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 = "TRKNN"
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': 'TRKNN',
 'out_figures': PosixPath('runs/alzheimer_study/figures'),
 'out_folder': PosixPath('runs/alzheimer_study/diff_analysis/AD/PI_vs_TRKNN'),
 '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_TRKNN/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	0.274	1	0.399	0.528	0.002	0.277	0.670	False
	age	0.212	1	0.309	0.579	0.002	0.237	0.712	False
	Kiel	2.676	1	3.897	0.050	0.020	1.303	0.121	False
	Magdeburg	5.765	1	8.393	0.004	0.042	2.376	0.016	True
	Sweden	8.898	1	12.955	0.000	0.064	3.391	0.002	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.074	1	0.070	0.791	0.000	0.102	0.872	False
	age	0.829	1	0.785	0.377	0.004	0.424	0.538	False
	Kiel	0.040	1	0.038	0.846	0.000	0.073	0.909	False
	Magdeburg	3.442	1	3.263	0.072	0.017	1.140	0.163	False
	Sweden	6.688	1	6.340	0.013	0.032	1.899	0.041	True

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	TRKNN
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.994	1	7.134	0.008	0.036	2.085	0.023	True
	age	0.004	1	0.029	0.864	0.000	0.063	0.913	False
	Kiel	0.269	1	1.933	0.166	0.010	0.780	0.277	False
	Magdeburg	0.519	1	3.727	0.055	0.019	1.259	0.114	False
	Sweden	1.796	1	12.893	0.000	0.063	3.378	0.002	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	2.295	1	4.480	0.036	0.023	1.449	0.080	False
	age	0.398	1	0.777	0.379	0.004	0.421	0.516	False
	Kiel	2.981	1	5.819	0.017	0.030	1.775	0.043	True
	Magdeburg	3.440	1	6.716	0.010	0.034	1.987	0.028	True
	Sweden	27.114	1	52.939	0.000	0.217	11.062	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				TRKNN
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.528	0.277	0.670	False	0.008	2.085	0.023	True
	Kiel	0.050	1.303	0.121	False	0.166	0.780	0.277	False
	Magdeburg	0.004	2.376	0.016	True	0.055	1.259	0.114	False
	Sweden	0.000	3.391	0.002	True	0.000	3.378	0.002	True
	age	0.579	0.237	0.712	False	0.864	0.063	0.913	False
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.791	0.102	0.872	False	0.036	1.449	0.080	False
	Kiel	0.846	0.073	0.909	False	0.017	1.775	0.043	True
	Magdeburg	0.072	1.140	0.163	False	0.010	1.987	0.028	True
	Sweden	0.013	1.899	0.041	True	0.000	11.062	0.000	True
	age	0.377	0.424	0.538	False	0.379	0.421	0.516	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', 'TRKNN': 'TRKNN'}

Describe scores

Show code cell source

Hide code cell source

scores.describe()

model	PI			TRKNN
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	0.259	2.472	0.336	0.230	3.114	0.287
std	0.301	5.305	0.328	0.296	5.792	0.323
min	0.000	0.000	0.000	0.000	0.000	0.000
25%	0.004	0.343	0.016	0.001	0.392	0.003
50%	0.123	0.910	0.246	0.066	1.182	0.131
75%	0.454	2.409	0.605	0.405	3.156	0.540
max	1.000	144.895	1.000	1.000	82.663	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_77149/3761369923.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				TRKNN
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.528	0.277	0.670	False	0.008	2.085	0.023	True
A0A024R0T9;K7ER74;P02655	AD	0.045	1.351	0.111	False	0.031	1.512	0.071	False
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	AD	0.078	1.106	0.174	False	0.264	0.578	0.394	False
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	AD	0.499	0.302	0.644	False	0.266	0.575	0.396	False
A0A075B6H7	AD	0.091	1.040	0.195	False	0.020	1.707	0.048	True
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	AD	0.175	0.756	0.318	False	0.175	0.756	0.289	False
Q9Y6X5	AD	0.096	1.019	0.203	False	0.113	0.946	0.205	False
Q9Y6Y8;Q9Y6Y8-2	AD	0.083	1.079	0.182	False	0.083	1.079	0.160	False
Q9Y6Y9	AD	0.452	0.345	0.604	False	0.334	0.476	0.472	False
S4R3U6	AD	0.791	0.102	0.872	False	0.036	1.449	0.080	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			TRKNN
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	0.251	1.400	0.333	0.239	1.579	0.301
std	0.290	1.600	0.314	0.294	1.800	0.317
min	0.000	0.000	0.000	0.000	0.002	0.000
25%	0.012	0.371	0.038	0.007	0.373	0.021
50%	0.124	0.907	0.247	0.086	1.063	0.164
75%	0.426	1.934	0.583	0.423	2.151	0.559
max	0.999	21.057	1.000	0.996	19.900	0.997

and the boolean decision values

Show code cell source

Hide code cell source

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

model	PI	TRKNN
var	rejected	rejected
count	1421	1421
unique	2	2
top	False	False
freq	1023	936

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				TRKNN				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.528	0.277	0.670	False	0.008	2.085	0.023	True	186
A0A024R0T9;K7ER74;P02655	0.045	1.351	0.111	False	0.031	1.512	0.071	False	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.078	1.106	0.174	False	0.264	0.578	0.394	False	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.499	0.302	0.644	False	0.266	0.575	0.396	False	196
A0A075B6H7	0.091	1.040	0.195	False	0.020	1.707	0.048	True	91
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	0.175	0.756	0.318	False	0.175	0.756	0.289	False	197
Q9Y6X5	0.096	1.019	0.203	False	0.113	0.946	0.205	False	173
Q9Y6Y8;Q9Y6Y8-2	0.083	1.079	0.182	False	0.083	1.079	0.160	False	197
Q9Y6Y9	0.452	0.345	0.604	False	0.334	0.476	0.472	False	119
S4R3U6	0.791	0.102	0.872	False	0.036	1.449	0.080	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)  - TRKNN (no)    878
PI (yes) - TRKNN (yes)   340
PI (no)  - TRKNN (yes)   145
PI (yes) - TRKNN (no)     58
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_77149/1417621106.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				TRKNN				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.528	0.277	0.670	False	0.008	2.085	0.023	True	186
A0A075B6H7	0.091	1.040	0.195	False	0.020	1.707	0.048	True	91
A0A075B6J9	0.038	1.415	0.099	False	0.009	2.040	0.026	True	156
A0A075B6Q5	0.584	0.234	0.716	False	0.002	2.639	0.008	True	104
A0A075B6R2	0.189	0.723	0.335	False	0.001	2.926	0.004	True	164
...	...	...	...	...	...	...	...	...	...
Q9UJ14	0.016	1.788	0.050	False	0.014	1.846	0.037	True	169
Q9UP79	0.420	0.376	0.578	False	0.000	4.258	0.000	True	135
Q9UQ52	0.050	1.302	0.121	False	0.001	3.136	0.003	True	188
Q9Y653;Q9Y653-2;Q9Y653-3	0.013	1.879	0.042	True	0.490	0.310	0.619	False	177
Q9Y6C2	0.442	0.355	0.595	False	0.002	2.626	0.008	True	119

203 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	TRKNN	frequency	Differential Analysis Comparison
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.670	0.023	186	PI (no) - TRKNN (yes)
A0A024R0T9;K7ER74;P02655	0.111	0.071	195	PI (no) - TRKNN (no)
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.174	0.394	174	PI (no) - TRKNN (no)
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.644	0.396	196	PI (no) - TRKNN (no)
A0A075B6H7	0.195	0.048	91	PI (no) - TRKNN (yes)
...	...	...	...	...
Q9Y6R7	0.318	0.289	197	PI (no) - TRKNN (no)
Q9Y6X5	0.203	0.205	173	PI (no) - TRKNN (no)
Q9Y6Y8;Q9Y6Y8-2	0.182	0.160	197	PI (no) - TRKNN (no)
Q9Y6Y9	0.604	0.472	119	PI (no) - TRKNN (no)
S4R3U6	0.872	0.080	126	PI (no) - TRKNN (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	TRKNN	frequency	Differential Analysis Comparison	diff_qvalue
protein groups
F5GWE5;I3L2X8;I3L3W1;I3L459;I3L471;I3L4C0;I3L4H1;I3L4U7;Q00169	0.991	0.003	78	PI (no) - TRKNN (yes)	0.988
O94898	0.979	0.002	60	PI (no) - TRKNN (yes)	0.977
D6RF35	0.994	0.040	57	PI (no) - TRKNN (yes)	0.954
P22748	0.999	0.048	159	PI (no) - TRKNN (yes)	0.951
Q9GZT8;Q9GZT8-2	0.950	0.002	86	PI (no) - TRKNN (yes)	0.948
...	...	...	...	...	...
A0A0J9YXX1	0.058	0.048	197	PI (no) - TRKNN (yes)	0.010
Q9NX62	0.056	0.046	197	PI (no) - TRKNN (yes)	0.010
F5GY80;F5H7G1;P07358	0.057	0.047	197	PI (no) - TRKNN (yes)	0.009
P00740;P00740-2	0.053	0.044	197	PI (no) - TRKNN (yes)	0.009
K7ERG9;P00746	0.052	0.043	197	PI (no) - TRKNN (yes)	0.009

203 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_TRKNN/diff_analysis_comparision_1_TRKNN

• 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_TRKNN/diff_analysis_comparision_2_TRKNN

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
APP	ENSP00000284981	5.000
PSEN1	ENSP00000326366	5.000
APOE	ENSP00000252486	5.000
PSEN2	ENSP00000355747	5.000
TREM2	ENSP00000362205	4.825
...	...	...
hsa-miR-760	hsa-miR-760	0.682
PCDH11Y	ENSP00000355419	0.682
JPH1	ENSP00000344488	0.682
RCN1	ENSP00000054950	0.682
RNF157	ENSP00000269391	0.682

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/43fbe714d68d8fe6f9b0c93f5652adb3_/lib/python3.12/site-packages/IPython/core/interactiveshell.py:3756: 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