HolobiomicsLab
- 7.4k skills
- 0 followers
- 15 hours ago last updated
- ▌ Neural Network Encoder Implementation 2 · holobiomicslabUse when when you need to benchmark multiple encoder types (e.g., FFN vs. GNN) on the same predictive task and require evidence that performance differences reflect genuine architectural trade-offs rather than suboptimal tuning.
- ▌ Neutral Mass Inference Via Regression 2 · holobiomicslabUse when use this skill after khipu has assigned observed ions to grid positions (isotope and adduct combinations). Apply it when you have a connected subnetwork of feature ions that have been matched to known isotope and adduct patterns and need to estimate the neutral mass of the parent compound.
- ▌ Nonparametric Reproducibility Ranking 2 · holobiomicslabUse when you have high-dimensional replicate experiment data (e.
- ▌ Peak Background Binary Classification 2 · holobiomicslabUse when you have LC-HRMS profile-mode chromatograms with extracted local maxima exported as standardized 2D rt×mz areas, and you need to disambiguate true chromatographic peaks from background signals (including wall artifacts and noise) at scale.
- ▌ Spectral Fragment Identifier Matching 2 · holobiomicslabUse when when you have downloaded fragment records from separate experimental and predicted online databases and need to verify that each fragment can be traced back to a valid compound entry in a reference compound database (e.g., SDF-format DNA adduct compound collection).
- ▌ Domain Specific Masst API Integration 2 · holobiomicslabUse when your research involves searching MS/MS spectra against multiple curated taxonomic or domain-specific databases (microbial, plant, tissue, microbiome, or food origin) and you need to aggregate, compare, and visualize matching results across all domains in a single interface.
- ▌ Latent Space Dimensionality Reduction 2 · holobiomicslabUse when you have imaging mass spectrometry (IMS) datasets where peak intensities are high-dimensional and sparse, and you need to extract compressed latent features that preserve spatial adjacency relationships and enable iterative automatic peak picking to identify marker ions.
- ▌ Mass Spectrometry Image Preprocessing 3 · holobiomicslabUse when you have raw or preprocessed single-channel (2D array) or multi-channel (spectral) ion images from mass spectrometry imaging (MSI) data and need to train a contrastive deep learning model.
- ▌ Msi Data Processing Speed Measurement 2 · holobiomicslabUse when when you need to validate that MSI software (e.g., LipidQMap) achieves documented processing speeds on your target hardware, or when you need to establish a performance baseline before deploying the software for high-throughput imaging studies.
- ▌ Natural Isotope Abundance Calculation 2 · holobiomicslabUse when when processing mass spectrometry imaging (MSI) data in positive ion mode where both [M+H]+ and [M+Na]+ adducts are present for the same lipid species, and you observe intensity overlap in [M+H]+ ion images caused by the isotopic fine structure of [M+Na]+ adducts.
- ▌ Parameter Sharing In Siamese Networks 2 · holobiomicslabUse when when processing paired augmented versions of the same input (e.g., two augmented ion images in COL or ISO mode) and you need to learn meaningful low-dimensional representations via contrastive loss.
- ▌ Activity Score Computation And Reporting 2 · holobiomicslabUse when you have preprocessed metabolite intensity data (log2-transformed, zero-mean unit-variance standardized) mapped to compound annotations, and you need to derive activity scores for a set of metabolite groups (pathways, Molecular Families, Mass2Motifs, or custom metabolite sets) to rank them.
- ▌ Chemical Database Querying And Retrieval 2 · holobiomicslabUse when you have BioTransformer-predicted metabolite structures (in SMILES or InChI format) and need to identify which known compounds in public databases match those structures.
- ▌ Chromatographic Method Transfer Learning 2 · holobiomicslabUse when you have experimental RT measurements from a source chromatographic method and need to predict RTs for the same molecules on a target chromatographic method, but lack a large calibration dataset (typical scenario: 10–100 molecules with ground truth RTs on both methods).
- ▌ Comparative Enrichment Method Evaluation 2 · holobiomicslabUse when you are selecting a pathway enrichment method for metabolomics peak data and need to assess which method will remain stable when your data contains noise, dropout, or missing identifications.
- ▌ Contrastive Learning Loss Implementation 2 · holobiomicslabUse when when you have paired augmented ion images processed through ResNet18 encoders producing 512-dimensional representation vectors, and you need to learn meaningful low-dimensional representations without labeled data by enforcing that augmentations of the same image remain similar while.
- ▌ Cross Method Chromatographic Scalability 2 · holobiomicslabUse when you have a pretrained RT-Transformer model checkpoint from a large, well-characterized chromatographic dataset (e.g., SMRT) and need to predict retention times for a different chromatographic method or instrument condition represented in a smaller, domain-specific dataset (e.g., PredRet).
- ▌ Deep Neural Network Latent Space Mapping 2 · holobiomicslabUse when you have a pre-trained DNN model for retention time prediction and need to adapt it to a new chromatographic method or instrument where you have only 10–20 calibration molecules with known retention times;
- ▌ Documentation And Metadata Modernization 2 · holobiomicslabUse when a mature scientific package (e.g., Mummichog 3) is being migrated to a new GitHub organization that enforces standardized project structure, and the current setup.py, pyproject.toml, requirements.txt, .
- ▌ Error Metric Comparison And Benchmarking 2 · holobiomicslabUse when you have predicted retention times from one or more machine learning models (DNN, Gaussian Process, or ensemble) applied to small-molecule chromatography data, along with corresponding experimental ground-truth retention times, and need to quantify prediction accuracy and rank competing.
- ▌ Feature Matrix Normalization And Scaling 2 · holobiomicslabUse when you have a heterogeneous feature matrix combining molecular descriptors (from RDKit/mordred) and chromatographic metadata (column length, temperature, pH, flow rate, particle size) with different physical units, ranges, and scales.
- ▌ Fragmentation Pattern Similarity Scoring 2 · holobiomicslabUse when after feature detection and alignment have produced a feature table with MS/MS spectra, and you have access to a reference spectral database (e.g., xenobiotic reaction libraries or public databases).
- ▌ Gnps Spectral Library Compound Retrieval 2 · holobiomicslabUse when you have GNPS library accession IDs (e.g. CCMSLIB00011906190) for a reference compound and a chemically or biologically modified analog, and need to load their full MS/MS spectra and structural annotations to set up a modification-finding analysis.
- ▌ Identifier Format Parsing And Validation 2 · holobiomicslabUse when you receive mass spectrometry data through heterogeneous identifier formats—specifically when the input could be a GNPS Task ID, a Universal Spectrum Identifier (USI), or a Feature-Based Molecular Networking (FBMN) identifier—and you need to programmatically determine which format was.
- ▌ Inference Model Cpu Thread Configuration 2 · holobiomicslabUse when when running Mass2SMILES inference on a TensorFlow-CPU build (e.g., delser292/mass2smiles:final container) and you need to optimize inference speed by controlling CPU core allocation.
- ▌ Mass Spectrometry Data Format Conversion 2 · holobiomicslabUse when you have mass spectral libraries from multiple sources (e.g., NIST EI, RIKEN MS2, MoNA GC-MS or LC-MS/MS, GNPS mgf) that need to be consolidated for use in MS-DIAL, or you have a single library with incomplete or malformed metadata (e.
- ▌ Mass Spectrometry File Format Conversion 2 · holobiomicslabUse when you have raw MS data files in vendor-native format (.raw, .d, .ms) from CE-MS or LC-MS instruments and need to process them through AriumMS or other open-source metabolomics pipelines that require standardized XML-based interchange formats.
- ▌ Metabolite Detection Matrix Construction 2 · holobiomicslabUse when after GNPS spectral library matching has been completed on a batch of MS2 spectra from public MassIVE datasets and you need to aggregate chemical annotations into a tabular format suitable for downstream comparative metabolomics, co-analysis, or chemical explorer visualizations across.
- ▌ Metabolite Edge Scoring Dbedges Bioedges 2 · holobiomicslabUse when you have a measured m/z value from spatially-resolved metabolomics or mass spectrometry imaging and need to assign a molecular formula with high confidence. Use it specifically when you have access to a pre-constructed formula network (KnownSet database) linking 2.
- ▌ Molecular Structure Graph Representation 2 · holobiomicslabUse when when you have a set of chemical structures (SMILES strings or SDF files) that need to be processed for training a graph neural network model on molecular property prediction tasks, specifically when the target property (e.
- ▌ Ms Ms Fragment Assignment And Annotation 2 · holobiomicslabUse when when you have predicted MS/MS fragments from quantum chemistry calculations on N-Me derived unsaturated sterol structures and need to map each fragment to its precursor lipid, calculate exact m/z values, estimate relative intensities, and produce a machine-readable reference table for.
- ▌ Multiple Testing Correction Metabolomics 2 · holobiomicslabUse when you have computed raw p-values from partial Spearman correlations (or other univariate tests) between each metabolite in a SummarizedExperiment object and a phenotype of interest, adjusted for epidemiological confounders (e.
- ▌ Neutral Mass Inference From Ion Ensemble 2 · holobiomicslabUse when you have a connected subnetwork of feature ions that have been validated as belonging to the same empirical compound (khipu instance), with isotope and adduct edges assigned, and you need to estimate the true neutral mass M0 rather than relying on any single observed m/z.
- ▌ Nontargeted Metabolomics Data Processing 2 · holobiomicslabUse when you have raw LC-MS data in vendor or mzML format and need to systematically discover and extract all detectable metabolite features across the full retention time range, without predefined target lists.
- ▌ Pathway Activity Decomposition Via Plage 2 · holobiomicslabUse when you have a log2-transformed, standardized peak intensity matrix (rows = metabolite features, columns = samples) with compound annotations mapped to curated pathway databases (KEGG, Reactome, or custom metabolite sets), and you need to rank pathways by their activity level while tolerating.
- ▌ Peak Prominence Calculation Local Maxima 2 · holobiomicslabUse when when processing LC-MS mass tracks (EICs) and you need to identify genuine chromatographic peaks rather than noise artifacts.
- ▌ Python Package Migration And Refactoring 2 · holobiomicslabUse when you have a mature Python package (e.g., Mummichog 2.x) that needs to be relocated to a new GitHub organization (e.
- ▌ Retention Time Prediction Chromatography 2 · holobiomicslabUse 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.
- ▌ Robust Statistical Spread Quantification 2 · holobiomicslabUse when after drift correction of LC-MS peak intensity data, when you need to identify metabolic features with excessive internal spread (within-group variability in QC samples) or poor biological-to-technical reproducibility (QC-versus-sample spread).
- ▌ Spectral Clustering And Feature Grouping 2 · holobiomicslabUse when you have raw MS/MS feature data with m/z, retention time, and fragmentation spectra from an untargeted metabolomics experiment, and you need to annotate reaction-derived metabolites of xenobiotics without relying on a priori targeted methods.
- ▌ Spectral Library Query Reference Pairing 2 · holobiomicslabUse when when evaluating a trained spectral embedding model on publicly available datasets (GNPS, MoNA, MTBLS1572, MassBank, or MassSpecGym) and you need to report averaged performance metrics with standard deviation to demonstrate robustness and reproducibility.
- ▌ Spectral Peak Alignment With Mass Offset 2 · holobiomicslabUse when when comparing two MS/MS spectra where the precursor m/z values differ (indicating potential mass modifications, adducts, or related compounds), and you want to detect structurally conserved fragmentation patterns that would be missed by direct m/z matching.
- ▌ Spectral Peak Smoothing Artifact Removal 2 · holobiomicslabUse when raw Agilent MassHunter (.d) or UIMF mass spectrometry files exhibit jagged or noisy peaks, particularly for low-abundance ions where signal-to-noise ratio is poor.
- ▌ Spectral Similarity Network Construction 2 · holobiomicslabUse when after acquiring MS/MS spectral data from untargeted metabolomics experiments and having candidate transformed structures from biotransformation rule application.
- ▌ Spectrum Preprocessing And Normalization 2 · holobiomicslabUse when you have raw MS/MS spectra in MGF or other standard formats that need to be ingested into a machine learning pipeline for cross-modal matching against molecular structures, or when spectra from different collision energy levels or instruments require standardization before comparative.
- ▌ Time And Memory Complexity Visualization 2 · holobiomicslabUse when when deploying a metabolomics processing tool (such as asari) and needing to predict resource requirements or validate claimed scalability on laptop-class hardware (≤16 GB RAM, single CPU core).
- ▌ Uncertainty Quantification Rt Prediction 2 · holobiomicslabUse when you have trained a DNN retention time predictor and need to rank candidate metabolites for an unknown compound: the DNN outputs both point estimates and uncertainty bounds for each candidate's RT, and you need to convert these into probabilistic scores that reflect confidence in each.
- ▌ Untargeted Metabolomics Feature Analysis 2 · holobiomicslabUse when you have a feature table from untargeted metabolomics (with m/z, retention time, and p-values from differential abundance testing) but lack or wish to bypass metabolite annotation.
- ▌ Cloud Hosted Computational Chemistry 2 · holobiomicslabUse when you have a curated dataset of ≤10,000 molecular structures with known collision cross section values for training, a target set of ≤10,000 molecules requiring CCS predictions, a compatible browser, and either lack local Python installation or prefer cloud-based execution to avoid.
- ▌ Conformer Generation And Enumeration 2 · holobiomicslabUse when you have SMILES strings of molecules at specific ionization states (e.g., protonated or deprotonated adducts) and need to predict collision cross section values for mass spectrometry-based metabolite annotation.
- ▌ Frame Metadata Extraction And Export 2 · holobiomicslabUse when after completing multidimensional smoothing and saturation repair on Agilent MassHunter (.
- ▌ Molecular Structure Dataset Curation 2 · holobiomicslabUse when you have a collection of molecular structures (with SMILES strings, InChI, or similar identifiers) and corresponding experimentally determined or reference CCS values, and you need to format and validate them as input to a machine learning CCS prediction model.
- ▌ Spike Artifact Detection And Removal 2 · holobiomicslabUse when processing raw IM-MS data (Agilent MassHunter .d or UIMF format) that exhibits isolated high-intensity noise artifacts or instrumental artifacts that appear as discrete, non-continuous signals in the retention time, ion mobility, or m/z dimensions.
- ▌ Batch Effect Correction Chromatography 2 · holobiomicslabUse when when analyzing untargeted LC/HRMS data from population-scale projects (n > 500) spanning multiple sample batches or instrument runs, peaks with identical or near-identical m/z values appear at systematically shifted retention times across batches due to instrument drift, column aging, or.
- ▌ Chemical Similarity Metric Aggregation 2 · holobiomicslabUse when when you have an unknown metabolite compound with mass spectral data, have retrieved candidate structures from a molecular structure database (PubChem, HMDB), and have obtained predictions of structurally related metabolites from a deep-learning semantic similarity model (e.g., DeepMASS2).
- ▌ Chemical Structure Format Verification 2 · holobiomicslabUse when working with mass spectrometry spectral libraries (GNPS, MoNA, MTBLS1572, MassBank) that have been preprocessed by prior teams but may contain formatting errors or entries with missing/null SMILES fields.
- ▌ Compound Class Prediction From Spectra 2 · holobiomicslabUse when you have an unknown mass spectrometry spectrum (acquired experimentally or computationally) and need to assign it to a known drug class or identify candidate structures.
- ▌ Multivariate Lipid Metabolite Analysis 2 · holobiomicslabUse when you have integrated, normalized lipidomic and metabolomic feature tables from the Multi-ABLE method or similar concurrent multiomics workflows, with matched sample phenotypes (e.
- ▌ Reference Feature Combination Strategy 2 · holobiomicslabUse when when you have isolated, high-confidence reference chromatographic peaks (ground-truth) from reference LC-HRMS chromatograms that have been matched across multiple samples, and you need to train a CNN model to detect peaks in new chromatograms but lack sufficient labelled instances.
- ▌ Spectral Data Preprocessing Lipidomics 2 · holobiomicslabUse when you have raw lipidomic and metabolomic spectral data files from a Multi-ABLE barocycler-based concurrent multiomics experiment and need to normalize ion intensities, align retention times and m/z values across samples, and remove noise or low-signal features before statistical comparison.
- ▌ Structure Database Candidate Retrieval 2 · holobiomicslabUse when you have a mass spectrum of an unknown metabolite with a known or inferred precursor m/z, you have run a deep-learning semantic similarity model (e.
- ▌ Synthetic Training Instance Generation 2 · holobiomicslabUse when when you have a small set of matched reference features (isolated, high-quality chromatographic peaks from reference chromatograms that have been aligned to a ground-truth reference list) and need to train a CNN model for peak detection in LC-HRMS profile mode data.
- ▌ Colocalization Coefficient Computation 2 · holobiomicslabUse when you have two co-registered LA-ICP-MS element channel images and need to quantify whether their spatial distributions are statistically correlated or independent. Use it specifically when investigating whether two elements co-occur spatially (e.
- ▌ Mass Spectrometry Image Reconstruction 2 · holobiomicslabUse when you have paired .imzML (XML metadata) and .
- ▌ Multimodal Spot Correspondence Mapping 2 · holobiomicslabUse when when you have paired spatial transcriptome and metabolome datasets in h5ad format with spatial coordinate matrices (obsm['spatial']) and you need to establish spot-level correspondence across modalities for downstream integration or co-analysis.
- ▌ Conda Environment Creation And Management 2 · holobiomicslabUse when when setting up a new computational workflow (e.g., ENPKG) that depends on pinned versions of Python packages and system libraries, or when collaborating across machines where package availability or versions may differ.
- ▌ Automated Feature Extraction From Spectra 2 · holobiomicslabUse when when you have raw or processed direct-infusion MS (DI-MS) or ASAP-MS spectra as mz/intensity pairs and need to rapidly identify salient peaks for species authentication, sample scoring, or comparative profiling without manual inspection.
- ▌ Block Layout Analysis For Io Optimization 2 · holobiomicslabUse when when preparing NMR datasets for processing in NMRFx and the Dataset.createDataFile() method must choose among competing storage backends.
- ▌ Chemical Annotation Confidence Assessment 2 · holobiomicslabUse when when you have received chemical annotations from GNPS spectral library matching workflow and need to assess their reliability before downstream analysis (e.g., chemical explorer visualization, sample filtering, or comparative metabolomics).
- ▌ Chemical Structure Annotation Oracle Mode 2 · holobiomicslabUse when you have a known compound structure with validated MS/MS spectrum and a structural analog (modified version) with its own MS/MS spectrum, and you need to assess whether a modification site prediction method correctly identifies which atoms were altered.
- ▌ Chemical Structure Descriptor Computation 2 · holobiomicslabUse when when you have a set of molecular structures (N-Me derived unsaturated sterol lipids or structurally similar organic molecules with C=C bonds) represented as SMILES or molecular geometry files, and you need to train or apply a machine-learning model to predict an instrument-dependent.
- ▌ Chimeric Spectrum Detection And Filtering 2 · holobiomicslabUse when you have acquired LC-MS/MS data in Data-Dependent Acquisition (DDA) mode for untargeted metabolomics and suspect contamination from chimeric (co-fragmented) MS/MS spectra.
- ▌ Compound Annotation Confidence Assessment 2 · holobiomicslabUse when you have MS/MS spectra matched to a reference library via both identity search (exact or high-similarity matches) and fuzzy/analog search (structurally related compounds with similar fragmentation), and you need to prioritize which annotations to trust for downstream reporting, validation.
- ▌ Contrastive Learning Encoder Construction 2 · holobiomicslabUse when you have mass spectrometry imaging (MSI) data with ion images that need low-dimensional representation learning for downstream tasks like co-localized ion searching or isotope discovery.
- ▌ Convolutional Neural Network Layer Design 2 · holobiomicslabUse when you have 1H NMR spectral tensors as input and need to extract local features (e.g., peak patterns, signal neighborhoods) before applying attention-based or sequence-level processing.
- ▌ Decision Tree Training And Interpretation 2 · holobiomicslabUse when you have tandem mass spectra data and need to predict a discrete molecular property (e.g., presence/absence of a sulfo group) while maintaining full interpretability of the decision logic.
- ▌ Deep Learning Architecture Implementation 2 · holobiomicslabUse when you have two augmented versions of the same ion image (from mass spectrometry imaging data) and need to extract learnable 512-dimensional feature representations using a shared-weight encoder for contrastive loss optimization.
- ▌ Feature To Metabolite Network Propagation 2 · holobiomicslabUse when you have an untargeted metabolomics feature table (m/z, retention time, p-value from statistical test) but lack comprehensive metabolite identifications or MS/MS annotations.
- ▌ Functional Module Inference From Networks 2 · holobiomicslabUse when you have an untargeted metabolomics feature table (m/z and retention time columns) and a statistical test result (p-value) per feature, but lack confident metabolite identifications.
- ▌ Gaussian Process Regression Model Fitting 2 · holobiomicslabUse when after you have accumulated experimental MS data from ≥2 LC gradient trials, extracted separation efficiency metrics (retention time spacing) from each trial, and encoded each gradient as a feature vector.
- ▌ Injection Order Assignment And Scheduling 2 · holobiomicslabUse when designing multi-batch LC/GC-MS experiments where you need to control for batch effects (e.g., instrument drift, reagent lot variation) and have identified both a balance dimension (e.g., sample group, treatment condition) and a randomization dimension (e.
- ▌ M Z Database Matching With Mass Tolerance 2 · holobiomicslabUse when you have a set of observed m/z values extracted from a Cardinal MSImagingExperiment object, raw LC-MS data, or similar high-throughput MS dataset, and you need to assign them to known metabolites in a reference database (HMDB, Lipidmaps, etc.) with control over mass accuracy tolerance and.
- ▌ Mass Spectrometry Data Loader Integration 2 · holobiomicslabUse when you have mass spectrometry data available in multiple identifier formats (GNPS Task ID, Universal Spectrum Identifier, or Feature-Based Molecular Networking task reference) and need to route each format to its specific loader without manual preprocessing.
- ▌ Metabolite Signal Extraction From Lc Hrms 2 · holobiomicslabUse when you have raw untargeted LC/HRMS data (mzXML, mzML, or netCDF format) from population-scale studies (n > 500 samples) and need to extract a comprehensive peaklist with aligned features across all samples.
- ▌ Metabolomics Model Performance Comparison 2 · holobiomicslabUse when you have trained multiple machine learning classifiers (e.g., AdaBoost, SVM, Random Forest) on the same metabolomics peak-quality training set using k-fold cross-validation with repeated runs (e.
- ▌ Microbial Genome Annotation Harmonization 2 · holobiomicslabUse when you have draft metabolic reconstructions (in SBML or standard format) for multiple organisms sampled from the same microbial community and need to produce a single consensus model per organism that reflects only metabolic capabilities agreed upon across the input reconstructions, or when.
- ▌ Molecular Network Clustering And Analysis 2 · holobiomicslabUse when after generating candidate transformed structures from biotransformation rules and when you have MS/MS spectral feature data that you wish to organize into putative molecular families.
- ▌ Nmr Metabolomic Quality Control Reporting 2 · holobiomicslabUse when you have uploaded a pre-analytical data table containing sample metadata, processing delay timestamps (pre- and post-centrifugation), and NMR metabolomic measurements for a cohort of plasma or serum samples, and you need to assess how processing delays affect metabolite concentrations and.
- ▌ Nmr Spectrum Tiling Format Interpretation 2 · holobiomicslabUse when when loading or creating an NMR spectral dataset (Dataset.createDataFile) and the system must decide between multiple storage backends (SubMatrixFile, BigMappedMatrixFile, MappedSubMatrixFile, MappedMatrixFile). Triggers include: (1) dataset metadata specifies a cache-file flag;
- ▌ Pca Dimensionality Reduction Unsupervised 2 · holobiomicslabUse when you have a feature-by-sample matrix (rows = annotated chemical features such as m/z, retention time, GNPS spectral library matches;
- ▌ Probability Prediction Metric Computation 2 · holobiomicslabUse when after running ModiFinder's probability generation on a known compound–modified compound pair, you have a vector of per-atom modification probabilities and need to validate whether the predicted probability peaks align with the true modification sites.
- ▌ Retention Time Mass Tolerance Calibration 2 · holobiomicslabUse 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.
- ▌ Retention Time Prediction From Structures 2 · holobiomicslabUse 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.
- ▌ Singular Value Decomposition Metabolomics 2 · holobiomicslabUse when when you have a log2-normalized, zero-mean, unit-variance intensity matrix (rows=metabolites, columns=samples) and a curated metabolite set database (e.
- ▌ Statistical Filtering Metabolite Features 2 · holobiomicslabUse when when you have peak area tables (unlabeled C12 and labeled C13) from LC-MS metabolomics with sample metadata indicating case and control groups, and you need to distinguish true metabolic changes from instrumental noise or batch artifacts before attempting isotopic pairing.
- ▌ Tandem Mass Spectra Fragmentation Parsing 2 · holobiomicslabUse when when you have raw tandem mass spectra in mz/intensity format with precursor m/z values, and need to extract all fragmentation features (observed peaks and neutral losses) as a foundation for building interpretable machine learning models.
- ▌ Tissue Specific Metabolite Quantification 2 · holobiomicslabUse when you have LC-IM-MS/MS raw data from multiple tissue samples and need to identify and quantify unsaturated sterol lipids at the isomer level (distinguishing double-bond position and stereochemistry).
- ▌ Mass Grid Index Traversal And Retrieval 2 · holobiomicslabUse when when you have constructed a MassGrid (m/z-aligned mass tracks across multiple samples) and need to retrieve all sample-specific mass tracks for a given m/z value in order to sum their intensities, apply retention time calibration, or construct composite mass track objects for peak.
- ▌ Molecular Structure Tokenization Smiles 2 · holobiomicslabUse when when you have molecular structures encoded as SMILES strings and need to incorporate them into a multi-modal language model (such as BART) that also processes mass spectra.
- ▌ Multistage Neural Architecture Training 2 · holobiomicslabUse when you have paired mass spectra and molecular structure datasets and need to train a model that jointly understands both modalities for tasks like structure elucidation. Specifically, use it when: (1) you have large unlabeled or weakly-labeled pretraining data with both spectra and molecules;