Claude Skills by HolobiomicsLab

Use when you have processed LC-MS/MS spectral data (as a .mgf file with feature identifiers) and computed pairwise ms2deepscore similarity scores, and you need to create a 2-D projection suitable for dashboard visualization or high-level pattern discovery without losing similarity structure.

Use when when comparing two MS/MS spectra where the precursor m/z values differ (indicating potential mass modifications, adducts, or related compounds), and you want to detect structurally conserved fragmentation patterns that would be missed by direct m/z matching.

Use when you have an annotated or raw tandem mass spectrometry spectrum and need to identify which observed peaks correspond to expected peptide fragment ions from a known or predicted peptidoform. Use it before spectrum visualization if you want highlighted, labeled fragment matches;

Use when you have a tandem mass spectrum with observed m/z peaks and a known peptide sequence (as a ProForma string, optionally with post-translational modifications), and you want to determine which observed peaks correspond to expected fragment ions (b-type, y-type, a-type) within a specified.

Use when you have raw MS/MS spectra with variable numbers of peaks at continuous m/z values and need to feed them to a neural network (e.g., Siamese network for similarity prediction) that requires fixed-size vector input.

Use when when you have raw high-resolution tandem mass spectra (mzML, mzXML, or MGF format) that you intend to cluster or compare at scale, and you need to convert continuous m/z and intensity measurements into discrete bins suitable for feature hashing or similarity searching.

Use when you have raw LC-MS data in mzML or mzXML format and need to extract reproducible, high-quality metabolite features (m/z, retention time, intensity) for global metabolomics.

Use when when you have aligned mass tracks (extracted ion chromatograms) across multiple LC-MS samples consolidated into a composite map and need to detect reproducible elution peaks (features) that will be tracked back to individual samples.

Use when you have a 1D intensity array (e.g., a single MS1 or MS2 spectrum extracted from an MZA HDF5 file) and need to identify prominent peaks with their m/z indices and heights.

Use when when you have variable-length MS/MS peak lists (m/z and intensity arrays) that must be fed into a transformer-based model for spectra analysis, and you need deterministic, normalized embeddings that preserve peak frequency information across multiple scales.

Use when working with raw or minimally processed MS/MS spectra from repositories like GNPS that contain variable peak intensities, noise, and formatting inconsistencies that would interfere with downstream deep learning models trained on normalized spectral representations.

Use when you have raw or annotated MS/MS spectra (in MGF, mzML, or mzXML format) destined for de novo peptide sequencing with Casanovo. Use it specifically when your dataset contains variable spectral quality (e.

Use when you have MS/MS spectral data (mzML, mzXML format) and a parent mass or molecular formula, and you need to identify the metabolite(s) responsible for the observed fragmentation pattern by scoring candidates against their theoretical fragmentation profiles.

Use when you have MS/MS spectra with fragment frequency annotations (from consensus spectrum generation) and need to decide which fragments to retain versus remove. Trigger conditions: (1) you have replicate MS/MS spectra for the same feature with per-fragment recurrence frequencies calculated;

Use when after extracting raw MS/MS spectra from mzML files when you observe high fragment counts per spectrum (e.g., 98 fragments) and want to reduce noise from instrument measurement uncertainty.

Use when you have multiple replicate MS/MS spectra for the same metabolic feature (e.g., 66 top-TIC spectra for feature 1982) and need to identify robust peaks by merging nearby m/z values and pooling their signal strength.

Use when you have a molecular structure (SMILES, InChI, or chemical formula) and need to predict which fragments will appear with high intensity in a tandem MS spectrum, or when you are performing structural elucidation by ranking candidate molecules against experimental spectra and need.

Use when after loading raw m/z peak data (in MetaboAnalyst, MetaboShiny native, or Metabolights format) and merging it with sample metadata (batch IDs, concentration values, experimental group labels).

Use when when comparing a query MS/MS spectrum (e.g., from an unknown metabolite) against a library spectrum to establish correspondence between peaks. Use this skill before calculating similarity scores (cosine, entropy, Bhattacharyya) or when applying penalty factors to unmatched peaks.

Use when when you have replicate MS/MS spectra for the same feature (precursor m/z and retention time) and need to distinguish genuine fragment ions from noise.

Use when when generating synthetic LC/GC-MS .mzML files from MoNA or HMDB spectral records where you need to compute absolute ground-truth maximum intensity (sim_ins) for each peak while accounting for chromatographic band broadening, peak tailing, and retention-time dispersion.

Use when raw Agilent MassHunter (.d) or UIMF mass spectrometry files exhibit jagged or noisy peaks, particularly for low-abundance ions where signal-to-noise ratio is poor.

Use when you have a resolved mass spectrum (m/z values, intensities, and metadata) from a supported USI source (GNPS, MassBank, MetaboLights, Metabolomics Workbench, ProteoXchange, MS2LDA, or MassIVE) and need to create a publication-ready image that retains a link back to an interactive spectrum.

Use when when you have MS/MS spectra (LC-MS or equivalent positive ionization mode data) that you intend to embed using Word2Vec or similar distributional semantic models, or when you need to prepare spectral data for training similarity models that learn peak co-occurrence patterns rather than.

Use when after loading a raw MsmsSpectrum object from a tandem mass spectrometry experiment (e.g., via USI) and before intensity filtering or scaling.

Use when you have pre-trained MLP and GNN spectral prediction models evaluated on the same ESI/LC-MS test dataset, and you seek to improve average rank performance beyond either baseline model alone.

Use when when preparing raw MS2 spectra (m/z and intensity pairs) for kernel-based scoring methods such as IOKR, especially when the training dataset is large and represents diverse ion types.

Use when when you have extracted a raw Orbitrap scan from a .raw file and need to verify that the instrument operated within expected parameters and that observed peptide fragment ions rise substantially above noise—i.

Use when after MS1 extraction (coarse/fine error correction, EIC window extraction) and retention time windowing on a set of mzML files tagged with ionization mode and compound adducts.

Use when you have a query mass spectrum (or representative metabolite spectrum from public data) and need to identify it by searching against large spectral reference databases (millions to billions of spectra).

Use when after running annotateRC to generate ranked candidate annotations for LC-MS AIF features, when you need to confirm that (1) the top-ranked candidate match is chemically plausible given the observed fragment ions, (2) alternative candidate annotations exist and are correctly ranked, and (3).

Use when when you have identified a spectral window of interest in a 1H NMR spectrum from a complex biological sample (serum, urine, CSF, tissue, saliva, or sweat) and need to systematically retrieve all metabolites from HMDB whose reference proton NMR chemical shifts fall within that window.

Use when you have real LC-MS/MS data (mzML) from a complex sample (e.g., beer, metabolomics extract) and need to prototype or validate a new data-dependent acquisition (DDA) strategy—such as Top-N fragmentation—before deploying it on physical instrumentation.

Use when you have extracted MS1 and MS2 scans in mzML/mzXML format from raw chromatogram files and a structured metadata file (containing retention time, m/z, compound name, molecular weight, and annotation fields), and you need to pair each scan set with its corresponding chemical record to build.

Use when you have executed multiple database search pipelines (Dereplicator, VarQuest, and/or Dereplicator+) on centroided LC-MS/MS spectra (in MGF, mzXML, mzML, or mzData format) against a chemical structure database of known natural products, and you need to: (1) identify which pipeline(s).

Use when when you need to understand or modify how MS2Query routes query spectra through its dual-pathway architecture, or when integrating MS2Query into another tool and need to trace how spectral similarity scores (MS2Deepscore) feed into library-match versus analogue-search branches with.

Use when after inferring Mass2Motif definitions from LDA modeling when you need to build a network representation of motif relationships.

Use when when you have processed LC-MS/MS spectral data in .mgf format with feature identifiers and need to compute a pairwise similarity matrix to support interactive exploration.

Use when when you have computed a sparse pairwise distance matrix from nearest neighbor indexes of high-resolution MS/MS spectra and need to partition them into clusters such that spectra within each cluster correspond to similar fragmentation patterns (e.g., same peptide or metabolite).

Use when when you have experimental MS/MS spectra (from mzML or .rda preprocessed format) and need to annotate them against a reference fragmentation library.

Use when after extracting and optionally combining MS2 spectra from a chromatographic peak (e.g., at a known m/z value like 304.1131), you need to determine which compound(s) in a reference library match the experimental spectrum.

Use when after preprocessing and filtering mass spectra (peak filtering, metadata cleaning) when you need to compare all spectrum pairs within a dataset or between a query set and a reference library to identify similar or related spectra.

Use when you have MSMS spectra from two or more compounds and need to identify which are structurally related. Use this skill when you want to rank spectrum pairs by similarity to discover novel analogs or validate structural assignments in untargeted metabolomics or natural products discovery.

Use when when you have detected LC-MS/MS features (MS1 peaks with MS2 fragmentation spectra) from untargeted metabolomics experiments and seek to organize them into a chemical hierarchy for comparative metabolomic analysis.

Use when after acquiring MS/MS spectral data from untargeted metabolomics experiments and having candidate transformed structures from biotransformation rule application.

Use when after feature detection and alignment across LC-MS/MS runs (via MZmine2 or Optimus) have produced a feature quantification table and MGF file with MS/MS spectra, and you need to discover molecular relationships and detect unknown compounds through spectral clustering and library matching.

Use when when you have paired MS/MS spectra (unknown and known metabolites) with annotated structural similarity labels, and you need to rank candidate structures for metabolite identification.

Use when when you have paired MS/MS spectra with known structural similarity labels (Tanimoto scores from molecular fingerprints) and need to predict structural similarity for new spectrum pairs faster than fingerprint-based methods, or when you want to assess model prediction confidence per.

Use when you have a query MS/MS spectrum and need to identify the -matching library spectrum from a large spectral database, particularly when the research goal requires distinguishing between exact matches and structural analogues without separate workflows.

Use when when you have pairs of MS/MS spectra (in mgf, msp, mzml, mzxml, json, or usi format) and need to retrieve structurally related compounds or rank spectral similarity on a continuous scale (Tanimoto prediction).