Claude Skills by HolobiomicsLab

Use when you have GC-MS data with multiple replicate injections or samples, need to identify a predefined set of query chemicals by name, and want to consolidate all instances of those chemicals (which may appear with varying match factors or peak areas across different samples or injection.

Use when working with large GCIMS matrices where computational speed or memory constraints are a concern, after filtering retention time (e.g., 0–1100 s) and drift time (e.g., 5–16 ms) ranges and applying Savitzky-Golay smoothing. Use it as a preprocessing step before alignment operations.

Use when you have raw spectra files from a liquid chromatography experiment (in-house or external database) and need to adapt a pretrained GNN-RT model to predict retention times for your molecules. Preprocessing is the mandatory first step before any model training or transfer learning can proceed.

Use when after peak clustering has been performed on aligned GCIMS samples and a peak table matrix has been constructed, but the matrix contains NA values because some samples did not yield detected peaks at certain cluster positions.

Use when analyzing complex GC-MS mixtures where two or more chemical compounds elute at similar or identical retention times, producing overlapping or merged peaks in the raw chromatogram.

Use when raw GC-MS data (netCDF or mzML format) exhibits overlapping chromatographic peaks—i.e., when multiple analytes elute at similar retention times and produce composite mass spectra with ambiguous m/z signals.

Use when when you have uploaded a pre-analytical data table containing sample metadata, processing delay annotations (pre- and post-centrifugation times), and paired NMR metabolomic measurements for a plasma or serum cohort, and you need to determine how processing delays impact metabolite.

Use when you have developed or adapted a peak detection method for chromatography–mass spectrometry and need to validate its reliability against an established baseline on the same raw GC–MS dataset. Specifically when: (1) the input is raw GC–MS data in m/z vs retention time format;

Use when you have a GC-MS dataset with multiple sample files (e.g., Std_soln_00, Std_soln_07, Std_soln_00a) where the same chemical is detected in different runs with varying Match.Factor scores, and you need to consolidate area values by compound identity rather than by individual peak detection.

Use when you have a GC-MS dataset with a Match.Factor column (or equivalent quality metric) and need to evaluate how many unique compounds are retained at different confidence thresholds, or when you must subset the compound list to a user-defined quality level before downstream cheminformatics.

Use when you have raw GC-MS or LC-MS data in vendor format (NetCDF, .raw, .d) or generic mass lists, and you need to assign chemical identities to detected peaks.

Use when after training a FlavorFormer model end-to-end with weighted loss on 1H NMR spectra and compound labels, apply this skill to a held-out test set to measure compound identification accuracy and ranking quality.

Use when ingesting compound metadata from multiple sources (PubChem, DrugBank, LOTUS, Dictionary of Natural Products, DrugCentral) that lack uniform column naming, have incomplete structure information, or contain only compound names without structural data.

Use when after XCMS feature detection, retention time correction, regrouping, and missing value imputation have produced an aligned feature table with multiple signals per compound. Use it when your data contains isotopic peaks (e.g., ¹³C variants) and multiple ionization products (e.

Use when you have a set of query chemicals and a reference library (organized by type or group), and you need to determine which reference compounds most closely resemble each query chemical based on structural features.

Use when after GCMSFormer (or similar Transformer model) has predicted pure mass spectra (matrix S) for all components in overlapped GC-MS peaks, apply this skill to quantify the relative abundance of each component.

Use when you need to create a synthetic feature table with known, ground-truth condition effects for method validation when: (1) testing normalization or batch-correction algorithms that must not confound condition signal with batch noise;

Use when you need to understand how a data-processing software system discriminates among multiple input types (LC, GC, IMS, MALDI) and selectively instantiates processing pipelines.

Use when when you need to understand how a multi-instrument mass spectrometry platform (such as mzmine) selectively routes data to different processing pipelines based on declared input type (LC, GC, IMS, or MS Imaging).

Use when when deploying a Word2Vec-based spectral similarity model (such as Spec2Vec) on a new mass spectrometry dataset and needing to assess whether the pre-trained model's learned peak embeddings sufficiently represent the peaks in your query spectra.

Use when you have a collection of deconvolved mass spectra (in MGF or mzTab format) from GC-MS analysis and need to group them into a molecular network to identify structural relationships and enable compound annotation.

Use when after identifying statistically significant features within individual LC-MS assays (e.g., via MB-VIP and permutation testing), use this skill when you have multiple parallel assays acquired in complementary ionization modes (e.

Use when you have raw or partially processed metabolomics data (mzML/mzXML format) from LC-MS or GC-MS runs and need to apply standardized feature detection, alignment, and intensity normalization as part of a reproducible workflow.

Use when you have raw GC-MS output in CSV format with columns Component.RT, Base.Peak.MZ, Component.Area, Compound.Name, Match.Factor, and File.

Use when building or auditing a multi-instrument MS data processing system that must route different chromatography modes (LC, GC), ion mobility, or imaging modalities (MALDI) to distinct processing workflows.

Use when after auto-deconvolution of GC-MS data has produced a table of deconvolved mass spectra, and you need to organize these spectra into clusters or detect which compounds co-elute or share similar fragmentation patterns.

Use when you have GCIMS samples exhibiting misalignment across drift time (typically 5–16 ms range) and retention time (typically 0–1100 s range) caused by pressure/temperature fluctuations or chromatographic column degradation, and you need to normalize sample positions before downstream peak.

Use when you have loaded a raw GCIMS dataset and need to isolate the region of interest in drift time (typically 5–16 ms for small organic molecules) to exclude low-drift-time chemical noise, high-drift-time tail artifacts, or off-scale ion signals that would degrade subsequent alignment and peak.

Use when after peak detection in GCIMS when you need to group detected peaks across multiple samples into reproducible clusters.

Use when when you have obtained a DrugBank release file (requiring access credentials) and need to integrate drug chemical structure, name, and identifier information into a metadata cleanup or chemical enrichment pipeline.

Use when you have per-sample metabolite abundance data (e.g., from LC-MS or GC-MS) and a metabolite-to-pathway assignment table, and need to generate a sample-by-pathway dysregulation matrix for downstream classification, prognosis prediction, or pathway-level phenotype association.

Use when you have raw or archived MSP spectral library files and need to load them into R for library searching, spectral matching, or batch reprocessing. Specifically, when you must extract precursor m/z values, peak intensity pairs, and spectrum metadata (e.

Use when when you have a molecular structure (XYZ or equivalent format) and need to predict its EI mass spectrum including major fragment ions and their relative intensities, particularly for validation against experimental data or when experimental spectra are unavailable;

Use when you need to build a comprehensive EI spectral reference library for GC-MS compound identification in MS-DIAL, starting from raw downloads of NIST, RIKEN, MoNA, or SWGDRUG libraries that have inconsistent metadata organization (SMILES in different fields or absent, RI values missing or.

Use when you have raw electron ionization mass spectra (m/z and intensity pairs) that you intend to match against a library using the Identity (EI Normal) or Similarity (EI Simple) algorithms. Different ionization runs and instrument conditions produce spectra with varying absolute intensities;

Use when after abundance-correlation-based feature group refinement when you observe that larger feature groups (particularly those with 3+ features in the same m/z–retention-time window) may contain features with different peak shapes or retention-time shifts in their EICs, or when abundance.

Use when you have a query electron ionization (EI) mass spectrum in msp format and wish to identify it by matching against a reference spectral library. Apply this skill when you need ranked similarity scores between the query and each library entry to prioritize candidate identifications.

Use when after generating a feature table from mzML data (via Asari) and before performing MS1 or MS2 annotation.

Use when after feature detection from mzML files (e.g., via Asari) when you have a feature table with m/z, retention time, and intensity columns, and before MS1 or MS2 annotation.

Use when you have pre-trained MLP and GNN models that generate different spectral predictions for the same metabolite candidates, and you want to combine them to improve ranking performance (average rank, Rank@K metrics) without retraining the base models.

Use when after loading raw Agilent Unknowns Analysis CSV output and when you need to convert tentative compound identifications (matched only by GC-MS library cosine similarity or Match.Factor score) into searchable, curated chemical records with exact masses and multi-source confirmation.

Use when you have a GC-MS dataset in CSV format with retention times, base peak m/z values, component areas, and compound names, and you need to identify whether specific query chemicals are present in your samples and retrieve their -match factors (scoring the confidence of the spectral match) and.

Use when after initial retention-time-based feature grouping (e.g., ±20 s window) when you need to separate co-eluting features that are chemically distinct. Triggers include: (1) large feature groups (>2–3 members) suspected to contain multiple compounds;

Use when after blank masking and sample dropping, when you have a feature table with intensity values that exhibit systematic variation across sample collection batches or instrument runs.

Use when use this skill after XCMS feature detection and alignment on non-targeted LC-MS or GC-MS metabolomics data, when you have aligned features with quantitative profiles across samples and need to group features that co-originate from the same compound (accounting for isotopic peaks, adducts.

Use when when you need to generate a realistic LC/GC-MS feature table (peak intensity matrix) with controlled, quantifiable condition effects (e.g., differential metabolite abundance across disease states) and batch effects (e.g., instrument drift, sample processing day).

Use when when initializing a SmartPeak session from a sequence file, you need to load and validate the workflow.csv and sequence.csv files that are co-located in the session directory.

Use when you have aligned and baseline-corrected GC-IMS data with detected and clustered peaks, and you want to extract peak intensities using a consistent integration window.

Use when when you have completed ORCA single-point energy calculations on interpolated reaction pathway geometries and need to convert quantum mechanical fragment energies and molecular properties into a structured fragmentation channel database suitable for automated EI mass spectrum simulation.

Use when you have FTICR-MS direct injection (mzML) data with identified chromatographic peaks and need to correct systematic m/z bias.