Update merge_str_prep.py (#84)

* Update merge_str_prep.py

* linting

* Update str/trtools/merge_str_prep.py

Co-authored-by: Matt Welland <mattwellie@gmail.com>

---------

Co-authored-by: Matt Welland <mattwellie@gmail.com>

str/trtools/merge_str_prep.py

@@ -4,7 +4,7 @@
 This script prepares GangSTR/EH VCF files for input into mergeSTR. 
 Required input: --caller, --input-dir, and external sample IDs
 For example: 
-analysis-runner --access-level test --dataset tob-wgs --description 'tester --output-dir 'tester' merge_prep.py --caller=eh --input-dir=gs://cpg-tob-wgs-main/str/expansionhunter/pure_repeats --dataset=tob-wgs TOBXXXX TOBXXXX
+analysis-runner --access-level test --dataset tob-wgs --description 'tester --output-dir 'tester' merge_prep.py --caller=eh --input-dir=gs://cpg-tob-wgs-main/str/expansionhunter/pure_repeats --dataset=tob-wgs CPGXXXX CPGXXXX
 
 Required packages: sample-metadata, hail, click, os
 pip install sample-metadata hail click
@@ -13,8 +13,6 @@
 import os
 import click
 
-from sample_metadata.apis import SampleApi
-
 from cpg_utils.config import get_config
 from cpg_utils.hail_batch import output_path
 from cpg_workflows.batch import get_batch
@@ -33,23 +31,17 @@
     help='gangstr or eh',
     type=click.Choice(['eh', 'gangstr'], case_sensitive=True),
 )
-# dataset
-@click.option('--dataset', help='dataset eg tob-wgs')
 # input directory
 @click.option('--input-dir', help='gs://...')
 # input sample ID
-@click.argument('external-wgs-ids', nargs=-1)
+@click.argument('internal-wgs-ids', nargs=-1)
 @click.command()
 def main(
-    dataset, caller, input_dir, external_wgs_ids: list[str]
+    caller, input_dir, internal_wgs_ids: list[str]
 ):  # pylint: disable=missing-function-docstring
     # Initializing Batch
     b = get_batch()
 
-    external_id_to_cpg_id: dict[str, str] = SampleApi().get_sample_id_map_by_external(
-        dataset, list(external_wgs_ids)
-    )
-
     # Working with CRAM files requires the reference fasta
     ref = b.read_input_group(
         **dict(
@@ -62,8 +54,7 @@ def main(
 
     input_vcf_dict = {}
 
-    for id in list(external_id_to_cpg_id.values()):
-        input_vcf_dict[id] = os.path.join(input_dir, f'{id}_{caller}.vcf')
+    input_vcf_dict = {id: os.path.join(input_dir, f'{id}_{caller}.vcf') for id in internal_wgs_ids}
 
     for id in list(input_vcf_dict.keys()):
         bcftools_job = b.new_job(name=f'{id} {caller} Files prep')
@@ -93,7 +84,7 @@ def main(
                 """
             )
             # Output writing
-            output_path_eh = output_path(f'{id}_eh')
+            output_path_eh = output_path(f'{id}_eh', 'analysis')
             b.write_output(bcftools_job.vcf_sorted, output_path_eh)
 
         else:
@@ -113,7 +104,7 @@ def main(
                 """
             )
             # Output writing
-            output_path_gangstr = output_path(f'{id}_gangstr')
+            output_path_gangstr = output_path(f'{id}_gangstr', 'analysis')
             b.write_output(bcftools_job.vcf_sorted, output_path_gangstr)
 
     b.run(wait=False)