Compare outcomes from differential analysis based on different imputation methods

• load scores based on 10_1_ald_diff_analysis

Show code cell source

Hide code cell source

import logging
from pathlib import Path

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from IPython.display import display

import pimmslearn
import pimmslearn.databases.diseases

logger = pimmslearn.logging.setup_nb_logger()

plt.rcParams['figure.figsize'] = (2, 2)
fontsize = 5
pimmslearn.plotting.make_large_descriptors(fontsize)
logging.getLogger('fontTools').setLevel(logging.ERROR)

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

Parameters

Default and set parameters for the notebook.

folder_experiment = 'runs/appl_ald_data/plasma/proteinGroups'

target = 'kleiner'
model_key = 'VAE'
baseline = 'RSN'
out_folder = 'diff_analysis'
selected_statistics = ['p-unc', '-Log10 pvalue', 'qvalue', 'rejected']

disease_ontology = 5082  # code from https://disease-ontology.org/
# split diseases notebook? Query gene names for proteins in file from uniprot?
annotaitons_gene_col = 'PG.Genes'

# Parameters
disease_ontology = 10652
folder_experiment = "runs/alzheimer_study"
target = "AD"
baseline = "PI"
model_key = "RF"
out_folder = "diff_analysis"
annotaitons_gene_col = "None"

Add set parameters to configuration

Show code cell source

Hide code cell source

params = pimmslearn.nb.get_params(args, globals=globals())
args = pimmslearn.nb.Config()
args.folder_experiment = Path(params["folder_experiment"])
args = pimmslearn.nb.add_default_paths(args,
                                 out_root=(
                                     args.folder_experiment
                                     / params["out_folder"]
                                     / params["target"]
                                     / f"{params['baseline']}_vs_{params['model_key']}"))
args.update_from_dict(params)
args.scores_folder = scores_folder = (args.folder_experiment
                                      / params["out_folder"]
                                      / params["target"]
                                      / 'scores')
args.freq_features_observed = args.folder_experiment / 'freq_features_observed.csv'
args

root - INFO     Removed from global namespace: folder_experiment
root - INFO     Removed from global namespace: target
root - INFO     Removed from global namespace: model_key
root - INFO     Removed from global namespace: baseline
root - INFO     Removed from global namespace: out_folder
root - INFO     Removed from global namespace: selected_statistics
root - INFO     Removed from global namespace: disease_ontology
root - INFO     Removed from global namespace: annotaitons_gene_col
root - INFO     Already set attribute: folder_experiment has value runs/alzheimer_study
root - INFO     Already set attribute: out_folder has value diff_analysis

{'annotaitons_gene_col': 'None',
 'baseline': 'PI',
 'data': PosixPath('runs/alzheimer_study/data'),
 'disease_ontology': 10652,
 'folder_experiment': PosixPath('runs/alzheimer_study'),
 'freq_features_observed': PosixPath('runs/alzheimer_study/freq_features_observed.csv'),
 'model_key': 'RF',
 'out_figures': PosixPath('runs/alzheimer_study/figures'),
 'out_folder': PosixPath('runs/alzheimer_study/diff_analysis/AD/PI_vs_RF'),
 'out_metrics': PosixPath('runs/alzheimer_study'),
 'out_models': PosixPath('runs/alzheimer_study'),
 'out_preds': PosixPath('runs/alzheimer_study/preds'),
 'scores_folder': PosixPath('runs/alzheimer_study/diff_analysis/AD/scores'),
 'selected_statistics': ['p-unc', '-Log10 pvalue', 'qvalue', 'rejected'],
 'target': 'AD'}

Excel file for exports

files_out = dict()
writer_args = dict(float_format='%.3f')

fname = args.out_folder / 'diff_analysis_compare_methods.xlsx'
files_out[fname.name] = fname
writer = pd.ExcelWriter(fname)
logger.info("Writing to excel file: %s", fname)

root - INFO     Writing to excel file: runs/alzheimer_study/diff_analysis/AD/PI_vs_RF/diff_analysis_compare_methods.xlsx

Load scores

Load baseline model scores

Show all statistics, later use selected statistics

Show code cell source

Hide code cell source

fname = args.scores_folder / f'diff_analysis_scores_{args.baseline}.pkl'
scores_baseline = pd.read_pickle(fname)
scores_baseline

	model	PI
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.633	1	0.931	0.336	0.005	0.474	0.502	False
	age	0.035	1	0.052	0.820	0.000	0.086	0.894	False
	Kiel	2.253	1	3.315	0.070	0.017	1.154	0.159	False
	Magdeburg	5.871	1	8.639	0.004	0.043	2.432	0.015	True
	Sweden	10.533	1	15.498	0.000	0.075	3.937	0.001	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.795	1	0.798	0.373	0.004	0.428	0.538	False
	age	0.835	1	0.838	0.361	0.004	0.442	0.526	False
	Kiel	0.537	1	0.538	0.464	0.003	0.333	0.619	False
	Magdeburg	3.819	1	3.831	0.052	0.020	1.286	0.125	False
	Sweden	4.139	1	4.153	0.043	0.021	1.367	0.108	False

7105 rows × 8 columns

Load selected comparison model scores

Show code cell source

Hide code cell source

fname = args.scores_folder / f'diff_analysis_scores_{args.model_key}.pkl'
scores_model = pd.read_pickle(fname)
scores_model

	model	RF
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.989	1	7.408	0.007	0.037	2.149	0.021	True
	age	0.003	1	0.024	0.878	0.000	0.057	0.923	False
	Kiel	0.210	1	1.575	0.211	0.008	0.676	0.337	False
	Magdeburg	0.389	1	2.911	0.090	0.015	1.048	0.172	False
	Sweden	1.494	1	11.191	0.001	0.055	3.004	0.004	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	1.173	1	2.552	0.112	0.013	0.952	0.205	False
	age	0.686	1	1.492	0.223	0.008	0.651	0.352	False
	Kiel	2.153	1	4.683	0.032	0.024	1.499	0.073	False
	Magdeburg	1.711	1	3.723	0.055	0.019	1.258	0.116	False
	Sweden	14.171	1	30.831	0.000	0.139	7.030	0.000	True

7105 rows × 8 columns

Combined scores

show only selected statistics for comparsion

Show code cell source

Hide code cell source

scores = scores_model.join(scores_baseline, how='outer')[[args.baseline, args.model_key]]
scores = scores.loc[:, pd.IndexSlice[scores.columns.levels[0].to_list(),
                                     args.selected_statistics]]
scores

	model	PI				RF
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.336	0.474	0.502	False	0.007	2.149	0.021	True
	Kiel	0.070	1.154	0.159	False	0.211	0.676	0.337	False
	Magdeburg	0.004	2.432	0.015	True	0.090	1.048	0.172	False
	Sweden	0.000	3.937	0.001	True	0.001	3.004	0.004	True
	age	0.820	0.086	0.894	False	0.878	0.057	0.923	False
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.373	0.428	0.538	False	0.112	0.952	0.205	False
	Kiel	0.464	0.333	0.619	False	0.032	1.499	0.073	False
	Magdeburg	0.052	1.286	0.125	False	0.055	1.258	0.116	False
	Sweden	0.043	1.367	0.108	False	0.000	7.030	0.000	True
	age	0.361	0.442	0.526	False	0.223	0.651	0.352	False

7105 rows × 8 columns

Models in comparison (name mapping)

Show code cell source

Hide code cell source

models = pimmslearn.nb.Config.from_dict(
    pimmslearn.pandas.index_to_dict(scores.columns.get_level_values(0)))
vars(models)

{'PI': 'PI', 'RF': 'RF'}

Describe scores

Show code cell source

Hide code cell source

scores.describe()

model	PI			RF
var	p-unc	-Log10 pvalue	qvalue	p-unc	-Log10 pvalue	qvalue
count	7,105.000	7,105.000	7,105.000	7,105.000	7,105.000	7,105.000
mean	0.262	2.481	0.339	0.234	3.078	0.293
std	0.304	5.331	0.332	0.296	5.795	0.323
min	0.000	0.000	0.000	0.000	0.000	0.000
25%	0.004	0.332	0.015	0.001	0.385	0.003
50%	0.119	0.923	0.239	0.072	1.142	0.144
75%	0.465	2.416	0.620	0.412	3.064	0.550
max	1.000	149.342	1.000	1.000	84.976	1.000

One to one comparison of by feature:

Show code cell source

Hide code cell source

scores = scores.loc[pd.IndexSlice[:, args.target], :]
scores.to_excel(writer, 'scores', **writer_args)
scores

/tmp/ipykernel_80292/3761369923.py:2: FutureWarning: Starting with pandas version 3.0 all arguments of to_excel except for the argument 'excel_writer' will be keyword-only.
  scores.to_excel(writer, 'scores', **writer_args)

	model	PI				RF
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.336	0.474	0.502	False	0.007	2.149	0.021	True
A0A024R0T9;K7ER74;P02655	AD	0.043	1.364	0.109	False	0.029	1.535	0.069	False
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	AD	0.072	1.144	0.161	False	0.363	0.440	0.502	False
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	AD	0.586	0.232	0.724	False	0.259	0.587	0.394	False
A0A075B6H7	AD	0.111	0.955	0.227	False	0.002	2.610	0.009	True
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	AD	0.175	0.756	0.318	False	0.175	0.756	0.292	False
Q9Y6X5	AD	0.032	1.495	0.086	False	0.173	0.762	0.289	False
Q9Y6Y8;Q9Y6Y8-2	AD	0.083	1.079	0.182	False	0.083	1.079	0.162	False
Q9Y6Y9	AD	0.409	0.388	0.572	False	0.412	0.385	0.550	False
S4R3U6	AD	0.373	0.428	0.538	False	0.112	0.952	0.205	False

1421 rows × 8 columns

And the descriptive statistics of the numeric values:

Show code cell source

Hide code cell source

scores.describe()

model	PI			RF
var	p-unc	-Log10 pvalue	qvalue	p-unc	-Log10 pvalue	qvalue
count	1,421.000	1,421.000	1,421.000	1,421.000	1,421.000	1,421.000
mean	0.255	1.414	0.336	0.245	1.518	0.311
std	0.296	1.648	0.321	0.290	1.755	0.314
min	0.000	0.001	0.000	0.000	0.000	0.000
25%	0.011	0.365	0.038	0.009	0.369	0.027
50%	0.116	0.934	0.234	0.104	0.985	0.193
75%	0.432	1.941	0.592	0.427	2.032	0.564
max	0.998	23.733	0.999	1.000	17.488	1.000

and the boolean decision values

Show code cell source

Hide code cell source

scores.describe(include=['bool', 'O'])

model	PI	RF
var	rejected	rejected
count	1421	1421
unique	2	2
top	False	False
freq	1025	965

Load frequencies of observed features

Show code cell source

Hide code cell source

freq_feat = pd.read_csv(args.freq_features_observed, index_col=0)
freq_feat.columns = pd.MultiIndex.from_tuples([('data', 'frequency'),])
freq_feat

	data
	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	186
A0A024R0T9;K7ER74;P02655	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	196
A0A075B6H7	91
...	...
Q9Y6R7	197
Q9Y6X5	173
Q9Y6Y8;Q9Y6Y8-2	197
Q9Y6Y9	119
S4R3U6	126

1421 rows × 1 columns

Compare shared features

Show code cell source

Hide code cell source

scores_common = (scores
                 .dropna()
                 .reset_index(-1, drop=True)
                 ).join(
    freq_feat, how='left'
)
scores_common

	PI				RF				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.336	0.474	0.502	False	0.007	2.149	0.021	True	186
A0A024R0T9;K7ER74;P02655	0.043	1.364	0.109	False	0.029	1.535	0.069	False	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.072	1.144	0.161	False	0.363	0.440	0.502	False	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.586	0.232	0.724	False	0.259	0.587	0.394	False	196
A0A075B6H7	0.111	0.955	0.227	False	0.002	2.610	0.009	True	91
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	0.175	0.756	0.318	False	0.175	0.756	0.292	False	197
Q9Y6X5	0.032	1.495	0.086	False	0.173	0.762	0.289	False	173
Q9Y6Y8;Q9Y6Y8-2	0.083	1.079	0.182	False	0.083	1.079	0.162	False	197
Q9Y6Y9	0.409	0.388	0.572	False	0.412	0.385	0.550	False	119
S4R3U6	0.373	0.428	0.538	False	0.112	0.952	0.205	False	126

1421 rows × 9 columns

Annotate decisions in Confusion Table style:

Show code cell source

Hide code cell source

def annotate_decision(scores, model, model_column):
    return scores[(model_column, 'rejected')].replace({False: f'{model} (no) ', True: f'{model} (yes)'})


annotations = None
for model, model_column in models.items():
    if annotations is not None:
        annotations += ' - '
        annotations += annotate_decision(scores_common,
                                         model=model, model_column=model_column)
    else:
        annotations = annotate_decision(
            scores_common, model=model, model_column=model_column)
annotations.name = 'Differential Analysis Comparison'
annotations.value_counts()

Differential Analysis Comparison
PI (no)  - RF (no)    896
PI (yes) - RF (yes)   327
PI (no)  - RF (yes)   129
PI (yes) - RF (no)     69
Name: count, dtype: int64

List different decisions between models

Show code cell source

Hide code cell source

mask_different = (
    (scores_common.loc[:, pd.IndexSlice[:, 'rejected']].any(axis=1))
    & ~(scores_common.loc[:, pd.IndexSlice[:, 'rejected']].all(axis=1))
)
_to_write = scores_common.loc[mask_different]
_to_write.to_excel(writer, 'differences', **writer_args)
logger.info("Writen to Excel file under sheet 'differences'.")
_to_write

/tmp/ipykernel_80292/1417621106.py:6: FutureWarning: Starting with pandas version 3.0 all arguments of to_excel except for the argument 'excel_writer' will be keyword-only.
  _to_write.to_excel(writer, 'differences', **writer_args)
root - INFO     Writen to Excel file under sheet 'differences'.

	PI				RF				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.336	0.474	0.502	False	0.007	2.149	0.021	True	186
A0A075B6H7	0.111	0.955	0.227	False	0.002	2.610	0.009	True	91
A0A075B6I0	0.027	1.575	0.074	False	0.001	3.159	0.003	True	194
A0A075B6R2	0.384	0.415	0.548	False	0.002	2.766	0.006	True	164
A0A075B7B8	0.143	0.846	0.272	False	0.000	4.539	0.000	True	57
...	...	...	...	...	...	...	...	...	...
Q9ULP0-3;Q9ULP0-6	0.023	1.635	0.067	False	0.001	2.892	0.005	True	136
Q9ULZ9	0.000	3.578	0.002	True	0.045	1.347	0.098	False	171
Q9UP79	0.372	0.429	0.537	False	0.000	3.977	0.001	True	135
Q9UQ52	0.073	1.134	0.164	False	0.001	3.136	0.003	True	188
Q9Y281;Q9Y281-3	0.000	3.368	0.002	True	0.210	0.677	0.337	False	51

198 rows × 9 columns

Plot qvalues of both models with annotated decisions

Prepare data for plotting (qvalues)

Show code cell source

Hide code cell source

var = 'qvalue'
to_plot = [scores_common[v][var] for v in models.values()]
for s, k in zip(to_plot, models.keys()):
    s.name = k.replace('_', ' ')
to_plot.append(scores_common['data'])
to_plot.append(annotations)
to_plot = pd.concat(to_plot, axis=1)
to_plot

	PI	RF	frequency	Differential Analysis Comparison
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.502	0.021	186	PI (no) - RF (yes)
A0A024R0T9;K7ER74;P02655	0.109	0.069	195	PI (no) - RF (no)
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.161	0.502	174	PI (no) - RF (no)
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.724	0.394	196	PI (no) - RF (no)
A0A075B6H7	0.227	0.009	91	PI (no) - RF (yes)
...	...	...	...	...
Q9Y6R7	0.318	0.292	197	PI (no) - RF (no)
Q9Y6X5	0.086	0.289	173	PI (no) - RF (no)
Q9Y6Y8;Q9Y6Y8-2	0.182	0.162	197	PI (no) - RF (no)
Q9Y6Y9	0.572	0.550	119	PI (no) - RF (no)
S4R3U6	0.538	0.205	126	PI (no) - RF (no)

1421 rows × 4 columns

List of features with the highest difference in qvalues

Show code cell source

Hide code cell source

# should it be possible to run not only RSN?
to_plot['diff_qvalue'] = (to_plot[str(args.baseline)] - to_plot[str(args.model_key)]).abs()
to_plot.loc[mask_different].sort_values('diff_qvalue', ascending=False)

	PI	RF	frequency	Differential Analysis Comparison	diff_qvalue
protein groups
Q8N9I0	0.989	0.007	141	PI (no) - RF (yes)	0.982
Q96PQ0	0.005	0.986	177	PI (yes) - RF (no)	0.981
O00187;O00187-2	0.999	0.033	119	PI (no) - RF (yes)	0.965
O75083	0.016	0.973	102	PI (yes) - RF (no)	0.957
F6VDH7;P50502;Q3KNR6	0.010	0.966	175	PI (yes) - RF (no)	0.956
...	...	...	...	...	...
A0A0J9YXX1	0.058	0.049	197	PI (no) - RF (yes)	0.009
F5GY80;F5H7G1;P07358	0.057	0.048	197	PI (no) - RF (yes)	0.009
Q9NX62	0.055	0.047	197	PI (no) - RF (yes)	0.008
P00740;P00740-2	0.053	0.045	197	PI (no) - RF (yes)	0.008
K7ERG9;P00746	0.052	0.044	197	PI (no) - RF (yes)	0.008

198 rows × 5 columns

Differences plotted with created annotations

Show code cell source

Hide code cell source

figsize = (4, 4)
size = 5
fig, ax = plt.subplots(figsize=figsize)
x_col = to_plot.columns[0]
y_col = to_plot.columns[1]
ax = sns.scatterplot(data=to_plot,
                     x=x_col,
                     y=y_col,
                     s=size,
                     hue='Differential Analysis Comparison',
                     ax=ax)
_ = ax.legend(fontsize=fontsize,
              title_fontsize=fontsize,
              markerscale=0.4,
              title='',
              )
ax.set_xlabel(f"qvalue for {x_col}")
ax.set_ylabel(f"qvalue for {y_col}")
ax.hlines(0.05, 0, 1, color='grey', linestyles='dotted')
ax.vlines(0.05, 0, 1, color='grey', linestyles='dotted')
sns.move_legend(ax, "upper right")
files_out[f'diff_analysis_comparision_1_{args.model_key}'] = (
    args.out_folder /
    f'diff_analysis_comparision_1_{args.model_key}')
fname = files_out[f'diff_analysis_comparision_1_{args.model_key}']
pimmslearn.savefig(fig, name=fname)

pimmslearn.plotting - INFO     Saved Figures to runs/alzheimer_study/diff_analysis/AD/PI_vs_RF/diff_analysis_comparision_1_RF

• also showing how many features were measured (“observed”) by size of circle

Show code cell source

Hide code cell source

fig, ax = plt.subplots(figsize=figsize)
ax = sns.scatterplot(data=to_plot,
                     x=to_plot.columns[0],
                     y=to_plot.columns[1],
                     size='frequency',
                     s=size,
                     sizes=(5, 20),
                     hue='Differential Analysis Comparison')
_ = ax.legend(fontsize=fontsize,
              title_fontsize=fontsize,
              markerscale=0.6,
              title='',
              )
ax.set_xlabel(f"qvalue for {x_col}")
ax.set_ylabel(f"qvalue for {y_col}")
ax.hlines(0.05, 0, 1, color='grey', linestyles='dotted')
ax.vlines(0.05, 0, 1, color='grey', linestyles='dotted')
sns.move_legend(ax, "upper right")
files_out[f'diff_analysis_comparision_2_{args.model_key}'] = (
    args.out_folder / f'diff_analysis_comparision_2_{args.model_key}')
pimmslearn.savefig(
    fig, name=files_out[f'diff_analysis_comparision_2_{args.model_key}'])

pimmslearn.plotting - INFO     Saved Figures to runs/alzheimer_study/diff_analysis/AD/PI_vs_RF/diff_analysis_comparision_2_RF

Only features contained in model

• this block exist due to a specific part in the ALD analysis of the paper

Show code cell source

Hide code cell source

scores_model_only = scores.reset_index(level=-1, drop=True)
_diff = scores_model_only.index.difference(scores_common.index)
if not _diff.empty:
    scores_model_only = (scores_model_only
                         .loc[
                             _diff,
                             args.model_key]
                         .sort_values(by='qvalue', ascending=True)
                         .join(freq_feat.squeeze().rename(freq_feat.columns.droplevel()[0])
                               )
                         )
    display(scores_model_only)
else:
    scores_model_only = None
    logger.info("No features only in new comparision model.")

if not _diff.empty:
    scores_model_only.to_excel(writer, 'only_model', **writer_args)
    display(scores_model_only.rejected.value_counts())
    scores_model_only_rejected = scores_model_only.loc[scores_model_only.rejected]
    scores_model_only_rejected.to_excel(
        writer, 'only_model_rejected', **writer_args)

root - INFO     No features only in new comparision model.

DISEASES DB lookup

Query diseases database for gene associations with specified disease ontology id.

Show code cell source

Hide code cell source

data = pimmslearn.databases.diseases.get_disease_association(
    doid=args.disease_ontology, limit=10000)
data = pd.DataFrame.from_dict(data, orient='index').rename_axis('ENSP', axis=0)
data = data.rename(columns={'name': args.annotaitons_gene_col}).reset_index(
).set_index(args.annotaitons_gene_col)
data

pimmslearn.databases.diseases - WARNING  There are more associations available

	ENSP	score
None
APOE	ENSP00000252486	5.000
PSEN2	ENSP00000355747	5.000
PSEN1	ENSP00000326366	5.000
APP	ENSP00000284981	5.000
TREM2	ENSP00000362205	4.825
...	...	...
ERP27	ENSP00000266397	0.681
ZNF585B	ENSP00000433773	0.681
KIR3DL2	ENSP00000325525	0.681
C12orf66	ENSP00000311486	0.681
ELP2	ENSP00000414851	0.681

10000 rows × 2 columns

Shared features

ToDo: new script -> DISEASES DB lookup

Show code cell source

Hide code cell source

feat_name = scores.index.names[0]  # first index level is feature name
if args.annotaitons_gene_col in scores.index.names:
    logger.info(f"Found gene annotation in scores index:  {scores.index.names}")
else:
    logger.info(f"No gene annotation in scores index:  {scores.index.names}"
                " Exiting.")
    import sys
    sys.exit(0)

root - INFO     No gene annotation in scores index:  ['protein groups', 'Source'] Exiting.
/home/runner/work/pimms/pimms/project/.snakemake/conda/924ec7e362d761ecf0807b9074d79999_/lib/python3.12/site-packages/IPython/core/interactiveshell.py:3707: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.
  warn("To exit: use 'exit', 'quit', or Ctrl-D.", stacklevel=1)

An exception has occurred, use %tb to see the full traceback.

SystemExit: 0

Show code cell source

Hide code cell source

gene_to_PG = (scores.droplevel(
    list(set(scores.index.names) - {feat_name, args.annotaitons_gene_col})
)
    .index
    .to_frame()
    .reset_index(drop=True)
    .set_index(args.annotaitons_gene_col)
)
gene_to_PG.head()

Show code cell source

Hide code cell source

disease_associations_all = data.join(
    gene_to_PG).dropna().reset_index().set_index(feat_name).join(annotations)
disease_associations_all

only by model

Show code cell source

Hide code cell source

idx = disease_associations_all.index.intersection(scores_model_only.index)
disease_assocications_new = disease_associations_all.loc[idx].sort_values(
    'score', ascending=False)
disease_assocications_new.head(20)

Show code cell source

Hide code cell source

mask = disease_assocications_new.loc[idx, 'score'] >= 2.0
disease_assocications_new.loc[idx].loc[mask]

Only by model which were significant

Show code cell source

Hide code cell source

idx = disease_associations_all.index.intersection(
    scores_model_only_rejected.index)
disease_assocications_new_rejected = disease_associations_all.loc[idx].sort_values(
    'score', ascending=False)
disease_assocications_new_rejected.head(20)

Show code cell source

Hide code cell source

mask = disease_assocications_new_rejected.loc[idx, 'score'] >= 2.0
disease_assocications_new_rejected.loc[idx].loc[mask]

Shared which are only significant for by model

mask = (scores_common[(str(args.model_key), 'rejected')] & mask_different)
mask.sum()

Show code cell source

Hide code cell source

idx = disease_associations_all.index.intersection(mask.index[mask])
disease_assocications_shared_rejected_by_model = (disease_associations_all.loc[idx].sort_values(
    'score', ascending=False))
disease_assocications_shared_rejected_by_model.head(20)

Show code cell source

Hide code cell source

mask = disease_assocications_shared_rejected_by_model.loc[idx, 'score'] >= 2.0
disease_assocications_shared_rejected_by_model.loc[idx].loc[mask]

Only significant by RSN

mask = (scores_common[(str(args.baseline), 'rejected')] & mask_different)
mask.sum()

Show code cell source

Hide code cell source

idx = disease_associations_all.index.intersection(mask.index[mask])
disease_assocications_shared_rejected_by_RSN = (
    disease_associations_all
    .loc[idx]
    .sort_values('score', ascending=False))
disease_assocications_shared_rejected_by_RSN.head(20)

Show code cell source

Hide code cell source

mask = disease_assocications_shared_rejected_by_RSN.loc[idx, 'score'] >= 2.0
disease_assocications_shared_rejected_by_RSN.loc[idx].loc[mask]

Write to excel

Show code cell source

Hide code cell source

disease_associations_all.to_excel(
    writer, sheet_name='disease_assoc_all', **writer_args)
disease_assocications_new.to_excel(
    writer, sheet_name='disease_assoc_new', **writer_args)
disease_assocications_new_rejected.to_excel(
    writer, sheet_name='disease_assoc_new_rejected', **writer_args)

Outputs

Show code cell source

Hide code cell source

writer.close()
files_out