diff options
| author | gunturkunhakan | 2021-05-18 22:39:49 -0500 |
|---|---|---|
| committer | gunturkunhakan | 2021-05-18 22:39:49 -0500 |
| commit | 6235fb58955e2bc193d6ce40a4d74b33ab47dfce (patch) | |
| tree | 557418e4f22e608a6c45ee220c02d47ca49510e0 /utility/catalog_process.py | |
| parent | a637889f13c2151303998e411dc81f3196a974f6 (diff) | |
| download | genecup-6235fb58955e2bc193d6ce40a4d74b33ab47dfce.tar.gz | |
Welcome to GeneCup
Diffstat (limited to 'utility/catalog_process.py')
| -rw-r--r-- | utility/catalog_process.py | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/utility/catalog_process.py b/utility/catalog_process.py new file mode 100644 index 0000000..7841e54 --- /dev/null +++ b/utility/catalog_process.py @@ -0,0 +1,10 @@ +import pandas as pd +col_list = ['PUBMEDID', 'DISEASE/TRAIT', 'REPORTED GENE(S)', 'MAPPED_GENE', 'MAPPED_TRAIT', 'P-VALUE', 'SNPS'] +datf = pd.read_csv('gwas_catalog_v1.0.2-associations_e100_r2021-05-05.tsv', sep='\t', usecols=col_list) + +datf_sub = datf[datf['DISEASE/TRAIT'].str.contains('addiction')] + +print(datf_sub) + +#datf2 = pd.read_csv('gwas_catalog_v1.0.2-associations_e100_r2021-05-05.tsv', sep='\t') +#print(datf2.shape) |