Allow numbers flag in VEP online and update tests

LUMC · Nov 5, 2024 · d454f7a · d454f7a
1 parent 8f569d5
commit d454f7a
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 8 deletions.
diff --git a/includes/snv-indels/Snakefile b/includes/snv-indels/Snakefile
@@ -343,6 +343,7 @@ rule annotate_vars:
             --polyphen b \
             --sift b \
             --hgvs \
+            --numbers \
             --stats_file {output.stats} \
             --output_file STDOUT | gzip > {output.vep}\
             2> {log}

diff --git a/test/data/output/v2/SRR8615409.vardict.summary.json b/test/data/output/v2/SRR8615409.vardict.summary.json
@@ -230,7 +230,7 @@
             "input": "chrM\t8566\t.\tA\tG\t151\tPASS\tSAMPLE=SRR8615409;TYPE=SNV;DP=27;END=8566;VD=27;AF=1;BIAS=0:2;REFBIAS=0:0;VARBIAS=14:13;PMEAN=28.7;PSTD=1;QUAL=31.8;QSTD=1;SBF=1;ODDRATIO=0;MQ=255;SN=5.75;HIAF=1.0000;ADJAF=0.1111;SHIFT3=0;MSI=1;MSILEN=1;NM=2.9;HICNT=23;HICOV=23;LSEQ=CTTCATTCATTGCCCCCACA;RSEQ=TCCTAGGCCTACCCGCCGCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0\tGT:DP:VD:AD:AF:RD:ALD\t1/1:27:27:0,27:1:0,0:14,13",
             "is_in_hotspot": false,
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8566,
             "strand": 1,
             "transcript_consequences": [
@@ -335,7 +335,7 @@
             "input": "chrM\t8701\t.\tA\tG\t199\tPASS\tSAMPLE=SRR8615409;TYPE=SNV;DP=48;END=8701;VD=46;AF=0.9583;BIAS=0:2;REFBIAS=0:2;VARBIAS=18:28;PMEAN=27.6;PSTD=1;QUAL=36.2;QSTD=1;SBF=0.52128;ODDRATIO=0;MQ=255;SN=45;HIAF=0.9574;ADJAF=0.0208;SHIFT3=1;MSI=2;MSILEN=1;NM=2.6;HICNT=45;HICOV=47;LSEQ=TAACCTCAAAACAAATGATA;RSEQ=CCATACACAACACTAAAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0\tGT:DP:VD:AD:AF:RD:ALD\t1/1:48:46:2,46:0.9583:0,2:18,28",
             "is_in_hotspot": true,
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8701,
             "strand": 1,
             "transcript_consequences": [
@@ -430,7 +430,7 @@
             "input": "chrM\t8860\t.\tA\tG\t123\tPASS\tSAMPLE=SRR8615409;TYPE=SNV;DP=13;END=8860;VD=13;AF=1;BIAS=0:2;REFBIAS=0:0;VARBIAS=10:3;PMEAN=20.8;PSTD=1;QUAL=33.5;QSTD=1;SBF=1;ODDRATIO=0;MQ=255;SN=5.5;HIAF=1.0000;ADJAF=0.1538;SHIFT3=0;MSI=1;MSILEN=1;NM=2.8;HICNT=11;HICOV=11;LSEQ=CCATCCCCTTATGAGCGGGC;RSEQ=CAGTGATTATAGGCTTTCGC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0\tGT:DP:VD:AD:AF:RD:ALD\t1/1:13:13:0,13:1:0,0:10,3",
             "is_in_hotspot": true,
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8860,
             "strand": 1,
             "transcript_consequences": [
@@ -512,7 +512,7 @@
             "input": "chrM\t8390\t.\tT\tA\t166\tPASS\tSAMPLE=SRR8615409;TYPE=SNV;DP=25;END=8390;VD=25;AF=1;BIAS=0:1;REFBIAS=0:0;VARBIAS=24:1;PMEAN=8.8;PSTD=1;QUAL=35.8;QSTD=1;SBF=1;ODDRATIO=0;MQ=255;SN=24;HIAF=1.0000;ADJAF=0.12;SHIFT3=0;MSI=2;MSILEN=1;NM=4.2;HICNT=24;HICOV=24;LSEQ=CCCAACTAAATACTACCGTA;RSEQ=GGCCCACCATAATTACCCCC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0\tGT:DP:VD:AD:AF:RD:ALD\t1/1:25:25:0,25:1:0,0:24,1",
             "is_in_hotspot": true,
             "most_severe_consequence": "stop_gained",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8390,
             "strand": 1,
             "transcript_consequences": [

diff --git a/test/data/output/v2/full-report.summary.json b/test/data/output/v2/full-report.summary.json
@@ -118,7 +118,7 @@
             "id": ".",
             "input": "chrM\t8566\t.\tA\tG\t.\tPASS\tADP=26;WT=0;HET=0;HOM=1;NC=0\tGT:GQ:SDP:DP:RD:AD:FREQ:PVAL:RBQ:ABQ:RDF:RDR:ADF:ADR\t1/1:129:26:26:0:23:100%:1.2146E-13:0:32:0:0:12:11",
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8566,
             "strand": 1,
             "transcript_consequences": [
@@ -133,6 +133,7 @@
                 "consequence_terms": [
                   "missense_variant"
                 ],
+                "exon": "1/1",
                 "gene_id": "ENSG00000198899",
                 "hgvsc": "ENST00000361899.2:c.40A>G",
                 "hgvsp": "ENSP00000354632.2:p.Ile14Val",
@@ -158,6 +159,7 @@
                 "consequence_terms": [
                   "missense_variant"
                 ],
+                "exon": "1/1",
                 "gene_id": "ENSG00000198899",
                 "hgvsc": "ENST00000361899.2:c.40A>G",
                 "hgvsp": "ENSP00000354632.2:p.Ile14Val",
@@ -205,7 +207,7 @@
             "id": ".",
             "input": "chrM\t8701\t.\tA\tG\t.\tPASS\tADP=45;WT=0;HET=0;HOM=1;NC=0\tGT:GQ:SDP:DP:RD:AD:FREQ:PVAL:RBQ:ABQ:RDF:RDR:ADF:ADR\t1/1:206:45:45:2:39:95.12%:2.1258E-21:33:41:0:2:18:21",
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8701,
             "strand": 1,
             "transcript_consequences": [
@@ -220,6 +222,7 @@
                 "consequence_terms": [
                   "missense_variant"
                 ],
+                "exon": "1/1",
                 "gene_id": "ENSG00000198899",
                 "hgvsc": "ENST00000361899.2:c.175A>G",
                 "hgvsp": "ENSP00000354632.2:p.Thr59Ala",
@@ -267,7 +270,7 @@
             "id": ".",
             "input": "chrM\t8860\t.\tA\tG\t.\tPASS\tADP=16;WT=0;HET=0;HOM=1;NC=0\tGT:GQ:SDP:DP:RD:AD:FREQ:PVAL:RBQ:ABQ:RDF:RDR:ADF:ADR\t1/1:64:16:16:0:12:100%:3.698E-7:0:33:0:0:9:3",
             "most_severe_consequence": "missense_variant",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8860,
             "strand": 1,
             "transcript_consequences": [
@@ -282,6 +285,7 @@
                 "consequence_terms": [
                   "missense_variant"
                 ],
+                "exon": "1/1",
                 "gene_id": "ENSG00000198899",
                 "hgvsc": "ENST00000361899.2:c.334A>G",
                 "hgvsp": "ENSP00000354632.2:p.Thr112Ala",
@@ -331,7 +335,7 @@
             "id": ".",
             "input": "chrM\t8390\t.\tT\tA\t.\tPASS\tADP=24;WT=0;HET=0;HOM=1;NC=0\tGT:GQ:SDP:DP:RD:AD:FREQ:PVAL:RBQ:ABQ:RDF:RDR:ADF:ADR\t1/1:117:24:24:0:21:100%:1.8578E-12:0:37:0:0:21:0",
             "most_severe_consequence": "stop_gained",
-            "seq_region_name": "MT",
+            "seq_region_name": "chrMT",
             "start": 8390,
             "strand": 1,
             "transcript_consequences": [
@@ -346,6 +350,7 @@
                 "consequence_terms": [
                   "stop_gained"
                 ],
+                "exon": "1/1",
                 "gene_id": "ENSG00000228253",
                 "hgvsc": "ENST00000361851.1:c.25T>A",
                 "hgvsp": "ENSP00000355265.1:p.Trp9Ter",

diff --git a/test/test_report.py b/test/test_report.py
@@ -77,6 +77,24 @@ def test_genes_in_order(workflow_dir):
     assert "MT-ATP8" in genes_of_interest[1].values()
 
 
+@pytest.mark.workflow('test-report')
+def test_chr_g_location_exon(workflow_dir):
+    """Test if chr ID, genomic location and exon info (e.g, (chr2:20000000, exon 1/12)) are shown in table"""
+    report = f"{workflow_dir}/report.html"
+    with open(report) as fin:
+        soup = bs4.BeautifulSoup(fin, features="html.parser")
+
+    # Extract HGVS column
+    variant_table = soup.find('table', id='var-overview')
+    HGVS_with_extra_info = variant_table.find_all('td', class_ = 'hgvs')
+    HGVS_with_extra_info_pattern = r"chr([a-zA-Z0-9]+).*?exon (\d+)"
+    for hgvs in HGVS_with_extra_info:
+        hgvs_text = hgvs.get_text(separator=" <br/> ", strip=True) 
+        import re
+        extra_info = hgvs_text.split("<br/> ")[-1]
+        match = re.search(HGVS_with_extra_info_pattern, extra_info)
+        assert match is not None
+
 
 @pytest.mark.workflow('test-report')
 def test_fusion_overview(workflow_dir):