Claude Skills by HolobiomicsLab

Use when when you have a set of small molecules (as SMILES or structures) that need to be identified or ranked by their elution order in RPLC systems with acidic pH (~2.7), and you want to assess model confidence in retention predictions.

Use when you have MS2 fragmentation spectra from multiple samples (in .mgf, .mzML, or .mzXML format) and want to compare them despite poor feature overlap, strong RT shifts between acquisitions, or use of different LC-MS platforms (e.g., Orbitrap vs. Q-ToF).

Use when you have extracted peaks from multiple LC/HRMS batches (n > 500 samples across different analytical runs or days) and observe systematic retention time drift or offset between batches, preventing reliable cross-batch peak matching on m/z and RT alone.

Use when you have two or more nontargeted LCMS feature tables from the same analytical method and need to establish matched feature correspondences across datasets, then consolidate redundant features.

Use when when processing a batch of centroided mzML or mzXML LC-MS raw data files where chromatographic retention times drift between sample acquisitions (common in large-scale metabolomics studies).

Use when when processing multiple LC-MS samples with varying scan numbers or retention-time drift, before constructing composite mass tracks for peak detection.

Use when after mass tracks have been aligned across samples into a MassGrid structure and retention time calibration dictionaries (rt_cal_dict) have been computed for each sample, but before summing intensity vectors element-wise to construct the composite map.

Use when after feature m/z grouping and pairwise alignment detection have identified candidate feature pairs, and anchor points have been selected to establish retention time correspondence.

Use when after sample alignment step in untargeted LC-MS workflows, particularly when processing multi-sample cohorts with QC samples interspersed throughout the sequence.

Use when after peak detection in untargeted metabolomics when you have identified ion signals across mass-to-charge and retention-time dimensions from replicate injections of the same samples, and you need to group peaks from different runs that represent the same metabolite before building a.

Use when after peak detection has been completed on individual LC-MS samples and you have a collection of detected peaks with m/z, retention time, and intensity values from each sample.

Use when after anchor selection and RT mapping spline construction, when you have a fitted metabCombiner object with pre-aligned feature pair candidates and need to tune the scoring metric that combines retention time, m/z, and cosine similarity components.

Use when after chromatographic peak detection on preprocessed LC-MS data when you have an xcms result object (XcmsExperiment or xcmsSet) with detected peaks and need to collapse redundant m/z signals into feature groups.

Use when you have LC-MS data from authentic standards run in positive and negative ESI modes, converted to .mzML format, and you need to build an in-house metabolite reference library for untargeted identification workflows.

Use when after mass track construction and before composite map building, when you need to align retention times across multiple LC-MS samples. Trigger conditions: (1) you have identified high-selectivity landmark peaks (mSelectivity > 0.99) in a reference sample;

Use when after mass track extraction and alignment across samples, when preparing to detect elution peaks on composite mass tracks. Use this when inter-sample retention time variation exceeds acceptable alignment tolerance (e.

Use when you have extracted feature tables (via MS1 peak picking, MS2 recognition, or targeted list extraction) from two or more individual LC-MS samples and need to identify which features represent the same metabolite across samples before generating a unified, sample-aligned feature table for.

Use when after matching mass-to-charge ratios to a compound database (e.g., KEGG) and assigning adduct/fragment types, when you have an annotated feature table with retention times, m/z values, and intensity profiles across samples.

Use when you have multiple LC-MS runs with the same set of targets (compounds) and observe or expect retention time drift or jitter between runs.

Use when you have detected multiple LC-MS features (m/z peaks) across a chromatogram and need to distinguish true chemical relationships (isotopes differing by 1.003 Da, adducts with characteristic mass shifts, neutral loss fragments) from noise or unrelated peaks.

Use when when you have detected multiple features from non-targeted mass spectrometry and need to group them by putative compound origin.

Use when you have LC-MS data processed through XCMS grouping that shows signs of RT drift (e.g., data acquired over extended periods or across many samples) and you suspect misalignment of feature groups.

Use when you have multidimensional MS data converted to MZA HDF5 format and need to retrieve specific spectra or chromatographic slices defined by one or more of: retention time (in minutes), ion mobility arrival time (in milliseconds for DT/SLIM or Vs/cm² for TimsTOF), or m/z value (as a float or.

Use when when you have Thermo Orbitrap .raw files containing known reference peptides (e.

Use when after chromatographic peak detection (findChromPeaks) when you have a processed XcmsExperiment object with detected peaks and need to perform initial feature grouping. Use it when features of the same compound are expected to co-elute within a narrow retention-time window (e.

Use when you have extracted retention times from top MS1 features in an LC-MS/MS experiment and need to assess whether the gradient configuration (start and end time in minutes) achieves adequate compound separation across the full chemical space.

Use when you have acquired a bottom-up proteomics LC-MS/MS run (e.

Use when you have Thermo Fisher Scientific .raw files from an LC-MS experiment and need to extract spectral features (base-peak m/z, intensity, scan-level properties) indexed by retention time for downstream statistical analysis, method optimization, or diagnostic visualization.

Use when you have xcms-processed LC-MS data with detected misaligned feature groups and need to recover the underlying raw retention time–intensity profiles for each feature and sample combination prior to realignment.

Use when when you have a resolved mzML or mzXML spectrum file and need to visualize or analyze the temporal intensity profile of a specific analyte (defined by its m/z value).

Use when after anchor feature pairs (m/z and retention time values) have been selected from two disparately-acquired LC-MS datasets, and you need to correct for systematic retention time differences between the datasets.

Use when you have two independent LC-MS untargeted metabolomic feature datasets (each with retention time and m/z values) and need to identify which features in one dataset correspond to features in the other.

Use when you have two LC-MS untargeted metabolomic feature tables (each containing m/z, retention time, and intensity columns) and need to establish which features in dataset A correspond to which features in dataset B, typically for comparative metabolomics, batch effect correction, or.

Use when after sample alignment and grouping of isotopologues and adducts have been completed, when the aligned feature table contains NA or zero entries (missing intensities) for features that are detected in some samples but fall below the detection threshold in others.

Use when you have multiple feature tables (CSV files) from different LC-MS analytical experiments, each containing mass, retention time, intensity, isotope, and adduct annotations, and you need to merge them into a single aligned feature matrix.

Use when processing raw LC/MS data (mzML or mzXML format) from multi-sample cohorts where retention time or intensity drift is suspected due to batch effects, instrument calibration drift, or variable run order.

Use when when you have parsed .mzML or Thermo .raw LC-MS data and need to support interactive or programmatic queries by retention time (RT) and mass-to-charge ratio (m/z) without re-scanning the entire file.

Use when you have processed LC-MS run data (feature table or peak detection output) containing internal standard identifications with retention times, m/z values, and intensity measurements across multiple samples, and you need to rapidly detect instrumental drift, retention time shifts, or.

Use when after applying peak detection algorithms to identify local maxima in feature signals across retention time or m/z dimensions, but before exporting or filtering the peak list for further analysis.

Use when after drift correction and quality flagging, when you have a feature abundance matrix with associated metadata (Feature_ID, m/z, retention time) and need to identify which features likely represent the same underlying metabolite or adduct series before statistical analysis or metabolite.

Use when you have a new chromatographic dataset with molecular structures (as InChI or SMILES) and experimentally measured retention times, and you want to predict retention times for unannotated metabolites or validate predictions on a held-out test set without retraining from scratch.

Use when you have molecular structures (SMILES or SDF format) for which you need to predict retention time in liquid chromatography, especially when your target dataset contains fewer than ~500 annotated examples.

Use when you have a set of small-molecule compounds (e.g., from MS/MS library matching or database annotation) that require retention time validation or ranking to resolve ambiguous identifications.

Use when when you have a retention-time dataset (e.g., SMRT or Eawag_XBridgeC18_364) in .xlsx format and need to train or adapt a graph neural network model to predict chromatographic retention times for new compounds.

Use when you have a list of candidate metabolites for an unknown compound (from mass-to-structure search or library matching), experimental retention time(s) from one or more chromatographic methods, and access to a trained DNN RT predictor and meta-learned RT projection model.

Use when after training a GNN-RT model on preprocessed molecular graph data (from Train.py) or after applying transfer learning to an in-house dataset (from Transferlearning.

Use when you have MS1-formatted mass spectrometry files from a liquid chromatography–mass spectrometry (LC-MS) experiment and need to predict the retention time of peptide ions without relying on spectral libraries, empirical models, or manual feature engineering.

Use when when you have retention times measured on one chromatographic method and need to predict or map them to another method with minimal or no overlap in measured molecules.

Use when after initializing and executing a forward pass through a dual-branch RT-Transformer model (combining fingerprint and molecular graph inputs) on a batch of molecular samples, to verify that the output tensor conforms to the expected shape, data type, and numeric range for retention time.

Use when when you have loaded an LC-MS spectrum file (mzML, mzXML, or equivalent) into the GNPS LCMS Visualization Dashboard and need to annotate extracted ion chromatograms with the precise retention time or scan ID positions where MS2 events occurred.