code and data

Data/Input/DISNET/cases_csbj_gda.tsv

-	disease_id	drug_id
-0	C0023418	CHEMBL109
-1	C0346629	CHEMBL118
-2	C0006142	CHEMBL118
-3	C0002395	CHEMBL1201581
-4	C0024623	CHEMBL1201585
-5	C0019693	CHEMBL129
-6	C0009319	CHEMBL1370
-7	C0028754	CHEMBL1419
-8	C0006142	CHEMBL1431
-9	C0376358	CHEMBL1431
-10	C0919267	CHEMBL1434
-11	C1140680	CHEMBL1434
-12	C0020538	CHEMBL1509
-13	C0003873	CHEMBL1535
-14	C0002395	CHEMBL1581
-15	C0007134	CHEMBL1908360
-16	C0279702	CHEMBL1908360
-17	C0006142	CHEMBL34259
-18	C0003873	CHEMBL34259
-19	C0006826	CHEMBL364713
-20	C0041671	CHEMBL405
-21	C0030297	CHEMBL535
-22	C0006826	CHEMBL584
-23	C0030567	CHEMBL589
-24	C0002395	CHEMBL659
-25	C0020538	CHEMBL779
-26	C0376358	CHEMBL779
-27	C0238198	CHEMBL941
-28	C0376358	CHEMBL960
-29	C0011570	CHEMBL1175
-30	C0003873	CHEMBL118
-31	C0003873	CHEMBL1201572
-32	C0006142	CHEMBL125
-33	C0006826	CHEMBL129
-34	C0003873	CHEMBL1366
-35	C0011570	CHEMBL1419
-36	C0011849	CHEMBL1431
-37	C0020538	CHEMBL1581
-38	C0020538	CHEMBL1737
-39	C0011570	CHEMBL2110900
-40	C0014544	CHEMBL220492
-41	C0011570	CHEMBL259209
-42	C0020538	CHEMBL267936
-43	C0020538	CHEMBL317094
-44	C0006826	CHEMBL34259
-45	C0011570	CHEMBL41
-46	C0006826	CHEMBL428647
-47	C0030567	CHEMBL53
-48	C0238198	CHEMBL535
-49	C0007134	CHEMBL535
-50	C0279702	CHEMBL535
-51	C0020538	CHEMBL589
-52	C0020538	CHEMBL597
-53	C0030567	CHEMBL641
-54	C0007222	CHEMBL779
-55	C0020538	CHEMBL802
-56	C0006142	CHEMBL81
-57	C0376358	CHEMBL81
-58	C0011570	CHEMBL894
-59	C0023473	CHEMBL941
-60	C0003873	CHEMBL960

Data/Input/DISNET/cases_repodb_pw_num.tsv

-disease_id	drug_id	pathway_id
-C0002395	CHEMBL502	1
-C0002892	CHEMBL2103737	1
-C0002892	CHEMBL2110563	1
-C0020538	CHEMBL1014	2
-C0020538	CHEMBL1017	2
-C0020538	CHEMBL1069	2
-C0020538	CHEMBL1165	2
-C0020538	CHEMBL1168	2
-C0020538	CHEMBL1200692	2
-C0020538	CHEMBL1237	2
-C0020538	CHEMBL1393	1
-C0020538	CHEMBL1480	1
-C0020538	CHEMBL1513	2
-C0020538	CHEMBL1519	2
-C0020538	CHEMBL1560	2
-C0020538	CHEMBL1581	2
-C0020538	CHEMBL1592	2
-C0020538	CHEMBL1639	2
-C0020538	CHEMBL191	2
-C0020538	CHEMBL3039598	2
-C0020538	CHEMBL431	2
-C0020538	CHEMBL515606	2
-C0020538	CHEMBL577	2
-C0020538	CHEMBL578	2
-C0020538	CHEMBL611	1
-C0020538	CHEMBL813	2
-C0020538	CHEMBL838	2
-C0025202	CHEMBL1229517	1
-C0026769	CHEMBL1434	1
-C0026769	CHEMBL25	1
-C0030567	CHEMBL1175	1
-C0030567	CHEMBL1201203	1
-C0030567	CHEMBL1201236	1
-C0030567	CHEMBL1373	1
-C0030567	CHEMBL502	1
-C0030567	CHEMBL59	1
-C0030567	CHEMBL887	1
-C0033578	CHEMBL806	1
-C0035579	CHEMBL1040	1
-C0035579	CHEMBL1042	1
-C0035579	CHEMBL1536	1
-C0035579	CHEMBL2356023	1
-C0035579	CHEMBL846	1
-C0376358	CHEMBL1082407	1
-C0376358	CHEMBL254328	1
-C0376358	CHEMBL3183409	1

Data/Input/DISNET/final_cases_csbj.tsv

-	disease_id	drug_id	pathway_id	gene_id
-0	C0020538	CHEMBL1581	WP554	1636
-1	C0020538	CHEMBL1581	WP4756	1636

Data/Input/DISNET/final_cases_repodb.tsv

-	disease_id	drug_id	pathway_id	gene_id
-0	C0020538	CHEMBL578	WP554	1636
-1	C0020538	CHEMBL578	WP4756	1636
-2	C0020538	CHEMBL577	WP554	1636
-3	C0020538	CHEMBL577	WP4756	1636
-4	C0020538	CHEMBL813	WP554	185
-5	C0020538	CHEMBL813	WP4756	185
-6	C0020538	CHEMBL1480	WP554	4306
-7	C0020538	CHEMBL1639	WP554	5972
-8	C0020538	CHEMBL1639	WP4756	5972
-9	C0033578	CHEMBL806	WP3981	367
-10	C0020538	CHEMBL3039598	WP554	1636
-11	C0020538	CHEMBL3039598	WP4756	1636
-12	C0020538	CHEMBL1513	WP554	185
-13	C0020538	CHEMBL1513	WP4756	185
-14	C0030567	CHEMBL59	WP2371	6531
-15	C0020538	CHEMBL1237	WP554	1636
-16	C0020538	CHEMBL1237	WP554	5972
-17	C0020538	CHEMBL1237	WP4756	1636
-18	C0020538	CHEMBL1237	WP4756	5972
-19	C0020538	CHEMBL191	WP554	185
-20	C0020538	CHEMBL191	WP4756	185
-21	C0020538	CHEMBL1165	WP554	1636
-22	C0020538	CHEMBL1165	WP4756	1636
-23	C0020538	CHEMBL1200692	WP554	185
-24	C0020538	CHEMBL1200692	WP4756	185
-25	C0020538	CHEMBL1581	WP554	1636
-26	C0020538	CHEMBL1581	WP4756	1636
-27	C0020538	CHEMBL1592	WP554	1636
-28	C0020538	CHEMBL1592	WP4756	1636
-29	C0020538	CHEMBL1168	WP554	1636
-30	C0020538	CHEMBL1168	WP4756	1636
-31	C0020538	CHEMBL431	WP554	1636
-32	C0020538	CHEMBL431	WP4756	1636
-33	C0020538	CHEMBL1393	WP554	1585
-34	C0020538	CHEMBL1393	WP554	4306
-35	C0020538	CHEMBL1017	WP554	185
-36	C0020538	CHEMBL1017	WP4756	185
-37	C0020538	CHEMBL1519	WP554	1636
-38	C0020538	CHEMBL1519	WP4756	1636
-39	C0020538	CHEMBL1069	WP554	185
-40	C0020538	CHEMBL1069	WP4756	185
-41	C0035579	CHEMBL1042	WP1531	7421
-42	C0020538	CHEMBL838	WP554	1636
-43	C0020538	CHEMBL838	WP4756	1636
-44	C0030567	CHEMBL1201203	WP2371	6531
-45	C0030567	CHEMBL887	WP2355	596
-46	C0020538	CHEMBL611	WP554	7040
-47	C0376358	CHEMBL254328	WP3981	367
-48	C0002892	CHEMBL2110563	WP1533	4548
-49	C0002892	CHEMBL2103737	WP1533	4548
-50	C0376358	CHEMBL1082407	WP3981	367
-51	C0035579	CHEMBL1040	WP1531	7421
-52	C0020538	CHEMBL1014	WP554	185
-53	C0020538	CHEMBL1014	WP4756	185
-54	C0020538	CHEMBL1560	WP554	1636
-55	C0020538	CHEMBL1560	WP4756	1636
-56	C0030567	CHEMBL1201236	WP2371	1644
-57	C0376358	CHEMBL3183409	WP3981	367
-58	C0020538	CHEMBL515606	WP554	1636
-59	C0020538	CHEMBL515606	WP4756	1636
-60	C0002395	CHEMBL502	WP2355	4790
-61	C0030567	CHEMBL502	WP2355	4790
-62	C0035579	CHEMBL1536	WP1531	7421
-63	C0035579	CHEMBL2356023	WP1531	7421
-64	C0035579	CHEMBL846	WP1531	7421
-65	C0026769	CHEMBL25	WP673	4609
-66	C0026769	CHEMBL25	WP673	595
-67	C0026769	CHEMBL25	WP673	7157
-68	C0026769	CHEMBL1434	WP673	5601
-69	C0025202	CHEMBL1229517	WP4685	673
-70	C0030567	CHEMBL1373	WP2371	6531
-71	C0030567	CHEMBL1175	WP2371	6531

Data/Input/DISNET/score_gdas_csbj.tsv

-	disease_id	gene_id	score	drug_id
-575	C0002395	1636	0.6	CHEMBL1581

Data/Input/DISNET/score_gdas_one_repodb.tsv

-	drug_id	disease_id	gene_id	score
-0	CHEMBL1513	C0004238	185	0.03
-1	CHEMBL1513	C0004238	185	0.03
-2	CHEMBL1513	C0011881	185	0.1
-3	CHEMBL1513	C0011881	185	0.1
-4	CHEMBL1168	C0004238	1636	0.4
-5	CHEMBL1168	C0004238	1636	0.4
-6	CHEMBL191	C0011881	185	0.1
-7	CHEMBL191	C0011881	185	0.1
-8	CHEMBL1560	C0011881	1636	0.4
-9	CHEMBL1560	C0011881	1636	0.4
-10	CHEMBL1560	C0011881	4313	0.03
-11	CHEMBL1560	C0011881	4313	0.03
-12	CHEMBL1560	C0011881	4318	0.08
-13	CHEMBL1560	C0011881	4318	0.08
-14	CHEMBL59	C0020649	1812	0.3
-15	CHEMBL59	C0020649	1813	0.3
-16	CHEMBL1434	C0010674	836	0.02
-17	CHEMBL1434	C0010674	3553	0.1
-18	CHEMBL1434	C0011581	3553	0.4
-19	CHEMBL1434	C0010674	4318	0.03
-20	CHEMBL1434	C0010674	4843	0.1
-21	CHEMBL1434	C0011581	4843	0.33
-22	CHEMBL1434	C0010674	7422	0.03
-23	CHEMBL1434	C0011581	7422	0.37
-24	CHEMBL1393	C0020428	1585	0.4
-25	CHEMBL1393	C0020428	1585	0.4
-26	CHEMBL1393	C0020428	1586	0.13
-27	CHEMBL1393	C0020428	1586	0.13
-28	CHEMBL1393	C0020428	2908	0.2
-29	CHEMBL1393	C0020428	2908	0.2
-30	CHEMBL1393	C0020428	4306	0.12
-31	CHEMBL1393	C0020428	4306	0.12
-32	CHEMBL1017	C0020473	5468	0.05
-33	CHEMBL1017	C0020473	5468	0.05
-34	CHEMBL1042	C0004096	7421	0.1
-35	CHEMBL1042	C0009324	7421	0.03
-36	CHEMBL1042	C0010346	7421	0.08
-37	CHEMBL1042	C0011849	7421	0.1
-38	CHEMBL1042	C0020598	7421	0.16
-39	CHEMBL1042	C0024141	7421	0.06
-40	CHEMBL1042	C0026769	7421	0.4
-41	CHEMBL1042	C0028754	7421	0.1
-42	CHEMBL1042	C0029456	7421	0.7
-43	CHEMBL1042	C0029458	7421	0.1
-44	CHEMBL1040	C0020598	7421	0.16
-45	CHEMBL1536	C0020598	7421	0.16
-46	CHEMBL1536	C0029456	7421	0.7
-47	CHEMBL1536	C0029458	7421	0.1
-48	CHEMBL2356023	C0020598	7421	0.16
-49	CHEMBL846	C0020598	7421	0.16
-50	CHEMBL502	C0026769	590	0.3
-51	CHEMBL502	C0002395	590	0.4
-52	CHEMBL502	C0026769	3553	0.4
-53	CHEMBL502	C0026769	3553	0.4
-54	CHEMBL502	C0002395	3553	0.6
-55	CHEMBL502	C0002395	3553	0.6
-56	CHEMBL502	C0026769	4790	0.03
-57	CHEMBL502	C0002395	4790	0.09
-58	CHEMBL502	C0002395	43	0.4
-59	CHEMBL502	C0002395	3356	0.1
-60	CHEMBL502	C0002395	4842	0.06
-61	CHEMBL502	C0002395	4842	0.06
-62	CHEMBL25	C0003873	595	0.02
-63	CHEMBL25	C0003873	595	0.02
-64	CHEMBL25	C0003873	595	0.02
-65	CHEMBL25	C0026764	595	0.7
-66	CHEMBL25	C0026764	595	0.7
-67	CHEMBL25	C0026764	595	0.7
-68	CHEMBL25	C0003873	834	0.03
-69	CHEMBL25	C0003873	834	0.03
-70	CHEMBL25	C0003873	834	0.03
-71	CHEMBL25	C0003873	834	0.03
-72	CHEMBL25	C0003873	834	0.03
-73	CHEMBL25	C0003873	834	0.03
-74	CHEMBL25	C0004153	834	0.03
-75	CHEMBL25	C0004153	834	0.03
-76	CHEMBL25	C0004153	834	0.03
-77	CHEMBL25	C0004153	834	0.03
-78	CHEMBL25	C0004153	834	0.03
-79	CHEMBL25	C0004153	834	0.03
-80	CHEMBL25	C0003873	836	0.05
-81	CHEMBL25	C0003873	836	0.05
-82	CHEMBL25	C0003873	836	0.05
-83	CHEMBL25	C0003873	836	0.05
-84	CHEMBL25	C0003873	836	0.05
-85	CHEMBL25	C0003873	836	0.05
-86	CHEMBL25	C0004153	836	0.03
-87	CHEMBL25	C0004153	836	0.03
-88	CHEMBL25	C0004153	836	0.03
-89	CHEMBL25	C0004153	836	0.03
-90	CHEMBL25	C0004153	836	0.03
-91	CHEMBL25	C0004153	836	0.03
-92	CHEMBL25	C0026764	836	0.1
-93	CHEMBL25	C0026764	836	0.1
-94	CHEMBL25	C0026764	836	0.1
-95	CHEMBL25	C0026764	836	0.1
-96	CHEMBL25	C0026764	836	0.1
-97	CHEMBL25	C0026764	836	0.1
-98	CHEMBL25	C0003873	1909	0.03
-99	CHEMBL25	C0003873	1909	0.03
-100	CHEMBL25	C0003873	1909	0.03
-101	CHEMBL25	C0004153	1909	0.03
-102	CHEMBL25	C0004153	1909	0.03
-103	CHEMBL25	C0004153	1909	0.03
-104	CHEMBL25	C0026764	1909	0.02
-105	CHEMBL25	C0026764	1909	0.02
-106	CHEMBL25	C0026764	1909	0.02
-107	CHEMBL25	C0003873	4792	0.02
-108	CHEMBL25	C0003873	4792	0.02
-109	CHEMBL25	C0003873	4792	0.02
-110	CHEMBL25	C0026764	4792	0.04
-111	CHEMBL25	C0026764	4792	0.04
-112	CHEMBL25	C0026764	4792	0.04
-113	CHEMBL25	C0003873	5111	0.03
-114	CHEMBL25	C0003873	5111	0.03
-115	CHEMBL25	C0003873	5111	0.03
-116	CHEMBL25	C0026764	5111	0.08
-117	CHEMBL25	C0026764	5111	0.08
-118	CHEMBL25	C0026764	5111	0.08
-119	CHEMBL25	C0003873	5742	0.34
-120	CHEMBL25	C0003873	5742	0.34
-121	CHEMBL25	C0003873	5742	0.34
-122	CHEMBL25	C0004153	5742	0.02
-123	CHEMBL25	C0004153	5742	0.02
-124	CHEMBL25	C0004153	5742	0.02
-125	CHEMBL25	C0026764	5742	0.02
-126	CHEMBL25	C0026764	5742	0.02
-127	CHEMBL25	C0026764	5742	0.02
-128	CHEMBL25	C0003873	5743	0.4
-129	CHEMBL25	C0003873	5743	0.4
-130	CHEMBL25	C0003873	5743	0.4
-131	CHEMBL25	C0004153	5743	0.4
-132	CHEMBL25	C0004153	5743	0.4
-133	CHEMBL25	C0004153	5743	0.4
-134	CHEMBL25	C0026764	5743	0.06
-135	CHEMBL25	C0026764	5743	0.06
-136	CHEMBL25	C0026764	5743	0.06
-137	CHEMBL25	C0003873	7157	0.1
-138	CHEMBL25	C0003873	7157	0.1
-139	CHEMBL25	C0003873	7157	0.1
-140	CHEMBL25	C0003873	7157	0.1
-141	CHEMBL25	C0003873	7157	0.1
-142	CHEMBL25	C0003873	7157	0.1
-143	CHEMBL25	C0004153	7157	0.1
-144	CHEMBL25	C0004153	7157	0.1
-145	CHEMBL25	C0004153	7157	0.1
-146	CHEMBL25	C0004153	7157	0.1
-147	CHEMBL25	C0004153	7157	0.1
-148	CHEMBL25	C0004153	7157	0.1
-149	CHEMBL25	C0004604	7157	0.1
-150	CHEMBL25	C0004604	7157	0.1
-151	CHEMBL25	C0004604	7157	0.1
-152	CHEMBL25	C0004604	7157	0.1
-153	CHEMBL25	C0004604	7157	0.1
-154	CHEMBL25	C0004604	7157	0.1
-155	CHEMBL25	C0026764	7157	0.2
-156	CHEMBL25	C0026764	7157	0.2
-157	CHEMBL25	C0026764	7157	0.2
-158	CHEMBL25	C0026764	7157	0.2
-159	CHEMBL25	C0026764	7157	0.2
-160	CHEMBL25	C0026764	7157	0.2
-161	CHEMBL25	C0004153	4609	0.02
-162	CHEMBL25	C0004153	4609	0.02
-163	CHEMBL25	C0004153	4609	0.02
-164	CHEMBL25	C0026764	4609	0.4
-165	CHEMBL25	C0026764	4609	0.4
-166	CHEMBL25	C0026764	4609	0.4
-167	CHEMBL25	C0026764	3309	0.03
-168	CHEMBL25	C0026764	3309	0.03
-169	CHEMBL25	C0026764	3309	0.03
-170	CHEMBL25	C0026764	6197	0.02
-171	CHEMBL25	C0026764	6197	0.02
-172	CHEMBL25	C0026764	6197	0.02
-173	CHEMBL1373	C0030193	6531	0.02
-174	CHEMBL1175	C0016053	6532	0.04

Data/Input/DISNET/score_gdas_two_repodb.tsv

-	drug_id	disease_id	gene_id	score
-0	CHEMBL59	C0242422	6531	0.2
-1	CHEMBL1201203	C0242422	6531	0.2
-2	CHEMBL1201236	C0242422	1644	0.31
-3	CHEMBL1237	C0027051	5972	0.4
-4	CHEMBL1237	C0027051	5972	0.4
-5	CHEMBL1237	C0027051	5972	0.4
-6	CHEMBL1237	C0027051	5972	0.4
-7	CHEMBL25	C0027051	834	0.02
-8	CHEMBL25	C0027051	834	0.02
-9	CHEMBL25	C0027051	834	0.02
-10	CHEMBL25	C0027051	834	0.02
-11	CHEMBL25	C0027051	834	0.02
-12	CHEMBL25	C0027051	834	0.02
-13	CHEMBL25	C0029408	834	0.02
-14	CHEMBL25	C0029408	834	0.02
-15	CHEMBL25	C0029408	834	0.02
-16	CHEMBL25	C0029408	834	0.02
-17	CHEMBL25	C0029408	834	0.02
-18	CHEMBL25	C0029408	834	0.02
-19	CHEMBL25	C0027051	836	0.32
-20	CHEMBL25	C0027051	836	0.32
-21	CHEMBL25	C0027051	836	0.32
-22	CHEMBL25	C0027051	836	0.32
-23	CHEMBL25	C0027051	836	0.32
-24	CHEMBL25	C0027051	836	0.32
-25	CHEMBL25	C0029408	836	0.05
-26	CHEMBL25	C0029408	836	0.05
-27	CHEMBL25	C0029408	836	0.05
-28	CHEMBL25	C0029408	836	0.05
-29	CHEMBL25	C0029408	836	0.05
-30	CHEMBL25	C0029408	836	0.05
-31	CHEMBL25	C0027051	1909	0.21
-32	CHEMBL25	C0027051	1909	0.21
-33	CHEMBL25	C0027051	1909	0.21
-34	CHEMBL25	C0030193	1909	0.04
-35	CHEMBL25	C0030193	1909	0.04
-36	CHEMBL25	C0030193	1909	0.04
-37	CHEMBL25	C0149931	1909	0.34
-38	CHEMBL25	C0149931	1909	0.34
-39	CHEMBL25	C0149931	1909	0.34
-40	CHEMBL25	C0027051	3309	0.3
-41	CHEMBL25	C0027051	3309	0.3
-42	CHEMBL25	C0027051	3309	0.3
-43	CHEMBL25	C0029408	3309	0.02
-44	CHEMBL25	C0029408	3309	0.02
-45	CHEMBL25	C0029408	3309	0.02
-46	CHEMBL25	C0027051	5742	0.02
-47	CHEMBL25	C0027051	5742	0.02
-48	CHEMBL25	C0027051	5742	0.02
-49	CHEMBL25	C0030193	5742	0.03
-50	CHEMBL25	C0030193	5742	0.03
-51	CHEMBL25	C0030193	5742	0.03
-52	CHEMBL25	C0027051	5743	0.1
-53	CHEMBL25	C0027051	5743	0.1
-54	CHEMBL25	C0027051	5743	0.1
-55	CHEMBL25	C0029408	5743	0.1
-56	CHEMBL25	C0029408	5743	0.1
-57	CHEMBL25	C0029408	5743	0.1
-58	CHEMBL25	C0030193	5743	0.1
-59	CHEMBL25	C0030193	5743	0.1
-60	CHEMBL25	C0030193	5743	0.1
-61	CHEMBL25	C0948089	5743	0.02
-62	CHEMBL25	C0948089	5743	0.02
-63	CHEMBL25	C0948089	5743	0.02
-64	CHEMBL25	C0027051	7157	0.33
-65	CHEMBL25	C0027051	7157	0.33
-66	CHEMBL25	C0027051	7157	0.33
-67	CHEMBL25	C0027051	7157	0.33
-68	CHEMBL25	C0027051	7157	0.33
-69	CHEMBL25	C0027051	7157	0.33
-70	CHEMBL25	C0029408	7157	0.03
-71	CHEMBL25	C0029408	7157	0.03
-72	CHEMBL25	C0029408	7157	0.03
-73	CHEMBL25	C0029408	7157	0.03
-74	CHEMBL25	C0029408	7157	0.03
-75	CHEMBL25	C0029408	7157	0.03
-76	CHEMBL25	C0030193	7157	0.1
-77	CHEMBL25	C0030193	7157	0.1
-78	CHEMBL25	C0030193	7157	0.1
-79	CHEMBL25	C0030193	7157	0.1
-80	CHEMBL25	C0030193	7157	0.1
-81	CHEMBL25	C0030193	7157	0.1
-82	CHEMBL25	C0032463	7157	0.03
-83	CHEMBL25	C0032463	7157	0.03
-84	CHEMBL25	C0032463	7157	0.03
-85	CHEMBL25	C0032463	7157	0.03
-86	CHEMBL25	C0032463	7157	0.03
-87	CHEMBL25	C0032463	7157	0.03
-88	CHEMBL1581	C0028754	1636	0.3
-89	CHEMBL1581	C0028754	1636	0.3
-90	CHEMBL1168	C0038454	1636	0.4
-91	CHEMBL1168	C0038454	1636	0.4
-92	CHEMBL1017	C0038454	185	0.08
-93	CHEMBL1017	C0038454	185	0.08
-94	CHEMBL1017	C0038454	5468	0.04
-95	CHEMBL1017	C0038454	5468	0.04
-96	CHEMBL1042	C0036341	7421	0.03
-97	CHEMBL1042	C0042870	7421	0.4
-98	CHEMBL502	C0036341	43	0.3
-99	CHEMBL502	C0036341	43	0.3
-100	CHEMBL502	C0030567	43	0.03
-101	CHEMBL502	C0497327	43	0.05
-102	CHEMBL502	C0497327	43	0.05
-103	CHEMBL502	C0036341	3356	0.4
-104	CHEMBL502	C0036341	3356	0.4
-105	CHEMBL502	C0036341	3553	0.4
-106	CHEMBL502	C0036341	3553	0.4
-107	CHEMBL502	C0036341	3553	0.4
-108	CHEMBL502	C0036341	3553	0.4
-109	CHEMBL502	C0026769	3553	0.4
-110	CHEMBL502	C0026769	3553	0.4
-111	CHEMBL502	C0030567	3553	0.28
-112	CHEMBL502	C0030567	3553	0.28
-113	CHEMBL502	C0497327	3553	0.09
-114	CHEMBL502	C0497327	3553	0.09
-115	CHEMBL502	C0497327	3553	0.09
-116	CHEMBL502	C0497327	3553	0.09
-117	CHEMBL502	C0036341	4790	0.1
-118	CHEMBL502	C0036341	4790	0.1
-119	CHEMBL502	C0026769	4790	0.03
-120	CHEMBL502	C0030567	4790	0.03
-121	CHEMBL502	C0036341	4842	0.5
-122	CHEMBL502	C0036341	4842	0.5
-123	CHEMBL502	C0036341	4842	0.5
-124	CHEMBL502	C0036341	4842	0.5
-125	CHEMBL502	C0030567	4842	0.38
-126	CHEMBL502	C0030567	4842	0.38
-127	CHEMBL1373	C0036341	6531	0.4
-128	CHEMBL1373	C1269683	6531	0.04
-129	CHEMBL1175	C0036341	6530	0.34
-130	CHEMBL1175	C1269683	6530	0.4
-131	CHEMBL1175	C0036341	6531	0.4
-132	CHEMBL1175	C0497327	6531	0.33
-133	CHEMBL1175	C1269683	6531	0.04
-134	CHEMBL1175	C0036341	6532	0.4
-135	CHEMBL1175	C0497327	6532	0.02
-136	CHEMBL1175	C1269683	6532	0.6
-137	CHEMBL1536	C0042870	7421	0.4
-138	CHEMBL846	C0042870	7421	0.4
-139	CHEMBL846	C0085682	7421	0.13
-140	CHEMBL2110563	C0042847	4548	0.22
-141	CHEMBL2103737	C0042847	4548	0.22
-142	CHEMBL1040	C0085682	7421	0.13
-143	CHEMBL2356023	C0085682	7421	0.13
-144	CHEMBL502	C0026769	590	0.3
-145	CHEMBL502	C0030567	590	0.02
-146	CHEMBL502	C0497327	590	0.06
-147	CHEMBL502	C0497327	590	0.06
-148	CHEMBL25	C0029408	1645	0.3
-149	CHEMBL25	C0029408	1645	0.3
-150	CHEMBL25	C0029408	1645	0.3
-151	CHEMBL25	C0030193	4792	0.02
-152	CHEMBL25	C0030193	4792	0.02
-153	CHEMBL25	C0030193	4792	0.02
-154	CHEMBL1434	C0031099	4318	0.35
-155	CHEMBL1434	C0032285	4318	0.06
-156	CHEMBL1434	C0031099	7422	0.02
-157	CHEMBL1434	C0032285	7422	0.04
-158	CHEMBL1434	C0042029	7422	0.03
-159	CHEMBL1434	C0032285	240	0.02
-160	CHEMBL1434	C0032285	834	0.32
-161	CHEMBL1434	C0032285	3553	0.6
-162	CHEMBL1434	C0042029	4843	0.3
-163	CHEMBL1229517	C0026764	673	0.49

Data/Input/DISNET/triplets_total.csv

-disease_PwB;drug_id;disease_no_PwB
-C0020538;CHEMBL578;C0018802
-C0020538;CHEMBL578;C0018802
-C0020538;CHEMBL577;C0018802
-C0020538;CHEMBL577;C0018802
-C0020538;CHEMBL1513;C0004238
-C0020538;CHEMBL1513;C0011881
-C0020538;CHEMBL1513;C0004238
-C0020538;CHEMBL1513;C0011881
-C0030567;CHEMBL59;C0001206
-C0030567;CHEMBL59;C0020649
-C0030567;CHEMBL59;C0024586
-C0020538;CHEMBL191;C0010674
-C0020538;CHEMBL191;C0011881
-C0020538;CHEMBL191;C0010674
-C0020538;CHEMBL191;C0011881
-C0020538;CHEMBL1168;C0004238
-C0020538;CHEMBL1168;C0004238
-C0020538;CHEMBL1393;C0003962
-C0020538;CHEMBL1393;C0013604
-C0020538;CHEMBL1393;C0020428
-C0020538;CHEMBL1393;C0003962
-C0020538;CHEMBL1393;C0013604
-C0020538;CHEMBL1393;C0020428
-C0020538;CHEMBL1017;C0020473
-C0020538;CHEMBL1017;C0020473
-C0020538;CHEMBL1069;C0018801
-C0020538;CHEMBL1069;C0018801
-C0035579;CHEMBL1042;C0004096
-C0035579;CHEMBL1042;C0009324
-C0035579;CHEMBL1042;C0010346
-C0035579;CHEMBL1042;C0011849
-C0035579;CHEMBL1042;C0020598
-C0035579;CHEMBL1042;C0020626
-C0035579;CHEMBL1042;C0024141
-C0035579;CHEMBL1042;C0026769
-C0035579;CHEMBL1042;C0028754
-C0035579;CHEMBL1042;C0029456
-C0035579;CHEMBL1042;C0029458
-C0030567;CHEMBL1201203;C0015371
-C0035579;CHEMBL1040;C0020598
-C0035579;CHEMBL1040;C0035086
-C0020538;CHEMBL1560;C0011881
-C0020538;CHEMBL1560;C0011881
-C0030567;CHEMBL502;C0002395
-C0030567;CHEMBL502;C0026769
-C0035579;CHEMBL1536;C0020598
-C0035579;CHEMBL1536;C0020626
-C0035579;CHEMBL1536;C0029456
-C0035579;CHEMBL1536;C0029458
-C0035579;CHEMBL2356023;C0020598
-C0035579;CHEMBL2356023;C0020626
-C0035579;CHEMBL846;C0020598
-C0035579;CHEMBL846;C0020626
-C0035579;CHEMBL846;C0035086
-C0026769;CHEMBL25;C0003862
-C0026769;CHEMBL25;C0003873
-C0026769;CHEMBL25;C0004153
-C0026769;CHEMBL25;C0004604
-C0026769;CHEMBL25;C0009443
-C0026769;CHEMBL25;C0026764
-C0026769;CHEMBL25;C0003862
-C0026769;CHEMBL25;C0003873
-C0026769;CHEMBL25;C0004153
-C0026769;CHEMBL25;C0004604
-C0026769;CHEMBL25;C0009443
-C0026769;CHEMBL25;C0026764
-C0026769;CHEMBL25;C0003862
-C0026769;CHEMBL25;C0003873
-C0026769;CHEMBL25;C0004153
-C0026769;CHEMBL25;C0004604
-C0026769;CHEMBL25;C0009443
-C0026769;CHEMBL25;C0026764
-C0026769;CHEMBL1434;C0001144
-C0026769;CHEMBL1434;C0001261
-C0026769;CHEMBL1434;C0003175
-C0026769;CHEMBL1434;C0006277
-C0026769;CHEMBL1434;C0006309
-C0026769;CHEMBL1434;C0010674
-C0026769;CHEMBL1434;C0011581
-C0026769;CHEMBL1434;C0018081
-C0026769;CHEMBL1434;C0023860
-C0030567;CHEMBL1373;C0027404
-C0030567;CHEMBL1373;C0030193
-C0030567;CHEMBL1175;C0016053
-C0030567;CHEMBL59;C0184567
-C0030567;CHEMBL59;C0242422
-C0030567;CHEMBL59;C0600177
-C0030567;CHEMBL59;C1621958
-C0020538;CHEMBL1237;C0027051
-C0020538;CHEMBL1237;C0027051
-C0020538;CHEMBL1237;C0027051
-C0020538;CHEMBL1237;C0027051
-C0020538;CHEMBL1581;C0028754
-C0020538;CHEMBL1581;C0028754
-C0020538;CHEMBL1168;C0038454
-C0020538;CHEMBL1168;C0038454
-C0020538;CHEMBL1017;C0038454
-C0020538;CHEMBL1017;C0038454
-C0035579;CHEMBL1042;C0036337
-C0035579;CHEMBL1042;C0036341
-C0035579;CHEMBL1042;C0042870
-C0030567;CHEMBL1201203;C0242422
-C0020538;CHEMBL611;C1739363
-C0002892;CHEMBL2110563;C0042847
-C0002892;CHEMBL2110563;C0162316
-C0002892;CHEMBL2103737;C0006114
-C0002892;CHEMBL2103737;C0033860
-C0002892;CHEMBL2103737;C0042847
-C0035579;CHEMBL1040;C0085682
-C0030567;CHEMBL1201236;C0184567
-C0030567;CHEMBL1201236;C0242422
-C0002395;CHEMBL502;C0026769
-C0002395;CHEMBL502;C0030567
-C0002395;CHEMBL502;C0036341
-C0002395;CHEMBL502;C0497327
-C0030567;CHEMBL502;C0036341
-C0030567;CHEMBL502;C0497327
-C0035579;CHEMBL1536;C0042870
-C0035579;CHEMBL1536;C3536984
-C0035579;CHEMBL2356023;C0039621
-C0035579;CHEMBL2356023;C0085682
-C0035579;CHEMBL846;C0042870
-C0035579;CHEMBL846;C0085682
-C0035579;CHEMBL846;C1527383
-C0026769;CHEMBL25;C0027051
-C0026769;CHEMBL25;C0029408
-C0026769;CHEMBL25;C0030193
-C0026769;CHEMBL25;C0032463
-C0026769;CHEMBL25;C0040460
-C0026769;CHEMBL25;C0149931
-C0026769;CHEMBL25;C0393735
-C0026769;CHEMBL25;C0948089
-C0026769;CHEMBL25;C0027051
-C0026769;CHEMBL25;C0029408
-C0026769;CHEMBL25;C0030193
-C0026769;CHEMBL25;C0032463
-C0026769;CHEMBL25;C0040460
-C0026769;CHEMBL25;C0149931
-C0026769;CHEMBL25;C0393735
-C0026769;CHEMBL25;C0948089
-C0026769;CHEMBL25;C0027051
-C0026769;CHEMBL25;C0029408
-C0026769;CHEMBL25;C0030193
-C0026769;CHEMBL25;C0032463
-C0026769;CHEMBL25;C0040460
-C0026769;CHEMBL25;C0149931
-C0026769;CHEMBL25;C0393735
-C0026769;CHEMBL25;C0948089
-C0026769;CHEMBL1434;C0031099
-C0026769;CHEMBL1434;C0031350
-C0026769;CHEMBL1434;C0032064
-C0026769;CHEMBL1434;C0032285
-C0026769;CHEMBL1434;C0034362
-C0026769;CHEMBL1434;C0035854
-C0026769;CHEMBL1434;C0037199
-C0026769;CHEMBL1434;C0039128
-C0026769;CHEMBL1434;C0042029
-C0025202;CHEMBL1229517;C0026764
-C0030567;CHEMBL1373;C0036341
-C0030567;CHEMBL1373;C1269683
-C0030567;CHEMBL1175;C0036341
-C0030567;CHEMBL1175;C0497327
-C0030567;CHEMBL1175;C1269683
-C0020538;CHEMBL1581;C0002395

Notebooks/Processed data/.ipynb_checkpoints/1.2 DREGE_triples_selected-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4d974299",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sqlalchemy import create_engine\n",
+    "import mysql.connector"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d7450e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_repodb = pd.read_csv(\"./Data/Input/Drug Repurposing/triples_filter_repodb_final.tsv\", sep='\\,')\n",
+    "triples_repodb = triples_repodb.drop(columns=['Unnamed: 0'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8f4f9844",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug_gen = pd.read_csv('./Data/Input/DISNET/drug_gen.tsv', sep='\\t')\n",
+    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "899450d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target= triples_repodb.merge(drug_gen, left_on = \"drug\",right_on = \"drug_id\",how= \"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b1edb7eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target = tri_gen_target.drop([\"drug\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "d17dd8b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target = tri_gen_target.rename(columns={\"disease1\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "2c5af632",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target = tri_gen_target.rename(columns={\"disease2\": \"disease_id_new\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f8f0a4e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen = pd.read_csv('./Data/Input/DISNET/dis_gen.tsv', sep='\\t')\n",
+    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "31a63d57",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_new = dis_gen.rename(columns={\"disease_id\": \"disease2\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "9db0ad6c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_gen_one = tri_gen_target.merge(dis_gen, on = [\"gene_id\",\"disease_id\"],how=\"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "0cdd6380",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_gen_one = disease_gen_one.merge(dis_gen_new, on = [\"gene_id\",\"disease2\"],how=\"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "3e3fb7f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege = disease_gen_one.drop([\"score_x\",\"score_y\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "12980000",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege = triples_final_drege.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "95d6a637",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege = triples_final_drege.drop([\"gene_id\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "55455401",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege = triples_final_drege.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6e7cd640",
+   "metadata": {},
+   "source": [
+    "# CSBJ"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "32cdd921",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj = pd.read_excel(\"./Data/Input/DISNET/triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
+    "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "868f7e2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target_csbj= triplets_csbj.merge(drug_gen, on = \"drug_id\",how= \"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "c6bad999",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tri_gen_target_csbj = tri_gen_target_csbj.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "d86d80dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_gen_one_csbj = tri_gen_target_csbj.merge(dis_gen, on = [\"gene_id\",\"disease_id\"],how=\"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "54fed905",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_new = dis_gen.rename(columns={\"disease_id\": \"New Condition CUI\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "174647b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_gen_one_csbj_twounion = disease_gen_one_csbj.merge(dis_gen_new, on = [\"gene_id\",\"New Condition CUI\"],how=\"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "b8ee708d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj_drege = disease_gen_one_csbj_twounion[[\"disease_id\",\"New Condition CUI\",\"drug_id\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "8453abae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj_drege =triplets_csbj_drege.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ad972954",
+   "metadata": {},
+   "source": [
+    "# FINAL TRIPLES DREGE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "aad768b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege = triples_final_drege.rename(columns={\"disease2\": \"New Condition CUI\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "e6837711",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege_repo_csbj = pd.concat([triplets_csbj_drege,triples_final_drege])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "3e675cd1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege_repo_csbj = triples_final_drege_repo_csbj.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "75d2b323",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triples_final_drege_repo_csbj.to_excel(\"triples_final_drege_repo_csbj.xlsx\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Notebooks/Processed data/1.1 DREBIOP_triples_selected.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triples_repodb = pd.read_csv(\"triples_filter_repodb_final.tsv\", sep='\\,')\n",
+    "triples_repodb = pd.read_csv(\"./Data/Input/Drug Repurposing/triples_filter_repodb_final.tsv\", sep='\\,')\n",
     "triples_repodb = triples_repodb.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -33,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dis_path_direct = pd.read_csv('disease_pathway.tsv', sep='\\t')"
+    "dis_path_direct = pd.read_csv('./Data/Input/DISNET/disease_pathway.tsv', sep='\\t')"
    ]
   },
   {
@@ -63,7 +63,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "drug_gen = pd.read_csv('drug_gen.tsv', sep='\\t')\n",
+    "drug_gen = pd.read_csv('./Data/Input/DISNET/drug_gen.tsv', sep='\\t')\n",
     "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -114,7 +114,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dis_gen = pd.read_csv('dis_gen.tsv', sep='\\t')\n",
+    "dis_gen = pd.read_csv('./Data/Input/DISNET/dis_gen.tsv', sep='\\t')\n",
     "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -185,7 +185,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "drug_gen_pw = pd.read_csv(\"drug_gen_pw.tsv\", sep='\\t')\n",
+    "drug_gen_pw = pd.read_csv(\"./Data/Input/DISNET/drug_gen_pw.tsv\", sep='\\t')\n",
     "drug_gen_pw = drug_gen_pw.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -325,7 +325,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_csbj = pd.read_excel(\"triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
+    "triplets_csbj = pd.read_excel(\"./Data/Input/DISNET/triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
     "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },

Notebooks/Processed data/1.2 DREGE_triples_selected.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triples_repodb = pd.read_csv(\"triples_filter_repodb_final.tsv\", sep='\\,')\n",
+    "triples_repodb = pd.read_csv(\"./Data/Input/Drug Repurposing/triples_filter_repodb_final.tsv\", sep='\\,')\n",
     "triples_repodb = triples_repodb.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -33,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "drug_gen = pd.read_csv('drug_gen.tsv', sep='\\t')\n",
+    "drug_gen = pd.read_csv('./Data/Input/DISNET/drug_gen.tsv', sep='\\t')\n",
     "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dis_gen = pd.read_csv('dis_gen.tsv', sep='\\t')\n",
+    "dis_gen = pd.read_csv('./Data/Input/DISNET/dis_gen.tsv', sep='\\t')\n",
     "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -173,7 +173,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_csbj = pd.read_excel(\"triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
+    "triplets_csbj = pd.read_excel(\"./Data/Input/DISNET/triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
     "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },

Notebooks/Results/.ipynb_checkpoints/1.1 Patterns DREBIOP - Disease 1-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sqlalchemy import create_engine\n",
+    "from sklearn import preprocessing\n",
+    "import mysql.connector\n",
+    "from pandas import DataFrame"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_total = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total = triplets_total.drop(columns=['Unnamed: 0'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_total = triplets_total.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_one = triplets_total[[\"Original Condition CUI\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "disease_one = disease_one.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# genes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "genes = pd.read_excel((\"./Data/Input/DISNET/dis_gen.xlsx\"),engine='openpyxl')\n",
+    "genes = gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gene = disease_one.merge(genes, how= \"inner\", on= \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_num_gen = dis_gene.groupby(['disease_id']).count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_num_gen = dis_gen_num_gen.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count     23.000000\n",
+       "mean     105.130435\n",
+       "std      149.308194\n",
+       "min        2.000000\n",
+       "25%       17.500000\n",
+       "50%       37.000000\n",
+       "75%       91.500000\n",
+       "max      526.000000\n",
+       "Name: gene_id, dtype: float64"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dis_gen_num_gen[\"gene_id\"].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#### pw via gene"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pw_gene = pd.read_csv('./Data/Input/DISNET/pathways_genes.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_pw_gen = disease_one.merge(pw_gene, how= \"inner\", on= \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_pw_gen = dis_pw_gen.groupby(['disease_id']).count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_pw_gen = dis_pw_gen.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "391.04347826086956"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dis_pw_gen[\"pathway_id\"].mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#### pw direct"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_path_direct = pd.read_csv('./Data/Input/DISNET/disease_pathway.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dr_pw = disease_one.merge(dis_path_direct,on=\"disease_id\",how= \"inner\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dr_pw = dr_pw.groupby(['disease_id']).count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dr_pw = dr_pw.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "nan"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dr_pw[\"pathway_id\"].mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "### drug"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug = pd.read_csv('./Data/Input/DISNET/drugs.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_drug = disease_one.merge(drug, how= \"inner\", on= \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_drug = dis_drug.groupby(['disease_id']).count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_drug = dis_drug.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "384.6"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dis_drug[\"drug_id\"].mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "### symptom"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sint = pd.read_csv('./Data/Input/DISNET/sint_all.tsv', sep='\\t')\n",
+    "sint = sint.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_sint = disease_one.merge(sint, how= \"inner\", on= \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_sint = dis_sint.groupby(['disease_id']).count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_sint = dis_sint.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "68.6086956521739"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dis_sint[\"symptom\"].mean()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Notebooks/Results/.ipynb_checkpoints/3.1 Type of drugs - MESHPA-checkpoint.ipynb

@@ -20,7 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drebiop = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total_drebiop = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total_drebiop = triplets_total_drebiop.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -68,7 +68,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drege = pd.read_excel((\"triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
+    "triplets_total_drege = pd.read_excel((\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
     "triplets_total_drege = triplets_total_drege.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -96,7 +96,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "type_drug =pd.read_excel(\"Drug_Categories.xlsx\", engine='openpyxl')"
+    "type_drug =pd.read_excel(\"./Data/Input/DISNET/Drug_Categories.xlsx\", engine='openpyxl')"
    ]
   },
   {

Notebooks/Results/.ipynb_checkpoints/3.2 Types of drugs - ATC-checkpoint.ipynb

@@ -20,7 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drege = pd.read_excel((\"triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
+    "triplets_total_drege = pd.read_excel((\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
     "triplets_total_drege = triplets_total_drege.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -48,7 +48,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drebiop = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total_drebiop = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total_drebiop = triplets_total_drebiop.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -85,7 +85,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "drug_atc = pd.read_csv('drug_atc.tsv', sep='\\t')\n",
+    "drug_atc = pd.read_csv('./Data/Input/DISNET/drug_atc.tsv', sep='\\t')\n",
     "drug_atc = drug_atc.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -246,7 +246,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "atc_name = pd.read_excel(\"ATC_desc_name.xlsx\")\n",
+    "atc_name = pd.read_excel(\"./Data/Input/DISNET/ATC_desc_name.xlsx\")\n",
     "atc_name['index'] = atc_name['index'].str.strip()"
    ]
   },

Notebooks/Results/.ipynb_checkpoints/5. Pattern search based on phenotypical similarity-checkpoint.ipynb

@@ -69,7 +69,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sint = pd.read_csv('sint_all.tsv', sep='\\t')\n",
+    "sint = pd.read_csv('./Data/Input/DISNET/sint_all.tsv', sep='\\t')\n",
     "sint = sint.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -275,7 +275,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total = triplets_total.drop(columns=['Unnamed: 0'])\n",
     "triplets_total = triplets_total.drop_duplicates()"
    ]
@@ -475,7 +475,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "Triples_target_final = pd.read_excel(\"triples_final_drege_repo_csbj.xlsx\",engine='openpyxl')\n",
+    "Triples_target_final = pd.read_excel(\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\",engine='openpyxl')\n",
     "Triples_target_final = Triples_target_final.drop(columns=['Unnamed: 0'])\n",
     "Triples_target_final = Triples_target_final.drop_duplicates()"
    ]

Notebooks/Results/3.1 Type of drugs - MESHPA.ipynb

@@ -20,7 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drebiop = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total_drebiop = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total_drebiop = triplets_total_drebiop.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -68,7 +68,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drege = pd.read_excel((\"triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
+    "triplets_total_drege = pd.read_excel((\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
     "triplets_total_drege = triplets_total_drege.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -96,7 +96,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "type_drug =pd.read_excel(\"Drug_Categories.xlsx\", engine='openpyxl')"
+    "type_drug =pd.read_excel(\"./Data/Input/DISNET/Drug_Categories.xlsx\", engine='openpyxl')"
    ]
   },
   {

Notebooks/Results/3.2 Types of drugs - ATC.ipynb

@@ -20,7 +20,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drege = pd.read_excel((\"triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
+    "triplets_total_drege = pd.read_excel((\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\"),engine='openpyxl')\n",
     "triplets_total_drege = triplets_total_drege.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -48,7 +48,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total_drebiop = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total_drebiop = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total_drebiop = triplets_total_drebiop.drop(columns=['Unnamed: 0'])"
    ]
   },
@@ -85,7 +85,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "drug_atc = pd.read_csv('drug_atc.tsv', sep='\\t')\n",
+    "drug_atc = pd.read_csv('./Data/Input/DISNET/drug_atc.tsv', sep='\\t')\n",
     "drug_atc = drug_atc.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -246,7 +246,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "atc_name = pd.read_excel(\"ATC_desc_name.xlsx\")\n",
+    "atc_name = pd.read_excel(\"./Data/Input/DISNET/ATC_desc_name.xlsx\")\n",
     "atc_name['index'] = atc_name['index'].str.strip()"
    ]
   },

Notebooks/Results/5. Pattern search based on phenotypical similarity.ipynb

@@ -69,7 +69,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sint = pd.read_csv('sint_all.tsv', sep='\\t')\n",
+    "sint = pd.read_csv('./Data/Input/DISNET/sint_all.tsv', sep='\\t')\n",
     "sint = sint.drop([\"Unnamed: 0\"],axis=1)"
    ]
   },
@@ -275,7 +275,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "triplets_total = pd.read_excel('triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
+    "triplets_total = pd.read_excel('./Data/Input/DISNET/triples_drebiop_final_dos.xlsx',engine='openpyxl')\n",
     "triplets_total = triplets_total.drop(columns=['Unnamed: 0'])\n",
     "triplets_total = triplets_total.drop_duplicates()"
    ]
@@ -475,7 +475,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "Triples_target_final = pd.read_excel(\"triples_final_drege_repo_csbj.xlsx\",engine='openpyxl')\n",
+    "Triples_target_final = pd.read_excel(\"./Data/Input/DISNET/triples_final_drege_repo_csbj.xlsx\",engine='openpyxl')\n",
     "Triples_target_final = Triples_target_final.drop(columns=['Unnamed: 0'])\n",
     "Triples_target_final = Triples_target_final.drop_duplicates()"
    ]