Claude Skills by HolobiomicsLab

Use when you have preprocessed MSImagingArrays data (after normalization, smoothing, and baseline reduction) and need to detect peaks consistently across all spectra in an imaging experiment, create reference peak positions from a representative subset, and filter by signal-to-noise ratio and.

Use when when you have paired spatial transcriptome and metabolome datasets with spot-based coordinates that need to be aligned for multi-modal integration.

Use when you have paired spatial transcriptome and metabolome datasets (both as h5ad files with .obsm['spatial'] coordinate matrices and .

Use when you have paired spatial transcriptomics and spatial metabolomics datasets from the same sample(s) that are at different spatial resolutions or coordinate systems, and you need to integrate them for joint analysis of cross-modal spatial patterns.

Use when you have deposited SpaceM spatio-molecular matrices (MORPHnMOL.

Use when after correlation testing has validated putative parent–adduct ion pairs (e.g., via corrPairsMSI() on a massdiff object annotated with adductMatch results), use this skill to annotate and visualize the mass spectrum plot to confirm that identified pairs exhibit expected overlap—e.

Use when you have loaded raw MSI spectral data (imzML format) in profile or centroid mode and need to remove background noise and baseline artifacts before intensity normalization or ROI analysis.

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 after reading an imzML file (continuous or processed format) using readMSIData() in Cardinal, verify the resulting MSImagingExperiment object before performing normalization, baseline reduction, peak-picking, or statistical analysis.

Use when when generating augmented variants of single-channel or multi-channel ion images for contrastive learning in mass spectrometry imaging analysis.

Use when you have raw line-scan MSI data from any supported vendor (Agilent .d, Bruker .tsf/.baf/.tdf, Thermo .raw, or .

Use when when you have extracted a mean or ROI spectrum from MSI data (via centroid or profile mode conversion) and need to identify the biochemical composition by comparing against curated reference libraries such as LIPID MAPS, HMDB, or a custom metabolite database.

Use when you have imported raw MSI spectral data in imzML format and observe high background noise or low signal-to-noise ratio that would obscure biochemical annotations or ROI analysis.

Use when you have mass spectrometry imaging data with a histogram of pairwise mass differences that have already been matched to known adducts (via adductMatch), and you need to retrieve the actual mass peak pairs corresponding to a specific adduct of interest—particularly when you want to test.

Use when you have preprocessed MSImagingArrays objects (normalized via normalize(), smoothed via smooth(), and baseline-reduced via reduceBaseline()) and need to identify discrete peaks across all spectra in a mass spectrometry imaging dataset.

Use when after peak picking and alignment have been performed on preprocessed spectra (normalized, smoothed, and baseline-reduced), and you need to create a unified peak reference table that can be applied consistently across all spectra in an imaging dataset.

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

Use when when you need to quantify and compare the filtering efficacy of mutually exclusive noise-threshold methods on the same input mass spectrum, or when validating that a selected noise-filtering strategy retains an expected number of peaks for downstream molecular formula assignment.

Use when after loading spatial metabolomics data (from CSV, imzML, or merged positive/negative ion modes) into an AnnData object, and before filtering or alignment steps.

Use when you have completed batch spectral searches against multiple domain-specific MASST tools (via Fast Search API or individual domain searches) and need to combine and visualize the aggregated match results in a format compatible with metadataMASST web interface or downstream analysis.

Use when you have raw IMC (protein imaging) and SIMS (metabolite imaging) data from tissue regions that require spatial co-registration, single-cell-level intensity quantification, and joint analysis of protein–metabolite relationships.

Use when you have loaded a mass spectrometry imaging pixel array (NumPy format) and need to correct for variations in total ion signal across pixels before generating ion images or ratio images.

Use when you have GC–MS or LC–MS data represented as a two-dimensional map with m/z values on one axis and retention time on the other, and you need to identify analyte signals and chemo-/biomarker features while minimizing false positive and false negative peak detections.

Use when after preprocessing and normalizing joint ST/SM AnnData objects using joint_adata_sm_st and normalize_total_joint_adata_sm_st, when you need to align spatial transcriptomics and metabolomics data to a unified latent resolution for multi-omics integration and cross-modal spatial pattern.

Use when you have a raw MSI data file from an unknown or mixed set of vendors and need to apply format-specific data extraction, spectral parsing, or image reconstruction. The file extension alone must determine which parsing module (MSIGen.raw, MSIGen.D, MSIGen.baf, MSIGen.tdf, MSIGen.

Use when a task needs a skill from ASB Metabolomics — MS-imaging — search this unit's 292 evidence-grounded skills, then apply and optionally ground the one that fits.

Use when when you need to generate 2D metabolomic NMR spectra (COSY for homonuclear or HSQC/HMQC for heteronuclear correlations) from parsed metabolite concentration and spin-system J-coupling data, and you want to simulate realistic peak patterns including indirect-dimension evolution and phase.

Use when after running inference on a trained structure prediction model with one or more input modalities (1H NMR, 13C NMR, or combined), you have generated predicted molecular formulas and connectivity graphs that need to be compared against known ground truth structures.

Use when after MS1 feature detection and spectra merging in an untargeted or semi-targeted metabolomics workflow, when you have a list of observed accurate m/z values from high-resolution mass spectrometry (e.

Use when when you need to evaluate how a specific algorithm parameter (such as SearchMolecularFormulas first_hit mode) affects the quantity and quality of molecular formula assignments on a given spectrum or dataset.

Use when after MS-FINDER in silico annotation has been executed on exported LC-MS features and multiple database matches (with HRR scores) have been returned.

Use when after recursive annotation propagation has assigned metabolite labels to previously unannotated nodes in a two-layer metabolomic network, and before reporting final annotated metabolite identities.

Use when you have experimental mass spectra from untargeted metabolomics and need to assign compound identities with confidence estimates.

Use when you have nuclear magnetic resonance (NMR) peak data (proton 1H and carbon-13 13C measurements) that you need to classify using a deployed deep learning model, and you have access to a TensorFlow Serving instance running the SMART 3 classification model.

Use when you have tabular experimental data (e.g., sample metadata, mass spectrometry parameters, NMR acquisition details) in JSON table format and need to produce a list of structured objects for submission to a data repository (e.g., Metabolomics Workbench) or downstream format conversion.

Use when you have paired spectrum-compound reference data and need to simultaneously retrieve candidate compounds rapidly (bi-encoder) while also refining relevance scores through joint context modeling (cross-encoder).

Use when you encounter a proprietary or undocumented binary file (e.

Use when when you have (1) a molecular network graph from GNPS with node identifiers and edges, (2) LC-MS/MS features quantified across fractions in a feature table, and (3) bioassay measurements (e.

Use when you have untargeted metabolomics data with unknown or ambiguous molecular identities, anchor metabolites (known structures in SMILES or MOL format), and a curated database of biotransformation rules (e.g., from KEGG, RetroRules, or domain-specific repositories).

Use when when preparing NMR datasets for processing in NMRFx and the Dataset.createDataFile() method must choose among competing storage backends.

Use when when you have peripheral blood sample cohorts (plasma/serum) with multiple timestamps (e.

Use when you have predicted or partially assembled molecular fragments (as token sequences or substructure embeddings) and need to determine which atoms are bonded to which—that is, when the formula (atom inventory) is known or predicted but the connectivity graph is uncertain.

Use when you need to run a web application locally (by opening index.html directly in the browser) and the application uses WebWorker or WebAssembly modules that fail to load with cross-origin policy or file-access errors.

Use when you have raw Bruker NMR spectral files (from a Bruker instrument) in a directory and need to prepare them for automated metabolite identification and quantification using ASICS.

Use when after querying a formula database (KEGG, PubChem, or user-supplied) with neutral mass values derived from observed m/z peaks and adduct transformations, when multiple candidate formulae fall within the configured mass tolerance window (ppm or Da) and you need to rank them by likelihood.

Use when you have BioTransformer-predicted metabolite structures (in SMILES or InChI format) and need to identify which known compounds in public databases match those structures.

Use when after a machine learning model has generated predicted molecular structures (connectivity graphs and molecular formulas) from 1D NMR spectra. Use it to quantify accuracy on a held-out test set, measure degradation when applying the model beyond its training scope (e.

Use when after spreadOut() has converted raw CSV peak data into a structured list, when you have one or more Compound.Name entries from GC-MS that may be ambiguous, non-canonical, or missing standardized properties (exact mass, published retention times, reactive groups, database presence).

Use when when you have preprocessed 1H NMR spectral data with unidentified peaks and need to determine metabolite identity by exploiting the correlation structure of NMR signals.

Use when you have loaded an INADEQUATE NMR spectrum file and need to detect individual peaks (local maxima) across the chemical shift dimension with associated intensity values. This is the mandatory first processing step before filtering peaks into networks or matching against metabolite databases.