replace ukb_common with ukbb_common

assign_phecodes.py

@@ -6,7 +6,7 @@
 import hail as hl
 from hail.utils import hadoop_open
 from ukbb_pan_ancestry import *
-from ukb_common import *
+from ukbb_common import *
 
 
 def checkpoint_tmp(hail_obj, tmppath='gs://ukbb-diverse-temp-30day/', tmpname=None, overwrite=True):

get_timings.py

@@ -7,7 +7,7 @@
 import logging
 logging.basicConfig(format="%(levelname)s (%(name)s %(lineno)s): %(message)s", level='INFO', filename='saige_pipeline.log')
 
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry import *
 
 logger = logging.getLogger("saige_pan_ancestry")

get_timings_null_model.py

@@ -7,7 +7,7 @@
 import logging
 logging.basicConfig(format="%(levelname)s (%(name)s %(lineno)s): %(message)s", level='INFO', filename='saige_pipeline.log')
 
-from ukb_common import *
+from ukbb_common import *
 
 from ukbb_pan_ancestry import *
 

heritability/import_heritability.py

@@ -1,7 +1,7 @@
 __author__ = 'Rahul Gupta'
 
 import hail as hl
-from ukb_common.resources.generic import PHENO_KEY_FIELDS
+from ukbb_common.resources.generic import PHENO_KEY_FIELDS
 
 
 def get_h2_flat_file():

load_timings.py

@@ -7,7 +7,7 @@
 import logging
 logging.basicConfig(format="%(levelname)s (%(name)s %(lineno)s): %(message)s", level='INFO', filename='saige_pipeline.log')
 
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry import *
 
 logger = logging.getLogger("saige_pan_ancestry")

plink_clump_hail.py

@@ -11,9 +11,9 @@
 import argparse
 import hail as hl
 import sys
-import ukb_common
+import ukbb_common
 from ukbb_pan_ancestry import POPS, bucket, get_clumping_results_path, get_meta_analysis_results_path #get_pheno_manifest_path
-#from ukb_common import mwzj_hts_by_tree
+#from ukbb_common import mwzj_hts_by_tree
 
 ldprune_dir = f'{bucket}/ld_prune'
 
@@ -72,7 +72,7 @@ def tsv_to_ht(args):
                                     pos=ht.pos,
                                     reference_genome='GRCh37'),
                    alleles = ht.varid.split(':')[2:4])
-    ht = ht.annotate_globals(**{k: getattr(args, k) for k in ukb_common.PHENO_KEY_FIELDS})
+    ht = ht.annotate_globals(**{k: getattr(args, k) for k in ukbb_common.PHENO_KEY_FIELDS})
     ht = ht.drop('contig','varid','pos')
     ht.describe()
 #    ht.select().show()
@@ -142,7 +142,7 @@ def mwzj_hts_by_tree(all_hts, temp_dir, globals_for_col_key,
                      debug=False, inner_mode = 'overwrite', repartition_final: int = None,
                      read_if_exists = False):
     r'''
-    Adapted from ukb_common mwzj_hts_by_tree()
+    Adapted from ukbb_common mwzj_hts_by_tree()
     Uses read_clump_ht() instead of read_table()
     '''
     chunk_size = int(len(all_hts) ** 0.5) + 1
@@ -153,7 +153,7 @@ def mwzj_hts_by_tree(all_hts, temp_dir, globals_for_col_key,
     checkpoint_kwargs = {inner_mode: not read_if_exists,
                          '_read_if_exists': read_if_exists} #
     if repartition_final is not None:
-        intervals = ukb_common.get_n_even_intervals(repartition_final)
+        intervals = ukbb_common.get_n_even_intervals(repartition_final)
         checkpoint_kwargs['_intervals'] = intervals
 
     if debug: print(f'Running chunk size {chunk_size}...')
@@ -231,7 +231,7 @@ def join_clump_hts(pop, not_pop, max_pops, high_quality=False, overwrite=False):
     temp_dir = ('gs://ukbb-diverse-temp-30day/nb-temp/'+
                 'max_pops' if max_pops else f'{"not_" if not_pop else ""}{pop}'+
                 f'{"-hq" if high_quality else ""}')
-    globals_for_col_key = ukb_common.PHENO_KEY_FIELDS
+    globals_for_col_key = ukbb_common.PHENO_KEY_FIELDS
     mt = mwzj_hts_by_tree(all_hts=all_hts,
                          temp_dir=temp_dir,
                          globals_for_col_key=globals_for_col_key)

pre_process_saige_data.py

@@ -5,7 +5,7 @@
 import argparse
 from gnomad.utils.vep import *
 from gnomad.utils.filtering import *
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry import *
 
 

resources/results.py

@@ -1,5 +1,5 @@
 from .generic import *
-from ukb_common.resources.results import *
+from ukbb_common.resources.results import *
 
 
 def get_gene_intervals_path(reference: str = 'GRCh37'):

saige_pan_ancestry.py

@@ -9,12 +9,12 @@
 logging.basicConfig(format="%(levelname)s (%(name)s %(lineno)s): %(message)s", level='INFO', filename='saige_pipeline.log')
 
 from gnomad.utils import slack
-from ukb_common import *
+from ukbb_common import *
 import time
 import re
 
 from ukbb_pan_ancestry import *
-from ukb_common.utils.saige_pipeline import *
+from ukbb_common.utils.saige_pipeline import *
 
 logger = logging.getLogger("saige_pan_ancestry")
 logger.addHandler(logging.StreamHandler(sys.stderr))

summary_statistics_analysis.py

@@ -6,7 +6,7 @@
 from pprint import pprint
 
 from gnomad.utils import slack
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry import *
 
 def remove_phenos_from_analysis(mt: hl.MatrixTable):

utils/phenotype_loading.py

@@ -1,4 +1,4 @@
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry.resources import *
 
 

utils/results_loading.py

@@ -1,5 +1,5 @@
 import re
-from ukb_common import *
+from ukbb_common import *
 from ukbb_pan_ancestry.resources import *
 
 

website/docs/batch-pipeline.md

@@ -34,7 +34,7 @@ This file can then be loaded using:
 python load_phenotype_data.py --add_dataset TRAITTYPE_NAME
 ```
 
-If you do not have the google cloud connector installed, you can do this as a submission (`hailctl dataproc submit load_phenotype_data.py --add_dataset TRAITTYPE_NAME`); note that in either case, you will need to have the `ukb_common` and `ukbb_pan_ancestry` packages on your path. This script will make a backup copy of the existing phenotype MatrixTable and overwrite the master file with a new one including the new phenotype(s).
+If you do not have the google cloud connector installed, you can do this as a submission (`hailctl dataproc submit load_phenotype_data.py --add_dataset TRAITTYPE_NAME`); note that in either case, you will need to have the `ukbb_common` and `ukbb_pan_ancestry` packages on your path. This script will make a backup copy of the existing phenotype MatrixTable and overwrite the master file with a new one including the new phenotype(s).
 
 #### Step 2 - Run tests
 

website/docs/hail-format.md

@@ -33,12 +33,12 @@ gsutil -u your_project_id ls gs://ukb-diverse-pops-public/sumstats_release
 
 ## Using the libraries and files
 
-The files on Google Cloud Platform can be accessed by cloning the [ukbb_pan_ancestry](https://github.com/atgu/ukbb_pan_ancestry) and the [ukb_common](https://github.com/Nealelab/ukb_common) repos and accessing them programmatically. We recommend using these functions, as they apply our QC metrics (e.g. the raw file contains 7,271 phenotypes, but use of this function will return 7,221 phenotypes after removing low-quality ones) and include convenience metrics such as lambda GC.
+The files on Google Cloud Platform can be accessed by cloning the [ukbb_pan_ancestry](https://github.com/atgu/ukbb_pan_ancestry) and the [ukbb_common](https://github.com/Nealelab/ukbb_common) repos and accessing them programmatically. We recommend using these functions, as they apply our QC metrics (e.g. the raw file contains 7,271 phenotypes, but use of this function will return 7,221 phenotypes after removing low-quality ones) and include convenience metrics such as lambda GC.
 
 ```
 %%bash
 git clone https://github.com/atgu/ukbb_pan_ancestry
-git clone https://github.com/Nealelab/ukb_common
+git clone https://github.com/Nealelab/ukbb_common
 ```