MSExperiment#

class pyopenms.MSExperiment(*args, **kwargs)#

Bases: MSExperiment

__init__(*args, **kwargs)#

Overload:

__init__(self) → None

Overload:

__init__(self, in_0: MSExperiment) → None

Methods

`__init__`(args, *kwargs)
`addChromatogram`(self, chromatogram)
`addSpectrum`(self, spec)
`aggregateFromMatrix`(self, ranges, ms_level, ...)	Aggregates intensity values for multiple m/z and RT ranges specified in a matrix
`calculateTIC`(self)	Returns the total ion chromatogram
`chromatogramRanges`(self)	Returns a reference to the chromatogram range manager
`clear`(self, clear_meta_data)	Clear all spectra data and meta data (if called with True)
`clearMetaDataArrays`(self)
`clearMetaInfo`(self)	Removes all meta values
`clearRanges`(self)	Clear all ranges in all range managers
`empty`(self)
`extractXICsFromMatrix`(self, ranges, ...)	Extracts XIC chromatograms for multiple m/z and RT ranges specified in a matrix
`get2DPeakData`	Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty] get2DPeakData(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)
`get2DPeakDataIM`	Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty, np.array[float] ion_mobility] get2DPeakDataIM(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)
`get2DPeakDataIMLong`	Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty, np.array[float] ion_mobility] get2DPeakDataIMLong(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)
`get2DPeakDataLong`	Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty] get2DPeakDataLong(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)
`getChromatogram`	Cython signature: MSChromatogram getChromatogram(size_t id_)
`getChromatograms`(self)
`getComment`(self)	Returns the free-text comment
`getContacts`(self)	Returns a reference to the list of contact persons
`getDateTime`(self)	Returns the date the experiment was performed
`getExperimentalSettings`(self)
`getFractionIdentifier`(self)	Returns fraction identifier
`getHPLC`(self)	Returns a reference to the description of the HPLC run
`getIdentifier`(self)	Retrieve document identifier (e.g. an LSID).
`getInstrument`(self)	Returns a reference to the MS instrument description
`getKeys`(self, keys)	Fills the given vector with a list of all keys for which a value is set
`getLoadedFilePath`(self)	Returns the file_name which is the absolute path to the file loaded
`getLoadedFileType`(self)	Returns the file_type (e.g. featureXML, consensusXML, mzData, mzXML, mzML, ...) of the file loaded.
`getMSLevels`	Cython signature: list[int] getMSLevels()
`getMaxIntensity`(self)	Get the maximum intensity value from the combined ranges
`getMaxMZ`(self)	Get the maximum m/z value from the combined ranges
`getMaxMobility`(self)	Get the maximum mobility value from the combined ranges
`getMaxRT`(self)	Get the maximum RT value from the combined ranges
`getMetaValue`(self, in_0)	Returns the value corresponding to a string, or
`getMinIntensity`(self)	Get the minimum intensity value from the combined ranges
`getMinMZ`(self)	Get the minimum m/z value from the combined ranges
`getMinMobility`(self)	Get the minimum mobility value from the combined ranges
`getMinRT`(self)	Get the minimum RT value from the combined ranges
`getNrChromatograms`(self)	Returns the number of chromatograms
`getNrSpectra`(self)	Returns the number of MS spectra
`getPrecursorSpectrum`(self, zero_based_index)	Returns the index of the precursor spectrum for spectrum at index @p zero_based_index
`getPrimaryMSRunPath`(self, toFill)	References to the first MS file(s) after conversions.
`getSample`(self)	Returns a reference to the sample description
`getSize`(self)	Returns the total number of peaks
`getSourceFiles`(self)	Returns a reference to the source data file
`getSpectra`(self)
`getSpectrum`	Cython signature: MSSpectrum getSpectrum(size_t id_)
`get_df`([columns, ms_levels, long])	Generates a pandas DataFrame with all peaks in the MSExperiment
`get_df_columns`([long])	Returns a list of column names that get_df() would produce.
`get_ion_df`()	Generates a pandas DataFrame with all peaks and the ion mobility in the MSExperiment
`get_massql_df`([ion_mobility])	Exports data from MSExperiment to pandas DataFrames to be used with MassQL.
`isMetaEmpty`(self)	Returns if the MetaInfo is empty
`isSorted`
`metaRegistry`(self)	Returns a reference to the MetaInfoRegistry
`metaValueExists`(self, in_0)	Returns whether an entry with the given name exists
`removeMetaValue`(self, in_0)	Removes the DataValue corresponding to name if it exists
`reserve`(self, s)
`reserveSpaceChromatograms`(self, s)
`reserveSpaceSpectra`(self, s)
`reset`(self)
`resize`(self, s)
`setChromatograms`(self, chromatograms)
`setComment`(self, comment)	Sets the free-text comment
`setContacts`(self, contacts)	Sets the list of contact persons
`setDateTime`(self, date_time)	Sets the date the experiment was performed
`setFractionIdentifier`(self, fraction_identifier)	Sets the fraction identifier
`setHPLC`(self, hplc)	Sets the description of the HPLC run
`setIdentifier`(self, id)	Sets document identifier (e.g. an LSID).
`setInstrument`(self, instrument)	Sets the MS instrument description
`setLoadedFilePath`(self, file_name)	Sets the file_name according to absolute path of the file loaded, preferably done whilst loading
`setLoadedFileType`(self, file_name)	Sets the file_type according to the type of the file loaded from, preferably done whilst loading
`setMetaValue`(self, in_0, in_1)	Sets the DataValue corresponding to a name
`setSample`(self, sample)	Sets the sample description
`setSourceFiles`(self, source_files)	Sets the source data file
`setSpectra`(self, spectra)
`size`(self)
`sortChromatograms`
`sortSpectra`
`spectrumRanges`(self)	Returns a reference to the spectrum range manager
`swap`(self, in_0)
`updateRanges`(self)	Recalculate global ranges for both spectra and chromatrograms after changes to the data has been made.

addChromatogram(self, chromatogram: MSChromatogram) → None#

addSpectrum(self, spec: MSSpectrum) → None#

aggregateFromMatrix(self, ranges: MatrixDouble, ms_level: int, mz_agg: bytes) → List[List[float]]#: Aggregates intensity values for multiple m/z and RT ranges specified in a matrix

calculateTIC(self) → MSChromatogram#: Returns the total ion chromatogram

chromatogramRanges(self) → ChromatogramRangeManager#: Returns a reference to the chromatogram range manager

clear(self, clear_meta_data: bool) → None#: Clear all spectra data and meta data (if called with True)

clearMetaDataArrays(self) → bool#

clearMetaInfo(self) → None#: Removes all meta values

clearRanges(self) → None#: Clear all ranges in all range managers

empty(self) → bool#

extractXICsFromMatrix(self, ranges: MatrixDouble, ms_level: int, mz_agg: bytes) → List[MSChromatogram]#: Extracts XIC chromatograms for multiple m/z and RT ranges specified in a matrix

get2DPeakData()#: Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty] get2DPeakData(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)

get2DPeakDataIM()#: Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty, np.array[float] ion_mobility] get2DPeakDataIM(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)

get2DPeakDataIMLong()#: Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty, np.array[float] ion_mobility] get2DPeakDataIMLong(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)

get2DPeakDataLong()#: Cython signature: tuple[np.array[float] rt, np.array[float] mz, np.array[float] inty] get2DPeakDataLong(float min_rt, float max_rt, float min_mz, float max_mz, unsigned int ms_level)

getChromatogram()#: Cython signature: MSChromatogram getChromatogram(size_t id_)

getChromatograms(self) → List[MSChromatogram]#

getComment(self) → bytes | str | String#: Returns the free-text comment

getContacts(self) → List[ContactPerson]#: Returns a reference to the list of contact persons

getDateTime(self) → DateTime#: Returns the date the experiment was performed

getExperimentalSettings(self) → ExperimentalSettings#

getFractionIdentifier(self) → bytes | str | String#: Returns fraction identifier

getHPLC(self) → HPLC#: Returns a reference to the description of the HPLC run

getIdentifier(self) → bytes | str | String#: Retrieve document identifier (e.g. an LSID)

getInstrument(self) → Instrument#: Returns a reference to the MS instrument description

getKeys(self, keys: List[bytes]) → None#: Fills the given vector with a list of all keys for which a value is set

getLoadedFilePath(self) → bytes | str | String#: Returns the file_name which is the absolute path to the file loaded

getLoadedFileType(self) → int#: Returns the file_type (e.g. featureXML, consensusXML, mzData, mzXML, mzML, …) of the file loaded

getMSLevels()#: Cython signature: list[int] getMSLevels()

getMaxIntensity(self) → float#: Get the maximum intensity value from the combined ranges

getMaxMZ(self) → float#: Get the maximum m/z value from the combined ranges

getMaxMobility(self) → float#: Get the maximum mobility value from the combined ranges

getMaxRT(self) → float#: Get the maximum RT value from the combined ranges

getMetaValue(self, in_0: bytes | str | String) → int | float | bytes | str | List[int] | List[float] | List[bytes]#: Returns the value corresponding to a string, or

getMinIntensity(self) → float#: Get the minimum intensity value from the combined ranges

getMinMZ(self) → float#: Get the minimum m/z value from the combined ranges

getMinMobility(self) → float#: Get the minimum mobility value from the combined ranges

getMinRT(self) → float#: Get the minimum RT value from the combined ranges

getNrChromatograms(self) → int#: Returns the number of chromatograms

getNrSpectra(self) → int#: Returns the number of MS spectra

getPrecursorSpectrum(self, zero_based_index: int) → int#: Returns the index of the precursor spectrum for spectrum at index @p zero_based_index

getPrimaryMSRunPath(self, toFill: List[bytes]) → None#: References to the first MS file(s) after conversions. Used to trace results back to original data.

getSample(self) → Sample#: Returns a reference to the sample description

getSize(self) → int#: Returns the total number of peaks

getSourceFiles(self) → List[SourceFile]#: Returns a reference to the source data file

getSpectra(self) → List[MSSpectrum]#

getSpectrum()#: Cython signature: MSSpectrum getSpectrum(size_t id_)

get_df(columns: None | List[str] = None, ms_levels: List[int] = [], long: bool = False)#

Generates a pandas DataFrame with all peaks in the MSExperiment

Parameters: columns (list or None): List of column names to include. If None,

includes all columns. Use get_df_columns() to discover available columns.

ms_levels (List[int]): Get only spectra with the given MS levels. Default is an empty list, which means all MS levels will be included. long (bool): set to True if you want to have a long/expanded/melted dataframe with one row per peak. Faster but

replicated RT information. If False, returns rows in the style: rt, _np.array(mz), _np.array(int)

Returns: pandas.DataFrame: feature information stored in a DataFrame

Example:

>>> # Get all columns
>>> df = exp.get_df()

>>> # Discover available columns
>>> print(exp.get_df_columns())

>>> # Get only specific columns
>>> df = exp.get_df(columns=['rt', 'mz', 'intensity'], long=True)

get_df_columns(long: bool = False) → List[str]#

Returns a list of column names that get_df() would produce.

Useful for discovering available columns before export.

Args:

long (bool): If True, returns columns for long format.: If False, returns columns for compact format.

Returns:

list: List of column name strings.

Example:

>>> exp.get_df_columns(long=True)
['rt', 'mz', 'intensity', 'ms_level']

>>> exp.get_df_columns(long=False)
['rt', 'ms_level', 'mz_array', 'intensity_array']

get_ion_df()#

Generates a pandas DataFrame with all peaks and the ion mobility in the MSExperiment

Returns: pandas.DataFrame: feature information stored in a DataFrame

get_massql_df(ion_mobility=False)#

Exports data from MSExperiment to pandas DataFrames to be used with MassQL.

The Python module massql allows queries in mass spectrometry data (MS1 and MS2 data frames) in a SQL like fashion (mwang87/MassQueryLanguage).

Both dataframes contain the columns: ‘i’: intensity of a peak ‘i_norm’: intensity normalized by the maximun intensity in the spectrum ‘i_tic_norm’: intensity normalized by the sum of intensities (TIC) in the spectrum ‘mz’: mass to charge of a peak ‘scan’: number of the spectrum ‘rt’: retention time of the spectrum ‘polarity’: ion mode of the spectrum as integer value (positive: 1, negative: 2) ‘ion’: the ionic mobility of a peak if ion parameter is True

The MS2 dataframe contains additional columns: ‘precmz’: mass to charge of the precursor ion ‘ms1scan’: number of the corresponding MS1 spectrum ‘charge’: charge of the precursor ion

Parameters:: ion (bool): if True, returns the ion mobility of the peaks.

Returns: ms1_df (pandas.DataFrame): peak data of MS1 spectra ms2_df (pandas.DataFrame): peak data of MS2 spectra with precursor information

isMetaEmpty(self) → bool#: Returns if the MetaInfo is empty

isSorted()#

Overload:

isSorted(self, check_mz: bool) → bool

Checks if all spectra are sorted with respect to ascending RT

Overload:

isSorted(self) → bool

metaRegistry(self) → MetaInfoRegistry#: Returns a reference to the MetaInfoRegistry

metaValueExists(self, in_0: bytes | str | String) → bool#: Returns whether an entry with the given name exists

removeMetaValue(self, in_0: bytes | str | String) → None#: Removes the DataValue corresponding to name if it exists

reserve(self, s: int) → None#

reserveSpaceChromatograms(self, s: int) → None#

reserveSpaceSpectra(self, s: int) → None#

reset(self) → None#

resize(self, s: int) → None#

setChromatograms(self, chromatograms: List[MSChromatogram]) → None#

setComment(self, comment: bytes | str | String) → None#: Sets the free-text comment

setContacts(self, contacts: List[ContactPerson]) → None#: Sets the list of contact persons

setDateTime(self, date_time: DateTime) → None#: Sets the date the experiment was performed

setFractionIdentifier(self, fraction_identifier: bytes | str | String) → None#: Sets the fraction identifier

setHPLC(self, hplc: HPLC) → None#: Sets the description of the HPLC run

setIdentifier(self, id: bytes | str | String) → None#: Sets document identifier (e.g. an LSID)

setInstrument(self, instrument: Instrument) → None#: Sets the MS instrument description

setLoadedFilePath(self, file_name: bytes | str | String) → None#: Sets the file_name according to absolute path of the file loaded, preferably done whilst loading

setLoadedFileType(self, file_name: bytes | str | String) → None#: Sets the file_type according to the type of the file loaded from, preferably done whilst loading

setMetaValue(self, in_0: bytes | str | String, in_1: int | float | bytes | str | List[int] | List[float] | List[bytes]) → None#: Sets the DataValue corresponding to a name

setSample(self, sample: Sample) → None#: Sets the sample description

setSourceFiles(self, source_files: List[SourceFile]) → None#: Sets the source data file

setSpectra(self, spectra: List[MSSpectrum]) → None#

size(self) → int#

sortChromatograms()#

Overload:

sortChromatograms(self, sort_rt: bool) → None

Sorts chromatograms by m/z. If sort_rt=True also sort each chromatogram RT

Overload:

sortChromatograms(self) → None

sortSpectra()#

Overload:

sortSpectra(self, sort_mz: bool) → None

Sorts spectra by RT. If sort_mz=True also sort each peak in a spectrum by m/z

Overload:

sortSpectra(self) → None

spectrumRanges(self) → SpectrumRangeManager#: Returns a reference to the spectrum range manager

swap(self, in_0: MSExperiment) → None#

updateRanges(self) → None#: Recalculate global ranges for both spectra and chromatrograms after changes to the data has been made.