Claude Skills by HolobiomicsLab

Use when you have Nightingale Health 1H-NMR metabolomics assay output (metabolite concentrations in a samples × features matrix) and you want to compute a published metabolic risk score or surrogate biomarker (mortality risk, metabolic age, cardiovascular event risk, type-2 diabetes risk, COVID-19.

Use when when you have multi-batch metabolomics data (SummarizedExperiment object with raw or log-transformed assays) and need to assess whether specific metabolites exhibit systematic signal drift across experimental run order or strong batch effects that would justify hierarchical normalisation.

Use when you have two or more mass spectral libraries in different formats (NIST binary exports converted to MSP, MoNA downloads, RIKEN public databases, GNPS MGF, or batches of in-house standards in separate MSP files) and need to combine them with consistent metadata (SMILES, InChIKey, molecular.

Use when you have multiple tandem MS/MS libraries in different formats (msp, mgf) from different providers (NIST, RIKEN, MoNA, GNPS) with incomplete or inconsistent structural annotations (missing SMILES or molecular formula fields) and need to combine them into unified, polarity-specific msp files.

Use when you have metabolomic data (e.g., from LC-MS or GC-MS comparing patient to controls) showing differential abundant metabolites (DAMs), candidate genes from exome sequencing or variant calling, and access to a protein–protein or gene–gene interaction network (e.g., STRING).

Use when you have two or more CSV feature tables from independent metabolomic experiments (each with RT, m/z, intensity, isotope, and adduct columns), and you need to merge them into a single aligned feature matrix for downstream batch effect removal, marker identification, or pathway analysis.

Use when you have centroid mzML files from LC-MS acquisitions and need to detect, group, and quantify metabolomic features for a PCPFM experiment. Use it as the first feature-level processing step after file format conversion from raw instrument files (e.g., .raw to mzML via ThermoRawFileParser).

Use when after feature detection (e.g., Asari processing of mzML files to feature tables) but before normalization, batch correction, or annotation.

Use when you have a metabolomics feature table (rows=features, columns=samples) generated from LC-MS or GC-MS preprocessing and need to identify which features contain systematic errors from peak integration or alignment.

Use when you have generated a feature table via mzrtsim() with simulated LC/GC-MS abundances, condition assignments, and batch labels, and you need to pass it to Bioconductor tools (e.g., for batch correction, normalization, or statistical analysis) that expect SummarizedExperiment-class input.

Use when you have a raw feature table (TSV/CSV) derived from LC-MS peak detection (e.

Use when when you have a feature intensity table (samples × compounds) from targeted or non-targeted metabolomics and need to prepare it for statistical modeling or multivariate analysis.

Use when your metabolomics dataset (LC/MS or GC/MS) contains missing values encoded as NA or zero that represent compounds below the instrument's limit of detection (LOD) or limit of quantification (LOQ), rather than values missing completely at random.

Use when you have a raw metabolomics abundance table (e.g., LC/MS or GC/MS peak intensities or concentrations) with non-normal distributions and missing values, and you need to prepare it for Gibbs sampler or other model-based imputation.

Use when you have completed peak picking with two or more competing tools (e.g., IDSL.IPA, MZmine 2, xcms, MS-DIAL) on the same LC/HRMS dataset(s) and need to quantify which performs better. Use this skill when tool selection claims require validation (e.g., 'IDSL.

Use when when initializing a SmartPeak session and you have a workflow.csv file co-located with sequence.csv in the session directory, and you need to determine the precise order and validity of peak detection, calibration, and QC operations before execution.

Use when when you have generated a feature abundance matrix from mzrtsim() peak list simulation with known sample-level attributes (condition assignments, batch labels, sample identifiers) and need to package this into a SummarizedExperiment object for Bioconductor-compatible analysis pipelines.

Use when reading mass spectral library files (particularly MoNA EI or MS2 libraries) where structural metadata like SMILES information is embedded in general-purpose fields (e.g., Comment field) rather than in the dedicated SMILES field expected by mspcompiler's downstream processing steps.

Use when you have paired microbiome (16S rRNA, metagenomic) and metabolomic (LC-MS, GC-MS) abundance tables from the same biosamples, and you want to predict which metabolites are recoverable from microbial composition alone and identify groups of microbes and metabolites with correlated.

Use when when you have a metabolomics abundance table with missing values and need to decide which imputation method to apply, or when designing a simulation to evaluate imputation performance.

Use when after converting MS/MS spectra to fixed-length vector representations using a pre-trained Word2Vec model (as in Spec2Vec), filter spectra before computing similarity scores to flag those where a large fraction of the observed intensity comes from peaks or neutral losses not present in the.

Use when you have metabolomics data (targeted LC/MS or untargeted GC/MS) with left-censored missing values below the limit of quantification (LOQ) or limit of detection (LOD), and you need to impute these values while preserving the underlying distributional structure and avoiding bias from.

Use when training a Transformer or neural network model on a large dataset (e.g., 80,000+ training samples) where validation performance is monitored to prevent overfitting, and you need to halt training early or recover the -performing model checkpoint without re-executing the entire training loop.

Use when you have a raw GCxGC-MS chromatogram in NetCDF format (.cdf file) and need to import it into R as a 2D-TIC object for preprocessing (smoothing, baseline correction, peak alignment) or multivariate analysis.

Use when evaluating whether a mass spectrometry data analysis platform (such as mzmine) provides complete module coverage across all advertised separation and ionisation techniques.

Use when when you need to understand how a multi-instrument mass spectrometry platform (like mzmine) decides which processing module receives a given dataset based on its declared data type (LC vs. GC vs. IMS vs. MS imaging).

Use when when evaluating how well mass spectral similarity scores correlate with actual chemical structure for annotated spectral pairs (e.g., spectra with InChIKey metadata).

Use when you have an experimental tandem mass spectrum (collision energy annotated) and a known molecular formula or candidate structure list, and you need to rank or discriminate between isomeric or isobaric candidates by comparing predicted fragment-level spectral patterns.

Use when during MSP, MGF, JSON, or CSV file parsing when standardizing mass spectra from heterogeneous open mass spectral libraries (OMSLs).

Use when after GNPS_GC molecular networking job completion, when you have retrieved raw network output files and need to extract, validate, and structure the network topology for further metabolite assignment, comparative network analysis, or visualization.

Use when you have multiple mass spectrum prediction models to compare and need to establish a level playing field by implementing at least one well-characterized baseline (such as NEIMS) with both FFN and GNN encoder variants.

Use when you have access to pre-trained MSGO model weights (PFAS or lipid variants) and a set of 300+ real mass spectra (LC–QTOF or similar), and need to verify whether the model can generate correct molecular structures for unknown chemicals.

Use when you have EI-MS spectrum data (m/z and intensity pairs) from a sample and need a direct, model-based prediction of molecular weight.

Use when when you have loaded a MoNA mass spectral library (GC-MS or LC-MS/MS) in MSP format and observe that SMILES strings are present in the Comment field rather than in a dedicated SMILES metadata field.

Use when when receiving raw MS data files of unknown or mixed acquisition modalities and needing to route each to its corresponding analysis pipeline. Specifically, apply this skill when: (1) input files arrive without documented instrument type or chromatographic/mobility dimensionality;

Use when when evaluating or designing a mass spectrometry data analysis platform, and you need to verify that every supported separation/ionisation technique (LC, GC, IMS, MS Imaging) is covered by at least one processing module.

Use when immediately after loading a raw GC-MS CSV file and before executing the spreadOut() function. Use it when you have received peak table data from an instrument vendor (e.

Use when when you have a GC-MS dataset (CSV with columns: Component.RT, Component.Area, Base.Peak.MZ, File.Name, Compound.Name, Match.Factor) and a known set of target chemicals you wish to locate and extract with their spectral match quality and quantitation.

Use when you have FIA-MS, LC-MS, or GC-MS full-scan data in mzML format and need to identify unknown molecular features by accurate mass.

Use when you have acquired EI or MS2 library files in MSP format (e.g., from NIST via Lib2NIST export, RIKEN, MoNA, SWGDRUG, or GNPS) and need to read them into R to assign SMILES, retention indices, or combine multiple libraries into a single consolidated MSP file for MS-DIAL.

Use when you have a Mass Spectrum Point (MSP) file containing electron ionization mass spectral records with header fields and peak intensity pairs, and you need to load it into an R data structure for library searching, format validation, or round-trip conversion.

Use when your metabolomics experiment includes samples acquired across multiple instrument runs, different preparation dates, or distinct sample cohorts.

Use when you have a parsed sample list with metadata (sample IDs, classification dimensions, QC designations) and need to generate a physical injection-plate layout that (1) will be run across multiple batches, (2) has a known confounding dimension (e.

Use when when baseline MLP or GNN models for spectral prediction show limited performance on metabolite annotation tasks, and you have access to auxiliary spectral topic labels (e.g., via LDA on spectral features) that could provide regularization signal.

Use when after preprocessing and aligning 2D chromatogram data (baseline correction, smoothing, peak alignment) and after running m_prcomp multiway PCA on the joined chromatogram matrix.

Use when when invoking Asari to process centroid mzML files for the first time in a PCPFM experiment, or when RT and m/z accuracy characteristics of your LC-MS instrument differ from the pipeline defaults (e.

Use when when you need to generate reproducible synthetic LC/GC-MS raw data files with known ground-truth peak properties (m/z, retention time, intensity) for benchmarking peak detection, feature extraction, normalization, or batch correction algorithms;

Use when you have raw mzML files from a mass spectrometry instrument and need to begin a preprocessing workflow in xcms. This is the essential first step before any peak detection (centWave, MSWParam) or feature grouping can occur.

Use when you have loaded raw Agilent Unknowns Analysis CSV output with required columns (Component.RT, Base.Peak.MZ, Component.Area, Compound.Name, Match.Factor, File.

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.