Claude Skills by HolobiomicsLab

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 you have 1H NMR spectral data from complex mixtures and need to identify component compounds, but a single architecture (CNN or Transformer alone) fails to capture both fine local patterns in peak structures and long-range dependencies across the full spectral range.

Use when when you have experimental UHPLC-HRMS/MS or direct infusion MS/MS data and need to identify lipid species by comparing observed fragment m/z values against a library of simulated fragments. Apply this skill when your lipid library is incomplete or specialized (e.

Use when you have candidate metabolite structures (from database lookup or enumeration) and experimental MS/MS spectra (mzML, mzXML format), and need to rank candidates by how well their predicted fragments match observed peaks.

Use when you have clustered peak networks from INADEQUATE NMR spectra (output from the Clustering module) and need to assign metabolite identities by comparing them to known spectral signatures.

Use when you have raw INADEQUATE NMR spectrum files (e.g., in standard NMR formats) that require initial processing before metabolite annotation.

Use when you have NMR metabolomics measurements paired with pre-analytical metadata (processing delay times, centrifugation timing, sample type such as plasma vs. serum, cohort identifiers) and need to interactively explore how variation in processing conditions drives changes in metabolic.

Use when when analyzing LC-MS data from stable isotope labeling experiments where measured isotopologue abundances are contaminated by naturally occurring isotopes and tracer isotopic impurity, and you have access to unlabeled sample reference measurements to empirically model these confounding.

Use when you have parsed metabolite identities with known spin-system coupling constants (J-values) and chemical shifts, and need to generate the theoretical multiplet patterns that will form the basis of a simulated 1D or 2D NMR spectrum.

Use when you receive uploaded spectral data in JCAMP format (jcamp) as input to the /api/v1/chemspectra/file/convert endpoint, or when you need to extract and validate metadata and peak information from an existing JCAMP file before converting to another format or performing spectral analysis.

Use when when you have NMR peak assignments (1H and 13C chemical shift values) and need to submit them to the /api/smart3/search endpoint for automated structure classification. Use this skill before making API calls to ensure peak data conforms to the expected JSON schema.

Use when when a backend service receives structured prediction results from an external API (e.g., nmrshiftdb peak predictions) and must return them to a client application via HTTP POST response.

Use when you have loaded an mwTab file into a structured MWTabFile object and need to verify it conforms to MS or NMR schema specifications before deposition, curation, or downstream analysis.

Use when when you have 1H-NMR metabolite measurements from Nightingale Health assayed on a new cohort and wish to compute risk scores (e.g., all-cause mortality, cardiovascular event, type 2 diabetes) using published metabolic biomarker weights from a reference study.

Use when after generating theoretical spin multiplets for individual metabolites via first-order or density-matrix NMR simulation, but before combining spectra or applying Fourier transformation.

Use when you have a preprocessed peak list (m/z values and assigned molecular formulas) from direct injection FT-ICR MS of a complex organic mixture (e.

Use when you have raw LC-MS/MS spectral data in vendor formats or unvalidated .mgf files before feeding them into the specXplore importing pipeline.

Use when you have one or more individual MS/MS spectra (in mzML, mzXML, or JSON format) and need to identify the compound(s) and their biological source by searching against a domain-specific spectral library.

Use when you have raw mass spectrometry data in vendor-specific formats (Thermo RAW, Waters RAW, or open formats like mzML/jcamp) that need to be ingested, validated, and converted to a standardized representation for downstream peak detection, quantification, or integration with other NMR/IR/MS.

Use when you have an experimental tandem mass spectrum (collision-induced dissociation, CID) and a known chemical formula (or narrow set of candidate formulas), and you need to identify the most likely structure(s) by ranking against a large candidate library such as PubChem.

Use when initializing a Dataset object in NMRFx and must decide which storage backend to use for in-memory or memory-mapped file access.

Use when you have Nightingale Health 1H-NMR metabolomics data (feature matrix with named metabolite columns) and need to compute predicted metabolic age for each sample, typically to assess whether individuals' metabolic profiles align with or diverge from age-expected trajectories.

Use when when you have paired NMR metabolite measurements and corresponding processing metadata (pre-centrifugation delay, post-centrifugation delay, sample type, cohort) for a blood sample cohort and need to determine which metabolites remain stable across the expected or observed delay range, or.

Use when when you have a list of known metabolite concentrations and their corresponding J-coupling constants (spin systems) and need to generate realistic 1D 1H NMR spectra or 2D correlation spectra (COSY, HSQC, HMQC) for simulation, validation, or educational purposes, without access to actual.

Use when after peak networks have been identified and clustered from INADEQUATE spectra (typically via the clustering and finding modules), use this skill when you need to assign chemical identities to unknown peak networks by comparing them against reference spectral signatures in a simulated.

Use when you have raw NMR metabolomics measurements paired with pre-analytical metadata (e.g., processing delay times, sample type designations [plasma vs. serum], cohort identifiers) and need to investigate how delays affect measured metabolic parameters.

Use when you have a metabolomic SummarizedExperiment object with replicate QC (quality control) samples and need to remove non-reproducible metabolic features before phenotype association modeling. Use it specifically when your workflow requires FDA-compliant reproducibility thresholds (CV < 0.

Use when when you have a small-molecule structure (SMILES, MOL, or SDF format) and need to identify probable metabolites or degradation products in a specific biological compartment (e.g., soil/aquatic microbiota, mammalian liver, or gut microbiota).

Use when you have observed compounds (from LC-MS/MS, GC-MS, NMR, or other analytical techniques) with unknown identity and you want to assign candidate metabolite structures by comparing them to computationally predicted metabolism pathways.

Use when validating mwTab files deposited to the Metabolomics Workbench and you need to verify that metadata columns match standard naming conventions and contain values in the expected format.

Use when you have a 1D ¹H NMR spectrum (as chemical shift vs. intensity) and a corresponding peak list (chemical shift values), and you need to identify which metabolites are responsible for each detected peak.

Use when you have a SummarizedExperiment object containing NMR or MS metabolomic data with aligned phenotype information (BMI, disease status, age, gender), and you need to identify metabolites associated with a continuous or categorical outcome while controlling for known confounders that might.

Use when when you have a small-molecule structure (SMILES, MOL, or SDF format) and need to predict its metabolic fate across one or more biological systems.

Use when you have defined one or more proton NMR spectral regions-of-interest (ROIs) with lower and upper chemical-shift bounds (in ppm) from an experimental NMR spectrum of a biological sample, and you need to identify which metabolites in a reference database (HMDB) have published 1H NMR shifts.

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 an experimental mass spectrum (or a set of spectra from LC-MS/MS data) and need to identify the underlying metabolite(s) by comparing against known reference spectra in GNPS or a local indexed repository.

Use when you have uploaded a pre-analytical data table containing sample metadata, processing timestamps (pre- and post-centrifugation), and NMR metabolomic measurements for a cohort of peripheral blood samples (plasma/serum), and you need to quantify the magnitude and direction of metabolite.

Use when you have a parent compound (or set of compounds) in SMILES, MOL, or SDF format and need to predict plausible metabolite structures and pathways in a specific biological context (mammalian Phase I/II metabolism, human gut microbiota, or soil/aquatic microbial degradation).

Use when you have raw metabolomics count data (e.g., from mass spectrometry or NMR experiments) in tabular format and associated sample metadata (e.g., treatment groups, experimental factors) that need to be imported into R for analysis with packages like Omu.

Use when you have a raw MGF file containing fragmented LC-MS-MS metabolomics spectra and want to apply Latent Dirichlet Allocation (LDA) to discover hidden topics (molecular families, biochemical patterns) across your sample set.

Use when you have raw 1D NMR spectral data (urine, worm, or other biological samples) that needs to be converted into peak tables for metabolite identification and quantification.

Use when after you have detected LC-MS features, grouped them into empirical compounds via isotope and adduct clustering (using khipu), and have accurate m/z and retention time values.

Use when you have mwTab-formatted files from the Metabolomics Workbench containing MS or NMR experimental metadata and tabular data sections (e.g., METABOLITES, DATA blocks), and need to load them into memory for downstream conversion, validation, or analysis rather than manual text parsing.

Use when you have a matrix of Nightingale Health 1H-NMR metabolomics measurements (samples × features) and need to generate predicted metabolic scores published in peer-reviewed studies (MetaboAge, mortality score, cardiovascular event risk, Type-2 diabetes score, COVID-severity score, or surrogate.

Use when you have a binary file (e.g., NV format) with a known fixed-size header block (e.

Use when you have raw tabular experimental metadata (mass spectrometry or NMR sample descriptions, sample-to-treatment mappings, instrument parameters, etc.) that needs to be deposited into a structured online repository like Metabolomics Workbench, but the raw format does not conform to the.

Use when when starting with raw paired microbiome (16S rRNA, metagenomic taxonomic or functional features) and metabolome (LC-MS/MS, NMR) count tables from the same biospecimens, and planning to train prediction models or co-abundance networks.

Use when you have an NMR mixture spectrum and a library of single-compound reference spectra, and you need to identify which compounds are present and their relative abundances.

Use when you have an observed NMR mixture spectrum and one or more candidate reconstructed spectra (each formed by summing weighted single-compound spectra), and need a continuous, transportable distance metric to score how well the reconstruction approximates the observed mixture.