Done data loading in decagon_run.

experiments/decagon_run/decagon_run.py

@@ -5,6 +5,7 @@ import os
 import pandas as pd
 from bisect import bisect_left
 import torch
+import sys
 
 
 def index(a, x):
@@ -14,7 +15,7 @@ def index(a, x):
     raise ValueError
 
 
-def main():
+def load_data():
     path = '/pstore/data/data_science/ref/decagon'
     df_combo = pd.read_csv(os.path.join(path, 'bio-decagon-combo.csv'))
     df_effcat = pd.read_csv(os.path.join(path, 'bio-decagon-effectcategories.csv'))
@@ -43,6 +44,7 @@ def main():
     data.add_node_type('Gene', len(genes))
     data.add_node_type('Drug', len(drugs))
 
+    print('Preparing PPI...')
     print('Indexing rows...')
     rows = [index(genes, g) for g in df_ppi['Gene 1']]
     print('Indexing cols...')
@@ -56,6 +58,39 @@ def main():
     print('adj_mat created')
     fam = data.add_relation_family('PPI', 0, 0, True)
     rel = fam.add_relation_type('PPI', adj_mat)
+    print('OK')
+
+    print('Preparing Drug-Gene (Target) edges...')
+    rows = [index(drugs, d) for d in df_tgtall['STITCH']]
+    cols = [index(genes, g) for g in df_tgtall['Gene']]
+    indices = list(zip(rows, cols))
+    indices = torch.tensor(indices).transpose(0, 1)
+    values = torch.ones(len(rows))
+    adj_mat = torch.sparse_coo_tensor(indices, values, size=(len(drugs), len(genes)))
+    fam = data.add_relation_family('Drug-Gene (Target)', 1, 0, True)
+    rel = fam.add_relation_type('Drug-Gene (Target)', adj_mat)
+    print('OK')
+
+    print('Preparing Drug-Drug (Side Effect) edges...')
+    fam = data.add_relation_family('Drug-Drug (Side Effect)', 1, 1, True)
+    print('# of side effects:', len(df_combo), 'unique:', len(df_combo['Polypharmacy Side Effect'].unique()))
+    for eff, df in df_combo.groupby('Polypharmacy Side Effect'):
+        sys.stdout.write('.') # print(eff, '...')
+        sys.stdout.flush()
+        rows = [index(drugs, d) for d in df['STITCH 1']]
+        cols = [index(drugs, d) for d in df['STITCH 2']]
+        indices = list(zip(rows, cols))
+        indices = torch.tensor(indices).transpose(0, 1)
+        values = torch.ones(len(rows))
+        adj_mat = torch.sparse_coo_tensor(indices, values, size=(len(drugs), len(drugs)))
+        adj_mat = (adj_mat + adj_mat.transpose(0, 1)) / 2
+        rel = fam.add_relation_type(df['Polypharmacy Side Effect'], adj_mat)
+    print()
+    print('OK')
+
+
+def main():
+    data = load_data()
 
 
 if __name__ == '__main__':