Gene: ensembl, release-111

• https://www.ensembl.org/info/data/mysql.html

• https://www.ensembl.org/info/docs/api/core/core_schema.html

Install mysqlclient: https://pypi.org/project/mysqlclient/

from bionty_base.entities._gene import EnsemblGene

version = "release-111"

Human

ensembl_gene = EnsemblGene(organism="human", version=version)

df = ensembl_gene.download_df()

💡 fetching records from the core DB...
💡 fetching records from the external DBs...
❗ duplicated #rows ensembl_gene_id with ncbi_gene_id: 6031
✅ downloaded Gene table containing 76062 entries.

df.head()

	ensembl_gene_id	symbol	ncbi_gene_id	biotype	description	synonyms
0	ENSG00000000003	TSPAN6	7105	protein_coding	tetraspanin 6 [Source:HGNC Symbol;Acc:HGNC:11858]	TM4SF6|TSPAN-6|T245
1	ENSG00000000005	TNMD	64102	protein_coding	tenomodulin [Source:HGNC Symbol;Acc:HGNC:17757]	MYODULIN|BRICD4|TEM|CHM1L|TENDIN
2	ENSG00000000419	DPM1	8813	protein_coding	dolichyl-phosphate mannosyltransferase subunit...	CDGIE|MPDS
3	ENSG00000000457	SCYL3	57147	protein_coding	SCY1 like pseudokinase 3 [Source:HGNC Symbol;A...	PACE-1|PACE1
4	ENSG00000000460	FIRRM	55732	protein_coding	FIGNL1 interacting regulator of recombination ...	FLIP|C1ORF112|FLJ10706|APOLO1|MEICA1

# https://github.com/laminlabs/bionty/issues/533
df["description"] = df["description"].str.replace(r"\[.*?\]", "", regex=True)

df.head()

	ensembl_gene_id	symbol	ncbi_gene_id	biotype	description	synonyms
0	ENSG00000000003	TSPAN6	7105	protein_coding	tetraspanin 6	TM4SF6|TSPAN-6|T245
1	ENSG00000000005	TNMD	64102	protein_coding	tenomodulin	MYODULIN|BRICD4|TEM|CHM1L|TENDIN
2	ENSG00000000419	DPM1	8813	protein_coding	dolichyl-phosphate mannosyltransferase subunit...	CDGIE|MPDS
3	ENSG00000000457	SCYL3	57147	protein_coding	SCY1 like pseudokinase 3	PACE-1|PACE1
4	ENSG00000000460	FIRRM	55732	protein_coding	FIGNL1 interacting regulator of recombination ...	FLIP|C1ORF112|FLJ10706|APOLO1|MEICA1

df.to_parquet(f"df_human__ensembl__{version}__Gene.parquet")

df_legacy = ensembl_gene.download_legacy_ids_df(df)

df_legacy.shape

(8285, 14)

df_legacy.to_parquet(f"df-legacy_human__ensembl__{version}__Gene.parquet")

Mouse

ensembl_gene = EnsemblGene(organism="mouse", version=version)

df = ensembl_gene.download_df()

💡 fetching records from the core DB...
💡 fetching records from the external DBs...
❗ duplicated #rows ensembl_gene_id with ncbi_gene_id: 600
✅ downloaded Gene table containing 57545 entries.

df.head()

	ensembl_gene_id	symbol	ncbi_gene_id	biotype	description	synonyms
0	ENSMUSG00000000001	Gnai3	14679	protein_coding	guanine nucleotide binding protein (G protein)...	Galphai3
1	ENSMUSG00000000003	Pbsn	54192	protein_coding	probasin [Source:MGI Symbol;Acc:MGI:1860484]	PB
2	ENSMUSG00000000028	Cdc45	12544	protein_coding	cell division cycle 45 [Source:MGI Symbol;Acc:...	Cdc45l
3	ENSMUSG00000000031	H19	14955	lncRNA	H19, imprinted maternally expressed transcript...
4	ENSMUSG00000000037	Scml2	107815	protein_coding	Scm polycomb group protein like 2 [Source:MGI ...	4932420G07Rik

# https://github.com/laminlabs/bionty/issues/533
df["description"] = df["description"].str.replace(r"\[.*?\]", "", regex=True)

df.to_parquet(f"df_mouse__ensembl__{version}__Gene.parquet")

df_legacy = ensembl_gene.download_legacy_ids_df(df)

df_legacy.shape

(30685, 14)

df_legacy.head()

	mapping_session_id	old_stable_id	old_version	new_stable_id	new_version	type	score	old_db_name	new_db_name	old_release	new_release	old_assembly	new_assembly	created
0	59	ENSMUSG00000079169	4	ENSMUSG00000027157	12	gene	0.990000	mus_musculus_core_106_39	mus_musculus_core_107_39	106	107	GRCm39	GRCm39	2022-01-12 20:12:50
1	61	ENSMUSG00000095464	2	ENSMUSG00000046516	12	gene	0.990000	mus_musculus_core_108_39	mus_musculus_core_109_39	108	109	GRCm39	GRCm39	2022-08-25 23:23:22
2	59	ENSMUSG00000085431	8	ENSMUSG00000054510	7	gene	0.990000	mus_musculus_core_106_39	mus_musculus_core_107_39	106	107	GRCm39	GRCm39	2022-01-12 20:12:50
3	6	ENSMUSG00000067056	1	ENSMUSG00000070605	1	gene	0.993523	mus_musculus_core_36_34d	mus_musculus_core_38_35	36	38	NCBIM34	NCBIM35	2006-03-15 17:41:36
4	6	ENSMUSG00000068846	1	ENSMUSG00000071738	1	gene	0.991369	mus_musculus_core_36_34d	mus_musculus_core_38_35	36	38	NCBIM34	NCBIM35	2006-03-15 17:41:36

df_legacy.to_parquet(f"df-legacy_mouse__ensembl__{version}__Gene.parquet")

saccharomyces_cerevisiae

ensembl_gene = EnsemblGene(organism="saccharomyces cerevisiae", version=version)

df = ensembl_gene.download_df()

💡 fetching records from the core DB...
💡 fetching records from the external DBs...
❗ duplicated #rows ensembl_gene_id with ncbi_gene_id: 218
❗ no ensembl_gene_id found, writing to table_id column.
✅ downloaded Gene table containing 7248 entries.

# https://github.com/laminlabs/bionty/issues/533
df["description"] = df["description"].str.replace(r"\[.*?\]", "", regex=True)

df.to_parquet(f"df_saccharomyces cerevisiae__ensembl__{version}__Gene.parquet")

df_legacy = ensembl_gene.download_legacy_ids_df(df, col="stable_id")

df_legacy.shape

(0, 14)