from matchms.importing import load_from_mgf, load_from_mzml, load_from_msp, load_from_json
from matchms.exporting import save_as_mgf, save_as_msp, save_as_json

# Import spectra
spectra = list(load_from_mgf("spectra.mgf"))
spectra = list(load_from_mzml("data.mzML"))
spectra = list(load_from_msp("library.msp"))

# Export processed spectra
save_as_mgf(spectra, "output.mgf")
save_as_json(spectra, "output.json")

from matchms.filtering import default_filters, normalize_intensities
from matchms.filtering import select_by_relative_intensity, require_minimum_number_of_peaks

# Apply default metadata harmonization filters
spectrum = default_filters(spectrum)

# Normalize peak intensities
spectrum = normalize_intensities(spectrum)

# Filter peaks by relative intensity
spectrum = select_by_relative_intensity(spectrum, intensity_from=0.01, intensity_to=1.0)

# Require minimum peaks
spectrum = require_minimum_number_of_peaks(spectrum, n_required=5)

from matchms import calculate_scores
from matchms.similarity import CosineGreedy, ModifiedCosine, CosineHungarian

# Calculate cosine similarity (fast, greedy algorithm)
scores = calculate_scores(references=library_spectra,
                         queries=query_spectra,
                         similarity_function=CosineGreedy())

# Calculate modified cosine (accounts for precursor m/z differences)
scores = calculate_scores(references=library_spectra,
                         queries=query_spectra,
                         similarity_function=ModifiedCosine(tolerance=0.1))

# Get best matches
best_matches = scores.scores_by_query(query_spectra[0], sort=True)[:10]

from matchms import SpectrumProcessor
from matchms.filtering import default_filters, normalize_intensities
from matchms.filtering import select_by_relative_intensity, remove_peaks_around_precursor_mz

# Define a processing pipeline
processor = SpectrumProcessor([
    default_filters,
    normalize_intensities,
    lambda s: select_by_relative_intensity(s, intensity_from=0.01),
    lambda s: remove_peaks_around_precursor_mz(s, mz_tolerance=17)
])

# Apply to all spectra
processed_spectra = [processor(s) for s in spectra]

from matchms import Spectrum
import numpy as np

# Create a spectrum
mz = np.array([100.0, 150.0, 200.0, 250.0])
intensities = np.array([0.1, 0.5, 0.9, 0.3])
metadata = {"precursor_mz": 250.5, "ionmode": "positive"}

spectrum = Spectrum(mz=mz, intensities=intensities, metadata=metadata)

# Access spectrum properties
print(spectrum.peaks.mz)           # m/z values
print(spectrum.peaks.intensities)  # Intensity values
print(spectrum.get("precursor_mz")) # Metadata field

# Visualize spectra
spectrum.plot()
spectrum.plot_against(reference_spectrum)

# Metadata is automatically harmonized
spectrum.set("Precursor_mz", 250.5)  # Gets harmonized to lowercase key
print(spectrum.get("precursor_mz"))   # Returns 250.5

# Derive chemical information
from matchms.filtering import derive_inchi_from_smiles, derive_inchikey_from_inchi
from matchms.filtering import add_fingerprint

spectrum = derive_inchi_from_smiles(spectrum)
spectrum = derive_inchikey_from_inchi(spectrum)
spectrum = add_fingerprint(spectrum, fingerprint_type="morgan", nbits=2048)

pip install matchms

pip install matchms[chemistry]