Claude Skills by HolobiomicsLab

Use when after MS1 feature extraction and prescreening quality control have completed on mzML files, and you need to inspect the MS2 fragmentation patterns of candidate compounds to verify their identity or assess whether extracted features are genuine metabolites rather than noise or artifacts.

Use when you have raw MS/MS spectra from public repositories (e.

Use when when you have raw LC-MS or LC-IMS-MS data in instrument format (Agilent .d, Thermo .raw, Bruker .

Use when you have a large collection of tandem mass spectra (mzML, mzXML, or MGF format) and want to group similar spectra into clusters to identify redundancy, discover novel peptides or metabolites, or prepare data for downstream annotation.

Use when when you have raw predictions from a trained fragment generation or intensity prediction neural network model and need to convert those predictions into a standard spectrum file format (m/z–intensity pairs) for comparison against experimental spectra or for structural elucidation workflows.

Use when you have aligned features characterized across multiple dimensions (m/z, drift time, retention time) and need to: (1) resolve MS/MS spectra that may contain fragments from multiple co-eluting or co-mobilizing precursors; (2) identify and validate isotopic signatures (e.

Use when preparing tandem MS/MS datasets for cross-dataset similarity analysis or spectral matching, particularly when datasets originate from different instruments, acquisition dates, or sample preparation protocols that may introduce systematic variations in peak intensities.

Use when when you have raw or instrument-native tandem mass spectrometry data (MS/MS) in formats such as mzML, mzXML, or proprietary binary formats, and you need to align, match, or compare spectra using methods like SIMILE that require structured access to precursor m/z, fragment m/z values, and.

Use when you have a molecular structure (SMILES, InChI, or chemical formula) and need to predict its collision-induced dissociation (CID) tandem mass spectrum with fragment-level resolution. Use this when chemical-formula-level predictions (e.

Use when you have acquired raw MS/MS spectra (in MGF or mzML format) from a mass spectrometry instrument or public repository (e.g., MassIVE, MetaboLights, GNPS) that will be used for de novo chemical formula ranking or adduct assignment.

Use when you have an unknown tandem MS/MS spectrum (precursor m/z and fragment peaks) and need to infer the molecular formula and ionization mode (e.g., [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+) in a de novo setting without access to spectral libraries.

Use when importing MS/MS spectral libraries (particularly from MoNA or GNPS) where SMILES or chemical structure identifiers are embedded in free-text or non-standard Comment fields rather than in dedicated SMILES/InChIKey fields, or when positive and negative ionization mode spectra are commingled.

Use when after importing raw peak tables from tandem MS/MS preprocessing software (e.

Use when when you have raw feature tables exported from a tandem LC-MS/MS preprocessing tool (e.g., Progenesis QI, MS-DIAL, Bruker Metaboscape) and need to combine them with sample metadata (group assignments, replicate structure) before applying feature filtering or quality control workflows.

Use when you have received spectrum predictions (fragment masses and intensities) from a neural model (ICEBERG, SCARF, or similar) and need to extract structural information, rank candidate molecules, or validate predictions against experimental spectra.

Use when you have untargeted MS2 spectral data in MS2MP-compatible format and need to assign KEGG pathway annotations to spectra without spectral library matching or manual compound identification.

Use when when preparing paired MS/MS spectra for training or validation of a siamese neural network model, and you have chemical structure annotations (InChI, SMILES, or InChIKey) for each spectrum but lack pre-computed structural similarity labels.

Use when when you have a set of MS/MS spectra with ground-truth structural similarity labels (Tanimoto scores computed from molecular fingerprints) and need to choose a decision threshold for classifying spectrum pairs as 'chemically related' or 'unrelated'.

Use when you have a trained MS2DeepScore neural network and a set of MS/MS spectra (52 binned peaks per spectrum after preprocessing) for which you need to compute pairwise structural similarity predictions.

Use when when you have paired mass spectrometry spectra (e.g., from GNPS, MoNA, MassBank, or MSnLib) and need to predict continuous structural similarity scores (0–1 range) between them, especially when traditional spectral-distance metrics (e.

Use when you have a CSV-formatted target list with m/z, retention time, or ion mobility identifiers and need to locate and extract peak abundances from raw MS data files (Agilent .d, Thermo .raw, Bruker .d, mzML) acquired across LC-MS, LC-IMS-MS, DDA, DIA, or direct infusion modes.

Use when you have LC-MS data (mzML or netCDF format) and a predefined list of target metabolites with known m/z values and retention time windows that you wish to extract and quantify.

Use when when you have raw diaPASEF mzML files, a transition list with target analytes (protein, peptide, charge state), and search results (DIA-NN, OpenSwath output) containing feature metadata (retention time, ion mobility, m/z coordinates), and you need to isolate and visualize signal for.

Use when you have a curated target list of m/z values, retention times, and identifiers for specific metabolites of interest, and you want to extract only those features from LC-MS data (mzML or netCDF format) rather than performing untargeted feature discovery.

Use when when you have centroided .mzML LC–MS runs and a target list (compound ID, theoretical m/z, expected RT, polarity) but are uncertain whether your m/z and RT windows are wide enough to capture all targets without false positives.

Use when you have centroided LC-MS data (.mzML format) and a curated list of targeted metabolites or lipids (with m/z, retention time, and polarity) that you want to quantify and quality-assess across multiple analytical runs, and you need both per-run AUC values and averaged QC metrics for each.

Use when you have targeted metabolomics data with peak area intensities organized in rows (samples) × columns (compounds), accompanying sample metadata indicating which samples are blanks, calibration curve points, or QC samples with known concentration values, and a compound legend assigning.

Use when you have centroided mzML LC–MS data, a curated list of target compounds (with theoretical m/z, expected retention time, and polarity), and you need to confirm target presence and extract quantitative metrics (area under curve, max intensity, signal-to-noise ratio, peak correlation, point.

Use when you have raw MS data in a supported instrument format (Agilent .d, Thermo .raw, Bruker .d, mzML) and a predefined list of molecular targets (CSV with m/z and/or retention time) that you need to quantify.

Use when when performing targeted quantification of known compounds in LC-MS data using TARDIS, especially when the instrument acquired data with multiple overlapping m/z scan windows.

Use when you have loaded transition group chromatogram data from sqMass files and need to restrict the analyte selection dropdowns (protein, peptide, charge state) to only those features passing a specified Q-value threshold (default 1%), or when you need to selectively display or hide MS1 and MS2.

Use when you have a set of lipid targets defined by species name, acyl chain composition, and expected adducts, and you need to configure a targeted mass spectrometry workflow (PRM or MRM) in Skyline.

Use when you have a feature table with candidate metabolite annotations (m/z, retention time, chemical identifiers) and MS/MS spectra, and you know the organism or taxon of origin for your samples.

Use when a paired omics project record contains a genome identifier (e.g., from GenBank or NCBI) but lacks the corresponding organism scientific name.

Use when when preparing a metadata table (TSV format with species, genus, and family columns) for natural product metabolomics analysis where the Literature Component score must query known compounds by taxon.

Use when when reproducing or auditing FIDDLE's formula prediction pipeline, or when implementing the TCN encoder in your own codebase and need to confirm that the precursor m/z (env[:, 0]) has been removed from the feature vector to avoid leakage of mass information into the model's learned.

Use when you have tandem MS data with technical replicates and need to remove features showing high variability between replicates.

Use when your LCMS metabolomics dataset exhibits run-order-dependent intensity drift (signal decay or gain over the course of a sample batch), you have pooled technical replicates (identical biospecimen injected multiple times across the run sequence) and/or known internal standard compounds, and.

Use when after merging feature tables from non-targeted LC-MS/MS data and before statistical analysis, when samples were acquired across multiple instrument runs, different days, or instrumental calibration cycles.

Use when you have time-resolved direct injection mass spectrometry data (e.

Use when you have two embedding tensors of identical shape (e.g., both 512-dimensional) and need to produce a fused representation that captures multiplicative interactions between modalities.

Use when when you have raw MS/MS spectral data in the form of intensity arrays indexed by m/z values and need to feed them into the Spec2Mol encoder neural network. Apply this skill before encoder inference to ensure spectral inputs conform to the encoder's expected dimensionality and value ranges.

Use when deploying Mass2SMILES on a TensorFlow-CPU build and you need to optimize inference throughput on multi-core systems. This is particularly necessary when GPU inference is unavailable due to CUDA driver incompatibility, or when inference hardware has variable core counts (e.

Use when when you have a peptide sequence and need to predict its fragment ion spectrum for stable isotope labeling validation, particularly when comparing against observed mass spectrometry data with natural or enriched isotopic abundance (e.g., 1% or 50% 13C incorporation).

Use when when processing mass spectrometry data from stable isotope probing (SIP) experiments where peptides contain known levels of heavy isotope incorporation (13C, 15N, 2H, 18O), and you need to annotate observed MS2 peaks by matching them to theoretical B and Y ion fragments.

Use when you have a feature table from untargeted LC-MS (m/z, retention time, intensity) and need to annotate which observed m/z values correspond to isotopologues and adducts of the same neutral compound.

Use when you have a defined set of lipid species (identified by class and fatty acid composition) and need to create a high-throughput spectral library for mass spectrometry-based lipid identification.

Use when when you have a Thermo Fisher Scientific .

Use when you have acquired .raw files from a Thermo mass spectrometer (e.g., Q Exactive, Orbitrap) and need to expose their contents—scan numbers, retention times, m/z values, intensities, and precursor information—for downstream nontargeted LCMS feature detection and alignment.

Use when you have acquired multidimensional mass spectrometry data (MS1, MS/MS, or data-independent acquisition) from a Thermo instrument saved in the proprietary '.