Claude Skills by HolobiomicsLab

Use when after cleaning and clustering LC-MS features in MS-CleanR, when you need to assign putative compound identities to a feature set with MS/MS spectra, and when candidate compounds may exist across multiple specialized databases (e.g., natural products, pharmaceuticals, contaminants).

Use when you have multiple CSV feature tables from independent metabolomic experiments, each with RT and m/z annotations, and you need to produce a single consolidated feature matrix for comparative analysis across all samples.

Use when you have loaded LC-MS feature tables or peak detection output containing internal standard identifications with retention times, m/z values, and intensity measurements across multiple samples, and you need to detect anomalies such as retention time drift, m/z shifts, or intensity loss that.

Use when you have raw or processed mass spectrometry data in HDF5 (.h5) or mzML format and need to ingest it into DEIMoS for multi-dimensional analysis.

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

Use when after performing an ANOVA-style multi-group de_design() analysis on a LipidomicsExperiment object, when you need to determine whether a categorical sample variable (e.g., Cancer Stage, SampleType, Race) significantly associates with the lipid molecular profile.

Use when you have embedded sequences of chemical formulae (tokenized and converted to dense vectors) from tandem MS/MS spectra and need to learn context-dependent representations that capture dependencies between formula tokens at multiple semantic levels.

Use when when building a transformer-based model to process mass spectrometry data (MS/MS spectra or fingerprints) where you need the model to learn multiple independent attention patterns across spectrum features simultaneously.

Use when when you have an unknown tandem mass spectrum (MS/MS peaks with m/z and intensity) and need to assign both the precursor chemical formula and its ionization adduct type (e.g., [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+).

Use when you have DIA mass spectrometry raw files from multiple instrument types (timsTOF, TripleTOF, Orbitrap) in their native formats (.raw, .d, .

Use when when you have a pretrained encoder that captures domain knowledge (e.g., spectral feature extraction) and need to train task-specific decoder or scoring modules on top of it without degrading the encoder's learned representations.

Use when when you have matched transcriptomics (RNA-seq read counts), intracellular metabolomics (LC-MS abundance data), and extracellular flux measurements (YSI bioanalyzer or similar) from multiple biological samples or cell lines, and you need to determine whether differences in metabolic enzyme.

Use when when you need to visually compare two or more spectra (MS1, MS2, or extracted ion chromatograms) across different retention times, m/z ranges, or ion mobility bins in a single figure. Apply this skill after extracting spectra arrays from MZA files (e.

Use when you have untargeted metabolomics data from multiple MS instruments (e.

Use when after initial retention-time-based feature grouping (e.

Use when when you have MS1 mass spectrometry data from multiple samples (a cohort) acquired across an instrument run or batch, and you need to identify which samples deviate from cohort norms or which ion targets show anomalous behavior.

Use when you have two or more independently processed MemoMatrix objects (each generated from a separate sample set) and your analysis goal requires direct comparison of MS2 fingerprint profiles across those samples.

Use when you have two or more independent scoring functions ranking the same set of candidate links (GCF-MF pairs, BGC-spectrum associations, etc.), and you want to determine whether they capture complementary information that justifies combining them.

Use when when you have a Universal Spectrum Identifier (USI) string or collection of USI strings and need to programmatically retrieve the corresponding mass spectrometry spectrum data from one of seven supported repositories (GNPS Molecular Networking, GNPS Spectral Libraries, ProteoXchange.

Use when you have candidate lipid annotations from high-throughput spectral matching (e.

Use when when baseline MLP or GNN models for spectral prediction show limited performance on metabolite annotation tasks, and you have access to auxiliary spectral topic labels (e.g., via LDA on spectral features) that could provide regularization signal.

Use when when training an object detection network that must predict both discrete labels (e.g., true peak vs. false peak) and continuous coordinates (e.

Use when you have feature identification outputs from two or more DIA-MS search tools (e.g., DIA-NN and OpenSwath result files) and need to assess their agreement on analyte detection, quantification, and scoring.

Use when you have peak/feature table outputs from one or more peak-picking tools (MZmine, XCMS, MS-DIAL, Compound Discoverer) with different column names and metadata structures, and you need to ingest them into LipidMatch or another unified lipidomics pipeline that requires consistent column.

Use when you observe sawtooth or discontinuous peak profiles in EICs after running tardisPeaks() on LC-MS data acquired with multiple overlapping or sequential m/z scan windows (e.g., positive and negative polarity scans, or data-independent acquisition with staggered windows).

Use when you have split multi-assay LC-MS intensity data into training (90%) and test (10%) subsets with assay-specific column prefixes, and you need to fit a discriminant or regression model that respects the block structure (separate assays) while jointly predicting a phenotypic outcome (e.

Use when when you have a normalized metabolite abundance matrix with sample metadata assigning each sample to one of three or more distinct biological classes (e.

Use when you have detected feature tables from two or more LC-IMS-MS/MS samples (each containing m/z, drift_time, retention_time, and intensity measurements) and need to identify which features correspond to the same chemical compound across samples.

Use when you have a peak-picked feature table (HDF5 format) from high-dimensional MS data (m/z, drift_time, retention_time, intensity) and need to identify and label isotopic signatures to distinguish monoisotopic peaks from isotopologues, reduce feature redundancy, and support multi-dimensional.

Use when you have preprocessed MS/MS spectral data (normalized peak intensities and m/z values) and need to transform spectra into fixed-dimensional molecular embeddings for candidate matching against a reference database, especially when direct spectral comparison or classical fingerprinting.

Use when you have acquired untargeted MS data with orthogonal separations (LC, ion mobility) and/or data-independent acquisition (DIA) from Thermo, Agilent, or Bruker instruments, and you need to: (1) store multidimensional spectra in a vendor-neutral, platform-agnostic format;

Use when after computing a pairwise sample distance matrix from aligned MS2 fingerprint vectors and you need to visualize sample relationships, clustering, or separation by group identity in 2D space.

Use when processing raw IM-MS data (Agilent MassHunter .d or UIMF format) that contains jagged, low-abundance ion peaks or when saturation repair has been applied and the resulting reconstructed signals need artifact removal and enhancement.

Use when you have multidimensional MS data (with LC and/or ion mobility dimensions) converted to MZA HDF5 format and need to retrieve raw spectral intensity and m/z values for specific scans, retention times, drift times, or mass ranges.

Use when you have raw MS data in vendor formats (Agilent .d, Thermo .raw, Bruker .

Use when when you have an observed m/z value from mass spectrometry imaging and need to annotate it with a ranked list of candidate chemical formulae. Apply this skill when the KnownSet database (2.

Use when you have raw IM-MS data in UIMF or Agilent MassHunter .d format acquired from a multiplexed (interleaved) ion mobility experiment, and you need to recover individual, demultiplexed frames to reconstruct conventional IM-MS spectra for downstream omics analysis.

Use when you have SWATH-MS data (mzML or vendor binary format) where precursor isolation windows intentionally capture multiple co-eluting compounds, resulting in multiplexed MS/MS spectra that contain mixed fragment ion peaks from unknown metabolites.

Use when when you have preprocessed non-targeted LC-MS/MS feature tables (post-merging, cleanup, blank removal, and batch correction) and seek to uncover multivariate patterns across samples, discriminate between experimental groups, or reduce dimensionality of high-dimensional metabolomic data.

Use when after data normalization (Step 7) when you have a preprocessed feature matrix and need to identify samples that deviate significantly from the multivariate center of the data distribution due to instrumental drift, batch effects, sample degradation, or genuine biological outliers that.

Use when after loading a feature table with m/z values from MS-Dial output when you need to identify and remove features with anomalous decimal m/z values.

Use when when invoking Asari to process centroid mzML files for the first time in a PCPFM experiment, or when RT and m/z accuracy characteristics of your LC-MS instrument differ from the pipeline defaults (e.

Use when you have raw metabolomics data in mzML or mzXML format and need to extract ion features, align them across samples, and produce a normalized feature table for downstream statistical or chemotaxonomic analysis.

Use when you have LC–MS/MS data processed through MZmine2 or MZmine3 and need to construct a feature quantification table for natural product discovery pipelines (e.g., INVENTA prioritization, GNPS networking, or metabolite annotation).

Use when you have raw LCMS data in mzML format and a feature table (CSV) from a peak detection pipeline (e.g., MZmine) and need to prepare these inputs for NeatMS preprocessing, batch creation, or peak classification. This skill is the mandatory entry point for any NeatMS workflow.

Use when when you need to generate reproducible synthetic LC/GC-MS raw data files with known ground-truth peak properties (m/z, retention time, intensity) for benchmarking peak detection, feature extraction, normalization, or batch correction algorithms;

Use when when you have mass spectrometry raw data in mzML format and need to execute MassQL queries, perform batch analysis across a directory of spectra files, or programmatically access MS1 and MS2 scan data with retention time, m/z, and intensity metadata.

Use when you have peak properties (mass, intensity, retention time) for biomolecules, selected noise and fragmentation models, and instrument parameters (e.

Use when after frequency-based denoising and sample-level aggregation of replicate MS/MS spectra, when you need to export denoised spectra to a standardized, vendor-independent format compatible with spectral matching pipelines.

Use when you have raw mzML files from a mass spectrometry instrument and need to begin a preprocessing workflow in xcms. This is the essential first step before any peak detection (centWave, MSWParam) or feature grouping can occur.