oktoberfest.pr.Predictor.predict_rt

Predictor.predict_rt(data, **kwargs)

Generate retention time predictions and add them to the provided data object.

This function takes a Spectra object containing information about PSMs and predicts retention times. The configuration of Koina is set using the kwargs.

Parameters:

• data (Spectra) – Spectra object containing the data required for prediction and to store the predictions in after retrieval from the server.

• kwargs – Additional keyword arguments forwarded to Koina

Example:

>>> from oktoberfest.data.spectra import Spectra
>>> from oktoberfest import predict as pr
>>> import pandas as pd
>>> # Requiered columns: MODIFIED_SEQUENCE, COLLISION_ENERGY, PRECURSOR_CHARGE and FRAGMENTATION
>>> meta_df = pd.DataFrame({"MODIFIED_SEQUENCE": ["AAAC[UNIMOD:4]RFVQ","RM[UNIMOD:35]PC[UNIMOD:4]HKPYL"],
>>>                         "COLLISION_ENERGY": [30,35],
>>>                         "PRECURSOR_CHARGE": [1,2],
>>>                         "FRAGMENTATION": ["HCD","HCD"]})
>>> var = Spectra._gen_vars_df()
>>> library = Spectra(obs=meta_df, var=var)
>>> library.strings_to_categoricals()
>>> irt_predictor = pr.Predictor.from_koina(
>>>                         model_name="Prosit_2019_irt",
>>>                         server_url="koina.wilhelmlab.org:443",
>>>                         ssl=True)
>>> irt_predictor.predict_rt(data=library)
>>> print(library.obs["PREDICTED_IRT"])