Plant Gene: ensembl, release-57

arabidopsis thaliana

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

from bionty.base.entities._gene import EnsemblGene

version = "release-57"

ensembl_gene = EnsemblGene(organism="arabidopsis thaliana", taxa="plants", 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: 438
! no ensembl_gene_id found, writing to table_id column.
✓ downloaded Gene table containing 75285 entries.

df

	stable_id	symbol	ncbi_gene_id	biotype	description	synonyms	index
0	AT1G01010	NAC001	NaN	protein_coding	NAC domain containing protein 1 [Source:NCBI g...	T25K16_1	43080
1	AT1G01010	NAC001	NaN	protein_coding	NAC domain containing protein 1 [Source:NCBI g...	T25K16.1	43079
2	AT1G01010	NAC001	NaN	protein_coding	NAC domain containing protein 1 [Source:NCBI g...	NAC domain containing protein 1	43078
3	AT1G01010	NAC001	NaN	protein_coding	NAC domain containing protein 1 [Source:NCBI g...	ANAC001	43077
4	AT1G01020	ARV1	NaN	protein_coding	ARV1 family protein [Source:NCBI gene (formerl...	T25K16_2	46552
...	...	...	...	...	...	...	...
75280	ATMG09730	None	NaN	tRNA	None	None	1533
75281	ATMG09740	None	NaN	tRNA	None	None	1390
75282	ATMG09950	None	NaN	tRNA	None	None	435
75283	ATMG09960	None	NaN	tRNA	None	None	1466
75284	ATMG09980	None	NaN	tRNA	None	None	1420

75285 rows × 7 columns

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

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

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

df_legacy.shape

(0, 0)