions (e.

Use when when you have queued one or more spectral processing operations (e.g., smooth(), normalize(), reduceBaseline()) on an MSImagingArrays object and need to inspect the effect on representative spectra before processing the full dataset.

Use when you have preprocessed MSI data in Cardinal format (post-peakBin) and need to apply mass2adduct's adduct-detection workflow, OR you have exported MSI intensity data as CSV from third-party software (SCiLS, MSiReader) and must convert it into a standardized R object for downstream analysis.

Use when preparing ion image data for contrastive learning in mass spectrometry imaging (MSI), specifically when you need to augment single ion images into pairs of variants for encoder training in COL mode (co-localized ions) or as a base component of ISO mode (isotope ions).

Use when when you have raw mass spectrometry imaging data (full m/z profiles with intensity arrays) and want to classify spatial regions (e.

Use when you have collected imaging mass spectrometry data in vendor-specific raw format (.raw files from Bruker, Waters, Thermo, or other instrument manufacturers) and need to convert it to the open, vendor-agnostic mzML XML format before downstream imzML construction and spatial alignment.

Use when when you have raw or preprocessed mass spectrometry data (feature matrices or transient files) acquired at lower mass resolution or with signal degradation, and you possess high-resolution reference MSI data or simulated ground truth to train a reconstruction model.

Use when you have calculated pairwise mass differences from MS peaks (via massdiff()) and binned them into a histogram, and now need to identify which observed mass differences correspond to known molecular adducts (e.g., [M+Na]+, [M+H]+, matrix-related species) rather than random noise.

Use when after computing expected adduct ions for a metabolite using a derivatizing matrix ruleset, validate the predicted m/z values and adduct formulas against a curated reference dataset that documents which ions are actually produced by that matrix under standard ionization conditions.

Use when you need to validate that a software project''s release branch is stable and ready for distribution. Specifically, use it when: (1) a release tag has been created or code pushed to a release branch; (2) you need to confirm that CI/CD pipelines execute without failures;

Use when you need to validate that a scientific software project's continuous integration pipeline is functional and producing reproducible builds—particularly before releasing new versions, after merging changes to release branches, or when troubleshooting build failures that block distribution of.

Use when training a contrastive learning model on ion image data (mass spectrometry imaging) where augmented pairs of the same ion image must maximize similarity while different images minimize similarity.

Use when after obtaining 512-dimensional representation vectors from the Encoder module, when you need to compress these vectors for visualization, clustering, or downstream classification tasks on mass spectrometry imaging data while maintaining interpretability of ion relationships.

Use when your task requires a pretrained convolutional encoder (ResNet18) to produce fixed-size representation vectors of a specific dimensionality (e.g., 512 dimensions) rather than the default output size.

Use when when you have loaded imzML MSI data into napari and need to focus analysis on a specific anatomical or morphological region rather than the entire image.

Use when you have CDF-format mass spectrometry imaging files from plant roots with accompanying MATLAB workspace files (.mat), and your research goal is to reproduce linear-axis intensity profiles, feature distributions, and spatial metrics reported in a prior publication (e.g., Sama et al. 2025).

Use when apply Savitzky-Golay smoothing when your mass spectra contain significant noise but you need to preserve sharp peaks and spectral fine structure (e.g., isotope patterns, peak asymmetry).

Use when when converting mzML files to imzML format and the source mzML contains multiple scan filters (e.g., different MS/MS isolation windows, ionization modes, or mass ranges acquired in a single imaging experiment).

Use when you have executed batch searches of MS/MS spectra against multiple domain-specific MASST indices and need to synthesize results across domains (e.

Use when you have a SpaMTP Seurat object with a 'Spatial' assay containing metabolomics features (m/z values) and their associated metadata columns (e.

Use when apply this preprocessing chain when you have loaded raw or continuous imzML mass spectra into a Cardinal MSImagingArrays object and need to prepare them for peak picking, statistical analysis, or imaging.

Use when you have imported raw MSI spectral data in imzML format and need to improve signal-to-noise ratio before performing mean intensity calculations, ROI analysis, or database annotation.

Use when you have raw IMC and SIMS image data from the same tissue region(s) and need to: (1) register the two modalities spatially, (2) segment individual cells across both images, (3) extract per-cell protein and metabolite intensity vectors, and (4) prepare the data for downstream joint analysis.

Use when when you have a list of candidate metabolite identifiers in SMILES or mol format and need to programmatically apply chemical transformations (e.g., derivatization reactions), compute molecular weights, or enumerate adduct ions for mass spectrometry matching.

Use when analyzing MALDI-mass spectrometry imaging data in which sodium or other alkali metal contamination is suspected, or when peak lists show unexplained mass differences in the range of ~20–25 Da (characteristic of Na adducts).

Use when when you have a scientific software tool (e.g., Met-ID) that is architected to support plugins or configuration-driven modules, and you need to register and apply a novel reagent, derivatizing matrix, or analytical method (e.

Use when after loading and preprocessing a Cardinal MSImagingExperiment object (with normalized peaks and optional spatial segmentation results), and before conducting spatial statistical tests or co-localization analyses.

Use when you have raw imzML files (paired with .ibd binary data) from imaging mass spectrometry experiments and need to construct an AnnData object for spatial metabolomics analysis.

Use when when you have preprocessed spatial transcriptomics (ST) and spatial metabolomics (SM) datasets in AnnData format with spatial coordinates, and need to align them to a common resolution before joint downstream analysis.

Use when after annotating ion pairs with known adducts (using adductMatch or diffGetPeaks), use this skill to filter suspected adduct pairs by testing if their pixel-level intensity profiles are significantly correlated.

Use when after identifying candidate parent–adduct mass-difference pairs (via massdiff, histogram binning, and adductMatch), apply this skill to discriminate true molecular adducts from coincidental mass matches.

Use when when you have loaded MSI peak data with associated m/z values and need to disambiguate matrix ions from analyte ions. Apply this skill when chemical formula alone is insufficient (e.g., overlapping or isobaric peaks exist) and you have pixel-level spatial intensity maps for each ion.

Use when when analyzing imaging mass spectrometry datasets where you need to reduce high-dimensional peak intensity features while preserving spatial structure, and when automatic peak picking and marker ion identification are required.

Use when preparing raw ion image data from mass spectrometry imaging for deep learning-based representation learning.

Use when your spatial metabolomics dataset contains raw m/z features (e.g., from MALDI-MS imaging or LC-MS/MS) without metabolite annotations, and you have selected a reference database and adduct type appropriate for your ionization mode and biological sample.

Use when when you have paired spatial metabolomics and spatial transcriptomics measurements from the same tissue samples and need to identify how metabolite distributions relate to gene expression patterns at aligned spatial coordinates.

Use when when annotating matrix-related peaks in MSI datasets where candidate peaks have identical or near-identical m/z values (isobaric ions), or when multiple peaks exhibit overlapping spatial distributions across the tissue image that could confound downstream annotation filtering.

Use when you have mzML files from a mass spectrometry imaging (MSI) experiment and need to convert them to imzML format with correctly positioned pixel coordinates.

Use when apply SSC when you have preprocessed and normalized MS imaging data (e.g., after TIC normalization and peak processing) and need to discover spatially distinct metabolite regions without prior tissue annotation.