Claude Skills by HolobiomicsLab

Use when you have raw metabolomics mass spectrometry data in mzML or mzXML format and need to extract, align, and normalize metabolic features across multiple samples or conditions.

Use when you have a metabolomics matrix with metabolites as rows and samples as columns, each sample labeled with one of two experimental group identifiers (e.

Use when when you have cloned or accessed the Reverse_metabolomics_library_generation repository and need to verify that the Nextflow workflow is properly configured, executable, and produces expected spectral library outputs.

Use when you have raw untargeted metabolomics data in mzML, mzXML, or CDF format from qTOF, Orbitrap, or FTICR mass analyzers, at least 3 samples, a sample metadata spreadsheet linking filenames to experimental factors, and need to generate optimized processing parameters for XCMS or MZmine2.

Use when after completing outlier detection, batch correction, and quality metric calculation on a SummarizedExperiment object using mzQuality's doAnalysis function, and after manually or automatically filtering compounds and samples using the 'use' column in rowData and colData.

Use when you are curating metabolomics datasets with variable column naming conventions and need to detect, normalize, and populate standardized database-ID columns (HMDB_ID, PubChem_ID, KEGG_ID, etc.) across many mwTab files before deposition.

Use when when importing raw mass spectrometry data from files in supported formats (mzML, mzXML, msp, MGF, JSON, metabolomics-USI) and you need to extract and standardize metadata fields so that spectra are ready for metadata cleaning, validation, and comparative analysis.

Use when you have received new or updated MassBank records (in plain-text or structured format) that must be integrated into the MassBank-data repository and you need to ensure they conform to the MassBank format specification before acceptance.

Use when after loading a metadata file but before merging it with positive and negative mode m/z peaklists. Apply this skill when you have a candidate metadata table (e.

Use when a metadata table contains compound names and identifiers but lacks structural data (SMILES, InChI, or molecular formula). The compounds are publicly available in PubChem and can be reliably identified by their chemical names. Use this skill before performing structure-dependent analyses (e.

Use when you have mzML-format raw data files from mass spectrometry experiments and need to ingest them into MS-DIAL for untargeted metabolomics or lipidomics analysis.

Use when when you have experimental metadata (e.g., sample annotations, plate layouts, compound lists) with inconsistent or missing column names, non-standard field formats, or incomplete information required for downstream database queries (PubChem, DrugBank, LOTUS) or sequence generation for mass.

Use when your metabolomic dataset contains missing values (common in untargeted or targeted mass spectrometry data) and you need to perform PCA for outlier detection at multiple standard deviation thresholds (e.g., 3 SD, 4 SD, 5 SD) on principal component scores.

Use when you are implementing a custom MsBackend subclass for the Spectra package and need to ensure that spectraData() returns all core spectra variables (e.g., centroided, polarity, collisionEnergy) regardless of which ones are explicitly stored in your backend.

Use when you have a pre-trained MSGO model checkpoint (PFAS or lipid variant) and need to evaluate it against a real mass spectrometry dataset (300+ real spectra, LC–QTOF, or custom CSV) to generate predicted molecular structures and compare against ground truth or baseline results.

Use when releasing a new version of a Python package, validating packaging infrastructure changes, or confirming that distribution channels (PyPI, Bioconda) remain functional after upstream updates. Use it as a gate before finalizing a release to catch installation or import breakage early.

Use when when a major version release (e.g., v1.x → v2.0.0) deprecates a core neural module class, and new equivalent modules must be designed and integrated without breaking downstream prediction pipelines. Triggered by breaking changes in CHANGELOG or deprecation warnings in model initialization.

Use when after molecular formulas have been assigned to detected peaks (via CoreMS, Formularity, or equivalent) and you are constructing biochemical transformation networks where node interpretation requires understanding what chemical classes are being transformed.

Use when you have a formula-assigned FT-ICR MS dataset (CSV or tab-delimited table with molecular formulas and mass values) and need to quantify the structural diversity, elemental stoichiometry patterns, or complexity landscape of the organic mixture.

Use when when you have a query mass spectrum and a set of candidate molecular structures (as SMILES or 2D/3D coordinates), and you need to prepare them for cross-view similarity comparison or machine learning-based ranking.

Use when when you have labeled mass-spectrometry spectral data (precursor m/z and fragment m/z–intensity pairs) paired with known molecular structures (as InChIKeys or SMILES), and need to perform metabolite annotation by ranking candidate compounds based on spectral similarity.

Use when you have a calibrated FT-ICR transient (ESI_NEG or similar ionization mode) and need to annotate each detected m/z peak with its most likely elemental composition.

Use when after molecular formula assignment has been completed on detected peaks in a processed mass spectrum object.

Use when you have received a formula-assigned FT-ICR MS dataset (CSV or tab-delimited table containing molecular formulas and mass values) and need to convert those formula strings into quantified elemental compositions before computing molecular descriptors, diversity indices, or transformation.

Use when you have filtered FT-ICR MS peak data with valid molecular formula assignments (C, H, O, N, S, P elemental counts) and need to quantify molecular properties that predict metabolite reactivity, bioavailability, and biochemical role.

Use when you have a recalibrated FT-ICR mass spectrum (Bruker .d format or equivalent) with detected, noise-thresholded peaks and need to assign chemical formulas to each peak. This is particularly relevant when analyzing samples with unknown composition (e.

Use when when you have paired mass spectra and molecular structure data and need to train a model that can bidirectionally map between experimental spectra and chemical structures.

Use when when you have molecular structures encoded as SMILES strings and need to incorporate them into a multi-modal language model (such as BART) that also processes mass spectra.

Use when after completing the MS2LDA LDA modeling step when you have a JSON-serialized inferred motifset (Mass2Motifs with fragment and neutral-loss patterns) and need to annotate those motifs by comparing them against a curated MotifDB reference database to identify known structural subpatterns.

Use when you have raw MRM lipidomics export files in vendor-specific formats (e.g., TSV or CSV from a mass spectrometry instrument) and need to convert them into a standardized tabular format before performing lipid identification, statistical analysis, or visualization.

Use when you have MS data in a new format or storage system (e.g., a custom database, HDF5 file, or proprietary raw file) and need to make it accessible to Spectra-based analysis workflows without forking the Spectra package itself.

Use when implementing or validating a new MsBackend class that stores m/z and intensity values, or when assigning peak data to an existing backend. Triggers include: (1) implementing a replacement method (e.g., mz<- or intensity<-) for a backend class;

Use when you have raw breath HRMS data in mzML or mzXML format and need to extract volatile organic compound (VOC) features as a standardized CSV table indexed by m/z value, with columns for scan time or sample identifiers and corresponding intensity measurements.

Use when you are preparing to run LipoCLEAN on MS-DIAL output and need to create or update a configuration file, or you have switched between MS-DIAL 4 and MS-DIAL 5 data and need to verify that your options file and trained model are compatible with the current version's column naming and scaling.

Use when you have raw mass spectrometry data files from a mass spectrometer instrument and need to feed them into a peptide feature detection pipeline (e.g., IsoFusion) that accepts only MS1 format input.

Use when you have raw MS intensity data paired with known-concentration calibration standard measurements, and you need to convert intensities to absolute or relative concentrations.

Use when you have loaded raw MS intensity tables into QuantyFey and observe or suspect intensity drift artifacts across your measurement sequence. Drift is especially likely in long-running targeted MS experiments where calibration curves or internal standards show systematic variation over time.

Use when when you have loaded raw MS1 data from multiple instrument formats (Agilent, Thermo, Bruker, mzML) across a multi-sample cohort and need to prepare the ion intensity feature matrix for PCA analysis or cross-sample quality assessment.

Use when you need to create a new backend to integrate MS data from a novel file format, database, or in-memory storage system into the Spectra ecosystem. Use this skill when existing backends (MsBackendMemory, MsBackendMzR, MsBackendSql, etc.) do not support your data source or storage paradigm.

Use when when you need to convert vendor-specific raw mass spectrometry files (.raw) to the open mzML format using imzML Writer, and msconvert is not yet installed or its location is not recognized by the system.

Use when after peak alignment with peakAlign(), when you have an MSImagingExperiment with many detected peaks but want to retain only those present in a sufficient fraction of pixels.

Use when when you have successfully resolved a USI string to extract raw spectrum data from an online proteomics/metabolomics repository (PRIDE, MassIVE, etc.) and need to construct a spectrum object that exposes spectrum data as Python attributes and methods for downstream processing (filtering.

Use when you have raw .msp files containing mass spectra records and need to extract spectrum identifiers (compound name, precursor mass, retention time) as structured data for enrichment via external web services, or you have enriched spectrum objects and must write them back to .

Use when you have one or more .msp spectral library files (NIST format) that need to be ingested for metadata curation, enrichment via web services, or export after transformation. Use this skill as the entry and exit point for any .msp-based annotation or analysis pipeline.

Use when when you have a suite of Sphinx gallery example scripts targeting multiple plotting library backends and need to verify that all examples execute successfully within expected time constraints and produce output across matplotlib (static), bokeh (interactive), and plotly (interactive).

Use when you have raw metabolomics data files in one or more of the supported formats (.raw from Thermo instruments, .d directories from Agilent, or mzXML open-format exports) and need to ingest them into SMART for preprocessing, visualization, or statistical analysis.

Use when when you need to support multiple plotting library backends (static or interactive) for the same data visualization domain (e.

Use when you need to evaluate whether a newly released or candidate library (e.g., spectrum_utils v0.4.

Use when you have high-dimensional biological data (e.

Use when training neural network models (MLP or GNN) for metabolite annotation on mass spectrometry data and you have access to a large unlabeled or weakly labeled spectral dataset.