peptdeep.model.featurize¶

Functions:

`get_ascii_indices`(seq_array)	Convert peptide sequences into ASCII code array.
`get_batch_aa_indices`(seq_array)	Convert peptide sequences into AA ID array.
`get_batch_mod_feature`(batch_df)
`parse_instrument_indices`(instrument_list)
`parse_mod_feature`(nAA, mod_names, mod_sites)	Get modification feature of a given peptide (len=nAA).

peptdeep.model.featurize.get_ascii_indices(seq_array: List | ndarray) → ndarray[source][source]¶

Convert peptide sequences into ASCII code array. The values are from 0 to 127. Zeros are padded into the N- and C-term for each sequence.

Parameters:: seq_array (Union[List,np.ndarray]) – list or 1-D array of sequences.
Returns:: 2-D np.int32 array with the shape (len(seq_array), max seq length+2). For the the sequence whose length is shorter than max seq length, zeros are padded to the missing values.
Return type:: np.ndarray

peptdeep.model.featurize.get_batch_aa_indices(seq_array: List | ndarray) → ndarray[source][source]¶

Convert peptide sequences into AA ID array. ID=0 is reserved for masking, so ID of ‘A’ is 1, ID of ‘B’ is 2, …, ID of ‘Z’ is 26 (maximum). Zeros are padded into the N- and C-term for each sequence.

Parameters:: seq_array (Union[List,np.ndarray]) – list or 1-D array of sequences with the same length
Returns:: 2-D np.int32 array with the shape (len(seq_array), len(seq_array[0])+2). Zeros is padded into the N- and C-term of each sequence, so the 1st-D is len(seq_array[0])+2.
Return type:: np.ndarray

peptdeep.model.featurize.get_batch_mod_feature(batch_df: DataFrame) → ndarray[source][source]¶

Parameters:: batch_df (pd.DataFrame) – dataframe with ‘sequence’, ‘mods’, ‘mod_sites’ and ‘nAA’ columns. All sequence lengths must be the same, meaning that nAA values must be equal.
Returns:: 3-D tensor with shape (batch_size, nAA+2, mod_feature_size)
Return type:: np.ndarray

peptdeep.model.featurize.parse_instrument_indices(instrument_list)[source][source]¶

peptdeep.model.featurize.parse_mod_feature(nAA: int, mod_names: List[str], mod_sites: List[int]) → ndarray[source][source]¶

Get modification feature of a given peptide (len=nAA). Note that site=0 is for peptide N-term modification, site=-1 is for peptide C-term modification, and 1<=site<=nAA is for residue modifications on the peptide.

Parameters:

nAA (int) – the lenght of the peptide sequence
mod_names (List[str]) – the modification names
mod_sites (List[str]) – the modification sites corresponding to mod_names on the peptide

Returns:

2-D feature array with shape (nAA+2,mod_feature_size)

Return type:

np.ndarray