env via pydantic added

environment.yml

@@ -132,6 +132,7 @@ dependencies:
   - zipp=3.15.0=pyhd8ed1ab_0
   - zlib=1.2.11=h166bdaf_1014
   - pip:
+    - annotated-types==0.5.0
     - anyio==3.7.0
     - argon2-cffi==21.3.0
     - argon2-cffi-bindings==21.2.0
@@ -193,11 +194,14 @@ dependencies:
     - prompt-toolkit==3.0.38
     - psutil==5.9.5
     - ptyprocess==0.7.0
+    - pydantic==2.0.3
+    - pydantic-core==2.3.0
     - pygments==2.15.1
     - pyparsing==3.1.0
     - pyrsistent==0.19.3
     - pytest==7.4.0
     - python-dateutil==2.8.2
+    - python-dotenv==0.21.1
     - pytz==2023.3
     - pyzmq==25.1.0
     - qtconsole==5.4.3

preprocess/.env_paths

@@ -0,0 +1,7 @@
+vcf='/absolute_path_to_your_file/example.vcf'
+samples='/absolute_path_to_your_files/hapmap-ceu-all.lift.vcf'
+conform='/absolute_your_path/conform-gt.24May16.cee.jar'
+beagle='/absolute_your_path/beagle.22Jul22.46e.jar'
+ref='/absolute_your_path/reference'
+maps='/absolute_your_path/maps'
+gb=20

preprocess/run_beagle.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python
 import re
-import click
 import os
 import glob
+from setting import IMPUTATION_SETTINGS
+
 """
 script for running Beagle 5.4 
 All kind of data for this script like human reference panel, genetic maps
@@ -45,7 +46,6 @@ def run_conform(conform, vcf_gz_file, ref_folder):
        reference: files was downloaded from from Beagle human reference link
        https://bochet.gcc.biostat.washington.edu/beagle/1000_Genomes_phase3_v5a/b37.vcf/"""
     for ref_file in glob.glob(f'{ref_folder}/**/chr*.vcf.gz', recursive=True):
-        print('conform ', ref_file)
         if re.search("chr(\d+)", ref_file):
             chr_type = (re.search("chr(\d+)", ref_file))[1]
         elif re.search("chrX", ref_file):
@@ -58,7 +58,6 @@ def run_conform(conform, vcf_gz_file, ref_folder):
 def ensure_biallelic_ref(ref_dir):
     for ref_file in glob.glob(f'{ref_dir}/chr*.v5a.vcf.gz'):
         ref_biall_path = os.path.join(ref_dir, f'{ref_file.split("vcf")[0]}biallelic.vcf.gz')
-        print('ensure ', ref_file, ref_biall_path)
         os.system(f'bcftools view -m2 -M2 -v snps -Oz -o {ref_biall_path} {ref_file}')
         os.system(f'bcftools index {ref_biall_path}.gz')
         os.remove(ref_file)  # remove initial ref file
@@ -78,25 +77,42 @@ def run_beagle(beagle, gb, map_dir, ref_dir):
                           f' out=imputed_{chr_type} map={map_file}')
 
 
-@click.command()
-@click.option('--vcf', help='Path to the target vcf file')
-@click.option('--samples', help='Path to VCF with other samples for conform checks, not required if target VCF'
-                                'contains data for at least 20 individuals', required=False)
-@click.option('--conform', help='Path to conform .jar file')
-@click.option('--beagle', help='Path to beagle .jar file')
-@click.option('--ref', help='Path to folder with reference genome:'
-                            ' .vcf.gz files are expected to start with "chr1."..."chr22.", "chrX."')
-@click.option('--map', help='Path to folder with PLINK format genetic maps, files are expected to start with'
-                            '"plink.chr1.", ..."plink.chr22.", "plink.chrX."')
-@click.option('--gb', help='Number of gigabytes for running beagle', default=10, show_default=True)
-def main(vcf, samples, conform, beagle, ref, map, gb):
+# @click.command()
+# @click.option('--vcf', help='Path to the target vcf file')
+# @click.option('--samples', help='Path to VCF with other samples for conform checks, not required if target VCF'
+#                                 'contains data for at least 20 individuals', required=False)
+# @click.option('--conform', help='Path to conform .jar file')
+# @click.option('--beagle', help='Path to beagle .jar file')
+# @click.option('--ref', help='Path to folder with reference genome:'
+#                             ' .vcf.gz files are expected to start with "chr1."..."chr22.", "chrX."')
+# @click.option('--maps', help='Path to folder with PLINK format genetic maps, files are expected to start with'
+#                              '"plink.chr1.", ..."plink.chr22.", "plink.chrX."')
+# @click.option('--gb', help='Number of gigabytes for running beagle', default=10, show_default=True)
+def main():
+    vcf = IMPUTATION_SETTINGS.vcf
+    samples = IMPUTATION_SETTINGS.samples
+    conform = IMPUTATION_SETTINGS.conform
+    beagle = IMPUTATION_SETTINGS.beagle
+    ref = IMPUTATION_SETTINGS.ref
+    maps = IMPUTATION_SETTINGS.maps
+    gb = IMPUTATION_SETTINGS.gb
     bgzip_and_index(vcf, samples)
     if samples:
         merge(vcf, samples)
     cleaned_file = clean_and_gzip(vcf, samples)  # returned cleaned file in .vcf.gz (gzip) format
     ensure_biallelic_ref(ref)
     run_conform(conform, cleaned_file, ref)
-    run_beagle(beagle, gb, map, ref)
+    run_beagle(beagle, gb, maps, ref)
 
 
 main()
+"""
+python preprocess/run_beagle.py 
+--vcf /Users/alina/Documents/longevity/genomes/antonkulaga.hg37.pickard.annotate_bcf_alldbsnp.vcf 
+--samples /Users/alina/Documents/longevity/genomes/hapmap-ceu-all.lift.vcf 
+--conform /Users/alina/tools/conform-gt.24May16.cee.jar 
+--beagle /Users/alina/tools/beagle.22Jul22.46e.jar 
+--ref /Users/alina/progproj/gennet/test_beagle/reference
+ --map /Users/alina/progproj/gennet/test_beagle/maps --gb 20
+
+"""

preprocess/setting.py

@@ -0,0 +1,23 @@
+from typing import Optional
+from pydantic import BaseSettings, Field
+import os
+
+
+class EnvBeagle(BaseSettings):
+    vcf: str = Field(description='Path to the target vcf file')
+    samples: Optional[str] = Field(default=None,
+                                   description='Path to VCF with other samples for conform checks, not required if '
+                                               'target VCF contains data for at least 20 individuals')
+    conform: str = Field(description='Path to conform .jar file')
+    beagle: str = Field(description='Path to beagle .jar file')
+    ref: str = Field(description='Path to folder with reference genome:'
+                                 ' .vcf.gz files are expected to start with "chr1."..."chr22.", "chrX."')
+    maps: str = Field(description='Path to folder with PLINK format genetic maps, files are expected to start with'
+                                  '"plink.chr1.", ..."plink.chr22.", "plink.chrX."')
+    gb: int = Field(description='Number of gigabytes for running beagle')
+
+    class Config:
+        env_file = os.path.dirname(os.path.abspath(__file__))+"/.env_paths"
+
+
+IMPUTATION_SETTINGS = EnvBeagle()