Transfer data for NAGuideR format

Transfer data for NAGuideR format#

Hide code cell source

 
import pandas as pd

import pimmslearn
import pimmslearn.models
from pimmslearn.io import datasplits

Hide code cell source

 
# catch passed parameters
args = None
args = dict(globals()).keys()

Papermill script parameters:

# files and folders
# Datasplit folder with data for experiment
folder_experiment: str = 'runs/example'
folder_data: str = ''  # specify data directory if needed
file_format_in: str = 'csv'  # file format of original splits, default pickle (pkl)
file_format_out: str = 'csv'  # file format of transformed splits, default csv

# Parameters
folder_experiment = "runs/alzheimer_study"

Hide code cell source

 
args = pimmslearn.nb.get_params(args, globals=globals())
args

{'folder_experiment': 'runs/alzheimer_study',
 'folder_data': '',
 'file_format_in': 'csv',
 'file_format_out': 'csv'}

Hide code cell source

 
params = pimmslearn.nb.args_from_dict(args)
# params = OmegaConf.create(args)
params

{'data': Path('runs/alzheimer_study/data'),
 'file_format_in': 'csv',
 'file_format_out': 'csv',
 'folder_data': '',
 'folder_experiment': Path('runs/alzheimer_study'),
 'out_figures': Path('runs/alzheimer_study/figures'),
 'out_folder': Path('runs/alzheimer_study'),
 'out_metrics': Path('runs/alzheimer_study'),
 'out_models': Path('runs/alzheimer_study'),
 'out_preds': Path('runs/alzheimer_study/preds')}

Hide code cell source

 
splits = datasplits.DataSplits.from_folder(params.data, file_format=params.file_format_in)

Hide code cell source

 
train_data = splits.train_X.unstack()
train_data
protein groups A0A024QZX5;A0A087X1N8;P35237 A0A024R0T9;K7ER74;P02655 A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 A0A075B6H7 A0A075B6H9 A0A075B6I0 A0A075B6I1 A0A075B6I6 A0A075B6I9 ... Q9Y653;Q9Y653-2;Q9Y653-3 Q9Y696 Q9Y6C2 Q9Y6N6 Q9Y6N7;Q9Y6N7-2;Q9Y6N7-4 Q9Y6R7 Q9Y6X5 Q9Y6Y8;Q9Y6Y8-2 Q9Y6Y9 S4R3U6
Sample ID
Sample_000 15.912 16.852 15.570 16.481 17.301 20.246 16.764 17.584 16.988 20.054 ... 16.012 15.178 NaN 15.050 16.842 NaN NaN 19.563 NaN 12.805
Sample_001 NaN 16.874 15.519 16.387 NaN 19.941 18.786 17.144 NaN 19.067 ... 15.528 15.576 NaN 14.833 16.597 20.299 15.556 19.386 13.970 12.442
Sample_002 16.111 NaN 15.935 16.416 18.175 19.251 16.832 15.671 17.012 18.569 ... 15.229 14.728 13.757 15.118 17.440 19.598 15.735 20.447 12.636 12.505
Sample_003 16.107 17.032 15.802 16.979 15.963 19.628 17.852 18.877 14.182 18.985 ... 15.495 14.590 14.682 15.140 17.356 19.429 NaN 20.216 NaN 12.445
Sample_004 15.603 15.331 15.375 16.679 NaN 20.450 18.682 17.081 14.140 19.686 ... 14.757 NaN NaN 15.256 17.075 19.582 15.328 NaN 13.145 NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
Sample_205 15.682 16.886 14.910 16.482 NaN 17.705 17.039 NaN 16.413 19.102 ... NaN 15.684 14.236 15.415 17.551 17.922 16.340 19.928 12.929 NaN
Sample_206 15.798 17.554 15.600 15.938 NaN 18.154 18.152 16.503 16.860 18.538 ... 15.422 16.106 NaN 15.345 17.084 18.708 NaN 19.433 NaN NaN
Sample_207 15.739 NaN 15.469 16.898 NaN 18.636 17.950 16.321 16.401 18.849 ... 15.808 16.098 14.403 15.715 NaN 18.725 16.138 19.599 13.637 11.174
Sample_208 15.477 16.779 14.995 16.132 NaN 14.908 NaN NaN 16.119 18.368 ... 15.157 16.712 NaN 14.640 16.533 19.411 15.807 19.545 NaN NaN
Sample_209 NaN 17.261 15.175 16.235 NaN 17.893 17.744 16.371 15.780 18.806 ... 15.237 15.652 15.211 14.205 16.749 19.275 15.732 19.577 11.042 11.791

210 rows × 1421 columns

Save placeholder sample annotation for use in NAGuideR app which requires such a file

Hide code cell source

 
annotation = pd.Series('test', train_data.index).to_frame('group')
annotation.index.name = 'Samples'
annotation
group
Samples
Sample_000 test
Sample_001 test
Sample_002 test
Sample_003 test
Sample_004 test
... ...
Sample_205 test
Sample_206 test
Sample_207 test
Sample_208 test
Sample_209 test

210 rows × 1 columns

Hide code cell source

 
fname = params.data / 'sample_annotation_placeholder.csv'
annotation.to_csv(fname)
fname

Path('runs/alzheimer_study/data/sample_annotation_placeholder.csv')

# Save with samples in columns

Hide code cell source

 
fname = params.data / 'data_wide_sample_cols.csv'
# fillna('Filtered')
train_data.T.to_csv(fname)
fname

Path('runs/alzheimer_study/data/data_wide_sample_cols.csv')

Hide code cell source

 
# 'data_wide_sample_cols.csv'