Healthcare
20 columns
209 rows
8 formats

Genomic Variant Disease Associations

This dataset provides a comprehensive mapping of genetic variants to disease risk, including detailed genomic coordinates, variant types, disease associations, statistical evidence, and machine learning-based pathogenicity annotations. Designed for bioinformatics and ML research, it enables advanced analysis of genotype-phenotype relationships, risk prediction, and variant prioritization for clinical or research applications.

last updated 12 Jul 2025
by GoMask

The brief that made it

Machine learning model training for disease risk prediction

Sample rows

preview · 8 of 209 rows · all 20 columns

variant_idstring	ml_annotation_labelstring	ml_annotation_scorefloat	chromosomestring	positioninteger	reference_allelestring	alternate_allelestring	gene_symbolstring	variant_typestring	disease_namestring	disease_ontology_idstring	association_typestring	odds_ratiofloat	confidence_interval_lowerfloat	confidence_interval_upperfloat	p_valuefloat	populationstring	sourcestring	evidence_levelstring	last_updateddate
rs8321047	pathogenic	0.97	17	41232556	A	G	BRCA1	SNP	Hereditary breast cancer	OMIM:113705	risk	11.7	8.6	14.2	8.2e-7	European	ClinVar	strong	2023-09-01
rs1169209	likely pathogenic	0.78	6	32650812	C	T	HLA-DRB1	SNP	Rheumatoid arthritis	DOID:7148	risk	1.8	1.4	2.3	0.012	European	GWAS Catalog	moderate	2022-11-04
rs9876543	likely pathogenic	0.82	21	36589724	T	C	APP	SNP	Alzheimer's disease	OMIM:104300	risk	2.2	1.7	2.9	0.029	African	GWAS Catalog	moderate	2022-04-17
rs6654321	likely benign	0.49	1	5554221	G	A	CFH	SNP	Age related macular degeneration	OMIM:603075	protective	0.68	0.57	0.81	0.038	East Asian	GWAS Catalog	moderate	2022-02-14
rs1839201	pathogenic	0.98	X	15389213	T	C	FMR1	SNP	Fragile X syndrome	OMIM:300624	risk	15.1	11.4	20.3	0.0000011	Mixed	ClinVar	strong	2023-03-02
rs1589204	pathogenic	0.96	12	11384992	C	A	PAH	SNP	Phenylketonuria	OMIM:261600	risk	7.3	5.1	9.8	3e-7	European	ClinVar	strong	2023-06-15
rs2398450	likely pathogenic	0.84	2	12839842	A	G	INS	SNP	Type 1 diabetes mellitus	DOID:9744	risk	1.32	1.08	1.59	0.041	Hispanic	GWAS Catalog	moderate	2021-09-11
rs1920301	pathogenic	0.91	14	7058201	T	C	SERPINA1	SNP	Alpha-1-antitrypsin deficiency	OMIM:613490	risk	3.8	2.2	5.3	0.0008	European	ClinVar	strong	2023-10-10
rs2201487	pathogenic	0.95	16	48739218	G	T	APOB	SNP	Familial hypercholesterolemia	OMIM:144010	risk	8.2	6.1	10.8	0.0000025	European	ClinVar	strong	2023-04-12
rs3019482	pathogenic	1	7	17832412	C	A	CFTR	SNP	Cystic fibrosis	OMIM:219700	risk	19.4	15.8	24.3	7.7e-8	European	ClinVar	strong	2023-07-25
rs9004127	pathogenic	0.99	MT	15347	A	G	MT-ND1	SNP	Leber hereditary optic neuropathy	OMIM:535000	risk	6.1	4.2	8.6	0.0002	Mixed	ClinVar	strong	2023-01-19
rs4754112	pathogenic	0.97	8	19874512	T	C	MYC	SNP	Burkitt lymphoma	OMIM:113970	risk	12.5	9.2	15.7	0.0000033	African	ClinVar	strong	2023-11-11
rs3815051	pathogenic	0.98	3	8741122	G	T	VHL	SNP	Von Hippel-Lindau syndrome	OMIM:193300	risk	14.2	10.7	17.9	2.1e-7	European	ClinVar	strong	2023-08-03
rs4198720	pathogenic	0.99	13	32984721	A	G	RB1	SNP	Retinoblastoma	OMIM:180200	risk	16.7	11.2	22.3	5.6e-8	European	ClinVar	strong	2023-05-20
rs4992841	pathogenic	0.96	19	50194822	C	G	APOE	SNP	Alzheimer's disease	OMIM:104310	risk	7.5	6.2	9.4	9.6e-7	European	ClinVar	strong	2023-07-04
rs1284741	pathogenic	0.97	10	12039484	G	T	RET	SNP	Hirschsprung disease	OMIM:142623	risk	10.3	7.1	13.4	0.0000016	South Asian	ClinVar	strong	2023-06-29
rs7193240	pathogenic	0.99	9	3891741	A	G	JAK2	SNP	Polycythemia vera	OMIM:263300	risk	13.2	10.1	16.8	4.9e-8	European	ClinVar	strong	2023-10-05
rs1208457	pathogenic	0.93	5	23987412	T	C	TERT	SNP	Idiopathic pulmonary fibrosis	OMIM:614742	risk	4.2	2.7	5.7	0.0004	European	ClinVar	strong	2023-08-11
rs2800940	pathogenic	0.98	11	7894120	C	A	HBB	SNP	Sickle cell anemia	OMIM:603903	risk	17.5	12.8	23.4	6.7e-8	African	ClinVar	strong	2023-07-16
rs2801892	blank	blank	20	42984134	G	T	blank	CNV	Rare epilepsy syndrome	blank	unknown	blank	blank	blank	blank	Native American	Literature	computational	2020-05-14

What the 209 rows show

from the 209-row sample

Pathogenic (ml annotation label) stands out: mean ml_annotation_score is 0.97, against 0.72 for the rest.

0.95median ml_annotation_score
3association types
3sources
4variant types
4evidence levels
8alternate alleles

Mean ml_annotation_score by ml_annotation_label178 rows

ml_annotation_score178 rows, in bands of 0.1

Median 0.95, from 0.35 to 1.0.

chromosome209 rows · top 10 of 25 values

616
115
1113
212
1612
1012
710
1910
39
59

20 columns by typefrom the column list below

string 13
integer 1
float 5
date 1

Columns

20 columns in three groups

blueprint · 20 columns
column	type	description	example
Text 13 columns
`variant_id`	string	Unique identifier for the genetic variant, typically in dbSNP (rsID) or custom format.unique	rs8321047
`chromosome`	string	Chromosome where the variant is located (e.g., 1-22, X, Y, MT).25 values	17
`reference_allele`	string	Reference allele at the variant position.12 alleles	A
`alternate_allele`	string	Alternate allele observed at the variant position.8 alleles	G
`gene_symbol`	string	HGNC gene symbol associated with the variant, if applicable.optional	BRCA1
`variant_type`	string	Type of genetic variant (e.g., SNP, insertion, deletion, CNV).SNP · insertion · deletion · CNV · other	SNP
`disease_name`	string	Name of the disease associated with the variant.	Hereditary breast cancer
`disease_ontology_id`	string	Standardized ontology ID for the disease (e.g., OMIM, DOID, Orphanet).optional	OMIM:113705
`association_type`	string	Type of association between variant and disease (e.g., risk, protective, unknown).risk · protective · unknown	risk
`population`	string	Population or cohort in which the association was observed (e.g., European, East Asian, African, Mixed).9 populations · optional	European
`ml_annotation_label`	string	ML-derived categorical label (e.g., pathogenic, benign, uncertain).5 values · optional	pathogenic
`source`	string	Source of the association (e.g., GWAS Catalog, ClinVar, literature reference).3 sources · optional	ClinVar
`evidence_level`	string	Level of evidence supporting the association (e.g., strong, moderate, limited, computational).strong · moderate · limited · computational · optional	strong
Numbers 6 columns
`position`	integer	Genomic position of the variant (1-based coordinate).1 or more	41232556
`odds_ratio`	float	Odds ratio quantifying the strength of association (if available).0 or more · optional	11.7
`confidence_interval_lower`	float	Lower bound of the confidence interval for the odds ratio.0 or more · optional	8.6
`confidence_interval_upper`	float	Upper bound of the confidence interval for the odds ratio.0 or more · optional	14.2
`p_value`	float	P-value for the statistical significance of the association.0 to 1 · optional	8.2e-7
`ml_annotation_score`	float	Machine learning-derived annotation score indicating predicted pathogenicity or relevance.0 to 1 · optional	0.97
Dates and times 1 column
`last_updated`	date	Date the record was last updated or reviewed.optional	2023-09-01

Use it for

A healthcare dashboard
Ml_annotation_score by ml_annotation_label and a breakdown of chromosome. Excel, Power BI or Tableau.
Why do the 97 pathogenic rows have a mean ml_annotation_score of 0.97?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Variants209
rs83210470.97pathogen…
rs11692090.78likely p…
rs98765430.82likely p…
A software demo
Believable variants with chromosome, position and reference_allele to fill a screen in front of a buyer.

This dataset209 rows20 columns

Yours1,000 rows20 columns

blueprint · genomic-variant-disease-associations

Behind this dataset

Same schema. As many rows as you need.

These 209 rows came out of a blueprint — 20 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with

Each record: individual ID, variant, associated disease
Risk score (0–1) per variant-disease pair
Demographic and family history fields
Variants randomly distributed
Control (healthy) samples included

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: genomic-variant-disease-associations

What should your data show?

No signup. No card.

Sample rows

What the 209 rows show

Columns

Use it for

A healthcare dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Healthcare

What should your data show?