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 = "CF"
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': 'CF',
 'out_figures': PosixPath('runs/alzheimer_study/figures'),
 'out_folder': PosixPath('runs/alzheimer_study/diff_analysis/AD/PI_vs_CF'),
 '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_CF/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	CF
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	1.046	1	7.580	0.006	0.038	2.189	0.019	True
	age	0.002	1	0.015	0.903	0.000	0.044	0.937	False
	Kiel	0.237	1	1.714	0.192	0.009	0.717	0.308	False
	Magdeburg	0.457	1	3.311	0.070	0.017	1.152	0.139	False
	Sweden	1.703	1	12.341	0.001	0.061	3.257	0.002	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	1.235	1	2.661	0.104	0.014	0.981	0.190	False
	age	0.929	1	2.002	0.159	0.010	0.799	0.265	False
	Kiel	1.513	1	3.260	0.073	0.017	1.139	0.142	False
	Magdeburg	1.112	1	2.396	0.123	0.012	0.909	0.217	False
	Sweden	15.111	1	32.552	0.000	0.146	7.360	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	CF				PI
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.006	2.189	0.019	True	0.336	0.474	0.502	False
	Kiel	0.192	0.717	0.308	False	0.070	1.154	0.159	False
	Magdeburg	0.070	1.152	0.139	False	0.004	2.432	0.015	True
	Sweden	0.001	3.257	0.002	True	0.000	3.937	0.001	True
	age	0.903	0.044	0.937	False	0.820	0.086	0.894	False
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.104	0.981	0.190	False	0.373	0.428	0.538	False
	Kiel	0.073	1.139	0.142	False	0.464	0.333	0.619	False
	Magdeburg	0.123	0.909	0.217	False	0.052	1.286	0.125	False
	Sweden	0.000	7.360	0.000	True	0.043	1.367	0.108	False
	age	0.159	0.799	0.265	False	0.361	0.442	0.526	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)

{'CF': 'CF', 'PI': 'PI'}

Describe scores

Show code cell source

Hide code cell source

scores.describe()

model	CF			PI
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	0.227	3.255	0.282	0.262	2.481	0.339
std	0.293	6.213	0.320	0.304	5.331	0.332
min	0.000	0.000	0.000	0.000	0.000	0.000
25%	0.001	0.401	0.002	0.004	0.332	0.015
50%	0.065	1.190	0.129	0.119	0.923	0.239
75%	0.397	3.234	0.529	0.465	2.416	0.620
max	1.000	85.873	1.000	1.000	149.342	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_80117/3761369923.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	CF				PI
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.006	2.189	0.019	True	0.336	0.474	0.502	False
A0A024R0T9;K7ER74;P02655	AD	0.034	1.472	0.076	False	0.043	1.364	0.109	False
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	AD	0.331	0.480	0.467	False	0.072	1.144	0.161	False
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	AD	0.257	0.590	0.385	False	0.586	0.232	0.724	False
A0A075B6H7	AD	0.001	2.924	0.004	True	0.111	0.955	0.227	False
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	AD	0.175	0.756	0.286	False	0.175	0.756	0.318	False
Q9Y6X5	AD	0.156	0.808	0.261	False	0.032	1.495	0.086	False
Q9Y6Y8;Q9Y6Y8-2	AD	0.083	1.079	0.159	False	0.083	1.079	0.182	False
Q9Y6Y9	AD	0.473	0.325	0.600	False	0.409	0.388	0.572	False
S4R3U6	AD	0.104	0.981	0.190	False	0.373	0.428	0.538	False

1421 rows × 8 columns

And the descriptive statistics of the numeric values:

Show code cell source

Hide code cell source

scores.describe()

model	CF			PI
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	0.239	1.568	0.302	0.255	1.414	0.336
std	0.287	1.827	0.311	0.296	1.648	0.321
min	0.000	0.001	0.000	0.000	0.001	0.000
25%	0.007	0.385	0.021	0.011	0.365	0.038
50%	0.091	1.040	0.170	0.116	0.934	0.234
75%	0.412	2.142	0.544	0.432	1.941	0.592
max	0.997	20.025	0.998	0.998	23.733	0.999

and the boolean decision values

Show code cell source

Hide code cell source

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

model	CF	PI
var	rejected	rejected
count	1421	1421
unique	2	2
top	False	False
freq	958	1025

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

	CF				PI				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.006	2.189	0.019	True	0.336	0.474	0.502	False	186
A0A024R0T9;K7ER74;P02655	0.034	1.472	0.076	False	0.043	1.364	0.109	False	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.331	0.480	0.467	False	0.072	1.144	0.161	False	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.257	0.590	0.385	False	0.586	0.232	0.724	False	196
A0A075B6H7	0.001	2.924	0.004	True	0.111	0.955	0.227	False	91
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	0.175	0.756	0.286	False	0.175	0.756	0.318	False	197
Q9Y6X5	0.156	0.808	0.261	False	0.032	1.495	0.086	False	173
Q9Y6Y8;Q9Y6Y8-2	0.083	1.079	0.159	False	0.083	1.079	0.182	False	197
Q9Y6Y9	0.473	0.325	0.600	False	0.409	0.388	0.572	False	119
S4R3U6	0.104	0.981	0.190	False	0.373	0.428	0.538	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
CF (no)  - PI (no)    891
CF (yes) - PI (yes)   329
CF (yes) - PI (no)    134
CF (no)  - PI (yes)    67
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_80117/1417621106.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'.

	CF				PI				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.006	2.189	0.019	True	0.336	0.474	0.502	False	186
A0A075B6H7	0.001	2.924	0.004	True	0.111	0.955	0.227	False	91
A0A075B6I0	0.001	3.066	0.003	True	0.027	1.575	0.074	False	194
A0A075B6R2	0.002	2.633	0.008	True	0.384	0.415	0.548	False	164
A0A075B6S5	0.007	2.142	0.021	True	0.188	0.725	0.335	False	129
...	...	...	...	...	...	...	...	...	...
Q9ULZ9	0.024	1.627	0.056	False	0.000	3.578	0.002	True	171
Q9UP79	0.000	3.812	0.001	True	0.372	0.429	0.537	False	135
Q9UQ52	0.000	3.462	0.001	True	0.073	1.134	0.164	False	188
Q9Y281;Q9Y281-3	0.074	1.133	0.143	False	0.000	3.368	0.002	True	51
Q9Y6C2	0.014	1.854	0.036	True	0.775	0.110	0.864	False	119

201 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

	CF	PI	frequency	Differential Analysis Comparison
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.019	0.502	186	CF (yes) - PI (no)
A0A024R0T9;K7ER74;P02655	0.076	0.109	195	CF (no) - PI (no)
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.467	0.161	174	CF (no) - PI (no)
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.385	0.724	196	CF (no) - PI (no)
A0A075B6H7	0.004	0.227	91	CF (yes) - PI (no)
...	...	...	...	...
Q9Y6R7	0.286	0.318	197	CF (no) - PI (no)
Q9Y6X5	0.261	0.086	173	CF (no) - PI (no)
Q9Y6Y8;Q9Y6Y8-2	0.159	0.182	197	CF (no) - PI (no)
Q9Y6Y9	0.600	0.572	119	CF (no) - PI (no)
S4R3U6	0.190	0.538	126	CF (no) - PI (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)

	CF	PI	frequency	Differential Analysis Comparison	diff_qvalue
protein groups
Q8N9I0	0.006	0.989	141	CF (yes) - PI (no)	0.983
P51688	0.023	0.994	58	CF (yes) - PI (no)	0.971
O15197;O15197-3	0.010	0.980	104	CF (yes) - PI (no)	0.970
O00187;O00187-2	0.035	0.999	119	CF (yes) - PI (no)	0.963
Q9NPH3;Q9NPH3-2;Q9NPH3-5	0.041	0.976	186	CF (yes) - PI (no)	0.935
...	...	...	...	...	...
A0A0J9YXX1	0.048	0.058	197	CF (yes) - PI (no)	0.010
F5GY80;F5H7G1;P07358	0.047	0.057	197	CF (yes) - PI (no)	0.010
Q9NX62	0.046	0.055	197	CF (yes) - PI (no)	0.010
P00740;P00740-2	0.043	0.053	197	CF (yes) - PI (no)	0.009
K7ERG9;P00746	0.043	0.052	197	CF (yes) - PI (no)	0.009

201 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_CF/diff_analysis_comparision_1_CF

• 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_CF/diff_analysis_comparision_2_CF

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