first code

Data/Input/DISNET/dis_genes_gda.tsv

+	disease_id	gene_id	score
+0	C0001080	2261	1.0
+1	C0001815	3717	1.0
+2	C0001815	4352	1.0
+3	C0002066	3081	1.0
+4	C0002986	2717	1.0
+5	C0003076	5080	1.0
+6	C0004135	472	1.0
+7	C0004779	5727	1.0
+8	C0005859	641	1.0
+9	C0006413	4609	1.0
+10	C0007959	4359	1.0
+11	C0007965	1130	1.0
+12	C0008029	6452	1.0
+13	C0008525	1121	1.0
+14	C0008533	2158	1.0
+15	C0008928	860	1.0
+16	C0010674	1080	1.0
+17	C0011195	1959	0.93
+18	C0011195	4359	1.0
+19	C0011195	5376	1.0
+20	C0013264	1756	1.0
+21	C0013364	8518	1.0
+22	C0013903	2121	0.96
+23	C0013903	132884	1.0
+24	C0015306	2131	1.0
+25	C0015523	2160	1.0
+26	C0015526	2161	0.96
+27	C0016037	90	1.0
+28	C0016395	64840	1.0
+29	C0016667	2332	1.0
+30	C0016719	2395	1.0
+31	C0017495	5621	1.0
+32	C0017920	2538	1.0
+33	C0017922	178	1.0
+34	C0017924	5837	1.0
+35	C0017926	5213	0.94
+36	C0018425	4942	1.0
+37	C0018553	5728	1.0
+38	C0018609	340024	1.0
+39	C0019069	2157	1.0
+40	C0019202	540	1.0
+41	C0019562	7428	1.0
+42	C0020074	4914	1.0
+43	C0020725	79158	1.0
+44	C0021171	8517	1.0
+45	C0022336	5621	1.0
+46	C0022350	1244	1.0
+47	C0022387	3784	1.0
+48	C0022521	27019	1.0
+49	C0022595	488	1.0
+50	C0022716	538	1.0
+51	C0022797	54982	0.92
+52	C0023195	3931	1.0
+53	C0023374	3251	1.0
+54	C0023467	1050	1.0
+55	C0023467	2322	1.0
+56	C0023817	4023	1.0
+57	C0023931	1277	1.0
+58	C0024591	6261	1.0
+59	C0024796	2200	1.0
+60	C0025202	673	1.0
+61	C0025221	57152	1.0
+62	C0025267	4221	1.0
+63	C0025269	5979	1.0
+64	C0026705	3423	1.0
+65	C0027341	4010	1.0
+66	C0027831	4763	1.0
+67	C0027832	4771	1.0
+68	C0028326	5781	1.0
+69	C0031069	4210	1.0
+70	C0031269	6794	1.0
+71	C0031511	5979	1.0
+72	C0032463	3717	1.0
+73	C0033300	4000	1.0
+74	C0033835	2778	1.0
+75	C0033847	368	1.0
+76	C0034960	5264	1.0
+77	C0035372	4204	1.0
+78	C0035828	3784	1.0
+79	C0035934	1387	1.0
+80	C0036391	3339	0.97
+81	C0039292	19	1.0
+82	C0039445	94	1.0
+83	C0039445	2022	1.0
+84	C0039585	367	1.0
+85	C0039685	1482	0.96
+86	C0039685	23414	0.98
+87	C0040015	3690	1.0
+88	C0041341	7248	1.0
+89	C0041341	7249	1.0
+90	C0043116	6606	1.0
+91	C0043119	7486	1.0
+92	C0043194	7454	1.0
+93	C0043207	7466	1.0
+94	C0043459	5189	1.0
+95	C0079153	3848	1.0
+96	C0079295	3852	0.91
+97	C0079295	3861	0.93
+98	C0079474	1294	1.0
+99	C0079683	3914	0.92
+100	C0080024	3815	1.0
+101	C0085131	2720	1.0
+102	C0085132	2990	1.0
+103	C0085390	7157	1.0
+104	C0085413	5310	1.0
+105	C0085548	5314	1.0
+106	C0085859	326	1.0
+107	C0086647	6448	1.0
+108	C0086648	4669	1.0
+109	C0086651	2588	1.0
+110	C0152109	6606	0.98
+111	C0162309	215	1.0
+112	C0162361	10804	1.0
+113	C0162530	7390	1.0
+114	C0162531	1371	1.0
+115	C0162565	3145	1.0
+116	C0162566	7389	1.0
+117	C0162635	7337	1.0
+118	C0175692	197131	1.0
+119	C0175694	1717	1.0
+120	C0175697	3664	1.0
+121	C0175699	7291	1.0
+122	C0175704	5781	1.0
+123	C0206042	5621	1.0
+124	C0220663	668	1.0
+125	C0220668	2201	1.0
+126	C0220685	1280	0.96
+127	C0220704	6899	1.0
+128	C0220710	34	1.0
+129	C0220743	249	0.92
+130	C0220754	686	1.0
+131	C0220767	1947	1.0
+132	C0221026	695	1.0
+133	C0221036	55630	1.0
+134	C0221043	6338	1.0
+135	C0238198	3815	1.0
+136	C0238357	6329	1.0
+137	C0239849	26154	1.0
+138	C0265205	7474	0.96
+139	C0265234	2138	1.0
+140	C0265252	6197	1.0
+141	C0265259	3664	1.0
+142	C0265260	8200	0.95
+143	C0265264	6910	1.0
+144	C0265269	2255	0.93
+145	C0265289	1300	0.94
+146	C0265306	2737	1.0
+147	C0265326	5728	1.0
+148	C0265354	55636	1.0
+149	C0265961	2707	1.0
+150	C0266526	4693	1.0
+151	C0267662	1811	0.99
+152	C0268113	7369	1.0
+153	C0268120	353	0.99
+154	C0268125	4860	0.93
+155	C0268225	175	1.0
+156	C0268237	1352	0.94
+157	C0268238	51099	1.0
+158	C0268250	2629	0.93
+159	C0268251	2629	0.93
+160	C0268255	427	1.0
+161	C0268263	285362	1.0
+162	C0268275	2760	0.92
+163	C0268338	1281	1.0
+164	C0268362	1277	0.96
+165	C0268362	1278	0.95
+166	C0268363	1277	0.96
+167	C0268412	249	1.0
+168	C0268413	249	0.94
+169	C0268425	7840	1.0
+170	C0268450	6559	1.0
+171	C0268490	2184	1.0
+172	C0268494	7299	1.0
+173	C0268495	4948	1.0
+174	C0268547	435	1.0
+175	C0268548	383	1.0
+176	C0268623	3242	0.94
+177	C0270724	8398	1.0
+178	C0270911	5376	1.0
+179	C0270912	4359	1.0
+180	C0270968	22954	1.0
+181	C0271093	24	0.98
+182	C0271568	2690	1.0
+183	C0271829	5172	1.0
+184	C0272302	23218	0.99
+185	C0272375	462	1.0
+186	C0282102	10682	1.0
+187	C0339510	7439	1.0
+188	C0339541	10002	0.95
+189	C0340968	5313	1.0
+190	C0341306	4645	1.0
+191	C0342287	10560	1.0
+192	C0342288	50943	1.0
+193	C0342482	190	1.0
+194	C0342637	846	1.0
+195	C0342642	8074	0.94
+196	C0342684	4935	0.99
+197	C0342687	1621	0.91
+198	C0342783	35	0.97
+199	C0342788	6584	1.0
+200	C0343068	114548	1.0
+201	C0345893	657	1.0
+202	C0345893	4089	1.0
+203	C0346010	201163	1.0
+204	C0349639	3845	1.0
+205	C0349639	5781	1.0
+206	C0349653	5373	1.0
+207	C0391816	4286	0.93
+208	C0391826	5728	1.0
+209	C0393576	23230	1.0
+210	C0393590	6575	0.97
+211	C0393808	2705	1.0
+212	C0393814	5376	1.0
+213	C0393818	1959	0.99
+214	C0398738	3689	1.0
+215	C0406557	55612	1.0
+216	C0409818	114548	1.0
+217	C0410173	6445	1.0
+218	C0410174	2218	1.0
+219	C0410180	57190	1.0
+220	C0410538	1311	1.0
+221	C0432215	8838	1.0
+222	C0432217	9451	1.0
+223	C0432252	4041	1.0
+224	C0432284	5159	0.94
+225	C0521802	7018	0.91
+226	C0524582	4591	1.0
+227	C0543669	1441	0.93
+228	C0549463	4068	1.0
+229	C0574080	2593	0.94
+230	C0587248	3265	1.0
+231	C0599973	64093	0.96
+232	C0687720	551	1.0
+233	C0733682	5251	1.0
+234	C0751122	6323	1.0
+235	C0751383	1201	1.0
+236	C0751587	4854	1.0
+237	C0751748	2731	1.0
+238	C0751753	1373	0.92
+239	C0751783	7957	1.0
+240	C0751783	378884	1.0
+241	C0751785	1476	1.0
+242	C0751951	6261	1.0
+243	C0752123	6712	1.0
+244	C0752124	773	1.0
+245	C0795833	79813	0.99
+246	C0795889	6567	1.0
+247	C0795953	3897	1.0
+248	C0796004	8085	1.0
+249	C0796085	4810	1.0
+250	C0796147	374654	0.95
+251	C0796154	2719	1.0
+252	C0812437	2697	1.0
+253	C0877024	50485	1.0
+254	C0878677	3920	1.0
+255	C0917796	4541	1.0
+256	C0950121	7490	1.0
+257	C1142166	6331	1.0
+258	C1261473	7157	1.0
+259	C1263858	3908	1.0
+260	C1275081	673	1.0
+261	C1275126	7132	1.0
+262	C1275808	8929	1.0
+263	C1327915	4352	1.0
+264	C1328840	355	1.0
+265	C1328840	356	0.93
+266	C1333990	4292	1.0
+267	C1414216	55145	0.95
+268	C1449563	4000	1.0
+269	C1567742	1287	1.0
+270	C1567744	1285	1.0
+271	C1568247	4647	1.0
+272	C1568248	7401	1.0
+273	C1568249	25861	0.94
+274	C1623209	57167	1.0
+275	C1631597	6262	1.0
+276	C1719788	3736	1.0
+277	C1720416	773	1.0
+278	C1720861	5468	0.94
+279	C1721005	3851	0.94
+280	C1785148	8626	0.99
+281	C1832174	2202	1.0
+282	C1832274	2617	0.97
+283	C1832370	1674	1.0
+284	C1832399	8898	0.97
+285	C1832525	6444	0.94
+286	C1832567	859	0.92
+287	C1832702	8200	0.95
+288	C1832916	775	1.0
+289	C1833104	3630	0.98
+290	C1833104	3767	1.0
+291	C1833662	7415	1.0
+292	C1834570	8910	1.0
+293	C1835896	547	0.91
+294	C1836336	121512	0.95
+295	C1836383	2259	0.91
+296	C1836727	6663	0.92
+297	C1836876	3913	1.0
+298	C1837355	57165	0.92
+299	C1838062	9211	1.0
+300	C1838103	80324	0.95
+301	C1838244	7273	0.98
+302	C1838457	675	0.92
+303	C1838570	2055	0.93
+304	C1838571	256471	0.95
+305	C1839264	5354	1.0
+306	C1840333	2625	1.0
+307	C1841679	3209	1.0
+308	C1842362	8546	0.94
+309	C1842983	54332	0.91
+310	C1843225	4747	0.94
+311	C1843512	1282	0.92
+312	C1845055	546	1.0
+313	C1845862	6535	1.0
+314	C1846545	841	0.92
+315	C1846564	6687	0.92
+316	C1846574	55775	0.96
+317	C1846672	79147	0.95
+318	C1847024	7299	0.91
+319	C1847640	23400	1.0
+320	C1847800	5077	1.0
+321	C1847827	3981	0.99
+322	C1847836	51151	0.95
+323	C1848336	1184	0.94
+324	C1848410	5429	0.94
+325	C1848519	1910	1.0
+326	C1848533	7274	1.0
+327	C1848561	25974	0.95
+328	C1848634	7399	0.98
+329	C1849334	4920	0.99
+330	C1849394	10002	1.0
+331	C1849678	51	0.92
+332	C1850343	701	0.96
+333	C1850386	8139	1.0
+334	C1850442	1203	0.91
+335	C1850451	5538	0.94
+336	C1850889	8291	1.0
+337	C1850938	7078	1.0
+338	C1852020	2202	0.99
+339	C1852406	2263	0.97
+340	C1852529	866	0.94
+341	C1852759	5076	1.0
+342	C1853249	10939	0.96
+343	C1853733	30061	0.98
+344	C1854065	114902	0.97
+345	C1854467	3329	0.92
+346	C1855465	24	1.0
+347	C1855794	2304	0.93
+348	C1856728	7476	0.93
+349	C1856738	8200	0.92
+350	C1856934	3691	1.0
+351	C1857242	8443	0.91
+352	C1857277	4036	0.95
+353	C1857569	83959	1.0
+354	C1857663	9896	0.95
+355	C1858084	1301	0.95
+356	C1858479	80208	0.96
+357	C1858517	3508	1.0
+358	C1858593	6443	0.94
+359	C1858664	7036	0.99
+360	C1858680	5274	0.93
+361	C1859133	5191	0.98
+362	C1859405	10436	0.95
+363	C1859486	285440	1.0
+364	C1859722	26276	1.0
+365	C1859727	5167	0.98
+366	C1859844	6121	0.94
+367	C1861922	6662	1.0
+368	C1862103	8200	1.0
+369	C1862151	3549	0.97
+370	C1864356	4882	0.96
+371	C1864436	2261	1.0
+372	C1865020	3757	0.91
+373	C1865349	23474	1.0
+374	C1865872	27130	0.93
+375	C1866282	54982	0.91
+376	C1866495	6557	0.91
+377	C1866636	79628	0.96
+378	C1866855	6683	0.99
+379	C1866994	6926	1.0
+380	C1868570	7021	0.96
+381	C1869117	25953	1.0
+382	C1869123	825	1.0
+383	C1876161	1200	0.98
+384	C1879286	6331	0.96
+385	C1961835	2629	1.0
+386	C1969785	203859	0.92
+387	C1970011	9896	0.99
+388	C1970431	6925	1.0
+389	C2607929	5573	0.92
+390	C2675204	26090	0.94
+391	C2678061	2273	0.92
+392	C2699746	3239	1.0
+393	C2748515	9060	0.92
+394	C2748536	83706	0.92
+395	C2748572	3766	1.0
+396	C2750737	4072	0.96
+397	C2750785	4000	0.91
+398	C2931008	4247	0.92
+399	C2936332	6442	1.0
+400	C2940786	7068	1.0
+401	C3280428	23600	0.91
+402	C3539495	23259	0.92
+403	C3553774	22909	0.91
+404	C3711389	58	0.92
+405	C3887523	37	0.98
+406	C3888198	7439	1.0
+407	C4225349	1909	0.91

Data/Input/DISNET/drugs_pathways.tsv

+	drug_id
+0	CHEMBL578
+2	CHEMBL577
+4	CHEMBL1513
+8	CHEMBL59
+11	CHEMBL191
+15	CHEMBL1168
+17	CHEMBL1393
+23	CHEMBL1017
+25	CHEMBL1069
+27	CHEMBL1042
+38	CHEMBL1201203
+39	CHEMBL1040
+41	CHEMBL1560
+43	CHEMBL502
+45	CHEMBL1536
+49	CHEMBL2356023
+51	CHEMBL846
+54	CHEMBL25
+72	CHEMBL1434
+81	CHEMBL1373
+83	CHEMBL1175
+88	CHEMBL1237
+92	CHEMBL1581
+102	CHEMBL611
+103	CHEMBL2110563
+105	CHEMBL2103737
+109	CHEMBL1201236
+157	CHEMBL1229517
+0	CHEMBL641
+1	CHEMBL81
+9	CHEMBL118
+23	CHEMBL960
+39	CHEMBL1201572
+45	CHEMBL1366
+49	CHEMBL53
+63	CHEMBL1908360
+93	CHEMBL413
+119	CHEMBL1201182
+120	CHEMBL1138
+130	CHEMBL672
+146	CHEMBL557555
+147	CHEMBL41
+179	CHEMBL490
+200	CHEMBL809
+230	CHEMBL814
+234	CHEMBL415
+238	CHEMBL1628227
+252	CHEMBL726
+255	CHEMBL71
+258	CHEMBL643
+268	CHEMBL567
+269	CHEMBL1423
+312	CHEMBL54
+317	CHEMBL831
+319	CHEMBL715
+331	CHEMBL716
+349	CHEMBL85
+354	CHEMBL1112
+364	CHEMBL1621
+367	CHEMBL1237021
+372	CHEMBL1201154
+377	CHEMBL564
+388	CHEMBL741
+403	CHEMBL807
+438	CHEMBL49
+450	CHEMBL11
+453	CHEMBL445
+455	CHEMBL21731
+457	CHEMBL644
+459	CHEMBL46516
+461	CHEMBL26
+462	CHEMBL908
+463	CHEMBL2105760
+464	CHEMBL42
+465	CHEMBL1764
+466	CHEMBL243712
+468	CHEMBL6437
+472	CHEMBL479
+473	CHEMBL297302
+552	CHEMBL563
+558	CHEMBL154
+575	CHEMBL424
+597	CHEMBL15770
+637	CHEMBL112
+650	CHEMBL94081
+651	CHEMBL622
+655	CHEMBL1297
+657	CHEMBL521
+667	CHEMBL6
+675	CHEMBL571
+680	CHEMBL509
+684	CHEMBL599
+686	CHEMBL1070
+687	CHEMBL527
+688	CHEMBL122
+693	CHEMBL154111
+694	CHEMBL421
+696	CHEMBL93645
+699	CHEMBL139
+707	CHEMBL898
+710	CHEMBL1071
+712	CHEMBL365795
+714	CHEMBL1020
+716	CHEMBL468
+862	CHEMBL35
+865	CHEMBL1577
+866	CHEMBL349803
+867	CHEMBL1148
+869	CHEMBL1055
+870	CHEMBL888
+1021	CHEMBL629
+1062	CHEMBL654
+1065	CHEMBL621
+1125	CHEMBL435
+1126	CHEMBL406
+1128	CHEMBL842
+1131	CHEMBL389621
+1387	CHEMBL650
+1627	CHEMBL131
+1927	CHEMBL635
+2131	CHEMBL1451
+2308	CHEMBL632
+2461	CHEMBL1650
+2656	CHEMBL384467
+3001	CHEMBL1091
+3118	CHEMBL1370
+3135	CHEMBL1648
+3137	CHEMBL45816
+3138	CHEMBL1484
+3139	CHEMBL193
+3143	CHEMBL6966
+3153	CHEMBL1491
+3167	CHEMBL23
+3179	CHEMBL742
+3229	CHEMBL220492
+3240	CHEMBL750
+3244	CHEMBL108
+3258	CHEMBL973
+3285	CHEMBL301265
+3289	CHEMBL493
+3291	CHEMBL1009
+3294	CHEMBL589
+3295	CHEMBL1303
+3316	CHEMBL219916
+3392	CHEMBL945
+3393	CHEMBL585
+3413	CHEMBL549
+3434	CHEMBL637
+3563	CHEMBL46
+3571	CHEMBL894
+3763	CHEMBL657
+4051	CHEMBL14370
+4172	CHEMBL1372950
+4296	CHEMBL896
+4398	CHEMBL1101
+4626	CHEMBL34259
+4671	CHEMBL19019
+4689	CHEMBL13
+4703	CHEMBL649
+4704	CHEMBL546
+4705	CHEMBL27
+4713	CHEMBL24
+4715	CHEMBL423
+4717	CHEMBL645
+4718	CHEMBL642
+4720	CHEMBL499
+4724	CHEMBL839
+4726	CHEMBL723
+4729	CHEMBL27810
+4771	CHEMBL802
+4784	CHEMBL134
+4790	CHEMBL2
+4791	CHEMBL707
+4832	CHEMBL405
+4836	CHEMBL1574
+4837	CHEMBL1201201
+4844	CHEMBL1437
+4877	CHEMBL428647
+4899	CHEMBL40
+4908	CHEMBL861
+4909	CHEMBL45029
+4910	CHEMBL448
+4921	CHEMBL452
+4949	CHEMBL856
+4953	CHEMBL441
+4955	CHEMBL267894
+4957	CHEMBL447
+5079	CHEMBL608
+5172	CHEMBL796
+5226	CHEMBL1336
+5229	CHEMBL535
+5234	CHEMBL477772
+5235	CHEMBL1289601
+5249	CHEMBL1289926
+5284	CHEMBL185
+5302	CHEMBL1773
+5305	CHEMBL1324
+5311	CHEMBL109
+5442	CHEMBL264374
+5445	CHEMBL111
+5453	CHEMBL1200826
+5475	CHEMBL1396
+5481	CHEMBL2097081
+5482	CHEMBL1873475
+5511	CHEMBL862
+5512	CHEMBL420
+5546	CHEMBL16
+5785	CHEMBL160
+6380	CHEMBL92
+6396	CHEMBL53463
+6432	CHEMBL44657
+6444	CHEMBL32
+6457	CHEMBL1201496
+6458	CHEMBL1487
+6490	CHEMBL1064
+6622	CHEMBL135
+6638	CHEMBL691
+6652	CHEMBL940
+6657	CHEMBL294199
+6662	CHEMBL1140
+6689	CHEMBL573
+6697	CHEMBL1489
+6703	CHEMBL1201129
+6713	CHEMBL225072
+6770	CHEMBL659
+6778	CHEMBL636
+6815	CHEMBL503
+6822	CHEMBL98
+6829	CHEMBL465
+6856	CHEMBL911
+6903	CHEMBL1286
+6933	CHEMBL553
+6965	CHEMBL1431
+7079	CHEMBL679
+7113	CHEMBL1399
+7115	CHEMBL595
+7129	CHEMBL547
+7131	CHEMBL45
+7203	CHEMBL86304
+7223	CHEMBL414357
+7225	CHEMBL1201866
+7245	CHEMBL773
+7263	CHEMBL386630
+7271	CHEMBL554
+7273	CHEMBL266481
+7295	CHEMBL395429
+7347	CHEMBL1201293
+7352	CHEMBL848
+7379	CHEMBL600
+7385	CHEMBL1201497
+7555	CHEMBL1094
+7582	CHEMBL94
+7583	CHEMBL1535
+7589	CHEMBL76
+7693	CHEMBL1029
+7694	CHEMBL972
+7700	CHEMBL1624
+7705	CHEMBL1544
+7708	CHEMBL1542
+7715	CHEMBL2216870
+7716	CHEMBL1201570
+7730	CHEMBL1464
+7744	CHEMBL1276308
+7746	CHEMBL121
+7766	CHEMBL1622
+7816	CHEMBL472
+7820	CHEMBL314854
+7822	CHEMBL1201222
+7826	CHEMBL932
+7827	CHEMBL19224
+7831	CHEMBL1131
+7834	CHEMBL1520
+7835	CHEMBL1201563

Notebooks/Processed data/1.1 Target gene-based treated disease_CSBJ_DREBIOP.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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": [
+    "# Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_csbj = pd.read_csv(\"final_cases_csbj.tsv\", sep='\\t')\n",
+    "cases_csbj = cases_csbj.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj = pd.read_excel(\"triplets_chembl_disnet.xlsx\",engine='openpyxl')\n",
+    "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj =triplets_csbj.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj = cases_csbj.merge(triplets_csbj,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases = join_csbj[\"New Condition CUI\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases = pd.DataFrame(join_csbj_diseases).drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases =join_csbj_diseases.rename(columns={\"New Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 1. DRUG - GENE - TARGET"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen = pd.read_csv('dis_genes.tsv', sep='\\t')\n",
+    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen_dise_join = join_csbj_diseases.merge(dis_gen,how = \"inner\",on = \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug_gen = pd.read_csv('drug_gen.tsv', sep='\\t')\n",
+    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen_dise_join_dru = gen_dise_join.merge(drug_gen,how = \"inner\",on = \"gene_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "score_gdas_csbj = gen_dise_join_dru[gen_dise_join_dru[\"drug_id\"]== \"CHEMBL1581\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "score_gdas_csbj.to_csv(\"score_gdas_csbj.tsv\", sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2.PATHWAYS"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2.1 Pathways direct "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_path_direct = pd.read_csv('disease_pathway.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "direct_dise_pw = join_csbj_diseases.merge(dis_path_direct,how = \"inner\",on = \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2.2 Pathways via genes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_pw = pd.read_csv('dis_gen_pw.tsv', sep='\\t')\n",
+    "dis_gen_pw = dis_gen_pw.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_filter = join_csbj.drop(columns = [\"disease_id\",\"drug_id\",\"gene_id\",\"Original Condition\",\"Drugs\",\"New Condition\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_filter = join_csbj_filter.rename(columns={\"New Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pws_via_gen = join_csbj_filter.merge(dis_gen_pw,how = \"inner\",on = [\"disease_id\",\"pathway_id\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Notebooks/Processed data/2. Processed data DREGE.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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": [
+    "### 1. DATA "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duples_repodb = pd.read_csv(\"repoDB_all_disdru.tsv\", sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duples_csbj = pd.read_csv(\"duplas_CSBJ.tsv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duples_csbj = duples_csbj.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duples_csbj = duples_csbj.rename(columns={\"Disease CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>disease_id</th>\n",
+       "      <th>pathway_id</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>C0020538</td>\n",
+       "      <td>WP554</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>C0018799</td>\n",
+       "      <td>WP1544</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>C0018799</td>\n",
+       "      <td>WP1528</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>C0027947</td>\n",
+       "      <td>WP229</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>C0013369</td>\n",
+       "      <td>WP229</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>659</th>\n",
+       "      <td>C0268274</td>\n",
+       "      <td>WP4153</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>660</th>\n",
+       "      <td>C0085131</td>\n",
+       "      <td>WP4153</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>661</th>\n",
+       "      <td>C0036161</td>\n",
+       "      <td>WP4153</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>662</th>\n",
+       "      <td>C0268275</td>\n",
+       "      <td>WP4153</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>663</th>\n",
+       "      <td>C0162666</td>\n",
+       "      <td>WP4236</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>664 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    disease_id pathway_id\n",
+       "0     C0020538      WP554\n",
+       "1     C0018799     WP1544\n",
+       "2     C0018799     WP1528\n",
+       "3     C0027947      WP229\n",
+       "4     C0013369      WP229\n",
+       "..         ...        ...\n",
+       "659   C0268274     WP4153\n",
+       "660   C0085131     WP4153\n",
+       "661   C0036161     WP4153\n",
+       "662   C0268275     WP4153\n",
+       "663   C0162666     WP4236\n",
+       "\n",
+       "[664 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dis_path_direct = pd.read_csv('disease_pathway.tsv', sep='\\t')\n",
+    "dis_path_direct"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug_gen = pd.read_csv('drug_gen.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen = pd.read_csv('dis_genes_gda.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_sinfil = pd.read_csv('dis_genes.tsv', sep='\\t')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen_sinfil = dis_gen_sinfil.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### JOIN REPODB"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_drug_gen_sinfil = dis_gen_sinfil.merge(drug_gen, how =\"inner\", on = \"gene_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duplas_target_repodb = dis_drug_path_fil.merge(dis_drug_gen_sinfil, how = \"inner\", on =[\"disease_id\",\"drug_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_repodb_target = duples_repodb.merge(duplas_target_repodb,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_repodb_target.to_csv(\"cases_repodb_target.tsv\", sep =\"\\t\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.27445783132529894"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cases_repodb_target[\"score\"].mean()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### JOIN CSBJ"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duplas_target_csbj = dis_drug_path_csbj_fil.merge(dis_drug_gen_sinfil, how = \"inner\", on =[\"disease_id\",\"drug_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_csbj_target = duples_csbj.merge(duplas_target_csbj,how = \"inner\",on = [\"disease_id\",\"drug_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_csbj_target.to_csv(\"cases_csbj_target.tsv\", sep =\"\\t\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Notebooks/Processed data/2.1 Target gene-based treated disease _CSBJ-DREGE.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "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": [
+    "# Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cases_csbj_target = pd.read_csv(\"cases_csbj_target.tsv\", sep =\"\\t\")\n",
+    "cases_csbj = cases_csbj_target.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "22"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(cases_csbj[\"disease_id\"].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj = pd.read_excel(\"triplets_chembl_disnet.xlsx\",engine='openpyxl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj =triplets_csbj.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "triplets_csbj =triplets_csbj.rename(columns={\"Original Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj = cases_csbj.merge(triplets_csbj,how = \"inner\",on = [\"drug_id\",\"disease_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "13"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(join_csbj[\"disease_id\"].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_drug = join_csbj.drop([\"gene_id\",\"score\",\"Original Condition\",\"New Condition\",\"New Condition CUI\",\"Drugs\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_drug =join_csbj_drug.drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases = join_csbj[\"New Condition CUI\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases = pd.DataFrame(join_csbj_diseases).drop_duplicates()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "join_csbj_diseases =join_csbj_diseases.rename(columns={\"New Condition CUI\": \"disease_id\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 1. DRUG - GENE - TARGET"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dis_gen = pd.read_csv('dis_genes.tsv', sep='\\t')\n",
+    "dis_gen = dis_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen_dise_join = join_csbj_diseases.merge(dis_gen,how = \"inner\",on = \"disease_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drug_gen = pd.read_csv('drug_gen.tsv', sep='\\t')\n",
+    "drug_gen = drug_gen.drop([\"Unnamed: 0\"],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen_dise_join_dru = gen_dise_join.merge(drug_gen,how = \"inner\",on = \"gene_id\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "score_gdas_csbj = gen_dise_join_dru.merge(join_csbj ,how = \"inner\",on = [\"drug_id\",\"disease_id\",\"score\",\"gene_id\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.28196850393700795"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "score_gdas_csbj[\"score\"].mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "score_gdas_csbj.to_csv(\"score_gdas_csbj_target_filtergen.tsv\", sep='\\t')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}