Pulling more realistic bam from outside source

getwilds · Dec 16, 2024 · a5f64bd · a5f64bd
1 parent abd0e1e
commit a5f64bd
Showing 1 changed file with 41 additions and 37 deletions.
diff --git a/.github/workflows/variant-calling-test-run.yml b/.github/workflows/variant-calling-test-run.yml
@@ -36,7 +36,7 @@ jobs:
 
       - name: Setup Test Data
         run: |
-          # mkdir -p test/data
+          mkdir -p test/data
           cd test/data
           
           # Download reference chromosome 20 from NCBI
@@ -152,13 +152,8 @@ jobs:
           {
             "PanelBwaGatk4Annovar.sample_batch": [
               {
-                "sample_name": "TESTBAM1",
-                "bam_file": "test/data/TESTBAM1.unmapped.bam",
-                "bed_file": "test/data/test.bed"
-              },
-              {
-                "sample_name": "TESTBAM2",
-                "bam_file": "test/data/TESTBAM2.unmapped.bam",
+                "sample_name": "test_sample",
+                "bam_file": "test/data/test.unmapped.bam",
                 "bed_file": "test/data/test.bed"
               }
             ],
@@ -203,38 +198,47 @@ jobs:
           gatk ValidateVariants -V mills_1000G.vcf.gz -R ref.fasta
           gatk ValidateVariants -V known_indels.vcf.gz -R ref.fasta
 
-          # # Create a test BAM with unmapped reads
-          # cat << EOF > test.sam
-          # @HD	VN:1.6	SO:queryname
-          # @SQ	SN:chr20	LN:63025520
-          # @RG	ID:test	SM:test_sample	PL:ILLUMINA	LB:lib1	PU:unit1
-          # read1	77	*	0	0	*	*	0	0	$(get_ref_base 1000100 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # read1	141	*	0	0	*	*	0	0	$(get_ref_base 1000200 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # read2	77	*	0	0	*	*	0	0	$(get_ref_base 1000300 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # read2	141	*	0	0	*	*	0	0	$(get_ref_base 1000400 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # read3	77	*	0	0	*	*	0	0	$(get_ref_base 1000500 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # read3	141	*	0	0	*	*	0	0	$(get_ref_base 1000600 16)	FFFFFFFFFFFFFFFF	RG:Z:test
-          # EOF
+          # Navigating back to original directory
+          cd ../../
+
+      - name: Generate test BAM
+        run: |
+          # Download NA12878 data
+          wget https://ftp-trace.ncbi.nlm.nih.gov/ReferenceSamples/giab/data/NA12878/Garvan_NA12878_HG001_HiSeq_Exome/project.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam
           
-          # # Convert SAM to BAM and proper sorting
-          # samtools view -b test.sam > test.unsorted.bam
-          # samtools sort -n test.unsorted.bam > test.unmapped.bam
+          # Generate BAM index
+          samtools index project.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam
           
-          # # Debug: Check the BAM
-          # echo "=== Checking final BAM structure ==="
-          # samtools view -H test.unmapped.bam
-          # echo "=== First few reads ==="
-          # samtools view test.unmapped.bam | head -n 2
+          # Extract region and ensure proper pairing
+          samtools view -h -f 0x2 -s 0.1 project.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam chr20:1000000-1100000 | \
+          samtools sort -n - | \
+          samtools fastq -1 test/data/r1.fq -2 test/data/r2.fq -0 /dev/null -s /dev/null -n
           
-          # # Clean up intermediate files
-          # rm test.sam test.unsorted.bam
-
-          # # Validate BAM file
-          # echo "=== Validating BAM file ==="
-          # gatk ValidateSamFile -I test.unmapped.bam
-
-          # Navigating back to original directory
-          cd ../../
+          # Convert back to unmapped BAM with proper read groups
+          gatk FastqToSam \
+            -F1 test/data/r1.fq \
+            -F2 test/data/r2.fq \
+            -O test/data/test.unmapped.bam \
+            -SM NA12878 \
+            -RG test \
+            -PL ILLUMINA \
+            -LB lib1 \
+            -PU unit1
+          
+          # Debug: Check the BAM
+          echo "=== Checking final BAM structure ==="
+          samtools view -H test/data/test.unmapped.bam
+          echo "=== First few reads ==="
+          samtools view test/data/test.unmapped.bam | head -n 2
+          
+          # Clean up intermediate files
+          rm test/data/r1.fq test/data/r2.fq \
+              project.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam \
+              project.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam.bai
+          
+          # Validate BAM file
+          echo "=== Validating BAM file ==="
+          gatk ValidateSamFile -I test/data/test.unmapped.bam
 
       - name: Run test workflow
         run: |