From 17b10a110a9ffe56b03e8ada4df992a4de9162e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pontus=20H=C3=B6jer?= <pontushojer@gmail.com>
Date: Wed, 7 Jun 2023 17:28:46 +0200
Subject: [PATCH] test calling DELs

---
 tests/data/make_testdata.sh |  8 ++++++++
 tests/test_run.py           | 19 +++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/tests/data/make_testdata.sh b/tests/data/make_testdata.sh
index 3f2c708..71acc6e 100644
--- a/tests/data/make_testdata.sh
+++ b/tests/data/make_testdata.sh
@@ -25,3 +25,11 @@ bam="https://s3-us-west-2.amazonaws.com/10x.files/samples/genome/HCC1954T_WGS_21
 region="chr21:18,709,465-18,956,782"
 samtools view "${bam}" "${region}" -o HCC1954T_10xGenomics_chr21_INV.bam
 samtools index HCC1954T_10xGenomics_chr21_INV.bam
+
+# DELETION ON CHROMOSOME 1 (NA24385)
+# GRCh38: chr1  115686862    115690219
+# source: CMRG benchmark,  https://ftp-trace.ncbi.nlm.nih.gov/giab/ftp/release/AshkenazimTrio/HG002_NA24385_son/CMRG_v1.00/GRCh38/StructuralVariant/
+bam="https://ftp-trace.ncbi.nlm.nih.gov/giab/ftp/data/AshkenazimTrio/analysis/10XGenomics_ChromiumGenome_LongRanger2.2_Supernova2.0.1_04122018/GRCh38/NA24385.GRCh38.phased_possorted_bam.bam"
+region="chr1:115,620,601-115,756,835"
+samtools view "${bam}" "${region}" -o NA24385_10xGenomics_chr1_DEL.bam
+samtools index NA24385_10xGenomics_chr1_DEL.bam
diff --git a/tests/test_run.py b/tests/test_run.py
index 7da02c9..edd3a95 100644
--- a/tests/test_run.py
+++ b/tests/test_run.py
@@ -10,6 +10,7 @@
 BAM_INV = Path("tests/data/HCC1954T_10xGenomics_chr21_INV.bam").absolute()
 CANDIDATES_INV = Path("tests/data/HCC1954T_10xGenomics_chr21_INV.candidates.bedpe").absolute()
 CANDIDATES_REV_INV = Path("tests/data/HCC1954T_10xGenomics_chr21_INV.candidates_reversed.bedpe").absolute()
+BAM_DEL = Path("tests/data/NA24385_10xGenomics_chr1_DEL.bam").absolute()
 BAM_TRA = Path("tests/data/HCC1954T_10xGenomics_chr_12_20_TRA.bam").absolute()
 
 
@@ -176,6 +177,24 @@ def test_consistent(tmp_path):
         same_pairwise_elements(line, new_line)
 
 
+def test_call_deletion(tmp_path):
+    config_file = io.StringIO(f"bam_file={BAM_DEL}\noutdir={tmp_path}\nDEBUG=True\n")
+    configs = Configs.from_file(config_file)
+
+    exitcode = run(configs)
+    assert exitcode == 0
+    output = tmp_path / "NAIBR_SVs.bedpe"
+    with open(output) as bedpe_reader:
+        nas = list(iter_novel_adjacencies(bedpe_reader))
+        assert len(nas) > 0
+        nas_pass = [na for na in nas if na.pass_threshold]
+        assert len(nas_pass) == 1
+        assert nas_pass[0].orient == "+-"
+        assert nas_pass[0].chrm1 == nas_pass[0].chrm2 == "chr1"
+        assert abs(nas_pass[0].break1 - 115686862) < 500
+        assert abs(nas_pass[0].break2 - 115690219) < 500
+
+
 def test_call_interchromosomal(tmp_path):
     config_file = io.StringIO(f"bam_file={BAM_TRA}\noutdir={tmp_path}\nDEBUG=True\n")
     configs = Configs.from_file(config_file)