from IPython.display import display, Image
Image("../img/cellular_molecular_processes.png", width=800)

from reactome_api import identifiers, token
import json
import pandas as pd

input_filename = "../data/selected_features_by_subtype.json"
with open(input_filename, "r") as f:
    selected_features = json.load(f)

subtype_of_interest = 'Basal'
_ids = ",".join(selected_features[subtype_of_interest]) # comma seperated list of gene features in string... 

result = identifiers(ids=_ids, interactors=False, page_size='1', page='1', species='Homo Sapiens',
                sort_by='ENTITIES_FDR', order='ASC', resource='TOTAL', p_value='0.05', include_disease=True,
                min_entities=None, max_entities=None, projection=False)

_token = result['summary']['token']

token_result = token(_token, species='Homo sapiens', page_size='-1', page='-1', sort_by='ENTITIES_FDR',
                                      order='ASC', resource='TOTAL', p_value='0.05', include_disease=False,
                                      min_entities=None, max_entities=None)

enrichment_analysis = [p for p in token_result['pathways']]
_names = [(e['name'], e['entities']['pValue'], e['entities']['total'], e['entities']['found']) for e in enrichment_analysis]
df = pd.DataFrame(_names, columns=['Pathway name', 'pValue', 'total', 'found'])
df = df.sort_values(by='pValue', ascending=True)
print("\nTCGA-BRCA Basal subtype features pathway enrichment analysis: \n\n", df)

x = Image("../img/PathwaysOverview.png") 
y = Image("../img/Reacfoam.jpg") 
display(x, y)

TCGA-BRCA Basal subtype features pathway enrichment analysis: 

                                          Pathway name    pValue  total  found
0             APC-Cdc20 mediated degradation of Nek2A  0.000342     26      4
1   Inactivation of APC/C via direct inhibition of...  0.002409     21      3
2   Inhibition of the proteolytic activity of APC/...  0.002409     21      3
3   APC:Cdc20 mediated degradation of cell cycle p...  0.007419     61      4
4   APC/C:Cdc20 mediated degradation of mitotic pr...  0.008282     63      4
5   Activation of APC/C and APC/C:Cdc20 mediated d...  0.008737     64      4
6    TP53 Regulates Transcription of Cell Cycle Genes  0.009208     65      4
7                   NEIL3-mediated resolution of ICLs  0.012352      1      1
8    RUNX2 regulates genes involved in cell migration  0.013438     14      2
10  APC/C-mediated degradation of cell cycle proteins  0.017597     79      4
9                    Regulation of mitotic cell cycle  0.017597     79      4
11                       Phosphorylation of the APC/C  0.026129     20      2
12  TP53 Regulates Transcription of Genes Involved...  0.026129     20      2
13  TP53 Regulates Transcription of Genes Involved...  0.028577     21      2
14  Conversion from APC/C:Cdc20 to APC/C:Cdh1 in l...  0.031113     22      2
15       APC/C:Cdc20 mediated degradation of Cyclin B  0.036438     24      2
17                   Chondroitin sulfate biosynthesis  0.039223     25      2
16  Cdc20:Phospho-APC/C mediated degradation of Cy...  0.039623     60      3
18  Regulation of MITF-M-dependent genes involved ...  0.048037     28      2

3. Pathway Enrichment Analysis¶