Merge pull request #9 from rbutleriii/the_phantom_variant

The phantom variant
rbutleriii · May 30, 2019 · ab06d1b · ab06d1b
2 parents bff7c92 + 28f3769
commit ab06d1b
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 4 deletions.
diff --git a/clinotator/getncbi.py b/clinotator/getncbi.py
@@ -110,7 +110,6 @@ def batch_local(file_type, query_type, id_list, **kwargs):
 
     for start in range(0, count, g.elink_batch):
         end = min(count, start + g.elink_batch)
-        time.sleep(0.37)
         logging.info("Looking up VIDs for rsIDs {} to {}"
                      .format(start + 1, end))
         webenv1, query_key1 = post_ncbi(
@@ -130,6 +129,7 @@ def batch_local(file_type, query_type, id_list, **kwargs):
             pass
         continue
         logging.debug('length result list: {}'.format(len(result_list)))
+        time.sleep(0.37)
     return result_list
 
 # getting xml variation files for query_results list, 

diff --git a/clinotator/global_vars.py b/clinotator/global_vars.py
@@ -10,7 +10,7 @@
 See main, eventually tests will be added for this module
 '''
 
-__version__ = "1.3.0"
+__version__ = "1.3.1"
 
 
 ### getncbi.py global variables 

diff --git a/clinotator/vcf.py b/clinotator/vcf.py
@@ -72,12 +72,14 @@ def vcf_prep(file_object, outprefix):
 def cat_info_column(info, rsid, alt, out_tbl):
     rsid_match = rsid.lstrip('rs')
     alt_list = alt.split(",")
+    info_tbl = pd.DataFrame()
     info_columns = ['VID', 'CVVT', 'CVAL', 'CVCS', 'CVSZ', 'CVNA', 'CVDS',
                     'CVLE', 'CTRS', 'CTAA', 'CTPS', 'CTRR']
     logging.debug('rsid: {} alt_list: {}'.format(rsid_match, alt_list))
     # logging.debug('out_tbl shape -> {}'.format(out_tbl.shape))
-    info_tbl = out_tbl.loc[(out_tbl['rsID'].astype('str') == rsid_match)
-                           & out_tbl['CVAL'].isin(alt_list)].copy()
+    if rsid_match != ".":
+        info_tbl = out_tbl.loc[(out_tbl['rsID'].astype('str') == rsid_match)
+                               & out_tbl['CVAL'].isin(alt_list)].copy()
 
     if len(info_tbl.index) > 0:
         info_tbl.replace({'CVCS': {',': '%2C', ';': '%3B'},

diff --git a/test/test.vcf b/test/test.vcf
@@ -17,6 +17,7 @@
 ##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
 ##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002
+1	216371836	rs111033524	C	A	47	PASS	NS=3;DP=13;AA=C	GT:GQ:DP:HQ	0|0:54:7:56,60	1|0:48:4:51,51
 7	140754187	rs180177040	A	C,G	50	PASS	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|2:48:1:51,51	1|0:48:8:51,51
 7	140754187	rs180177040	A	C	50	PASS	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51
 7	140754187	rs180177040	A	G	50	PASS	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51
@@ -25,6 +26,7 @@
 20	765535	rs34376836	C	A	3	q10	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3
 20	1110696	rs6040355	A	G,T	67	PASS	NS=2;DP=10;AF=0.333,0.667;AA=T;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2
 20	1230237	.	T	.	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|0:54:7:56,60	0|0:48:4:51,51
+20	1230237	.	T	A	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|1:54:7:56,60	0|0:48:4:51,51
 20	1980505	rs766877230	G	A	50	PASS	NS=3;DP=9;AA=G	GT:GQ:DP	0/1:35:4	0/2:17:2
 20	1980505	rs766877230	G	T	50	PASS	NS=3;DP=9;AA=G	GT:GQ:DP	0/1:35:4	0/2:17:2
 20	1980505	rs766877230	G	A,T	50	PASS	NS=3;DP=9;AA=G	GT:GQ:DP	0/1:35:4	0/2:17:2