dynamic snp adding switch

bin/dynamic_donor_exclusive_snp_selection.py

@@ -296,6 +296,14 @@ def donor_exclusive_sites(exclusive_don_variants2):
         help='cellsnp'
     )   
 
+    # parser.add_argument(
+    #     '-dny', '--add_dynamic_sites_or_not_to_panel',
+    #     action='store',
+    #     dest='add_dynamic_sites_or_not_to_panel',
+    #     required=True,
+    #     help='cellsnp'
+    # )   
+
     options = parser.parse_args()
     vcf = options.vcf
     cellsnp = options.cellsnp

conf/base.conf

@@ -14,7 +14,7 @@ params{
     profile='normal_run'
     citeseq=false
     estimate_and_provide_informative_snps_for_deconvolution=false
-
+    
     filter_outliers = true
     //# These are default parameters that can be overwriten to run in a different mode.
     //# Here we have listed the default parameters when running without any extrainput.
@@ -23,6 +23,7 @@ params{
     provide_within_pool_donor_specific_sites_for_pilup=true
     hard_filters_file = "no_file__file_sample_qc" //# This may point to the sample_qc.yml input which will apply hard filters to the merged cells.
     hard_filters_drop = false //#This indicates whether we want to drop the cells that fail hard filters of just flag them
+    add_snps_to_pile_up_based_on_genotypes_provided = false // #whether we want to add informative snp to pile up in bam to enhance deconvolutions.
     drop_cell_passes_qc_from_clustering = false //#This filter if set to true will drop the cells that dont pass the adaptive qc criteria before clustering.
     encrypt = false
     write_h5=false

modules/nf-core/modules/cellsnp/main.nf

@@ -33,17 +33,24 @@ process DYNAMIC_DONOR_EXCLUSIVE_SNP_SELECTION{
                 mode: "${params.copy_mode}",
                 overwrite: "true"
     input: 
+        val(add_dynamic_sites_or_not_to_panel)
         tuple val(samplename), path(vcf_file),path(csi),path(cellsnp_primary_file)
     output:
       tuple val(samplename), path("cellsnp_panel_${samplename}.vcf.gz"),emit:cellsnp_pool_panel
       tuple val(samplename), path("set2_informative_sites_${samplename}.tsv"), path("set1_uninformative_sites_${samplename}.tsv"),path("variants_description.tsv"),emit:informative_uninformative_sites 
     script:       
+      if (params.add_dynamic_sites_or_not_to_panel){
+        cmd1="ln -s ${vcf_file} dynamic_snps.vcf.gz"
+      }else{
+        cmd1="bcftools view -R ${cellsnp_primary_file} ${vcf_file} -Oz -o  dynamic_snps.vcf.gz"
+      }
+
       """
         echo ${samplename}
         echo ${vcf_file}
         echo ${cellsnp_primary_file}
         #// bcftools view -i 'MAF > 0.0001 & R2>=1.00' -Oz -o dynamic_snps.vcf.gz ${vcf_file}
-        ln -s ${vcf_file} dynamic_snps.vcf.gz
+        ${cmd1}
         dynamic_donor_exclusive_snp_selection.py -cpus ${task.cpus} -vcf dynamic_snps.vcf.gz -cellsnp ${cellsnp_primary_file}
         echo test > output.csv
         bcftools view -h ${cellsnp_primary_file} > cellsnp_panel_${samplename}.vcf

subworkflows/main_deconvolution.nf

@@ -75,7 +75,8 @@ workflow  main_deconvolution {
             // merged_expected_genotypes2.subscribe { println "merged_expected_genotypes2: $it" }
             GT_MATCH_POOL_IBD(SUBSET_WORKF.out.samplename_subsetvcf_ibd,'Withing_expected','Expected')
 
-            DYNAMIC_DONOR_EXCLUSIVE_SNP_SELECTION(merged_expected_genotypes2)
+
+            DYNAMIC_DONOR_EXCLUSIVE_SNP_SELECTION(params.add_snps_to_pile_up_based_on_genotypes_provided,merged_expected_genotypes2)
             cellsnp_panels = DYNAMIC_DONOR_EXCLUSIVE_SNP_SELECTION.out.cellsnp_pool_panel
 
             informative_uninformative_sites = DYNAMIC_DONOR_EXCLUSIVE_SNP_SELECTION.out.informative_uninformative_sites