Breast Cancer Gene Expression Profiles (METABRIC)

Clinical attributes, m-RNA levels z-score, and genes mutations for 1904 patients

@kaggle.raghadalharbi_breast_cancer_gene_expression_profiles_metabric

Table List

1 table(6.93 MB)

Metabric Rna Mutation

@kaggle.raghadalharbi_breast_cancer_gene_expression_profiles_metabric.metabric_rna_mutation

6.93 MB
1904 rows
693 columns
Only the first 100 columns are shown

patient_id Patient Id	age_at_diagnosis Age At Diagnosis	type_of_breast_surgery Type Of Breast Surgery	cancer_type Cancer Type	cancer_type_detailed Cancer Type Detailed	cellularity Cellularity	chemotherapy Chemotherapy	pam50_claudin_low_subtype Pam50 + Claudin-low Subtype	cohort Cohort	er_status_measured_by_ihc Er Status Measured By Ihc	er_status Er Status	neoplasm_histologic_grade Neoplasm Histologic Grade	her2_status_measured_by_snp6 Her2 Status Measured By Snp6	her2_status Her2 Status	tumor_other_histologic_subtype Tumor Other Histologic Subtype	hormone_therapy Hormone Therapy	inferred_menopausal_state Inferred Menopausal State	integrative_cluster Integrative Cluster	primary_tumor_laterality Primary Tumor Laterality	lymph_nodes_examined_positive Lymph Nodes Examined Positive	mutation_count Mutation Count	nottingham_prognostic_index Nottingham Prognostic Index	oncotree_code Oncotree Code	overall_survival_months Overall Survival Months	overall_survival Overall Survival	pr_status Pr Status	radio_therapy Radio Therapy	n_3_gene_classifier_subtype 3-gene Classifier Subtype	tumor_size Tumor Size	tumor_stage Tumor Stage	death_from_cancer Death From Cancer	brca1 Brca1	brca2 Brca2	palb2 Palb2	pten Pten	tp53 Tp53	atm Atm	cdh1 Cdh1	chek2 Chek2	nbn Nbn	nf1 Nf1	stk11 Stk11	bard1 Bard1	mlh1 Mlh1	msh2 Msh2	msh6 Msh6	pms2 Pms2	epcam Epcam	rad51c Rad51c	rad51d Rad51d	rad50 Rad50	rb1 Rb1	rbl1 Rbl1	rbl2 Rbl2	ccna1 Ccna1	ccnb1 Ccnb1	cdk1 Cdk1	ccne1 Ccne1	cdk2 Cdk2	cdc25a Cdc25a	ccnd1 Ccnd1	cdk4 Cdk4	cdk6 Cdk6	ccnd2 Ccnd2	cdkn2a Cdkn2a	cdkn2b Cdkn2b	myc Myc	cdkn1a Cdkn1a	cdkn1b Cdkn1b	e2f1 E2f1	e2f2 E2f2	e2f3 E2f3	e2f4 E2f4	e2f5 E2f5	e2f6 E2f6	e2f7 E2f7	e2f8 E2f8	src Src	jak1 Jak1	jak2 Jak2	stat1 Stat1	stat2 Stat2	stat3 Stat3	stat5a Stat5a	stat5b Stat5b	mdm2 Mdm2	tp53bp1 Tp53bp1	adam10 Adam10	adam17 Adam17	aph1a Aph1a	aph1b Aph1b	arrdc1 Arrdc1	cir1 Cir1	ctbp1 Ctbp1	ctbp2 Ctbp2	cul1 Cul1	dll1 Dll1	dll3 Dll3	dll4 Dll4	dtx1 Dtx1
	75.65	MASTECTOMY	Breast Cancer	Breast Invasive Ductal Carcinoma	nan		claudin-low	1	Positve	Positive	3	NEUTRAL	Negative	Ductal/NST	1	Post	4ER+	Right	10		6.044	IDC	140.5	1	Negative	1	ER-/HER2-	22	2	Living	-1.399	-0.5738	-1.6217	1.4524	0.3504	1.1517	0.0348	0.1266	-0.8361	-0.8578	-0.4294	-1.1201	-0.4844	-0.7483	-1.666	-0.125	-0.3721	-0.6508	-0.1278	1.733	-0.2769999999999999	-1.0673	0.0615	0.1034	-1.6635	-2.0649	-1.3388	-0.6208	-1.7309	-0.8059	-1.1037	0.0744	1.4313	-0.5785	1.218	2.5602	2.3152	-0.2487	0.1601	-1.8799	-1.3629	0.1992	-0.0907	-0.1167	-1.3917	-0.8178	-1.0737	1.1097	1.6186	0.0413	-0.7556	0.9765	3.9189	2.5773	0.3126	-0.6271	-0.5319	0.8721	0.002	-0.0098	-1.4652	-0.2752	-1.1021	0.8414	0.4469	0.6307	-0.5067	1.6931	1.71
2	43.19	BREAST CONSERVING	Breast Cancer	Breast Invasive Ductal Carcinoma	High		LumA	1	Positve	Positive	3	NEUTRAL	Negative	Ductal/NST	1	Pre	4ER+	Right		2	4.02	IDC	84.63333333	1	Positive	1	ER+/HER2- High Prolif	10	1	Living	-1.38	0.2777	-1.2154	0.5296	-0.0136	-0.2659	1.3594	0.7961	0.5419	-2.6059	0.512	0.439	1.2266	0.7612	0.1821	1.0104	0.56	-0.4018	-0.2909	0.7440000000000001	-1.7488	0.4602	0.7835	-0.2689999999999999	-0.2715	0.3895	-0.6273	0.1813	-1.2643	1.1057	0.4108	-0.604	0.0546	0.2754	-0.0952	0.7248	0.4389	1.8759	-1.8984	-0.3327	-1.456	1.0011	0.0519	-0.3793	-0.4915	-1.3693	-0.3297	0.9804	-0.0104	-1.194	-0.7991	-0.8428	-0.4983	-1.3251	0.8803	-1.5924	-1.2672	-0.2006	1.3135	0.688	1.3366	1.5911	1.1926	0.301	-0.4113	-1.5476	-0.1581	-0.1005	-0.9584
5	48.87	MASTECTOMY	Breast Cancer	Breast Invasive Ductal Carcinoma	High	1	LumB	1	Positve	Positive	2	NEUTRAL	Negative	Ductal/NST	1	Pre	3	Right	1	2	4.03	IDC	163.7		Positive		nan	15	2	Died of Disease	0.067	-0.8426	0.2114	-0.3326	0.5141	-0.0803	1.1398	0.4187	-0.4029999999999999	-1.1305	0.2362	-0.1721	-1.791	3.0955	0.6608	2.6127	2.5553	-0.0391	-0.4421	1.4528	1.4142	0.3143	-0.0662	-0.5558	0.6967	1.2949	-0.1245	-0.1109	-0.3923	-1.2747	-0.5312	0.2585	0.8958	-0.2269999999999999	1.1899	-0.7207	1.4829	3.0696	2.2248	-1.4859	-0.4127	-0.8333	0.2885	-0.3496	-0.3549	0.0908	-0.7181	1.5835	0.7379	-0.8346	-1.3487	-0.2243	0.0434	-1.0832	-0.8822	0.759	2.0364	-1.1229	3.1331	-0.4959	-1.0596	1.6744	-2.2695	0.2397	0.1616	-1.0439	0.9493	-1.7455	-0.8876
6	47.68	MASTECTOMY	Breast Cancer	Breast Mixed Ductal and Lobular Carcinoma	Moderate	1	LumB	1	Positve	Positive	2	NEUTRAL	Negative	Mixed	1	Pre	9	Right	3	1	4.05	MDLC	164.93333330000002	1	Positive	1	nan	25	2	Living	0.6744	-0.5428	-1.6592	0.6369	1.6708	-0.888	1.2491	-1.1889	-0.4174	-0.6165	1.0078	-0.401	-1.3905	4.8798	0.0615	2.9414	4.1161	-0.3098	-1.347	1.2102	1.5345	-0.6347	0.7279	0.0219	1.8801	0.0476	-0.6651	-1.4457	-0.3827	-0.4537	-1.5248	0.3689	1.1455	0.0432	1.0868	-0.5237	0.2119	3.4617	0.461	-1.5404	-0.2119	-0.8333	1.8323	0.3869	1.3434	0.0409	-0.3804	0.6194	0.8552	0.3317	-0.5512	-1.2401	-0.8535	-0.0195	0.2551	-1.0064	1.4659	-1.0490000000000002	2.3645	-1.2458	1.4919	2.6438	-0.7268	-0.4622	0.1933	0.4481	1.6109	-0.5916	-0.473
8	76.97	MASTECTOMY	Breast Cancer	Breast Mixed Ductal and Lobular Carcinoma	High	1	LumB	1	Positve	Positive	3	NEUTRAL	Negative	Mixed	1	Post	9	Right	8	2	6.08	MDLC	41.36666667		Positive	1	ER+/HER2- High Prolif	40	2	Died of Disease	1.2932	-0.9039	-0.7219	0.2168	0.3484	0.3897	0.9131	0.9356	0.7675	-0.294	-0.2961	0.632	-0.3582	0.3032	0.8747	0.6323	0.3349	-0.2652	-0.1541	-0.7631	1.0158	1.8996	0.6618	-0.7454	0.2862	1.1035	-1.0514	1.5423	1.2169	0.1169	1.7648	0.8892	-1.0195	0.3664	0.7145	0.5223	1.5638	0.1562	-0.2666	0.4509	-0.4449	-0.3181	2.2129	1.1063	-0.065	1.4216	0.972	0.0461	0.1645	0.2677	0.3308	-0.5049	-0.3295	-0.4278	-0.0063	0.1063	0.9378	-0.2383	0.1228	0.369	0.9222	0.2017	-0.8767	1.8501	-0.6839	-1.2165	-0.8212	0.2763	0.1702
10	78.77	MASTECTOMY	Breast Cancer	Breast Invasive Ductal Carcinoma	Moderate		LumB	1	Positve	Positive	3	NEUTRAL	Negative	Ductal/NST	1	Post	7	Left		4	4.062	IDC	7.8		Positive	1	ER+/HER2- High Prolif	31	4	Died of Disease	-0.4341	0.6931	0.6909	1.084	-1.9371	0.9252	1.152	0.7951	-0.9677	-0.775	-0.3532	1.0599	-0.2754	0.5496	1.1321	-0.4786	0.322	0.2841	-0.3295	-0.0611	0.8727	0.8561	0.5396	-0.0412	1.5735	1.5887	-0.4022	0.9184	0.4784	-0.8358	1.1628	-0.2269	-0.7485	-0.4693	-0.1114	-0.8320000000000001	-0.8937	0.376	1.4738	1.0299	0.2396	-1.0892	-0.6725	0.1387	0.5118	0.1876	-0.5544	0.7215	0.0223	-0.7983	-0.0821	-1.2582	-0.3493	-1.4171	-0.3743	-1.0313	1.4207	-0.6227	1.0733	-0.3213	0.3046	-0.4826	-2.2878	0.3841	-1.1976	-0.8885	-0.7506	1.2604	-1.2258
14	56.45	BREAST CONSERVING	Breast Cancer	Breast Invasive Ductal Carcinoma	Moderate	1	LumB	1	Positve	Positive	2	LOSS	Negative	Ductal/NST	1	Post	3	Right	1	4	4.02	IDC	164.33333330000002	1	Positive	1	nan	10	2	Living	0.2671	0.4129	-1.3333	0.7834	-0.5109	0.8859	-0.2009	1.0128	-0.0697	-0.63	-0.3787	-0.422	-1.1123	5.3881	1.2435	3.1943	3.8026	0.7204	-1.1349	0.7352	2.3714	-0.4342	0.1484	-0.5426	0.5741	0.2814	-0.899	-1.8162	-0.4865	-1.1509	-2.4795	-0.7581	0.4879	-0.319	1.0543	-1.3181	-0.5244	3.1545	1.9388	-1.7802	-0.5004	-2.3659	-0.3645	0.4111	-1.2494	0.5148	-1.9559	0.4944	0.845	-1.1931	-1.9183	-2.5688	-0.262	-0.2853	-0.1902	-0.5152	2.0754	-1.52	3.268	0.3924	-1.0832	4.1414	-3.2012	-1.8972	0.1049	-0.9883	-0.5094	0.2758	-0.6235
22	89.08	BREAST CONSERVING	Breast Cancer	Breast Mixed Ductal and Lobular Carcinoma	Moderate		claudin-low	1	Positve	Positive	2	NEUTRAL	Negative	Mixed	1	Post	3	Left	1	1	4.058	MDLC	99.53333333		Negative	1	nan	29	2	Died of Other Causes	0.3985	1.271	-1.5306	1.6104	-0.081	1.3899	-1.1327	0.0384	-0.7457	-2.1944	0.111	0.0464	-1.6484	4.9095	1.3845	2.0068	2.6033	0.1757	-1.7661	0.7613	2.2918	-0.7652	-0.0977	-0.9164	1.7403	1.0492	-0.7242	-1.2871	-0.2621	-0.4661	-1.0471	-0.2126	1.475	0.7799	2.0314	-1.3448	-0.4546	3.7777	-0.1638	-1.3456	0.3262	-0.7264	0.6436	-1.8493	-0.7752	1.3745	-1.1266	0.7319	2.3607	0.9293	-0.6708	-2.511	0.633	-0.0243	-0.6502	-1.3277	0.6248	-1.7408	3.4716	-0.4894	-1.1077	4.3261	-1.9203	-1.7044	-0.294	-0.4633	-0.4615	-0.8628	-0.2972
28	86.41	BREAST CONSERVING	Breast Cancer	Breast Invasive Ductal Carcinoma	Moderate		LumB	1	Positve	Positive	3	GAIN	Negative	Ductal/NST	1	Post	9	Right	1	4	5.032	IDC	36.56666667		Negative	1	ER+/HER2- High Prolif	16	2	Died of Other Causes	0.8347	-1.5038	0.3436	-0.555	0.0558	-0.9155	-0.8571	-0.1267	-0.1705	0.6442	-0.9723	-0.5814	-0.0452	0.1949	-0.4626	2.1214	0.1913	1.0653	-1.7788	-1.0525	-0.5491	-0.7065	-0.8563	-0.1951	1.5901	0.9728	-0.5719	0.7517	-0.0084	0.0581	-0.1177	-1.0804	-0.5086	-0.5819	-1.144	1.9134	1.0864	0.9473	1.7131	0.1973	1.0549	-2.0876	2.529	-1.0495	-0.5882	-1.3748	0.9949	-0.0414	-1.9081	-1.347	-1.4581	0.1985	-0.8418	0.156	0.4318	1.1283	0.8941	-0.2809	0.1787	0.0961	-1.4249	0.0407	0.1371	0.3941	-1.2112	1.7035	0.9264	1.3714	0.4099
35	84.22	MASTECTOMY	Breast Cancer	Breast Invasive Lobular Carcinoma	High		Her2	1	Negative	Positive	2	LOSS	Negative	Lobular		Post	3	Left		5	3.056	ILC	36.26666667		Negative		ER+/HER2- High Prolif	28	2	Died of Disease	-1.0087	-0.6074	0.0313	1.0975	0.5314	0.9105	-1.5068	-0.0196	0.3726	0.4892	0.4366	0.6445	-0.081	1.5764	1.2363	1.2717	-0.7842	-1.9774	-1.4492	-0.4918	0.148	-1.0821	-1.568	-0.7037	-0.0864	-0.1751	-0.067	-1.3067	0.0119	-1.2315	-1.1391	-0.1911	-1.998	-0.981	-0.7247	-2.8359	-0.8525	0.4414	-0.3853	-0.5522	0.2028	-2.0881	-0.1506	-1.3647	-1.2745	0.2568	-2.4993	-0.7607	0.8635	-1.2622	-1.3530000000000002	-1.7918	-1.0414	-1.1107	-1.375	0.1097	-1.1087	0.1035	1.1021	1.0367	2.4004	0.0701	-1.7711	0.8128	1.2275	-0.802	1.3031	0.5286	-0.1545


CREATE TABLE metabric_rna_mutation (
  "patient_id" BIGINT,
  "age_at_diagnosis" DOUBLE,
  "type_of_breast_surgery" VARCHAR,
  "cancer_type" VARCHAR,
  "cancer_type_detailed" VARCHAR,
  "cellularity" VARCHAR,
  "chemotherapy" BIGINT,
  "pam50_claudin_low_subtype" VARCHAR,
  "cohort" DOUBLE,
  "er_status_measured_by_ihc" VARCHAR,
  "er_status" VARCHAR,
  "neoplasm_histologic_grade" DOUBLE,
  "her2_status_measured_by_snp6" VARCHAR,
  "her2_status" VARCHAR,
  "tumor_other_histologic_subtype" VARCHAR,
  "hormone_therapy" BIGINT,
  "inferred_menopausal_state" VARCHAR,
  "integrative_cluster" VARCHAR,
  "primary_tumor_laterality" VARCHAR,
  "lymph_nodes_examined_positive" DOUBLE,
  "mutation_count" DOUBLE,
  "nottingham_prognostic_index" DOUBLE,
  "oncotree_code" VARCHAR,
  "overall_survival_months" DOUBLE,
  "overall_survival" BIGINT,
  "pr_status" VARCHAR,
  "radio_therapy" BIGINT,
  "n_3_gene_classifier_subtype" VARCHAR,
  "tumor_size" DOUBLE,
  "tumor_stage" DOUBLE,
  "death_from_cancer" VARCHAR,
  "brca1" DOUBLE,
  "brca2" DOUBLE,
  "palb2" DOUBLE,
  "pten" DOUBLE,
  "tp53" DOUBLE,
  "atm" DOUBLE,
  "cdh1" DOUBLE,
  "chek2" DOUBLE,
  "nbn" DOUBLE,
  "nf1" DOUBLE,
  "stk11" DOUBLE,
  "bard1" DOUBLE,
  "mlh1" DOUBLE,
  "msh2" DOUBLE,
  "msh6" DOUBLE,
  "pms2" DOUBLE,
  "epcam" DOUBLE,
  "rad51c" DOUBLE,
  "rad51d" DOUBLE,
  "rad50" DOUBLE,
  "rb1" DOUBLE,
  "rbl1" DOUBLE,
  "rbl2" DOUBLE,
  "ccna1" DOUBLE,
  "ccnb1" DOUBLE,
  "cdk1" DOUBLE,
  "ccne1" DOUBLE,
  "cdk2" DOUBLE,
  "cdc25a" DOUBLE,
  "ccnd1" DOUBLE,
  "cdk4" DOUBLE,
  "cdk6" DOUBLE,
  "ccnd2" DOUBLE,
  "cdkn2a" DOUBLE,
  "cdkn2b" DOUBLE,
  "myc" DOUBLE,
  "cdkn1a" DOUBLE,
  "cdkn1b" DOUBLE,
  "e2f1" DOUBLE,
  "e2f2" DOUBLE,
  "e2f3" DOUBLE,
  "e2f4" DOUBLE,
  "e2f5" DOUBLE,
  "e2f6" DOUBLE,
  "e2f7" DOUBLE,
  "e2f8" DOUBLE,
  "src" DOUBLE,
  "jak1" DOUBLE,
  "jak2" DOUBLE,
  "stat1" DOUBLE,
  "stat2" DOUBLE,
  "stat3" DOUBLE,
  "stat5a" DOUBLE,
  "stat5b" DOUBLE,
  "mdm2" DOUBLE,
  "tp53bp1" DOUBLE,
  "adam10" DOUBLE,
  "adam17" DOUBLE,
  "aph1a" DOUBLE,
  "aph1b" DOUBLE,
  "arrdc1" DOUBLE,
  "cir1" DOUBLE,
  "ctbp1" DOUBLE,
  "ctbp2" DOUBLE,
  "cul1" DOUBLE,
  "dll1" DOUBLE,
  "dll3" DOUBLE,
  "dll4" DOUBLE,
  "dtx1" DOUBLE
);