Condon Usage Dataset

DNA codon usage frequencies of a large sample of diverse biological organisms

@kaggle.meetnagadia_condon_usage_dataset

Table List

1 table(3.09 MB)

Codon Usage

@kaggle.meetnagadia_condon_usage_dataset.codon_usage

3.09 MB
13028 rows
69 columns

kingdom Kingdom	speciesid SpeciesID	ncodons Ncodons	speciesname SpeciesName	uuu UUU	uuc UUC	uua UUA	uug UUG	cuu CUU	cuc CUC	cua CUA	cug CUG	auu AUU	auc AUC	aua AUA	aug AUG	guu GUU	guc GUC	gua GUA	gug GUG	gcu GCU	gcc GCC	gca GCA	gcg GCG	ccu CCU	ccc CCC	cca CCA	ccg CCG	ugg UGG	ggu GGU	ggc GGC	gga GGA	ggg GGG	ucu UCU	ucc UCC	uca UCA	ucg UCG	agu AGU	agc AGC	acu ACU	acc ACC	aca ACA	acg ACG	uau UAU	uac UAC	caa CAA	cag CAG	aau AAU	aac AAC	ugu UGU	ugc UGC	cau CAU	cac CAC	aaa AAA	aag AAG	cgu CGU	cgc CGC	cga CGA	cgg CGG	aga AGA	agg AGG	gau GAU	gac GAC	gaa GAA	gag GAG	uaa UAA	uag UAG	uga UGA
vrl	100217	1995	Epizootic haematopoietic necrosis virus	0.01654	0.01203	0.0005	0.00351	0.01203	0.03208	0.001	0.0401	0.00551	0.02005	0.00752	0.02506	0.01103	0.0411	0.00902	0.03308	0.01003	0.05013	0.01554	0.01103	0.02356	0.03208	0.01203	0.00501	0.01003	0.01203	0.03158	0.01905	0.02456	0.01353	0.02155	0.00251	0.00652	0.0015	0.01554	0.00501	0.02105	0.00902	0.01053	0.00501	0.02256	0.00301	0.03108	0.00401	0.02607	0.00251	0.01153	0.00501	0.02356	0.01053	0.0386	0.00401	0.00702	0.00401	0.00451	0.01303	0.03559	0.01003	0.04612	0.01203	0.04361	0.00251	0.0005
vrl	100220	1474	Bohle iridovirus	0.02714	0.01357	0.00068	0.00678	0.00407	0.02849	0.00204	0.0441	0.01153	0.0251	0.00882	0.03324	0.00814	0.04071	0.00814	0.03256	0.01085	0.04885	0.01221	0.01357	0.00678	0.02714	0.01221	0.00407	0.01425	0.01221	0.01967	0.02239	0.01289	0.02103	0.01493	0.00407	0.00475	0.00068	0.02035	0.0095	0.02782	0.01425	0.00611	0.00475	0.02917	0.00407	0.02374	0.00882	0.02917	0.00271	0.01628	0.00204	0.01967	0.00543	0.03392	0.00136	0.00678	0.00136	0.00136	0.01696	0.03596	0.01221	0.04545	0.0156	0.0441	0.00271	0.00068
vrl	100755	4862	Sweet potato leaf curl virus	0.01974	0.0218	0.01357	0.01543	0.00782	0.01111	0.01028	0.01193	0.02283	0.01604	0.01316	0.0218	0.01625	0.01872	0.01213	0.0107	0.02406	0.01234	0.0144	0.00514	0.01604	0.0146	0.02098	0.0107	0.01728	0.01851	0.00864	0.01172	0.01892	0.01933	0.01419	0.01296	0.00967	0.01337	0.01337	0.01851	0.01131	0.01419	0.0109	0.02612	0.01275	0.01522	0.02365	0.02962	0.01789	0.01625	0.01234	0.01604	0.01687	0.02077	0.03949	0.00864	0.00596	0.00926	0.00596	0.01974	0.02489	0.03126	0.02036	0.02242	0.02468	0.00391		0.00144
vrl	100880	1915	Northern cereal mosaic virus	0.01775	0.02245	0.01619	0.00992	0.01567	0.01358	0.0094	0.01723	0.02402	0.02245	0.02507	0.02924	0.02089	0.02141	0.01723	0.01932	0.02141	0.00679	0.02245	0.00522	0.01358	0.00418	0.0141	0.00574	0.01201	0.00992	0.00366	0.02402	0.02663	0.02872	0.00992	0.0235	0.00522	0.01619	0.00836	0.02037	0.01358	0.02089	0.00731	0.02141	0.00888	0.01567	0.01253	0.02298	0.01358	0.00992	0.00888	0.00783	0.00679	0.03133	0.04282	0.00627	0.00261	0.00261	0.00366	0.0141	0.01671	0.0376	0.01932	0.03029	0.03446	0.00261	0.00157
vrl	100887	22831	Soil-borne cereal mosaic virus	0.02816	0.01371	0.00767	0.03679	0.0138	0.00548	0.00473	0.02076	0.02716	0.00867	0.0131	0.02773	0.02803	0.00508	0.0092	0.02965	0.02878	0.00574	0.01572	0.01577	0.01007	0.00508	0.00604	0.00679	0.01205	0.03127	0.00775	0.00959	0.00797	0.02006	0.00359	0.00933	0.01191	0.01616	0.00788	0.02593	0.00854	0.012	0.02098	0.02089	0.01367	0.01502	0.01809	0.02738	0.01796	0.01082	0.00705	0.01174	0.00858	0.03408	0.03964	0.0095	0.00429	0.00578	0.00604	0.01494	0.01734	0.04148	0.02483	0.03359	0.03679		0.00044	0.00131
vrl	101029	5274	Human adenovirus type 7d	0.02579	0.02218	0.01479	0.01024	0.02294	0.00758	0.01782	0.01403	0.02636	0.01327	0.01896	0.02579	0.01877	0.01346	0.00721	0.01782	0.02067	0.02313	0.01214	0.00265	0.01232	0.01953	0.02105	0.00322	0.01232	0.01631	0.01327	0.0256	0.01119	0.0201	0.01763	0.00986	0.0036	0.00929	0.01138	0.03527	0.03015	0.02844	0.00284	0.01555	0.02825	0.01953	0.01251	0.03906	0.03546	0.01138	0.00948	0.00683	0.01043	0.03223	0.00986	0.00398	0.00853	0.00322	0.00303	0.01593	0.00171	0.02427	0.02503	0.02825	0.0127	0.00133	0.00038	0.00209
vrl	101688	3042	Apple latent spherical virus	0.04635	0.01545	0.02005	0.024	0.02761	0.01611	0.01052	0.00493	0.02597	0.00888	0.01512	0.02268	0.02893	0.00789	0.01151	0.01611	0.04011	0.01151	0.01118	0.00427	0.02794	0.01085	0.01216	0.00131	0.01216	0.02137	0.01052	0.01512	0.00986	0.03846	0.01085	0.01249	0.00066	0.01085	0.00427	0.02728	0.01381	0.01315	0.00427	0.02465	0.01151	0.02465	0.01085	0.03452	0.01348	0.01545	0.0069	0.01512	0.00756	0.02926	0.02696	0.00888	0.00625	0.0069	0.00329	0.01315	0.00822	0.04011	0.01183	0.02663	0.02663	0.00033	0.00033
vrl	101764	2801	Aconitum latent virus	0.02285	0.02678	0.01214	0.02321	0.01714	0.02213	0.00893	0.01928	0.01785	0.02356	0.01107	0.01999	0.01714	0.01142	0.00893	0.02499	0.03106	0.01357	0.01571	0.01321	0.01392	0.01107	0.01178	0.005	0.01142	0.01964	0.01714	0.01214	0.01464	0.01499	0.00536	0.00821	0.005	0.01678	0.01464	0.01535	0.01142	0.01607	0.01071	0.01142	0.02321	0.01856	0.01107	0.0282	0.01535	0.01142	0.01821	0.01071	0.01464	0.02785	0.02713	0.01499	0.01607	0.00714	0.00678	0.0125	0.01107	0.03534	0.01571	0.03642	0.02785	0.00107	0.00036	0.00071
vrl	101947	2897	Pseudorabies virus Ea	0.01105	0.02106	0.00035	0.00104	0.00035	0.04142	0.00069	0.05868	0.00104	0.01933	0.00173	0.01691		0.04004	0.00069	0.04522	0.00276	0.06973	0.00069	0.05212	0.00173	0.04764	0.00173	0.04177	0.01139	0.00242	0.04108	0.00621	0.02969	0.00449	0.01622	0.00035	0.02313	0.00035	0.02071	0.00104	0.02589		0.03176	0.00173	0.02485	0.00138	0.01622	0.00138	0.01519	0.00035	0.01968	0.00173	0.01933	0.00035	0.00897	0.00207	0.0535	0.00311	0.02658	0.00207	0.00311	0.00414	0.04556	0.00449	0.04867	0.00138	0.00035	0.00138
vrl	10249	61247	Vaccinia virus Copenhagen	0.03411	0.0143	0.02771	0.01869	0.01148	0.00651	0.0186	0.0073	0.03713	0.01915	0.03896	0.02856	0.02025	0.00878	0.02338	0.00916	0.01264	0.00671	0.01133	0.00718	0.01097	0.00423	0.01239	0.00624	0.00731	0.01246	0.00371	0.0202	0.00271	0.02527	0.01053	0.016	0.0089	0.01489	0.00612	0.02158	0.0086	0.02111	0.00913	0.03509	0.01623	0.01533	0.00622	0.0466	0.02077	0.01616	0.00503	0.01517	0.00625	0.04835	0.02222	0.00634	0.00248	0.00578	0.00167	0.0223	0.00411	0.04866	0.01559	0.03695	0.01412	0.0025	0.00077	0.00103


CREATE TABLE codon_usage (
  "kingdom" VARCHAR,
  "dnatype" BIGINT,
  "speciesid" BIGINT,
  "ncodons" BIGINT,
  "speciesname" VARCHAR,
  "uuu" VARCHAR,
  "uuc" VARCHAR,
  "uua" DOUBLE,
  "uug" DOUBLE,
  "cuu" DOUBLE,
  "cuc" DOUBLE,
  "cua" DOUBLE,
  "cug" DOUBLE,
  "auu" DOUBLE,
  "auc" DOUBLE,
  "aua" DOUBLE,
  "aug" DOUBLE,
  "guu" DOUBLE,
  "guc" DOUBLE,
  "gua" DOUBLE,
  "gug" DOUBLE,
  "gcu" DOUBLE,
  "gcc" DOUBLE,
  "gca" DOUBLE,
  "gcg" DOUBLE,
  "ccu" DOUBLE,
  "ccc" DOUBLE,
  "cca" DOUBLE,
  "ccg" DOUBLE,
  "ugg" DOUBLE,
  "ggu" DOUBLE,
  "ggc" DOUBLE,
  "gga" DOUBLE,
  "ggg" DOUBLE,
  "ucu" DOUBLE,
  "ucc" DOUBLE,
  "uca" DOUBLE,
  "ucg" DOUBLE,
  "agu" DOUBLE,
  "agc" DOUBLE,
  "acu" DOUBLE,
  "acc" DOUBLE,
  "aca" DOUBLE,
  "acg" DOUBLE,
  "uau" DOUBLE,
  "uac" DOUBLE,
  "caa" DOUBLE,
  "cag" DOUBLE,
  "aau" DOUBLE,
  "aac" DOUBLE,
  "ugu" DOUBLE,
  "ugc" DOUBLE,
  "cau" DOUBLE,
  "cac" DOUBLE,
  "aaa" DOUBLE,
  "aag" DOUBLE,
  "cgu" DOUBLE,
  "cgc" DOUBLE,
  "cga" DOUBLE,
  "cgg" DOUBLE,
  "aga" DOUBLE,
  "agg" DOUBLE,
  "gau" DOUBLE,
  "gac" DOUBLE,
  "gaa" DOUBLE,
  "gag" DOUBLE,
  "uaa" DOUBLE,
  "uag" DOUBLE,
  "uga" DOUBLE
);