Performance & cost
7,061 rows, by stacks then stars
853 of these skill files have been read, by 797 distinct authors, and what they tell an agent counted. What Performance & cost authors agree on, and what they forbid
Metabolite detection and acquisition performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/metabolite-detection-and-acquisition-performance-benchmarking Skill
16★ repoUse when you have simulated or experimental mzML data from two or more fragmentation controllers (e.
Metabolite rank performance evaluation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/metabolite-rank-performance-evaluation Skill
16★ repoUse when after training an ensemble model (MLP, GNN, or ESP) on spectral data, use this skill to measure performance on test spectra where ground-truth metabolite identities are known. Essential for comparing model variants (e.
Metabolomics model performance comparison
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/metabolomics-model-performance-comparison Skill
16★ repoUse 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.
Modularity optimization clustering
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/modularity-optimization-clustering Skill
16★ repoUse when after MS-DIAL peak character estimation has grouped LC-MS features into preliminary clusters based on peak shape and chromatographic similarity, and you need to select a single representative parental feature from each cluster to reduce redundancy before MS-FINDER annotation.
Molecular conformer generation and optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/molecular-conformer-generation-and-optimization Skill
16★ repoUse when you have SMILES strings or 2D molecular structures of N-Me derived unsaturated sterol lipids (or other C=C-containing molecules) and need to generate 3D conformational and electronic structure data as input to a machine-learning CCS prediction model.
Motif pseudo spectra optimization filtering
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/motif-pseudo-spectra-optimization-filtering Skill
16★ repoUse when after LDA has converged and inferred Mass2Motifs from preprocessed mass spectrometry spectral data, when the raw motif-fragment distributions contain noise or low-confidence associations that obscure the dominant fragmentation patterns.
Multi window mass range parameter optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/multi-window-mass-range-parameter-optimization Skill
16★ repoUse when you observe sawtooth or discontinuous peak profiles in EICs after running tardisPeaks() on LC-MS data acquired with multiple overlapping or sequential m/z scan windows (e.g., positive and negative polarity scans, or data-independent acquisition with staggered windows).
Neural network threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/neural-network-threshold-optimization Skill
16★ repoUse when after training a NeatMS neural network model on labelled peak data (High_quality, Low_quality, Noise) and you need to determine the optimal probability threshold for classifying peaks in your untargeted LCMS dataset.
Noise artifact reduction optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/noise-artifact-reduction-optimization Skill
16★ repoUse when you have imported a raw GCxGC-MS chromatogram (NetCDF format folded into 2D-TIC) that exhibits chemical noise, instrumental artifacts, or baseline drift—conditions that obscure true metabolite signals and impede between-group differentiation in downstream multivariate analysis.
Pareto front multi objective optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pareto-front-multi-objective-optimization Skill
16★ repoUse when you have evaluated a parametric denoising strategy (e.g., frequency-based filtering) at multiple threshold values and computed two or more competing metrics (e.g., signal loss and noise reduction) for each threshold.
Peak detection optimization free
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/peak-detection-optimization-free Skill
16★ repoUse when when processing raw untargeted LC/MS data in mzML or mzXML format and you need to detect peaks across mass-to-charge (m/z) and retention time (rt) dimensions without prior knowledge of optimal signal detection parameters, QC samples, or domain expertise in LC/MS preprocessing.
Peak height threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/peak-height-threshold-optimization Skill
16★ repoUse when you have raw metabolomic LC-MS data processed through XCMS CentWave feature extraction and want to improve true positive feature recovery while controlling false positive rate and crash likelihood.
Peak intensity threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/peak-intensity-threshold-optimization Skill
16★ repoUse when you have loaded raw mass spectrometry spectral data (in MGF, MSP, mzML, or mzXML format) and need to decide which intensity threshold(s) to use for filtering out noise and low-abundance peaks.
Peak picking performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/peak-picking-performance-benchmarking Skill
16★ repoUse when when you have completed non-targeted peak picking and alignment with tools such as MZmine 2, XCMS, or MS-DIAL on LC-HRMS mzML data and need to quantify performance metrics (found peaks %, degenerated isotopologue ratio, alignment errors) by comparing against a curated benchmark of known.
Peak quality classifier optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/peak-quality-classifier-optimization Skill
16★ repoUse when after calculating 12 peak-quality metrics on a development set of extracted ion chromatograms (EICs) and labeled peaks, when you need to select both the classification algorithm and its optimal hyperparameters before training a final model on held-out test data.
Performance benchmarking computational systems
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/performance-benchmarking-computational-systems Skill
16★ repoUse when you have implemented or reconstructed a performance-critical computational module (e.g., an expeditious querying engine, a database lookup accelerator, or a real-time matching algorithm) and need to validate that it achieves claimed throughput targets.
Performance threshold filtering and analysis
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/performance-threshold-filtering-and-analysis Skill
16★ repoUse when when a trained model produces probabilistic or ensemble predictions and you need to achieve a specific target accuracy metric (e.g., RMSE ≤ 0.1) or minimize error on a test set, but the unfiltered model does not meet that target.
Precision recall optimization in spectral annotation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/precision-recall-optimization-in-spectral-annotation Skill
16★ repoUse when you have extracted fragmentation patterns from a collection of MS/MS spectra (using mineMS2) and have partitioned spectra into components via GNPS molecular networking (e.g., connected components, cliques, or high-similarity pairs with cosine > threshold).
Pytorch model training and optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pytorch-model-training-and-optimization Skill
16★ repoUse when when you have preprocessed molecular graph representations (from Preprocess.py or equivalent) and need to train a regression model to predict continuous retention time targets.
Rank performance metric computation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/rank-performance-metric-computation Skill
16★ repoUse when when you have predictions from one or more metabolite annotation models (MLP baseline, GNN, or ESP ensemble) and need to quantify ranking performance on ESI/LC-MS test spectra.
Ranking performance evaluation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ranking-performance-evaluation Skill
16★ repoUse when after running retention-order prediction experiments on a test or held-out evaluation dataset.
Ranking task loss optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ranking-task-loss-optimization Skill
16★ repoUse when you have multiple pre-trained neural network models (e.g., MLP and GNN) that produce overlapping predictions on the same set of candidates, and your evaluation metric is rank-based (average rank, Rank@K) rather than point-wise accuracy or RMSE.
Retention time prediction optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/retention-time-prediction-optimization Skill
16★ repoUse 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.
Rsd threshold parameter optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/rsd-threshold-parameter-optimization Skill
16★ repoUse when when preparing XCMS peak tables for quality classification and you observe that the default RSD threshold (0.3 or 30%) is either too permissive (retaining noisy EICs) or too stringent (discarding valid signals).
Runtime performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/runtime-performance-benchmarking Skill
16★ repoUse when when you have implemented or adopted a new clustering or analysis tool and need to validate that it meets stated runtime claims on a representative production-scale dataset. Particularly important when the tool uses hardware acceleration (GPU) and the claimed speedup is a core contribution;
Scalability extrapolation and throughput estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/scalability-extrapolation-and-throughput-estimation Skill
16★ repoUse when you have a new or modified LC-MS data processing tool and need to determine whether it can handle production-scale sample cohorts (50–100+ samples) on modest hardware (single-core CPU, ≤16 GB RAM).
Separation efficiency calculation from retention times
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/separation-efficiency-calculation-from-retention-times Skill
16★ repoUse when you have extracted retention times from MS1 spectra for top signals in a single LC-MS/MS run and need to evaluate whether that gradient's separation performance is sufficient, or when you are building the objective function for an iterative gradient optimization loop where each candidate.
Silhouette analysis threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/silhouette-analysis-threshold-optimization Skill
16★ repoUse when when you have a pre-computed hierarchical dendrogram from structural clustering (e.g., of LC-MS features based on m/z and retention time) and want to compare or validate the cluster assignments produced by a fixed constant-threshold method.
Software performance characterization and scaling analysis
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/software-performance-characterization-and-scaling-analysis Skill
16★ repoUse when when a tool claims to be 'scalable' or 'performance-conscious' but lacks published performance benchmarks, or when you need to confirm that runtime and memory scale linearly (or predictably) with sample count before deploying the tool on large LC-MS datasets (e.g., >100 samples).
Spectral alignment optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/spectral-alignment-optimization Skill
16★ repoUse when when you have two MS/MS fragmentation spectra (with precursor m/z values and fragment ion lists) and need to establish correspondence between their fragment ions beyond simple pairwise comparison.
Spectral peak frequency threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/spectral-peak-frequency-threshold-optimization Skill
16★ repoUse when you have MS/MS spectra with fragment frequency annotations (from consensus spectrum generation) and need to decide which fragments to retain versus remove. Trigger conditions: (1) you have replicate MS/MS spectra for the same feature with per-fragment recurrence frequencies calculated;
Spectrum alignment performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/spectrum-alignment-performance-benchmarking Skill
16★ repoUse when you have tandem MS spectra from structurally related or known compounds and need to decide which similarity metric will maximize correct ranking of related molecules in a spectral library search.
Sql query optimization for similarity search
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/sql-query-optimization-for-similarity-search Skill
16★ repoUse when when migrating spectral library data from file-based formats (JSON, CSV, binary) into a persistent store and need to support fast filtered queries on metadata and similarity computations against query spectra.
Tanimoto score threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/tanimoto-score-threshold-optimization Skill
16★ repoUse when when you have a set of MS/MS spectra with ground-truth structural similarity labels (Tanimoto scores computed from molecular fingerprints) and need to choose a decision threshold for classifying spectrum pairs as 'chemically related' or 'unrelated'.
Targeted metabolite detection parameter optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/targeted-metabolite-detection-parameter-optimization Skill
16★ repoUse when when you have centroided .mzML LC–MS runs and a target list (compound ID, theoretical m/z, expected RT, polarity) but are uncertain whether your m/z and RT windows are wide enough to capture all targets without false positives.
Tensorflow cpu runtime parameter tuning
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/tensorflow-cpu-runtime-parameter-tuning Skill
16★ repoUse when deploying Mass2SMILES on a TensorFlow-CPU build and you need to optimize inference throughput on multi-core systems. This is particularly necessary when GPU inference is unavailable due to CUDA driver incompatibility, or when inference hardware has variable core counts (e.
Thread utilization profiling and validation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/thread-utilization-profiling-and-validation Skill
16★ repoUse when when deploying Mass2SMILES inference on CPU-only hardware (e.g., when GPU/CUDA support is unavailable), you need to verify that the InferenceModel cpu_threads parameter (e.g., cpu_threads=128) actually controls thread allocation during execution.
Throughput optimization ms querying
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/throughput-optimization-ms-querying Skill
16★ repoUse when you have experimental MS/MS spectra that must be matched against a large hierarchical fragmentation library (e.g., 168.
Topic modeling hyperparameter optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/topic-modeling-hyperparameter-optimization Skill
16★ repoUse when when preparing to apply LDA to a new MS/MS spectral dataset in bag-of-fragments format, before running the full modeling pipeline.
Tree structure optimization for metabolite deconvolution
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/tree-structure-optimization-for-metabolite-deconvolution Skill
16★ repoUse when you have a connected subnetwork of LC-MS features that matched isotope or adduct patterns, and you need to establish a canonical tree representation with a single neutral mass assignment.
Xcms parameter optimization msw
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/xcms-parameter-optimization-msw Skill
16★ repoUse when when you have direct-injection or low-complexity mass spectrometry data (mzML files) and need to detect chromatographic peaks using wavelet-based methods instead of centWave, especially when standard retention-time-dependent peak detection is not suitable or when you need to tune.
Backend performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/backend-performance-benchmarking Skill
16★ repoUse when when you have execution time data for visualization scripts across multiple backends (matplotlib, Bokeh, Plotly) and need to determine which backend offers the fastest median performance for specific mass spectrometry plot types (chromatogram, mobilogram, peakmap, peakmap-marginals.
Backend performance comparison
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/backend-performance-comparison Skill
16★ repoUse when you have execution-time metrics (from a benchmark table or profiling logs) across multiple visualization backends for the same set of plots (e.
Classification performance evaluation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/classification-performance-evaluation Skill
16★ repoUse when after running inference on test mass spectrometry spectra with a trained deep learning model (e.g., PS2MS) to verify that class label predictions and confidence scores match expected reference outputs.
Comparative performance profiling
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/comparative-performance-profiling Skill
16★ repoUse when when you have implemented a new or optimized mass spectrometry data processing library and need to demonstrate its computational advantage over established alternatives (e.g., pymzML, pyOpenMS) on real proteomics data. Trigger on availability of: (1) a common input dataset (e.
Computational performance benchmarking and timing measurement
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/computational-performance-benchmarking-and-timing-measurement Skill
16★ repoUse when when you need to validate that a newly published bioinformatics pipeline meets stated performance claims, or when you must characterize how execution time scales with dataset size (sample count, peak count, or formula complexity) and optional analysis features (e.
Computational throughput measurement
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/computational-throughput-measurement Skill
16★ repoUse when when you need to compare the computational efficiency of different mass spectrometry libraries on identical data and processing pipelines, or when you want to establish baseline throughput for a library version and validate claims of performance improvement.
Cpu gpu performance benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/cpu-gpu-performance-benchmarking Skill
16★ repoUse when you have implemented both CPU and GPU versions of a spectral search algorithm (e.g., approximate nearest neighbor indexing with cascade filtering) and need to validate whether GPU acceleration is justified.
High dimensional similarity search optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/high-dimensional-similarity-search-optimization Skill
16★ repoUse when when you have a large spectral library (thousands to millions of spectra) represented as high-dimensional vectors and need to match unknown query spectra against it, but exhaustive pairwise comparison is computationally prohibitive.
High performance metric computation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/high-performance-metric-computation Skill
16★ repoUse when you have implemented or are evaluating an algorithmic or system optimization (e.g., MASST+) that claims to reduce execution time, and you need to quantify and statistically validate the speedup against a baseline system (e.g., MASST).
Hnsw graph construction and optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/hnsw-graph-construction-and-optimization Skill
16★ repoUse when when you have pre-computed Word2vec spectrum embeddings and need to perform fast approximate nearest-neighbor retrieval from a library of millions of spectra (e.g., NIST 2017, MassBank, or in-silico predicted spectra).
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/least-squares-optimization-1d Skill
16★ repoUse when when you have a 1D signal array (e.g., extracted ion chromatogram, arrival time distribution, or MS1 spectrum intensity profile) and need to identify and quantify overlapping or adjacent peaks with precise position, height, and width estimates.
Mass spectrometry benchmark design
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/mass-spectrometry-benchmark-design Skill
16★ repoUse when when claiming that one mass spectrometry processing library achieves higher throughput than competitors, or when evaluating whether a new or optimized implementation delivers the expected computational efficiency gains.
Memory profiling and benchmarking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/memory-profiling-and-benchmarking Skill
16★ repoUse when when designing or optimizing backends that handle large MS datasets (mzML, mzXML, CDF files via MsBackendMzR), to verify that claimed memory advantages of on-disk or chunked approaches actually materialize in practice.
Metadata column profiling across datasets
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/metadata-column-profiling-across-datasets Skill
16★ repoUse when you are curating metabolomics datasets with variable column naming conventions and need to detect, normalize, and populate standardized database-ID columns (HMDB_ID, PubChem_ID, KEGG_ID, etc.) across many mwTab files before deposition.
Peak detection parameter optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/peak-detection-parameter-optimization Skill
16★ repoUse when when loading and processing raw or recalibrated FT-ICR mass spectrum data (Bruker .d format) on a defined field-strength instrument (e.g., 12 T or 15 T), before executing molecular formula search.
Peak parameter optimization for targeted compounds
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/peak-parameter-optimization-for-targeted-compounds Skill
16★ repoUse when you have centroided high-resolution Orbitrap or GC-CI-MS mzML files and a formulaTable of target compounds with known m/z, retention time, and molecular formula, and you need to extract isotopologue abundances and quantification metrics (area, maxo intensity, ppm error) for each labeled.
Performance metric comparison across backends
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/performance-metric-comparison-across-backends Skill
16★ repoUse when when you have access to a set of gallery or benchmark scripts executed across multiple plotting backends and need to quantify which backend delivers the fastest median execution time for specific mass spectrometry plot types (chromatogram, mobilogram, peakmap, peakmap-marginals, spectrum.
Quality control threshold optimization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/quality-control-threshold-optimization Skill
16★ repoUse when when you have extracted a peak feature table (CSV or tabular format) with mass-to-charge ratios, retention times, and intensity values across multiple samples, and you need to distinguish genuine differential metabolic signals from instrumental noise or low-abundance background before.
Query latency throughput measurement
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/query-latency-throughput-measurement Skill
16★ repoUse when when you have implemented or obtained a spectral library search algorithm (such as Flash Entropy Search) and need to empirically verify its performance against reported benchmark metrics, or when comparing query performance across different library sizes, mass spectral file formats (.mgf, .