peptdeep.spec_lib.predict_lib

Classes:

PredictSpecLib([model_manager, ...])
PredictSpecLibFlat([min_fragment_intensity, ...])	Flatten the predicted spectral library, the key feature is to predict and flatten fragments in batch with predict_and_parse_lib_in_batch()

class peptdeep.spec_lib.predict_lib.PredictSpecLib(model_manager: ModelManager = None, charged_frag_types=['b_z1', 'b_z2', 'y_z1', 'y_z2'], precursor_mz_min: float = 400.0, precursor_mz_max: float = 2000.0, decoy: str = 'pseudo_reverse', rt_to_irt: bool = False, generate_precursor_isotope: bool = False)

Bases: SpecLibBase

Methods:

__init__([model_manager, ...])
predict_all([...])
set_precursor_and_fragment(*, precursor_df)
translate_rt_to_irt_pred([irt_pep_df])	Add 'irt_pred' into columns based on 'rt_pred'

__init__(model_manager: ModelManager = None, charged_frag_types=['b_z1', 'b_z2', 'y_z1', 'y_z2'], precursor_mz_min: float = 400.0, precursor_mz_max: float = 2000.0, decoy: str = 'pseudo_reverse', rt_to_irt: bool = False, generate_precursor_isotope: bool = False)

Parameters:

• model_manager (ModelManager, optional) – ModelManager, by default None

• charged_frag_types (list, optional) – Charged fragment types, by default [‘b_z1’,’b_z2’,’y_z1’,’y_z2’]

• precursor_mz_min (float, optional) – precursor_mz_min, by default 400.0

• precursor_mz_max (float, optional) – precursor_mz_max, by default 2000.0

• decoy (str, optional) – Decoy choice, see alphabase.spec_lib.decoy_library, by default ‘pseudo_reverse’

• rt_to_irt (bool, optional) – Convert predicted RT to iRT values, by default False

• generate_precursor_isotope (bool, optional) – Generate precursor isotopes, defaults to False

predict_all(min_required_precursor_num_for_mp: int = 2000, predict_items: list = ['rt', 'mobility', 'ms2'])

1. Predict RT/IM/MS2 for self._precursor_df

2. Calculate isotope information in self._precursor_df

set_precursor_and_fragment(*, precursor_df: DataFrame, fragment_mz_df: DataFrame = None, fragment_intensity_df: DataFrame = None)

translate_rt_to_irt_pred(irt_pep_df: DataFrame = None)

Add ‘irt_pred’ into columns based on ‘rt_pred’

class peptdeep.spec_lib.predict_lib.PredictSpecLibFlat(min_fragment_intensity: float = 0.001, keep_top_k_fragments: int = 1000, custom_fragment_df_columns: list = ['type', 'number', 'position', 'charge', 'loss_type'], **kwargs)

Bases: SpecLibFlat

Flatten the predicted spectral library, the key feature is to predict and flatten fragments in batch with predict_and_parse_lib_in_batch()

Parameters:

• min_fragment_intensity (float, optional) – minimal intensity to keep, by default 0.001

• keep_top_k_fragments (int, optional) – top k highest peaks to keep, by default 1000

Methods:

__init__([min_fragment_intensity, ...])
predict_and_parse_lib_in_batch(predict_lib)	Predict and flatten fragments in batch

__init__(min_fragment_intensity: float = 0.001, keep_top_k_fragments: int = 1000, custom_fragment_df_columns: list = ['type', 'number', 'position', 'charge', 'loss_type'], **kwargs)

Parameters:

• min_fragment_intensity (float, optional) – minimal intensity to keep, by default 0.001

• keep_top_k_fragments (int, optional) – top k highest peaks to keep, by default 1000

• custom_fragment_df_columns (list, optional) – See custom_fragment_df_columns, defaults to [‘type’,’number’,’position’,’charge’,’loss_type’]

predict_and_parse_lib_in_batch(predict_lib: PredictSpecLib, batch_size: int = 200000)

Predict and flatten fragments in batch

Parameters:

• predict_lib (PredictSpecLib) – spectral library to be predicted and flatten

• batch_size (int, optional) – the batch size, by default 200000