Claude Skills by HolobiomicsLab

Use when you have raw profile LC-MS data in .mzML format and need to prepare it for targeted or untargeted peak detection.

Use when when you have a real mzML file from an untargeted metabolomics LC-MS/MS experiment and need to extract the chemical features it contains—either to simulate a data-dependent acquisition (DDA) strategy on those same compounds, to benchmark different fragmentation controllers, or to reproduce.

Use when you have raw LC- or GC-HRMS data from vendor instruments (ESI or APCI ionization) that needs to be converted to a vendor-neutral format for non-target screening, or you already have mzML files that require loading into a Python environment for downstream feature detection and MS2 spectral.

Use when after running an Environment simulation in ViMMS that has generated MS1 and/or MS/MS scans from a virtual mass spectrometer and controller pair. Use this skill when you need to preserve the generated scans in a standard format compatible with existing metabolomics software (e.

Use when after completing a virtual LC-MS/MS acquisition simulation using ViMMS (e.g., after calling env.

Use when after running a ViMMS simulation loop with a fragmentation controller (e.

Use when after executing smiter.synthetic_mzml.write_mzml to generate synthetic LC-MS/MS runs from nucleoside or peptide fragmentation models.

Use when after downloading an mzML file from a remote repository (e.g., MetaboLights, MassIVE, GNPS) via USI resolution, before attempting to parse it into a spectrum container or visualization dashboard.

Use when you have raw LC-HRMS metabolomics data in mzML or ABF format that needs to be processed through a reproducible pipeline. Use this skill when: (1) you have public or proprietary .mzML LC-MS datasets (e.g. from MetaboLights, MassIVE, or PRIDE);

Use when your raw LC-MS data are in vendor-specific binary formats (e.g., .raw, .d, .

Use when you have raw LC-MS/MS data in mzML or mzXML format and need to isolate specific MS1/MS2 scan pairs for a targeted compound list or for building a local spectral library.

Use when you have mzML-format raw data files (from any mass spectrometry vendor or conversion tool) and need to ingest them into MS-DIAL version 5 or later for untargeted metabolomics or lipidomics analysis.

Use when when beginning a metabolomics annotation workflow with raw MS2 spectral data in .mzML format. This step is necessary when you have vendor-converted or standard .

Use when your input is an mzML file (XML-based mass spectrometry data format) and you need to expose spectral metadata, scan information, and ion data in a structured, programmatic form for alignment, clustering, drift correction, or quantification within the BMXP pipeline.

Use when after Casanovo has generated ranked peptide sequence predictions from MS/MS spectra and you need to persist, share, or integrate the results into a proteomics data management or visualization pipeline.

Use when after completing peak detection, MS1 feature picking, and accurate mass database search (e.g., against HMDB) on FIA-MS or LC-MS(/MS) data.

Use when you have LC-MS fractional abundances of measured isotopologues (FAM) from a stable isotope labeling experiment and need to recover the true mass distribution vectors (MDV) that reflect only the contribution from the isotopic tracer. Use this skill when naturally occurring isotopes (e.

Use when gNPS has ceased supplying ClassyFire ontology information for spectral library matches, causing downstream ConCISE consensus classification to fail or produce incomplete ontology fields.

Use when you have LC-MS/MS DDA metabolomics data (positive and/or negative ionization modes) and sample metadata (originating taxon) for one or more samples, and you need to generate a Wikidata-connected RDF knowledge graph for integrated natural products analysis, taxonomy-aware compound.

Use when you have raw fractional abundances of measured isotopologues (FAM) from LC-MS instruments in an isotope labeling experiment and need to correct them to obtain true mass distribution vectors (MDV) reflecting only the contribution from the isotopic tracer.

Use when processing LC-MS metabolomics studies with >10 samples where sample count and memory constraints make pairwise mass alignment infeasible.

Use when you have extracted mass tracks (EICs) from individual samples at 0.001 amu m/z resolution and need to align them into a composite mass grid for feature detection.

Use when when you have millions of high-resolution MS/MS spectra converted to low-dimensional vectors (via feature hashing) and need to compute a sparse pairwise distance matrix for downstream density-based clustering.

Use when you have millions of MS/MS spectra to cluster and have already constructed nearest neighbor indexes (partitioned Voronoi diagrams of spectrum vectors bucketed by precursor m/z).

Use when you have negative-mode MS/MS spectra with annotated molecular formulas and negative adducts (from repositories like MassIVE or MetaboLights), and your current formula inference model is restricted to positive mode only.

Use when when XCMS or other DTW-based aligners have produced misaligned LC-MS feature groups across hundreds of samples or long acquisition periods (>1 week), particularly when individual m/z bins or compounds show inconsistent retention-time drift patterns across neighboring samples.

Use when after library-matching has produced ranked candidate spectra with MS2Deepscore embeddings.

Use when you have an untargeted metabolomics feature table with m/z values, retention times, intensity measurements, and p-values from statistical testing, but lack or wish to bypass metabolite identification.

Use when when you have m/z values from spatially-resolved mass spectrometry imaging (MSI) and need to predict their molecular formulae with high precision.

Use when you have a GNPS GraphML molecular network and need to isolate cohesive subsets of spectra (components) before analyzing which fragmentation patterns explain them.

Use when after clustering and filtering KEGG candidates for LC-MS features, when you have a ranked set of candidate metabolites per feature and access to a metabolite interaction network (e.g., from FELLA).

Use when after completing dereplication and cosine similarity clustering in the MolNotator pipeline, when you have finalized molecular network data with molecule–ion relationships and need to visualize, analyze, or share the network in external software.

Use when you have a molecular network graph exported from GNPS (as GraphML, JSON, or adjacency format) and separate experimental data (bioassay activity matrix, feature quantification table, or MS/MS annotations) indexed by feature ID, retention time, or m/z.

Use when when you have completed an initial ModiFinder analysis on a compound pair (known compound + modified analog with unknown structure), and you subsequently acquire or determine the structure of the modified compound.

Use when you have constructed a NetworkX graph with LC-MS features as nodes and need to annotate each node with metadata derived from the MamsiStructSearch output (assay source, isotopologue group, adduct group, structural cluster ID, correlation cluster ID, and optional compound annotation).

Use when you have an untargeted metabolomics dataset with a two-layer network topology already constructed (one layer representing biochemical knowledge/pathways, the other representing data-driven MS2 similarity), seed metabolites with reliable annotations from database matching or curation, and.

Use when after executing a molecular networking workflow on GC-MS data that has been processed through auto-deconvolution, and a published reference network exists from a prior analysis of the same or analogous dataset.

Use when you have preprocessed MS/MS spectra pairs (unknown and known metabolites) with annotated structural similarity labels, and you need to learn a generalizable model that can rank candidate structures for novel unknowns by predicting their similarity to reference compounds in a database.

Use when you have raw mzML files and feature tables (CSV from mzMine or XCMS) for LCMS data, have generated training/validation/test batches with known class imbalance, and need to train a CNN model from scratch to achieve AUC ROC > 0.9 for distinguishing true from false positive MS1 peaks.

Use when you have a pretrained TCN spectrum encoder from formula prediction and need to train a rescoring model that ranks formula candidates by confidence. The input is a set of spectra with ground-truth formula labels and multiple candidate formulas per spectrum.

Use when you have MS/MS spectra with unknown precursor m/z values and need to assign the most likely chemical formula and adduct type (e.g., [M+H]+, [M+Na]+, [M+K]+) in a de novo setting where spectrum database matching is unavailable or undesirable.

Use when when you have a pre-trained encoder (e.g., TCN spectrum encoder in FIDDLE) that has learned useful representations on a source task (e.g., MS/MS spectrum encoding), and you want to train lightweight task-specific modules (e.

Use when when you have a trained neural network and need to quantify prediction uncertainty or improve accuracy by filtering low-confidence predictions. Particularly useful when input spectra pairs have variable quality or when downstream tasks (e.

Use when when you have paired or unpaired MS/MS spectra and need to compute structural similarity scores without explicit molecular fingerprint computation, or when you want to generate low-dimensional embeddings for spectral visualization, clustering, or retrieval tasks.

Use when you have (1) a molecular structure input in SMILES, InChI, or chemical formula format, (2) a pretrained ICEBERG model checkpoint with fragment generation and intensity prediction weights, and (3) a goal to predict fragmentation patterns and m/z intensities for unknown compound.

Use when when you have annotated representative LCMS samples (raw mzML files + labeled feature tables in mzmine CSV format) and need to convert them into balanced or unbalanced peak matrix batches with fixed dimensions for neural network training.

Use when when replacing deprecated model components (e.

Use when you have LC-MS feature tables (m/z and retention time columns) and corresponding .mzXML or .mzML files, and you need to automatically classify whether extracted ion chromatograms represent genuine metabolomic features or false positives.

Use when you have a pre-trained neural network model (e.g., MSBERT weights in .

Use when you have downloaded LC-MS spectral peak data (DOI 10.25345/C5FD2F or equivalent) and need to build a supervised deep neural network classifier to distinguish peak classes in mass spectrometry data.