Map mutation gene symbols to Entrez IDs (#12)

* In mutation data, map gene symbol to Entrez ID based on combination of chromosome and gene symbol.

* In mutation data, map gene symbol to Entrez ID based on combination of chromosome and gene symbol.

* Create python script that includes gene symbol -> entrez id conversion for mutation data.

* Move mutation gene -> entrez mapping to separate notebook.

* Include mutation mapping .tsv file

* Include small data matrices.

* Added comments and removed some string concatenation.

data/subset/expression-matrix-all-samples.tsv

@@ -4256,7 +4256,6 @@ TCGA-E8-A3X7-01	0	8.05	8.19	9.49	5.06	10.9	8.27	10.8	7.01	9.11	3.23	6.07	0	5.62
 TCGA-E8-A413-01	0	8.15	8.44	9.42	6	10.6	9.58	10.3	7.56	8.67	2.42	5.49	0	6.32	13.6
 TCGA-E8-A414-01	0	7.97	8.4	9.7	5.71	10.5	9.63	10.8	7.28	8.57	2.99	5.66	0	6.97	12.8
 TCGA-E8-A415-01	0	7.94	7.22	9.44	5.22	10.4	9.28	10.6	7.2	8.99	2	5.65	0	6.91	13.2
-TCGA-E8-A416-01	0	7.81	6.63	9.39	4.26	10.5	9.77	8.77	7.11	9.2	2.25	6.27	0	7	13.2
 TCGA-E8-A417-01	0	7.76	7.69	9.92	3.35	10.7	9.48	10.4	7.42	8.46	1.31	5.77	0	6.39	13.2
 TCGA-E8-A418-01	0	8.01	7.01	9.43	5.4	10.4	9.3	10.7	7.13	9.03	1.85	1.85	0	5.69	14.4
 TCGA-E8-A419-01	0	8.32	6.98	9.5	3.61	10.4	9.4	10.8	8.05	9	2.13	4	0	6.45	13.3

data/subset/expression-matrix-small.tsv

@@ -1,51 +1,51 @@
 sample_id	1421	5203	5818	9875	10675	10919	23262	23467	54941	79622	147746	255167	284123	646851	728689
-TCGA-25-1313-01	0.835	9.73	9.4	10.3	8.65	12.2	9.46	10.4	6.63	7.48	3.01	5.73	0	6.25	13.3
+TCGA-22-4593-01	0	9.53	13.6	10.9	4.56	10.7	9.45	9.86	5.4	9.49	1.76	4.26	0	5.07	14
+TCGA-2G-AALW-01	5.57	8.92	9.7	10.4	4.79	11.1	9.47	8.83	7.83	9.24	2.73	5.12	0	6.34	13.8
 TCGA-3G-AB0O-01	0	8.63	9.64	9.04	1.99	11.3	9.39	4.77	8.33	10.5	0	4.85	0	5.38	13.3
 TCGA-3N-A9WD-06	0	8.93	9.15	9.5	6.45	10.5	9.25	8.12	8.31	9.41	2.18	3.14	0	4.77	13.8
-TCGA-41-5651-01	6.15	9.24	11.5	10.1	12.5	11.3	9.38	11.7	6.3	10.4	2.83	5.67	0	5.45	13
-TCGA-44-6776-01	0	7.96	9.08	10.4	6.16	10.8	8.63	5.46	8.32	9.4	3.27	2.59	0	5.18	13.9
-TCGA-44-A47A-01	0	7.8	11.2	10.6	6.59	10.4	9.37	7.03	6.9	8.54	2.61	2.35	0	10.2	13.8
-TCGA-60-2721-01	0	7.69	14.1	10.8	3.2	11	9.12	7.89	7.01	9.03	1.74	3.88	0	5.76	13.3
-TCGA-A2-A3XZ-01	0	8.16	10.4	10.1	6.19	11.5	8.71	8.33	7.87	9.49	2.98	1.02	0	6.19	13.7
-TCGA-A3-3378-01	0	7.52	8.24	9.8	3.14	10.1	10.4	6.7	7.88	8.13	1.99	0	0	7.27	12.6
-TCGA-AA-3697-01	0	9.3	10.9	10.7	3.45	11.3	9.68	7.54	7.3	9.42	0	0	0	5.47	13.7
-TCGA-BA-4077-01	0	7.6	12.9	9.88	3.7	9.97	9.08	9.51	6.49	9.51	0.973	4.5	0	2.54	13
-TCGA-BJ-A2NA-01	0	8.05	7.85	9.76	4.48	10.3	9.31	10.5	7.73	8.46	2.51	4.96	0	5.75	14.4
+TCGA-49-4487-01	0	9.51	8.45	10.6	7.17	10.4	8.71	8.18	7.19	9.49	2.6	0.882	0	4.89	13.5
+TCGA-59-2363-01	5.11	9.3	10.7	9.46	6.01	12.1	9.73	8.94	6	8.47	2.86	6.33	0	7.61	13
+TCGA-69-8253-01	0	9.16	11.5	10.9	5.44	10.1	9.2	5.94	7.45	8.57	1.28	1.84	0	5.26	13.8
+TCGA-78-8662-01	0	7.75	10.6	11	9.06	11.6	9.02	4.43	5.42	10.3	4.51	1.58	0	6.79	13.7
+TCGA-86-A4P8-01	0	7.5	8.11	9.1	6.32	10.4	9.83	7.61	9.32	7.95	3.13	3.78	0	6.19	12.6
+TCGA-A7-A2KD-01	0	8.31	10.4	10.6	4.28	10.3	9.95	9.51	7.18	9.4	3.55	2.24	0	8.27	12.8
+TCGA-AN-A0FX-01	0	8.39	10.4	10.3	3.06	10.9	9.93	11.2	7.16	9.03	1.54	1.38	0	6.51	13
+TCGA-B6-A0WS-01	0	7.85	9.44	10.2	3.31	10.5	9.86	11.1	9.32	9.72	2.15	3.4	0	6.27	13.4
+TCGA-B6-A0WV-01	0	8.46	9.57	9.96	6.73	9.97	11.4	10.6	6.09	9.17	1.7	0.926	0	7.27	12.8
+TCGA-BA-4076-01	0	8.67	13.1	9.52	3.65	9.69	9.23	7.51	6.12	8.85	2.64	4.2	0	5.65	13.1
+TCGA-BH-A0HP-01	0	8.19	10.3	9.62	6.28	10.9	10.1	11	9.18	9.18	2.54	2.08	0	6.65	13.2
+TCGA-BH-A1ES-06	0	8.85	8.82	9.51	2.31	10.6	9.73	7.13	6.48	8.81	1.29	3.84	0	6.66	12.9
 TCGA-BP-4961-01	0	7.87	9.24	9.67	2.19	9.98	10.5	7.7	8.53	8.2	2.35	3.33	0	4.08	13.6
+TCGA-BR-6454-01	0	9.6	11.3	10.7	3.34	11	8.77	7.84	7.4	9.11	0.65	7.09	0	4.26	13.1
 TCGA-BR-A4IU-01	0	8.68	10.4	10.3	4.29	10.2	9.51	9.73	8.95	7.76	3.79	5.28	0	5.68	12.6
-TCGA-C8-A1HK-01	0	8.54	10.2	10.3	4.36	11	10	10.6	8.03	9.42	1.32	0	0	7.6	12.7
-TCGA-CR-6474-01	0	8.9	13	10.4	2.57	9.73	8.62	10.4	6.67	7.71	1.86	1.73	0	3.57	13.7
-TCGA-CR-7385-01	0	8.19	13.3	10.8	5.9	10.8	9.69	6.51	6.8	9.94	1.61	2.14	0	2.69	13.8
-TCGA-CX-7219-01	0	7.96	13.1	11	4.25	10.5	9.86	7.21	6.81	8.49	2.37	2.83	0	4.45	13.7
-TCGA-D6-6823-01	0	8.69	13.7	11.1	5.26	10.3	8.5	7.52	7.08	8.34	2.01	2.43	0	2.87	14
-TCGA-DD-AAE9-01	0	8.05	5.38	8.27	6.29	10.9	8.6	1.09	7.38	9.51	1.09	10.6	0	0	12.9
-TCGA-DS-A3LQ-01	0	8.53	12.5	9.76	5.34	10.5	9.02	5.74	4.75	10.8	0.686	6.77	0	2.89	13.7
-TCGA-DU-A76L-01	1.87	9.12	10.6	9.96	10.9	10.7	9.46	10.9	6.91	9.11	1.87	2.47	0	5.81	13
-TCGA-DW-7838-01	0	7.8	8.64	9.06	1.41	9.18	10	9.02	7.12	9.2	0.498	1.41	0	5.7	13.5
-TCGA-E9-A5FK-01	0	8.9	10.3	8.84	5.7	11	8.58	8.35	7.88	9.95	3.46	1.04	0	4.74	13.9
-TCGA-ED-A7PZ-01	0	8.88	6.91	9	1.68	11.5	8.48	2.43	2.93	11.1	2.57	3.99	0.633	2.11	14.9
-TCGA-EJ-8472-01	0	8.4	10.3	9.84	6.39	10.4	9.13	10.2	7.5	8.89	2.43	3.72	0	6.07	13
-TCGA-EP-A3JL-01	0	9.21	8.69	8.4	3.79	10	8.82	5.43	6.55	10.3	2.47	10.9	0	1.33	13.3
-TCGA-ET-A39O-01	0	8.26	7.64	9.66	4.07	10.3	9.46	11.1	7.81	8.35	2.59	1.97	0	4.58	14.1
-TCGA-F4-6857-01	0	9.75	9.52	10.2	2.97	10.7	9.49	8.46	7.64	8.77	1.83	2.8	0	6.63	14
-TCGA-FG-5965-01	0.943	7.68	10.4	10.9	13.6	11.3	8.97	12.2	6.45	9.74	3.63	4.61	0	7.18	12.3
-TCGA-G3-A3CH-01	0	7.81	9.07	9.32	6.08	9.43	9.09	10.6	9.58	9.44	3.11	10.9	0	1.54	13.1
-TCGA-G3-A3CJ-01	0	8.34	6.95	8.94	3.11	10	8.68	2.48	3.95	10.5	1.34	10.5	0	1.34	13.9
-TCGA-GN-A8LN-01	0	8.74	8.71	11.1	8.92	11.2	10.2	6.73	7.09	8.9	1.19	0	0	6.96	14.5
-TCGA-HT-7472-01	0	8.01	10.8	10.7	12.4	11.2	9.19	11.3	7.59	9.32	1	2	0	7.9	12.8
-TCGA-HU-A4GC-01	0	9.38	9.56	9.2	2.96	10.4	9.23	6.29	8.83	8.67	0.778	0.441	0	5.52	12.9
-TCGA-IB-A6UG-01	1.05	8.15	10.1	9.94	4	10.2	8.99	8.95	7.27	8.26	2.08	3.18	0	5.98	13.4
-TCGA-L6-A4EP-01	0	8.48	9.49	9.02	4.65	10.9	8.87	10.8	7.09	9.03	3.98	4.81	0	6.31	14.5
-TCGA-LT-A5Z6-01	0	7.96	11.4	9.11	6.43	11.6	9.54	11.5	6.19	9.2	1.36	1.62	0	8.58	12
-TCGA-OL-A5DA-01	0	8.02	9.71	9.46	4.07	12.1	9.36	8.46	7.33	9.3	3.15	1.41	0	8.03	13.5
-TCGA-OR-A5LA-01	0	9.32	7.1	10.3	3.54	9.64	9.36	10.8	6.94	10.2	0.916	0.916	0	5.19	14.8
-TCGA-PJ-A5Z9-01	0	8.98	8.18	6.98	2.62	10.3	8.14	8.81	4.52	10.2	0.719	0.719	0	7.32	13.8
-TCGA-QH-A6CY-01	2.3	8.69	11.1	10.1	13.7	11.2	8.67	12.7	7.33	10.1	6.05	6.31	0	7.06	13.1
-TCGA-SR-A6MP-01	0	9.11	11.5	8.98	6.21	10.2	10.3	9.71	7.94	9.55	2.82	8.4	0	4.26	13.7
-TCGA-V4-A9F0-01	0	7.77	10.2	12.1	7.37	11.3	9.05	9.09	6.41	9.73	4.48	2.99	0	2.71	15.1
-TCGA-VD-AA8T-01	0	8.65	9.19	12.4	7.96	11	10.4	9.35	5.58	8.76	4.98	3.7	0	3.78	14.9
-TCGA-VW-A8FI-01	1.13	8.45	9.09	9.42	13	11.5	9.44	11.1	6.11	10.1	2.53	4.33	0	7.17	12.6
-TCGA-WC-A885-01	0	7.74	9.66	11.2	4.73	12.6	6.71	9.28	2.4	9.56	2.66	0	0	1.65	16
-TCGA-YL-A8SA-01	0	7.3	9.44	10	6.02	10.7	9.2	9.74	6.58	9	3.54	2.54	0	6.1	13.4
-TCGA-ZF-A9RE-01	0	8.53	14.4	10.9	4.82	11.1	9.46	5.39	6.39	9.13	0.616	2.53	0	5.09	13.1
-TCGA-ZH-A8Y1-01	0	8.56	10.5	9.95	2.73	10.7	9.58	10.2	6.56	8.27	2.6	5.77	0	7.37	13.7
+TCGA-C4-A0EZ-01	0	9.29	11	9.64	6.46	12	9.79	12.7	4.43	10.2	0.794	3.5	0	7.64	13.8
+TCGA-C5-A1MI-01	0	9.49	10.2	10.3	6.52	11	10.4	7.89	6.59	9.14	2.25	6.03	0	4.65	13.4
+TCGA-C5-A1ML-01	0	9.03	12.9	9.93	6.81	10.3	9.93	10.1	5.84	8.9	2.08	7.21	0	4.95	12.5
+TCGA-D3-A3MO-06	0	8.68	9.82	10.3	6.76	10.9	10.2	7.13	9.57	8.8	2.25	0	0	6.83	13.7
+TCGA-DC-4745-01	0	9.5	10.9	9.3	2.35	9.66	9.58	4.57	5.36	9.95	0	1.5	0	4.27	13.8
+TCGA-DU-A7T6-01	1.47	8.82	11.7	11.2	11.7	11.9	9.31	11.5	6.63	9.68	4.22	4.15	0	4.49	14.1
+TCGA-E9-A3QA-01	0	8.24	10.4	9.9	4.61	11.4	8.63	10.4	7.67	9.52	2.79	4.35	0	5.82	13.8
+TCGA-EA-A43B-01	0	8.71	12	9.98	6.97	12.4	8.05	10.1	6.38	9.86	1.61	0	0	4.51	14.1
+TCGA-EJ-A7NJ-01	0	7.64	10.4	10.5	4.58	10.2	9.4	10.9	6.54	9.45	3.11	8	0	5.52	12.6
+TCGA-EK-A2RO-01	0	8.86	11.5	9.5	6.34	10.5	8.49	6.68	5.28	9.75	1.04	1.63	0	4.19	13.3
+TCGA-EL-A3D0-01	0	8.97	7.77	8.93	4.61	10.9	8.68	9.83	7.53	7.97	3.76	4.67	0	5.69	13.8
+TCGA-ER-A2NE-06	0	7.73	8.71	11.4	4.99	10.8	8.7	4.96	9.63	9.59	1.32	0	0	3.59	13.6
+TCGA-FG-6688-01	0	7.45	9.87	10.5	11.4	10.6	8.73	10.5	7.52	9.62	1.69	5.55	0	7.65	12.8
+TCGA-FG-A70Z-01	3.74	7.9	10.7	10.4	13.9	11	8.5	13.3	5.85	10.3	4.42	5.06	0	6.04	12.4
+TCGA-HC-7079-01	0	7.85	10.8	10.7	3.52	10.5	9.8	9.39	8.92	8.45	2.89	5.29	0	5.05	12.7
+TCGA-HC-8266-01	0	7.78	10.3	10.3	7.12	10.7	9.29	10.4	8.72	9.19	2.3	5.62	0	5.42	12.9
+TCGA-HN-A2OB-01	0	7.66	10.9	10.2	4.28	11.2	9.77	8.17	8.76	8.9	2.34	3.9	0	7.15	13.1
+TCGA-HT-A4DS-01	3.01	8.54	9.96	8.95	13.6	11.3	7.99	12.5	6.22	11.3	4.9	2.88	0	5.91	14.3
+TCGA-HT-A616-01	2.13	8.53	11.1	9.68	13.2	11.3	8.93	13.2	5.16	9.91	7.08	6.03	0	6.47	13
+TCGA-IB-A5SO-01	0.828	8.3	9.22	9.52	4.81	10.1	9.04	8.81	7.34	8.34	3	5.78	0	6.26	13.1
+TCGA-KS-A4I7-01	0	8.07	7.79	9.22	6.3	10.6	9.02	10.5	7.13	8.48	2.58	4.79	0	5.64	13.3
+TCGA-L5-A8NW-01	0	8.24	13.6	10.5	4.64	10.2	10.5	6.96	8.25	6.74	1.35	2.42	0	5.73	13.1
+TCGA-N8-A4PN-01	0.488	8.27	13.1	11.6	4.23	12	9.45	10.2	5.81	9.27	5.7	7.64	2.54	7.11	13.4
+TCGA-QU-A6IP-01	1.08	8.22	10.1	9.96	5.57	10.8	9.24	10.9	7.88	9.52	3.23	5.6	0	6.04	13.2
+TCGA-RY-A843-01	1.88	8.18	10.4	9.55	13.6	11.1	8.93	12.5	6.3	9.87	5.42	5.48	0	6.47	12.6
+TCGA-TM-A84F-01	1.37	8.22	9.53	9.72	11.7	11.1	8.85	10.9	7.2	10.1	3.06	4.36	0	7.53	13
+TCGA-TQ-A7RW-01	0	7.71	10.6	10.9	10.9	11.3	9.53	10.9	8.03	9.06	0.586	1	0	7.41	13.5
+TCGA-VM-A8CE-01	0.486	8.01	11.2	10.2	13.7	11.6	8.77	10.8	7.21	9.44	1.59	4.22	0	7.74	13
+TCGA-WA-A7GZ-01	0	8.86	14	11.3	4.7	10.8	8.37	9.69	5.2	9.44	2.41	3.06	0	5.27	14.3
+TCGA-WE-AAA3-06	0	7.34	8.71	11	7.26	11.3	8.68	7.54	8.53	9.69	1.25	0.942	0	5.74	13.6
+TCGA-WK-A8XO-01	0.672	8.35	9.36	9.83	4.97	10.9	9.04	10.4	7.26	9.5	3.55	3.31	0	5.67	13.5