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	0.180	1	0.291	0.590	0.002	0.229	0.728	False
	age	0.084	1	0.135	0.713	0.001	0.147	0.817	False
	Kiel	2.216	1	3.588	0.060	0.018	1.224	0.140	False
	Magdeburg	5.950	1	9.634	0.002	0.048	2.657	0.010	True
	Sweden	10.249	1	16.595	0.000	0.080	4.169	0.000	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.367	1	0.390	0.533	0.002	0.273	0.680	False
	age	1.453	1	1.542	0.216	0.008	0.666	0.365	False
	Kiel	0.099	1	0.105	0.746	0.001	0.127	0.840	False
	Magdeburg	3.254	1	3.453	0.065	0.018	1.189	0.148	False
	Sweden	8.790	1	9.329	0.003	0.047	2.589	0.011	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	RF
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.950	1	7.259	0.008	0.037	2.114	0.022	True
	age	0.001	1	0.011	0.916	0.000	0.038	0.951	False
	Kiel	0.182	1	1.391	0.240	0.007	0.620	0.371	False
	Magdeburg	0.363	1	2.773	0.097	0.014	1.011	0.184	False
	Sweden	1.466	1	11.202	0.001	0.055	3.007	0.004	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	1.247	1	2.791	0.096	0.014	1.016	0.182	False
	age	0.661	1	1.480	0.225	0.008	0.647	0.354	False
	Kiel	1.975	1	4.421	0.037	0.023	1.434	0.083	False
	Magdeburg	1.571	1	3.517	0.062	0.018	1.206	0.127	False
	Sweden	12.311	1	27.561	0.000	0.126	6.394	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	0.590	0.229	0.728	False	0.008	2.114	0.022	True
	Kiel	0.060	1.224	0.140	False	0.240	0.620	0.371	False
	Magdeburg	0.002	2.657	0.010	True	0.097	1.011	0.184	False
	Sweden	0.000	4.169	0.000	True	0.001	3.007	0.004	True
	age	0.713	0.147	0.817	False	0.916	0.038	0.951	False
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.533	0.273	0.680	False	0.096	1.016	0.182	False
	Kiel	0.746	0.127	0.840	False	0.037	1.434	0.083	False
	Magdeburg	0.065	1.189	0.148	False	0.062	1.206	0.127	False
	Sweden	0.003	2.589	0.011	True	0.000	6.394	0.000	True
	age	0.216	0.666	0.365	False	0.225	0.647	0.354	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	0.261	2.486	0.338	0.234	3.085	0.292
std	0.304	5.378	0.332	0.298	5.777	0.325
min	0.000	0.000	0.000	0.000	0.000	0.000
25%	0.004	0.327	0.015	0.001	0.387	0.003
50%	0.119	0.925	0.238	0.072	1.143	0.144
75%	0.471	2.440	0.628	0.410	3.097	0.547
max	1.000	143.804	1.000	0.999	84.747	0.999

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_103085/3761369923.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	0.590	0.229	0.728	False	0.008	2.114	0.022	True
A0A024R0T9;K7ER74;P02655	AD	0.059	1.228	0.139	False	0.032	1.492	0.074	False
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	AD	0.114	0.944	0.230	False	0.485	0.314	0.618	False
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	AD	0.524	0.281	0.672	False	0.260	0.585	0.394	False
A0A075B6H7	AD	0.109	0.964	0.223	False	0.003	2.579	0.009	True
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	AD	0.175	0.756	0.315	False	0.175	0.756	0.291	False
Q9Y6X5	AD	0.050	1.305	0.121	False	0.180	0.745	0.297	False
Q9Y6Y8;Q9Y6Y8-2	AD	0.083	1.079	0.181	False	0.083	1.079	0.162	False
Q9Y6Y9	AD	0.302	0.520	0.464	False	0.401	0.396	0.538	False
S4R3U6	AD	0.533	0.273	0.680	False	0.096	1.016	0.182	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	0.254	1.405	0.336	0.248	1.523	0.313
std	0.292	1.623	0.319	0.298	1.765	0.321
min	0.000	0.001	0.000	0.000	0.000	0.000
25%	0.011	0.352	0.036	0.009	0.364	0.026
50%	0.125	0.904	0.247	0.101	0.994	0.189
75%	0.444	1.960	0.605	0.433	2.038	0.569
max	0.997	23.616	0.998	0.999	19.321	0.999

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	1027	966

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	0.590	0.229	0.728	False	0.008	2.114	0.022	True	186
A0A024R0T9;K7ER74;P02655	0.059	1.228	0.139	False	0.032	1.492	0.074	False	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.114	0.944	0.230	False	0.485	0.314	0.618	False	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.524	0.281	0.672	False	0.260	0.585	0.394	False	196
A0A075B6H7	0.109	0.964	0.223	False	0.003	2.579	0.009	True	91
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	0.175	0.756	0.315	False	0.175	0.756	0.291	False	197
Q9Y6X5	0.050	1.305	0.121	False	0.180	0.745	0.297	False	173
Q9Y6Y8;Q9Y6Y8-2	0.083	1.079	0.181	False	0.083	1.079	0.162	False	197
Q9Y6Y9	0.302	0.520	0.464	False	0.401	0.396	0.538	False	119
S4R3U6	0.533	0.273	0.680	False	0.096	1.016	0.182	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)    902
PI (yes) - RF (yes)   330
PI (no)  - RF (yes)   125
PI (yes) - RF (no)     64
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_103085/1417621106.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	0.590	0.229	0.728	False	0.008	2.114	0.022	True	186
A0A075B6H7	0.109	0.964	0.223	False	0.003	2.579	0.009	True	91
A0A075B6R2	0.282	0.550	0.442	False	0.003	2.576	0.009	True	164
A0A075B7B8	0.102	0.992	0.212	False	0.000	4.078	0.000	True	57
A0A087WU43;A0A087WX17;A0A087WXI5;P12830;P12830-2	0.979	0.009	0.989	False	0.000	3.897	0.001	True	134
...	...	...	...	...	...	...	...	...	...
Q9ULZ9	0.000	3.552	0.002	True	0.041	1.384	0.091	False	171
Q9UNW1	0.010	1.999	0.033	True	0.915	0.039	0.950	False	171
Q9UP79	0.330	0.481	0.494	False	0.000	4.041	0.000	True	135
Q9UQ52	0.058	1.233	0.138	False	0.001	3.112	0.003	True	188
Q9Y281;Q9Y281-3	0.002	2.821	0.007	True	0.194	0.712	0.316	False	51

189 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	0.728	0.022	186	PI (no) - RF (yes)
A0A024R0T9;K7ER74;P02655	0.139	0.074	195	PI (no) - RF (no)
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.230	0.618	174	PI (no) - RF (no)
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.672	0.394	196	PI (no) - RF (no)
A0A075B6H7	0.223	0.009	91	PI (no) - RF (yes)
...	...	...	...	...
Q9Y6R7	0.315	0.291	197	PI (no) - RF (no)
Q9Y6X5	0.121	0.297	173	PI (no) - RF (no)
Q9Y6Y8;Q9Y6Y8-2	0.181	0.162	197	PI (no) - RF (no)
Q9Y6Y9	0.464	0.538	119	PI (no) - RF (no)
S4R3U6	0.680	0.182	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
Q96PQ0	0.006	0.997	177	PI (yes) - RF (no)	0.991
A0A087WU43;A0A087WX17;A0A087WXI5;P12830;P12830-2	0.989	0.001	134	PI (no) - RF (yes)	0.988
P22748	0.994	0.034	159	PI (no) - RF (yes)	0.960
P22692;P22692-2	0.998	0.044	170	PI (no) - RF (yes)	0.954
O15204;O15204-2	0.982	0.034	156	PI (no) - RF (yes)	0.948
...	...	...	...	...	...
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	0.044	197	PI (no) - RF (yes)	0.008
K7ERG9;P00746	0.052	0.044	197	PI (no) - RF (yes)	0.008
P26572	0.056	0.049	194	PI (no) - RF (yes)	0.007

189 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
PSEN1	ENSP00000326366	5.000
PSEN2	ENSP00000355747	5.000
APP	ENSP00000284981	5.000
TREM2	ENSP00000362205	4.825
...	...	...
CARMIL1	ENSP00000331983	0.681
CENPJ	ENSP00000371308	0.681
ERP27	ENSP00000266397	0.681
ZNF585B	ENSP00000433773	0.681
KIR3DL2	ENSP00000325525	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