fix barcode calculation and other functions with sample to prevent sp…

…ecial characters in name #321, docs #4
bioinfo-chru-strasbourg · Dec 9, 2024 · 39886a1 · 39886a1
1 parent 555435e
commit 39886a1
Show file tree

Hide file tree

Showing 16 changed files with 27,407 additions and 27,276 deletions.
diff --git a/README.pdf b/README.pdf
diff --git a/RELEASE_NOTES.pdf b/RELEASE_NOTES.pdf
diff --git a/docs/docs.pdf b/docs/docs.pdf
diff --git a/docs/help.configuration.calculation.pdf b/docs/help.configuration.calculation.pdf
diff --git a/docs/help.configuration.pdf b/docs/help.configuration.pdf
diff --git a/docs/help.configuration.prioritization.pdf b/docs/help.configuration.prioritization.pdf
diff --git a/docs/help.parameters.databases.pdf b/docs/help.parameters.databases.pdf
diff --git a/docs/help.parameters.pdf b/docs/help.parameters.pdf
diff --git a/docs/help.pdf b/docs/help.pdf
diff --git a/docs/pdoc/howard/objects/variants.html b/docs/pdoc/howard/objects/variants.html
diff --git a/docs/tips.pdf b/docs/tips.pdf
diff --git a/docs/user_guide.pdf b/docs/user_guide.pdf
diff --git a/howard/objects/variants.py b/howard/objects/variants.py
@@ -2514,7 +2514,9 @@ def export_variant_vcf(
             if not list_samples:
                 list_samples = self.get_header_sample_list()
             if list_samples:
-                samples_fields = " , FORMAT , " + " , ".join(list_samples)
+                samples_fields = " , FORMAT , " + " , ".join(
+                    [f""" "{sample}" """ for sample in list_samples]
+                )
             else:
                 samples_fields = ""
             log.debug(f"samples_fields: {samples_fields}")
@@ -9135,7 +9137,7 @@ def calculation_find_by_pipeline(self, tag: str = "findbypipeline") -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                self.get_header_sample_list()
+                [f""" "{sample}" """ for sample in self.get_header_sample_list()]
             )
 
             # Create dataframe
@@ -9235,7 +9237,7 @@ def calculation_genotype_concordance(self) -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                self.get_header_sample_list()
+                [f""" "{sample}" """ for sample in self.get_header_sample_list()]
             )
 
             # Create dataframe
@@ -9341,7 +9343,7 @@ def calculation_barcode(self, tag: str = "barcode") -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                self.get_header_sample_list()
+                [f""" "{sample}" """ for sample in self.get_header_sample_list()]
             )
 
             # Create dataframe
@@ -9510,7 +9512,7 @@ def calculation_barcode_family(self, tag: str = "BCF") -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                ped_samples
+                [f""" "{sample}" """ for sample in ped_samples]
             )
 
             # Create dataframe
@@ -9546,7 +9548,8 @@ def calculation_barcode_family(self, tag: str = "BCF") -> None:
             for sample in self.get_header_sample_list() + ["FORMAT"]:
                 if sample in ped_samples:
                     value = f'dataframe_barcode."{barcode_infos}"'
-                    value_samples = "'" + ",".join(ped_samples) + "'"
+                    value_samples = "'" + ",".join([f""" "{sample}" """ for sample in ped_samples]) + "'"
+                    ped_samples
                 elif sample == "FORMAT":
                     value = f"'{tag}'"
                     value_samples = f"'{tag}S'"
@@ -9710,7 +9713,7 @@ def calculation_trio(self) -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                self.get_header_sample_list()
+                [f""" "{sample}" """ for sample in self.get_header_sample_list()]
             )
 
             # Create dataframe
@@ -9917,7 +9920,7 @@ def calculation_genotype_stats(self, info: str = "VAF") -> None:
 
             # variant_id, FORMAT and samples
             samples_fields = f" {variant_id_column}, FORMAT , " + " , ".join(
-                self.get_header_sample_list()
+                [f""" "{sample}" """ for sample in self.get_header_sample_list()]
             )
 
             # Create dataframe

diff --git a/plugins/README.pdf b/plugins/README.pdf
diff --git a/tests/data/example.name_with_special_char.vcf b/tests/data/example.name_with_special_char.vcf
@@ -0,0 +1,62 @@
+##fileformat=VCFv4.1
+##FILTER=<ID=PASS,Description="All filters passed">
+##fileDate=20140624
+##source=./export.pl release 1.5
+##reference=IRC
+##phasing=unknown
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##FILTER=<ID=FSFilter,Description="FS > 200.0">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FILTER=<ID=QDFilter,Description="QD < 2.0">
+##FILTER=<ID=ReadPosFilter,Description="ReadPosRankSum < -20.0">
+##FILTER=<ID=TruthSensitivityTranche99.00to99.90,Description="Truth sensitivity tranche level at VSQ Lod: -3.9813 <= x < 3.448">
+##FILTER=<ID=TruthSensitivityTranche99.90to100.00+,Description="Truth sensitivity tranche level at VQS Lod < -29586.8217">
+##FILTER=<ID=TruthSensitivityTranche99.90to100.00,Description="Truth sensitivity tranche level at VSQ Lod: -29586.8217 <= x < -3.9813">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=AD,Number=2,Type=Integer,Description="Allelic Depth">
+##FORMAT=<ID=FILTER,Number=.,Type=String,Description="Filter quality">
+##FORMAT=<ID=QUAL,Number=1,Type=Integer,Description="Filter quality value">
+##INFO=<ID=CLNSIG,Number=1,Type=String,Description="CLNSIG">
+##contig=<ID=chr1,length=249250621,assembly=hg19>
+##contig=<ID=chr7,length=159138663,assembly=hg19>
+##contig=<ID=1,length=249250621,assembly=hg19>
+##contig=<ID=10,length=135534747,assembly=hg19>
+##contig=<ID=11,length=135006516,assembly=hg19>
+##contig=<ID=12,length=133851895,assembly=hg19>
+##contig=<ID=13,length=115169878,assembly=hg19>
+##contig=<ID=14,length=107349540,assembly=hg19>
+##contig=<ID=15,length=102531392,assembly=hg19>
+##contig=<ID=16,length=90354753,assembly=hg19>
+##contig=<ID=17,length=81195210,assembly=hg19>
+##contig=<ID=18,length=78077248,assembly=hg19>
+##contig=<ID=19,length=59128983,assembly=hg19>
+##contig=<ID=2,length=243199373,assembly=hg19>
+##contig=<ID=20,length=63025520,assembly=hg19>
+##contig=<ID=21,length=48129895,assembly=hg19>
+##contig=<ID=22,length=51304566,assembly=hg19>
+##contig=<ID=3,length=198022430,assembly=hg19>
+##contig=<ID=4,length=191154276,assembly=hg19>
+##contig=<ID=5,length=180915260,assembly=hg19>
+##contig=<ID=6,length=171115067,assembly=hg19>
+##contig=<ID=7,length=159138663,assembly=hg19>
+##contig=<ID=8,length=146364022,assembly=hg19>
+##contig=<ID=9,length=141213431,assembly=hg19>
+##contig=<ID=M,length=16571,assembly=hg19>
+##contig=<ID=X,length=155270560,assembly=hg19>
+##contig=<ID=Y,length=59373566,assembly=hg19>
+##INFO=<ID=SIFT,Number=.,Type=String,Description="Annotation 'SIFT'">
+##bcftools_viewVersion=1.15.1+htslib-1.15.1
+##bcftools_viewCommand=view tests/data/example.vcf.gz; Date=Fri Mar 10 21:25:44 2023
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	sample-1	sample-2	sample-3	sample-4
+chr1	28736	.	A	C	100	PASS	CLNSIG=pathogenic	GT:AD:DP:GQ	0/1:525,204:729:99	0/1:12659,4994:17664:99	1/1:12658,4995:17663:99	1/1:401,175:576:99
+chr1	35144	.	A	C	100	PASS	CLNSIG=non-pathogenic	GT:AD:DP:GQ	./.:.:.:.	0/1:12659,4994:17664:99	0/1:12658,4995:17663:99	0/1:401,175:576:99
+chr1	69101	.	A	G	100	PASS	DP=50	GT:AD:DP:GQ	0/1:525,204:729:99	./.:.:.:.	0/1:12658,4995:17663:99	0/1:401,175:576:99
+chr1	768251	.	A	G	100	PASS	.	GT:AD:DP:GQ	0/1:525,204:729:99	./.:.:.:.	0/1:12658,4995:17663:99	0/1:401,175:576:99
+chr1	768252	.	A	G	100	PASS	.	GT:AD:DP:GQ	0/1:525,204:729:99	./.:.:.:.	0/1:12658,4995:17663:99	0/1:401,175:576:99
+chr1	768253	.	A	G	100	PASS	.	GT:AD:DP:GQ	0/1:525,204:729:99	./.:.:.:.	0/1:12658,4995:17663:99	0/1:401,175:576:99
+chr7	55249063	rs1050171	G	A	5777	PASS	DP=125	GT:AD:DP:GQ	0/1:525,204:729:99	0/1:12659,4994:17664:99	./.:.:.:.	0/1:401,175:576:99
diff --git a/tests/test_variants_calculations.py b/tests/test_variants_calculations.py
@@ -1028,6 +1028,63 @@ def test_calculation_barcode():
             assert False
 
 
+def test_calculation_barcode_sample_name_special_char():
+    """
+    This is a test function for a Python script that calculates barcode information from a VCF file and
+    checks if the output is correct.
+    """
+
+    with TemporaryDirectory(dir=tests_folder) as tmp_dir:
+
+        # Init files
+        input_vcf = tests_data_folder + "/example.name_with_special_char.vcf"
+        output_vcf = f"{tmp_dir}/output.vcf.gz"
+
+        # Construct param dict
+        param = {"calculation": {"calculations": {"BARCODE": None}}}
+
+        # Create object
+        variants = Variants(
+            conn=None, input=input_vcf, output=output_vcf, param=param, load=True
+        )
+
+        # Calculation
+        variants.calculation()
+
+        result = variants.get_query_to_df(
+            """ SELECT INFO FROM variants WHERE INFO LIKE '%barcode%' """
+        )
+        assert len(result) == 7
+
+        result = variants.get_query_to_df(
+            """ SELECT * FROM variants WHERE INFO LIKE '%barcode=1122%' """
+        )
+        assert len(result) == 1
+
+        result = variants.get_query_to_df(
+            """ SELECT * FROM variants WHERE INFO LIKE '%barcode=0111%' """
+        )
+        assert len(result) == 1
+
+        result = variants.get_query_to_df(
+            """ SELECT * FROM variants WHERE INFO LIKE '%barcode=1011%' """
+        )
+        assert len(result) == 4
+
+        result = variants.get_query_to_df(
+            """ SELECT * FROM variants WHERE INFO LIKE '%barcode=1101%' """
+        )
+        assert len(result) == 1
+
+        # Check if VCF is in correct format with pyVCF
+        remove_if_exists([output_vcf])
+        variants.export_output()
+        try:
+            vcf.Reader(filename=output_vcf)
+        except:
+            assert False
+
+
 def test_calculation_barcode_genotype():
     """
     The function `test_calculation_barcode_genotype` is a test function in Python that calculates