new human variation test database

modules/t/test-genome-DBs/homo_sapiens/variation/allele.txt

+1	1	\N	0	1	0.8	\N	\N

modules/t/test-genome-DBs/homo_sapiens/variation/attrib.txt

+2	2	SNV
+1	1	SO:0001483
+3	3	SNP
+5	2	substitution
+4	1	SO:1000002
+7	2	copy_number_variation
+6	1	SO:0001019
+8	3	CNV
+10	2	insertion
+9	1	SO:0000667
+12	2	deletion
+11	1	SO:0000159
+14	2	indel
+13	1	SO:1000032
+16	2	tandem_repeat
+15	1	SO:0000705
+18	2	sequence_alteration
+17	1	SO:0001059
+375	2	genetic_marker
+376	1	SO:0001645
+111	2	structural_variant
+112	1	SO:0001537
+113	3	SV
+114	2	probe
+115	1	SO:0000051
+116	3	CNV_PROBE
+200	2	copy_number_gain
+201	1	SO:0001742
+202	3	Gain
+203	2	copy_number_loss
+204	1	SO:0001743
+205	3	Loss
+206	2	inversion
+207	1	SO:1000036
+208	2	complex_structural_alteration
+209	1	SO:0001784
+210	3	Complex
+211	2	tandem_duplication
+212	1	SO:1000173
+213	3	Tandem duplication
+242	2	mobile_element_insertion
+243	1	SO:0001837
+244	3	Mobile element insertion
+286	2	interchromosomal_breakpoint
+287	1	SO:0001873
+288	3	Interchromosomal breakpoint
+289	2	intrachromosomal_breakpoint
+290	1	SO:0001874
+291	3	Intrachromosomal breakpoint
+292	2	translocation
+293	1	SO:0000199
+253	2	duplication
+254	1	SO:1000035
+331	3	Duplication
+361	2	novel_sequence_insertion
+362	1	SO:0001838
+363	3	Novel sequence insertion
+19	1	SO:0001628
+20	2	intergenic_variant
+294	6	38
+21	3	INTERGENIC
+118	5	transcript
+295	1	SO:0001631
+296	2	upstream_gene_variant
+266	6	24
+24	3	UPSTREAM
+297	1	SO:0001632
+298	2	downstream_gene_variant
+265	6	25
+27	3	DOWNSTREAM
+125	4	splice-5
+126	5	primary_transcript
+32	1	SO:0001575
+33	2	splice_donor_variant
+145	6	3
+34	3	ESSENTIAL_SPLICE_SITE
+128	4	splice-3
+129	1	SO:0001574
+36	2	splice_acceptor_variant
+37	1	SO:0001630
+38	2	splice_region_variant
+135	6	13
+39	3	SPLICE_SITE
+131	4	intron
+40	1	SO:0001627
+41	2	intron_variant
+120	6	21
+42	3	INTRONIC
+133	4	untranslated_5
+134	5	mRNA
+43	1	SO:0001623
+44	2	5_prime_UTR_variant
+122	6	18
+45	3	5PRIME_UTR
+136	4	untranslated_3
+46	1	SO:0001624
+47	2	3_prime_UTR_variant
+124	6	19
+48	3	3PRIME_UTR
+139	4	cds-synon
+299	1	SO:0001819
+300	2	synonymous_variant
+132	6	15
+54	3	SYNONYMOUS_CODING
+141	4	missense
+55	1	SO:0001583
+301	2	missense_variant
+153	6	12
+57	3	NON_SYNONYMOUS_CODING
+302	1	SO:0001821
+303	2	inframe_insertion
+140	6	10
+304	1	SO:0001822
+305	2	inframe_deletion
+154	6	11
+144	4	nonsense
+62	1	SO:0001587
+63	2	stop_gained
+146	6	4
+64	3	STOP_GAINED
+65	1	SO:0001578
+66	2	stop_lost
+143	6	6
+67	3	STOP_LOST
+68	1	SO:0001567
+69	2	stop_retained_variant
+70	1	SO:0002012
+306	2	start_lost
+142	6	7
+147	4	frameshift
+72	1	SO:0001589
+73	2	frameshift_variant
+138	6	5
+74	3	FRAMESHIFT_CODING
+75	1	SO:0001626
+76	2	incomplete_terminal_codon_variant
+137	6	14
+77	3	PARTIAL_CODON
+78	1	SO:0001621
+79	2	NMD_transcript_variant
+262	6	22
+80	3	NMD_TRANSCRIPT
+150	5	ncRNA
+81	1	SO:0001619
+82	2	non_coding_transcript_variant
+263	6	23
+83	3	WITHIN_NON_CODING_GENE
+307	1	SO:0001792
+308	2	non_coding_transcript_exon_variant
+119	6	20
+152	5	miRNA
+84	1	SO:0001620
+85	2	mature_miRNA_variant
+151	6	17
+86	3	WITHIN_MATURE_miRNA
+87	1	SO:0001580
+88	2	coding_sequence_variant
+149	6	16
+89	3	CODING_UNKNOWN
+155	5	regulatory_region
+90	1	SO:0001566
+91	2	regulatory_region_variant
+309	6	36
+92	3	REGULATORY_REGION
+157	5	TF_binding_site
+158	1	SO:0001782
+159	2	TF_binding_site_variant
+310	6	30
+311	1	SO:0001893
+312	2	transcript_ablation
+127	6	1
+313	1	SO:0001889
+314	2	transcript_amplification
+130	6	8
+315	1	SO:0001895
+316	2	TFBS_ablation
+261	6	26
+317	1	SO:0001892
+318	2	TFBS_amplification
+319	6	28
+320	1	SO:0001894
+321	2	regulatory_region_ablation
+322	6	31
+323	1	SO:0001891
+324	2	regulatory_region_amplification
+325	6	33
+346	5	sequence_feature
+326	1	SO:0001907
+327	2	feature_elongation
+328	1	SO:0001906
+329	2	feature_truncation
+330	6	37
+416	1	SO:0001818
+417	2	protein_altering_variant
+98	2	mRNA
+97	1	SO:0000234
+100	2	transcript
+99	1	SO:0000673
+102	2	primary_transcript
+101	1	SO:0000185
+104	2	ncRNA
+103	1	SO:0000655
+106	2	miRNA
+105	1	SO:0000276
+108	2	regulatory_region
+107	1	SO:0005836
+110	2	binding_site
+109	1	SO:0000409
+255	2	sequence_feature
+256	1	SO:0000110
+377	420	uncertain significance
+378	420	not provided
+379	420	benign
+380	420	likely benign
+381	420	likely pathogenic
+382	420	pathogenic
+383	420	drug response
+384	420	histocompatibility
+385	420	other
+386	420	confers sensitivity
+387	420	risk factor
+388	420	association
+389	420	protective
+215	10	unknown
+216	10	untested
+217	10	non-pathogenic
+218	10	probable-non-pathogenic
+219	10	probable-pathogenic
+220	10	pathogenic
+221	10	drug-response
+222	10	histocompatibility
+223	10	other
+176	9	hapmap
+177	9	ind_venter
+178	9	ind_watson
+179	9	fail_all
+180	9	fail_nonref
+181	9	fail_ambig
+182	9	fail_gt_fq
+183	9	fail_incons_map
+184	9	fail_mult_map
+185	9	fail_no_alleles
+186	9	fail_no_gt
+187	9	fail_no_map
+188	9	fail_no_seq
+189	9	fail_non_nt
+190	9	fail_mult_alleles
+214	9	fail_dbsnp_suspect
+191	9	ph_hgmd_pub
+193	9	ph_nhgri
+194	9	ph_omim
+195	9	ph_variants
+196	9	ph_uniprot
+197	9	ph_cosmic
+198	9	ph_ega
+257	9	hapmap_ceu
+258	9	hapmap_hcb
+259	9	hapmap_jpt
+260	9	hapmap_yri
+332	9	Affy_500K
+333	9	Affy_SNP6
+337	9	Cardio-Metabo_Chip
+338	9	HumanOmni1-Quad
+335	9	Illumina_1M-duo
+334	9	Illumina_660Q
+339	9	Illumina_CytoSNP12v1
+342	9	Human610_Quad
+343	9	HumanHap550
+340	9	HumanHap650Y
+341	9	HumanOmni2.5
+245	9	PorcineSNP60
+344	9	esp_6500
+345	9	clin_assoc
+360	9	all_chips
+348	9	Chicken600K
+349	9	EquineSNP50
+350	9	BovineHD
+351	9	BovineLD
+352	9	BovineSNP50
+355	9	phencode
+354	9	HumanOmni5
+356	9	OvineSNP50
+357	9	OvineHDSNP
+358	9	ExomeChip
+359	9	ImmunoChip
+373	9	HumanOmniExpress
+374	9	ClinVar
+353	9	MGP
+390	9	HumanCoreExome
+404	9	1kg_3
+405	9	1kg_3_afr
+406	9	1kg_3_amr
+407	9	1kg_3_eas
+408	9	1kg_3_sas
+409	9	1kg_3_eur
+410	9	1kg_3_com
+411	9	1kg_3_afr_com
+412	9	1kg_3_amr_com
+413	9	1kg_3_eas_com
+414	9	1kg_3_sas_com
+415	9	1kg_3_eur_com
+395	9	LSDB
+396	9	dbPEX
+397	9	HbVar
+398	9	Infevers
+399	9	KAT6BDB
+400	9	LMDD
+401	9	OIVD
+402	9	PAHdb
+270	8	tolerated
+271	8	deleterious
+391	8	tolerated - low confidence
+392	8	deleterious - low confidence
+272	7	probably damaging
+273	7	possibly damaging
+274	7	benign
+275	7	unknown
+267	12	sift
+268	12	polyphen_humvar
+269	12	polyphen_humdiv
+224	11	Not tested
+225	11	Benign
+226	11	Pathogenic
+227	11	Uncertain Significance
+228	11	likely benign
+229	11	likely pathogenic
+364	11	not provided
+365	11	association
+366	11	risk factor
+367	419	Multiple_observations
+368	419	Frequency
+369	419	HapMap
+370	419	1000Genomes
+371	419	Cited
+372	419	ESP
+418	419	Phenotype_or_Disease
+421	419	ExAC

modules/t/test-genome-DBs/homo_sapiens/variation/attrib_set.txt

+1	1
+1	2
+1	3
+2	4
+2	5
+3	6
+3	7
+3	8
+4	9
+4	10
+5	11
+5	12
+6	13
+6	14
+7	15
+7	16
+8	17
+8	18
+38	97
+38	98
+39	99
+39	100
+40	101
+40	102
+41	103
+41	104
+42	105
+42	106
+43	107
+43	108
+44	109
+44	110
+45	111
+45	112
+45	113
+46	114
+46	115
+46	116
+49	200
+49	201
+49	202
+50	203
+50	204
+50	205
+51	206
+51	207
+52	208
+52	209
+52	210
+53	211
+53	212
+53	213
+54	242
+54	243
+54	244
+60	255
+60	256
+79	72
+79	73
+79	74
+79	134
+79	138
+79	147
+87	286
+87	287
+87	288
+88	289
+88	290
+88	291
+89	292
+89	293
+90	19
+90	20
+90	21
+90	294
+91	24
+91	118
+91	266
+91	295
+91	296
+92	27
+92	118
+92	265
+92	297
+92	298
+93	32
+93	33
+93	34
+93	125
+93	126
+93	145
+94	34
+94	36
+94	126
+94	128
+94	129
+94	145
+95	37
+95	38
+95	39
+95	126
+95	135
+97	43
+97	44
+97	45
+97	122
+97	133
+97	134
+98	46
+98	47
+98	48
+98	124
+98	134
+98	136
+99	54
+99	132
+99	134
+99	139
+99	299
+99	300
+100	55
+100	57
+100	134
+100	141
+100	153
+100	301
+101	57
+101	134
+101	140
+101	302
+101	303
+102	57
+102	134
+102	154
+102	304
+102	305
+103	62
+103	63
+103	64
+103	134
+103	144
+103	146
+104	65
+104	66
+104	67
+104	134
+104	143
+105	54
+105	68
+105	69
+105	132
+105	134
+106	57
+106	70
+106	134
+106	142
+106	306
+107	75
+107	76
+107	77
+107	134
+107	137
+109	81
+109	82
+109	83
+109	150
+109	263
+111	84
+111	85
+111	86
+111	151
+111	152
+112	87
+112	88
+112	89
+112	134
+112	149
+113	90
+113	91
+113	92
+113	155
+113	309
+114	92
+114	157
+114	158
+114	159
+114	310
+115	127
+115	134
+115	311
+115	312
+116	130
+116	134
+116	313
+116	314
+117	157
+117	261
+117	315
+117	316
+118	157
+118	317
+118	318
+118	319
+119	157
+119	320
+119	321
+119	322
+120	157
+120	323
+120	324
+120	325
+121	309
+121	326
+121	327
+121	346
+122	328
+122	329
+122	330
+122	346
+123	253
+123	254
+123	331
+124	40
+124	41
+124	42
+124	120
+124	126
+124	131
+125	78
+125	79
+125	80
+125	134
+125	262
+126	83
+126	119
+126	150
+126	307
+126	308
+127	361
+127	362
+127	363
+128	375
+128	376
+129	134
+129	153
+129	416
+129	417

modules/t/test-genome-DBs/homo_sapiens/variation/attrib_type.txt

+1	SO_accession		Sequence Ontology accession
+2	SO_term		Sequence Ontology term
+3	display_term		Ensembl display term
+4	NCBI_term		NCBI term
+5	feature_SO_term		Sequence Ontology term for the associated feature
+6	rank		Relative severity of this variation consequence
+7	polyphen_prediction		PolyPhen-2 prediction
+8	sift_prediction		SIFT prediction
+9	short_name	Short name	A shorter name for an instance, e.g. a VariationSet
+10	dbsnp_clin_sig	dbSNP/ClinVar clinical significance	The clinical significance of a variant as reported by ClinVar and dbSNP
+11	dgva_clin_sig	DGVa clinical significance	The clinical significance of a structural variant as reported by DGVa
+420	clinvar_clin_sig	ClinVar clinical significance	The clinical significance of a variant as reported by ClinVar
+12	prot_func_analysis	Protein function analysis 	The program used to make protein function predictions
+13	associated_gene	Associated gene	ID of gene(s) linked by phenotype association
+14	risk_allele	Risk allele	Risk allele in phenotype association
+15	p_value	P-value	P-value denoting significance of an observed phenotype annotation
+16	variation_names	Variation names	Variant ID(s) linked with a phenotype association
+17	sample_id	Sample ID	Sample ID for source of phenotype association
+18	strain_id	Strain ID	Strain ID for source of phenotype association
+19	lod_score	LOD score	Log Of Odds score
+20	variance	Variance	Variance statistic
+21	inheritance_type	Inheritance type	Inheritance type of a trait
+22	external_id	External ID	External identifier for an entity
+23	odds_ratio	Odds ratio	Odds ratio used to denote significance of an observed phenotype annotation
+24	beta_coef	Beta coefficient	Beta coefficient (or standardized coefficient) used to denote significance of an observed phenotype annotation
+25	allele_symbol	Allele symbol	Allele symbol linked with phenotype association
+26	allele_accession_id	Allele accession ID	Allele accession ID linked with phenotype association
+33	marker_accession_id	Marker accession ID	Marker ID linked with phenotype association
+419	evidence	Variant evidence status	Evidence status for a variant
+422	sequence_number	Number of sequences in alignment	Number of protein sequences in the alignment use to make a protein impact prediction
+423	based_on	Evidence type used for protein impact prediction	Evidence type used for a PolyPhen protein impact prediction
+424	conservation_score	Sift conservation score	Median conservation value in an alignment used to make a Sift prediction
+421	review_status	ClinVar review_status	ClinVar review_status for assertation

modules/t/test-genome-DBs/homo_sapiens/variation/failed_description.txt

+1	Variant maps to more than 3 different locations
+2	None of the variant alleles match the reference allele
+3	Variant has more than 3 different alleles
+4	Loci with no observed variant alleles in dbSNP
+5	Variant does not map to the genome
+6	Variant has no genotypes
+7	Genotype frequencies do not add up to 1
+8	Variant has no associated sequence
+9	Variant submission has been withdrawn by the 1000 genomes project due to high false positive rate
+11	Additional submitted allele data from dbSNP does not agree with the dbSNP refSNP alleles
+12	Variant has more than 3 different submitted alleles
+13	Alleles contain non-nucleotide characters
+14	Alleles contain ambiguity codes
+15	Mapped position is not compatible with reported alleles
+16	Flagged as suspect by dbSNP
+17	Variant can not be re-mapped to the current assembly
+18	Supporting evidence can not be re-mapped to the current assembly
+19	Variant maps to more than one genomic location
+20	Variant at first base in sequence

modules/t/test-genome-DBs/homo_sapiens/variation/individual_type.txt

+1	fully_inbred	multiple organisms have the same genome sequence
+2	partly_inbred	single organisms have reduced genome variability due to human intervention
+3	outbred	a single organism which breeds freely
+4	mutant	a single or multiple organisms with the same genome sequence that have a natural or experimentally induced mutation

modules/t/test-genome-DBs/homo_sapiens/variation/meta.txt

+1	\N	schema_type	variation
+2	\N	schema_version	84
+3	\N	patch	patch_83_84_a.sql|schema version

modules/t/test-genome-DBs/homo_sapiens/variation/meta_coord.txt

+variation_feature	1	1000002
+structural_variation_feature	1	1000002
+phenotype_feature	1	1000002