Claude Skills by HolobiomicsLab

Use when you have a trained graph neural network model for CCS prediction and need to identify which molecular structural features drive individual predictions or systematic biases.

Use when you have a collection of MS/MS spectra (stored as Spectrum2 objects in an ms2Lib class) and need to identify which spectra share identical fragmentation patterns—particularly when coupled to a GNPS molecular network to focus on explaining network components (connected components, cliques.

Use when you have a GNPS mass spectral molecular network and wish to annotate its nodes with both chemical class assignments (from GNPS public library matches) and MS2LDA-derived substructural motifs (from classical or feature-based LDA experiments) in a single integrated operation, typically for.

Use when you have a baseline GNN model trained on a molecular property prediction task (e.

Use when you have 1D or 2D NMR spectra (1H and/or 13C) and need to predict unknown molecular structure (formula and connectivity) up to ~19 heavy atoms; or you have a set of molecular fragment-structure pairs and need to model how fragments assemble into complete structures.

Use when you have a trained GNN model (stored as .h5 weights) and molecular graph representations (SMILES strings and/or 3D coordinates), and you need to compute predicted CCS values or perform feature importance analysis via ablation or gradient-based saliency mapping.

Use when you have statistically significant LC-MS features grouped into structural clusters (isotopologue groups, adduct groups, cross-assay links) and correlation cluster assignments from upstream MamsiStructSearch, and you need to create an interactive graph representation suitable for Cytoscape.

Use when after constructing a network graph where nodes represent Mass2Motifs (or spectra) and edges encode pairwise spectral similarity scores, and you need to export the network for visualization, post-processing, or sharing with collaborators using standard graph software (e.

Use when after constructing feature tensors encoding atom adjacency matrices, bond types, and chemical properties from canonical SMILES—and before feeding graphs into a GNN training loop—to enable reproducible, portable, and memory-efficient storage of graph objects that will be loaded in batches.

Use when you have constraint-based metabolic models with integrated transcriptomics (gene expression), intracellular metabolomics (substrate concentrations), and extracellular flux measurements (glucose uptake, lactate production, etc.), and you need to test whether differential expression of.

Use when you have mass spectrometry feature data stored in HDF5 format (.h5 files) and need to load specific dimensional columns (m/z, drift time, retention time, intensity) for multi-dimensional alignment, CCS calibration, or isotope detection.

Use when you have raw or peak-picked mass spectrometry data in HDF5 format that needs to be loaded into memory for downstream processing (feature alignment, isotope detection, CCS calibration), or when you need to export annotated feature tables with isotopologue metadata back to HDF5 for archival.

Use when when you need to work with mzMLb (HDF5-based) proteomics data in pyteomics and want to confirm that the required h5py and hdf5plugin libraries are installed and accessible, or when troubleshooting ImportError or missing format handler issues related to mzMLb modules.

Use when after invoking the DEIMoS CLI with a configuration file and allowing the Snakemake workflow to execute, use this skill to confirm successful completion of all workflow rules.

Use when when implementing or reverse-engineering a custom binary file format (e.

Use when you have a pre-computed hierarchical dendrogram from correlation-based clustering of LC-MS features (with fixed linkage criterion and distance metric) and need to decide whether a single constant-threshold cut or data-driven silhouette optimization better resolves the underlying cluster.

Use when your input is a tabular file (CSV or Excel) with column headers annotated using MESSES tagging syntax (#<table_name>.id for record identifiers and #.

Use when immediately after parsing and validating raw LC-MS/MS data files (mzML, mzXML, or vendor formats) when you need to prepare spectral data for fragmentation tree computation, isotope pattern analysis, or molecular formula ranking within the SIRIUS framework.

Use when when you have millions of high-dimensional objects (e.g., MS/MS spectra converted to feature-hashed vectors) and need to compute pairwise similarities or retrieve nearest neighbors efficiently.

Use when you have acquired high-resolution MS/MS spectra in mzML, mzXML, or MGF format and need to prepare them for large-scale clustering or similarity searching.

Use when you have centroided LC- or GC-HRMS data (in mzML format, ideally from data-dependent acquisition) and need to identify potential PFAS candidates from a large feature list.

Use when you have downloaded raw HMDB data (hmdb_metabolites.zip or pickle file) and need to generate a representative set of chemical objects for simulating LC-MS/MS acquisition strategies.

Use when you have raw or processed HRMS/MS data from Q-Exactive, Agilent Q-TOF, Bruker Q-TOF, or SCIEX Q-TOF instruments in formats such as mzML, CSV peaklists, or vendor-specific formats, and you need to extract experimental fragment m/z values and their intensities for comparison against.

Use when you have LC- or GC-HRMS data in mzML format and a feature list (CSV/TSL/Excel) from external feature detection software (e.

Use when you have deployed a microservice (e.g., TensorFlow Serving, REST API) and need to verify that specific endpoints (e.g., /model/metadata, /classify) return responses with correct schema, field names, and data types before consuming them in production workflows or downstream applications.

Use when you need to confirm that a documented web service URL is live and reachable before attempting to submit analysis jobs, download results, or integrate the service into an automated pipeline. Use it as a prerequisite check when the service documentation claims academic or public availability.

Use when when you have source code access to a webservice component (such as the MAGMa joblauncher) and need to enumerate all exposed HTTP endpoints, their methods (GET, POST, etc.), URL patterns, parameter names, request/response payload structures, and authentication requirements in order to.

Use when you have NMR peak data (1H and 13C chemical shift values) that must be submitted to a remote DeepSAT SMART 3 classification API for structural prediction, and you need to format the data correctly, validate the endpoint schema, and parse the response to extract predictions and confidence.

Use when when you have raw strain correlation scores (or similar overlap-based metrics) computed across genomic cluster family (GCF) and molecular family (MF) pairs of varying sizes, and you need to make those scores comparable across links with different GCF sizes (#G), MF sizes (#m), and.

Use when when training a fresh NeatMS CNN model from scratch on LCMS peak classification and you need to determine which optimizer (Adam vs. SGD) and learning rate will produce an AUC ROC > 0.9 without overfitting.

Use when you have mzML mass spectrometry files that need both compression and rapid random access by spectrum ID (e.g., direct retrieval of spectrum 2540 without sequential scanning).

Use when when implementing an igzip parser, decoder, or validator that must interpret the custom header format; when debugging igzip file corruption or encoding errors; or when extending pymzML's igzip support to handle new index schemes.

Use when when you have IM-MS lipidomics data acquired on samples spiked with U13C-labeled internal standards (fully labeled yeast extract) and need to quantify systematic CCS bias and apply lipid class-specific bias correction to all measured CCS values, particularly when multiple lipids per lipid.

Use when you have candidate library matches from MS2Deepscore ranking (top 2000 spectra per query) with InChIKey annotations, and need to quantify structural similarity between query and candidate compounds to inform downstream match ranking and filtering by MS2Query's random forest model.

Use when you have trained two or more graph neural network models on the same CCS dataset split (using identical hyperparameters, loss functions, and optimization settings) and need to rigorously compare their held-out test performance to determine which architecture balances prediction accuracy.

Use when you have a Sciex Multiquant TXT export file containing a metabolomics or lipidomics analytical sequence and need to locate QCpool samples that were injected at regular intervals, validate their spacing matches study design expectations, and compile structured metadata for downstream.

Use when apply IOKR when you have BGCs with structural predictions based on MIBiG homology (cumulative BLAST score ≥10,000) and you wish to rank hypothetical BGC–spectrum links using metabolite structure information rather than genomic or strain-based features alone.

Use when when setting up matchms for the first time in a new environment, after upgrading Python or conda, when switching between package managers (pip vs conda), or when distributing matchms to end users to confirm functionality across supported installation channels.

Use when after installing a package via conda or pip from a distribution channel (e.g., Bioconda, PyPI), run this skill to confirm the installation succeeded and that critical submodules are importable before proceeding to use the package in analysis workflows.

Use when when deploying a new Python package in a reproducible analysis environment or continuous integration pipeline, and you need to confirm that all required core modules (e.g., pyteomics.mass, pyteomics.pepxml, pyteomics.mzid, pyteomics.tandem, pyteomics.

Use when when preprocessing a heterogeneous spectral library (e.g., GNPS public library) that contains spectra from multiple instrument types, and you need to partition data by a single instrument class to train or evaluate a formula-prediction model.

Use when when adopting a mass spectrometry data processing tool (e.g., LipidMatch) and needing to verify whether your specific instrument platform (vendor + model) and acquisition mode combination (targeted, ddMS2-topN, AIF, direct infusion, imaging) have been formally validated.

Use when you have a time-series of repeated QCpool (pooled quality control) injections measured at regular intervals during one or more LC-MS/MS sequences, exported from Sciex Multiquant software (v3.0.

Use when when you have obtained a raw Orbitrap mass spectrometry file and need to verify that the instrument was configured as claimed in the methods section or dataset documentation—especially before investing in peptide fragmentation analysis, spectrum library matching, or quantitative proteomics.

Use when augmenting mass spectrometry ion images in ISO mode (isotope ions from the same molecule) and you need to simulate intensity-dependent data loss that reflects real detector behavior where lower-intensity pixels are more likely to be missed or undetected.

Use when processing raw MS intensity tables from long measurement sequences where you observe systematic, time-dependent changes in signal magnitude (e.g., progressive increase or decrease in peak intensity across a run).

Use when when working with raw or filtered MsmsSpectrum objects where peak intensities span a wide dynamic range and need to be normalized for downstream spectrum comparison, database matching, or publication-quality visualization.

Use when you have loaded a raw or partially processed MsmsSpectrum object and need to reduce spectral noise before annotation, matching, or visualization. Use it especially when spectra contain many weak peaks (e.

Use when you have raw MS intensity data paired with measurements from known concentration standards, and you need to produce absolute quantified concentration values rather than relative intensity measurements.

Use when after applying batch correction (e.g., via pycombat) to a multi-batch feature table, to validate whether the correction has reduced systematic intensity differences between batches.