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 = "QRILC"
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': 'QRILC',
 'out_figures': PosixPath('runs/alzheimer_study/figures'),
 'out_folder': PosixPath('runs/alzheimer_study/diff_analysis/AD/PI_vs_QRILC'),
 '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_QRILC/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	0.628	1	0.917	0.339	0.005	0.469	0.500	False
	age	0.142	1	0.208	0.649	0.001	0.188	0.769	False
	Kiel	2.676	1	3.910	0.049	0.020	1.306	0.121	False
	Magdeburg	5.703	1	8.331	0.004	0.042	2.362	0.017	True
	Sweden	9.257	1	13.523	0.000	0.066	3.514	0.002	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.135	1	0.141	0.707	0.001	0.150	0.812	False
	age	0.675	1	0.706	0.402	0.004	0.396	0.561	False
	Kiel	0.096	1	0.100	0.752	0.001	0.124	0.846	False
	Magdeburg	2.365	1	2.475	0.117	0.013	0.931	0.236	False
	Sweden	15.193	1	15.900	0.000	0.077	4.022	0.001	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	QRILC
	var	SS	DF	F	p-unc	np2	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.675	1	4.297	0.040	0.022	1.403	0.094	False
	age	0.012	1	0.079	0.779	0.000	0.109	0.855	False
	Kiel	0.381	1	2.429	0.121	0.013	0.918	0.227	False
	Magdeburg	0.843	1	5.373	0.022	0.027	1.667	0.058	False
	Sweden	2.148	1	13.685	0.000	0.067	3.549	0.001	True
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	4.169	1	2.067	0.152	0.011	0.818	0.271	False
	age	1.409	1	0.699	0.404	0.004	0.393	0.553	False
	Kiel	12.844	1	6.368	0.012	0.032	1.905	0.037	True
	Magdeburg	22.697	1	11.254	0.001	0.056	3.019	0.004	True
	Sweden	0.453	1	0.225	0.636	0.001	0.197	0.749	False

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				QRILC
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.339	0.469	0.500	False	0.040	1.403	0.094	False
	Kiel	0.049	1.306	0.121	False	0.121	0.918	0.227	False
	Magdeburg	0.004	2.362	0.017	True	0.022	1.667	0.058	False
	Sweden	0.000	3.514	0.002	True	0.000	3.549	0.001	True
	age	0.649	0.188	0.769	False	0.779	0.109	0.855	False
...	...	...	...	...	...	...	...	...	...
S4R3U6	AD	0.707	0.150	0.812	False	0.152	0.818	0.271	False
	Kiel	0.752	0.124	0.846	False	0.012	1.905	0.037	True
	Magdeburg	0.117	0.931	0.236	False	0.001	3.019	0.004	True
	Sweden	0.000	4.022	0.001	True	0.636	0.197	0.749	False
	age	0.402	0.396	0.561	False	0.404	0.393	0.553	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', 'QRILC': 'QRILC'}

Describe scores

Show code cell source

Hide code cell source

scores.describe()

model	PI			QRILC
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	2.483	0.335	0.245	2.746	0.311
std	0.301	5.337	0.329	0.297	5.181	0.325
min	0.000	0.000	0.000	0.000	0.000	0.000
25%	0.004	0.337	0.015	0.002	0.360	0.008
50%	0.121	0.918	0.242	0.092	1.036	0.184
75%	0.460	2.425	0.613	0.437	2.692	0.583
max	1.000	147.869	1.000	1.000	86.837	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_87574/3761369923.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				QRILC
	var	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected
protein groups	Source
A0A024QZX5;A0A087X1N8;P35237	AD	0.339	0.469	0.500	False	0.040	1.403	0.094	False
A0A024R0T9;K7ER74;P02655	AD	0.061	1.213	0.143	False	0.032	1.498	0.079	False
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	AD	0.058	1.238	0.136	False	0.357	0.447	0.506	False
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	AD	0.562	0.250	0.700	False	0.292	0.534	0.441	False
A0A075B6H7	AD	0.172	0.764	0.311	False	0.201	0.696	0.335	False
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	AD	0.175	0.756	0.315	False	0.175	0.756	0.302	False
Q9Y6X5	AD	0.047	1.325	0.117	False	0.045	1.347	0.104	False
Q9Y6Y8;Q9Y6Y8-2	AD	0.083	1.079	0.182	False	0.083	1.079	0.171	False
Q9Y6Y9	AD	0.570	0.244	0.707	False	0.847	0.072	0.904	False
S4R3U6	AD	0.707	0.150	0.812	False	0.152	0.818	0.271	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			QRILC
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	0.253	1.396	0.335	0.245	1.491	0.318
std	0.291	1.589	0.316	0.284	1.764	0.310
min	0.000	0.003	0.000	0.000	0.001	0.000
25%	0.011	0.347	0.037	0.009	0.365	0.028
50%	0.122	0.913	0.243	0.104	0.984	0.202
75%	0.450	1.943	0.605	0.431	2.045	0.577
max	0.992	19.497	0.995	0.998	24.172	0.999

and the boolean decision values

Show code cell source

Hide code cell source

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

model	PI	QRILC
var	rejected	rejected
count	1421	1421
unique	2	2
top	False	False
freq	1031	989

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				QRILC				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.339	0.469	0.500	False	0.040	1.403	0.094	False	186
A0A024R0T9;K7ER74;P02655	0.061	1.213	0.143	False	0.032	1.498	0.079	False	195
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.058	1.238	0.136	False	0.357	0.447	0.506	False	174
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.562	0.250	0.700	False	0.292	0.534	0.441	False	196
A0A075B6H7	0.172	0.764	0.311	False	0.201	0.696	0.335	False	91
...	...	...	...	...	...	...	...	...	...
Q9Y6R7	0.175	0.756	0.315	False	0.175	0.756	0.302	False	197
Q9Y6X5	0.047	1.325	0.117	False	0.045	1.347	0.104	False	173
Q9Y6Y8;Q9Y6Y8-2	0.083	1.079	0.182	False	0.083	1.079	0.171	False	197
Q9Y6Y9	0.570	0.244	0.707	False	0.847	0.072	0.904	False	119
S4R3U6	0.707	0.150	0.812	False	0.152	0.818	0.271	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)  - QRILC (no)    959
PI (yes) - QRILC (yes)   360
PI (no)  - QRILC (yes)    72
PI (yes) - QRILC (no)     30
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_87574/1417621106.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				QRILC				data
	p-unc	-Log10 pvalue	qvalue	rejected	p-unc	-Log10 pvalue	qvalue	rejected	frequency
protein groups
A0A075B6R2	0.373	0.428	0.534	False	0.010	1.988	0.031	True	164
A0A075B6S5	0.175	0.757	0.315	False	0.016	1.794	0.045	True	129
A0A087WWT2;Q9NPD7	0.025	1.607	0.070	False	0.006	2.247	0.019	True	193
A0A087X0M8	0.017	1.762	0.052	False	0.005	2.338	0.016	True	189
A0A087X152;D6RE16;E0CX15;O95185;O95185-2	0.011	1.956	0.036	True	0.084	1.077	0.171	False	176
...	...	...	...	...	...	...	...	...	...
Q9NZU1	0.011	1.979	0.035	True	0.493	0.307	0.633	False	72
Q9P0K9	0.025	1.609	0.070	False	0.011	1.970	0.033	True	192
Q9UKB5	0.014	1.854	0.044	True	0.025	1.609	0.064	False	148
Q9UNW1	0.011	1.942	0.037	True	0.164	0.786	0.286	False	171
Q9UQ52	0.043	1.365	0.109	False	0.005	2.272	0.018	True	188

102 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	QRILC	frequency	Differential Analysis Comparison
protein groups
A0A024QZX5;A0A087X1N8;P35237	0.500	0.094	186	PI (no) - QRILC (no)
A0A024R0T9;K7ER74;P02655	0.143	0.079	195	PI (no) - QRILC (no)
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8	0.136	0.506	174	PI (no) - QRILC (no)
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503	0.700	0.441	196	PI (no) - QRILC (no)
A0A075B6H7	0.311	0.335	91	PI (no) - QRILC (no)
...	...	...	...	...
Q9Y6R7	0.315	0.302	197	PI (no) - QRILC (no)
Q9Y6X5	0.117	0.104	173	PI (no) - QRILC (no)
Q9Y6Y8;Q9Y6Y8-2	0.182	0.171	197	PI (no) - QRILC (no)
Q9Y6Y9	0.707	0.904	119	PI (no) - QRILC (no)
S4R3U6	0.812	0.271	126	PI (no) - QRILC (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	QRILC	frequency	Differential Analysis Comparison	diff_qvalue
protein groups
Q8TEA8	0.041	0.955	56	PI (yes) - QRILC (no)	0.915
P43004;P43004-2;P43004-3	0.845	0.008	89	PI (no) - QRILC (yes)	0.838
J3KSJ8;Q9UD71;Q9UD71-2	0.873	0.046	51	PI (no) - QRILC (yes)	0.828
E7EN89;E9PP67;E9PQ25;F2Z2Y8;Q9H0E2;Q9H0E2-2	0.628	0.005	86	PI (no) - QRILC (yes)	0.623
Q9NZU1	0.035	0.633	72	PI (yes) - QRILC (no)	0.599
...	...	...	...	...	...
K7ERI9;P02654	0.040	0.052	196	PI (yes) - QRILC (no)	0.012
Q7L0X0	0.049	0.060	89	PI (yes) - QRILC (no)	0.010
P04271	0.055	0.047	183	PI (no) - QRILC (yes)	0.009
P00740;P00740-2	0.052	0.048	197	PI (no) - QRILC (yes)	0.004
K7ERG9;P00746	0.051	0.047	197	PI (no) - QRILC (yes)	0.004

102 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_QRILC/diff_analysis_comparision_1_QRILC

• 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_QRILC/diff_analysis_comparision_2_QRILC

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
PSEN2	ENSP00000355747	5.000
PSEN1	ENSP00000326366	5.000
APOE	ENSP00000252486	5.000
TREM2	ENSP00000362205	4.825
...	...	...
PTTG1	ENSP00000377536	0.682
ISL2	ENSP00000290759	0.682
hsa-miR-4433b-3p	hsa-miR-4433b-3p	0.682
NEURL1B	ENSP00000358815	0.681
SLC26A4	ENSP00000494017	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/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