Skip to content

K-Dense-AI/scientific-agent-skills / skills/pyopenms

pyopenms

Verified

Processes mass spectrometry data with pyOpenMS. Supports proteomics and metabolomics workflows—feature detection, peptide/protein identification, label-free quantification, adduct/accurate-mass annotation, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. For simple spectral comparison and small-molecule library matching use matchms.

scripts/process_spectra.py

View on GitHub
#!/usr/bin/env python3
"""
Signal Processing for Spectra

Apply a configurable chain of signal-processing steps to all (or selected MS-level)
spectra in an MS file: smoothing, centroiding (peak picking), normalization, and
intensity/S-N thresholding. Steps run in the order listed below.

Steps (enable with flags):
    --smooth gauss|sgolay   Smooth profile data
    --pick                  Centroid profile data (PeakPickerHiRes)
    --normalize to_one|to_TIC   Normalize intensities
    --threshold FLOAT       Remove peaks below absolute intensity
    --sn FLOAT              Remove peaks below this signal-to-noise ratio

Usage:
    python process_spectra.py raw.mzML centroided.mzML --smooth gauss --pick
    python process_spectra.py data.mzML out.mzML --normalize to_one --threshold 0.01
    python process_spectra.py data.mzML out.mzML --ms-level 1 --sn 2.0
"""

import argparse
import os
import sys

try:
    import pyopenms as ms
except ImportError:
    print("Error: pyopenms not installed. Install with: uv pip install pyopenms")
    sys.exit(1)


def main():
    parser = argparse.ArgumentParser(description="Apply signal processing to spectra.")
    parser.add_argument("input", help="Input mzML/mzXML file")
    parser.add_argument("output", help="Output mzML file")
    parser.add_argument("--ms-level", type=int, help="Process only this MS level (others passed through)")
    parser.add_argument("--smooth", choices=["gauss", "sgolay"], help="Smoothing filter")
    parser.add_argument("--gaussian-width", type=float, default=0.2, help="Gaussian width in m/z (Th; default 0.2)")
    parser.add_argument("--pick", action="store_true", help="Centroid via PeakPickerHiRes")
    parser.add_argument("--signal-to-noise", type=float, default=0.0,
                        help="PeakPicker S/N threshold (0 = off, default)")
    parser.add_argument("--normalize", choices=["to_one", "to_TIC"], help="Normalization method")
    parser.add_argument("--threshold", type=float, help="Remove peaks below this absolute intensity")
    parser.add_argument("--sn", type=float, help="Remove peaks below this S/N (SignalToNoiseEstimatorMedian)")
    parser.add_argument("--assume-profile", action="store_true", help="Allow smoothing/picking unknown spectrum type after independent verification")
    args = parser.parse_args()

    if not os.path.exists(args.input):
        print(f"Error: file not found: {args.input}")
        sys.exit(1)

    exp = ms.MSExperiment()
    ms.FileHandler().loadExperiment(args.input, exp)
    print(f"Loaded {exp.getNrSpectra()} spectra")

    # Work on copies and explicitly replace the experiment spectra. Iterating
    # an MSExperiment does not promise writable references to its C++ storage.
    processed = []
    for original in exp:
        spec = ms.MSSpectrum(original)
        if args.ms_level is not None and spec.getMSLevel() != args.ms_level:
            processed.append(spec)
            continue
        spec.sortByPosition()
        if args.smooth or args.pick:
            kind = spec.getType()
            if kind == ms.SpectrumSettings.SpectrumType.CENTROID:
                parser.error("smoothing/peak picking requires profile spectra; select a profile MS level")
            if kind == ms.SpectrumSettings.SpectrumType.UNKNOWN and not args.assume_profile:
                parser.error("spectrum type unknown; verify profile acquisition before --assume-profile")
        if args.smooth:
            smoother = ms.GaussFilter() if args.smooth == "gauss" else ms.SavitzkyGolayFilter()
            if args.smooth == "gauss":
                p = smoother.getParameters()
                p.setValue("gaussian_width", args.gaussian_width)
                smoother.setParameters(p)
            smoother.filter(spec)
        if args.pick:
            picker = ms.PeakPickerHiRes()
            p = picker.getParameters()
            p.setValue("signal_to_noise", args.signal_to_noise)
            picker.setParameters(p)
            picked = ms.MSSpectrum()
            picker.pick(spec, picked)
            spec = picked
        if args.normalize:
            normalizer = ms.Normalizer()
            p = normalizer.getParameters()
            p.setValue("method", args.normalize)
            normalizer.setParameters(p)
            normalizer.filterSpectrum(spec)
        if args.sn is not None:
            estimator = ms.SignalToNoiseEstimatorMedian()
            estimator.init(spec)
            spec.select([i for i in range(len(spec)) if estimator.getSignalToNoise(i) >= args.sn])
        if args.threshold is not None:
            _, intensity = spec.get_peaks()
            spec.select((intensity >= args.threshold).nonzero()[0].tolist())
        processed.append(spec)
    exp.setSpectra(processed)

    ms.MzMLFile().store(args.output, exp)
    print(f"Wrote {args.output}")


if __name__ == "__main__":
    main()
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall