Sample name

convert_gvf_to_vcf/convertGVFtoVCF.py

@@ -504,18 +504,21 @@ def __str__(self):
         return string_to_return
 
 #step 9 using custom unstructured meta-information line = generate_custom_unstructured_metainfomation_line
-def generate_vcf_metainformation(lines_custom_unstructured, gvf_pragmas, list_of_vcf_objects):
+def generate_vcf_metainformation(lines_custom_unstructured, gvf_pragmas, gvf_non_essential,  list_of_vcf_objects):
     """ Generates a list of metainformation lines for the VCF header
     :param lines_custom_unstructured: a list of formatted unstructured metainformation lines using a custom key value pair
     :param gvf_pragmas: list of gvf pragmas to convert
+    :param gvf_non_essential: list of non-essential gvf pragmas to convert
     :param list_of_vcf_objects: list of vcf objects
-    :return: unique_pragmas_to_add: a list of pragmas, this list contains no duplicates
+    :return: unique_pragmas_to_add, sample_names: a list of pragmas (this list contains no duplicates), list of sample names
     """
     pragmas_to_add = []
     unique_pragmas_to_add = []
+    sample_names = []
     # MANDATORY: file format for VCF
     pragma_fileformat = generate_custom_unstructured_metainfomation_line("fileformat", "VCFv4.4",lines_custom_unstructured)
     pragmas_to_add.append(pragma_fileformat)
+    #Go through essential pragmas
     #TODO: list of pragmas to add:reference=file, contig, phasing,INFO#
     for pragma in gvf_pragmas:
         # file date
@@ -548,15 +551,57 @@ def generate_vcf_metainformation(lines_custom_unstructured, gvf_pragmas, list_of
             pragmas_to_add.append(pragma_genome_build)
         else:
             pass
+    # Go through non-essential pragmas
+    for non_essential_pragma in gvf_non_essential:
+        if non_essential_pragma.startswith("#Study_accession"):
+            study_accession = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_study_accession = generate_custom_unstructured_metainfomation_line("Study_accession", study_accession, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_study_accession)
+        elif non_essential_pragma.startswith("#Study_type"):
+            study_type = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_study_type = generate_custom_unstructured_metainfomation_line("Study_type", study_type, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_study_type)
+        elif non_essential_pragma.startswith("#Display_name"):
+            display_name = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_display_name = generate_custom_unstructured_metainfomation_line("Display_name", display_name,lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_display_name)
+        elif non_essential_pragma.startswith("#Publication"):
+            publication = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_publication = generate_custom_unstructured_metainfomation_line("Publication", publication, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_publication)
+        elif non_essential_pragma.startswith("#Study"):
+            study = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_study = generate_custom_unstructured_metainfomation_line("Study", study, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_study)
+        elif non_essential_pragma.startswith("#Assembly_name"):
+            assembly_name = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_assembly_name = generate_custom_unstructured_metainfomation_line("Assembly_name", assembly_name, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_assembly_name)
+        elif non_essential_pragma.startswith("#subject"):
+            subject = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_subject = generate_custom_unstructured_metainfomation_line("subject", subject, lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_subject)
+        elif non_essential_pragma.startswith("#sample"):
+            sample_information = non_essential_pragma.split(": ")[1]
+            non_essential_pragma_sample = generate_custom_unstructured_metainfomation_line("sample", sample_information,
+                                                                                            lines_custom_unstructured)
+            pragmas_to_add.append(non_essential_pragma_sample)
+            list_of_sample_information = sample_information.split(";")
+            for sample_info in list_of_sample_information:
+                if sample_info.startswith("sample_name"):
+                    sample_name = sample_info.split("=")[1]
+                    sample_names.append(sample_name)
+        else:
+            print("Skipping unknown non-essential GVF pragma:", non_essential_pragma)
+
+    print("Total number of samples in this VCF: ", len(sample_names))
+
     for pragma in pragmas_to_add:
         if pragma not in unique_pragmas_to_add:
             unique_pragmas_to_add.append(pragma)
-
-    #TODO: add the pragmas for the GVF non-essentials
-    return unique_pragmas_to_add
+    return unique_pragmas_to_add, sample_names
 
 # step 10
-# TODO: finish the below for sample names
 def generate_vcf_header_line(samples):
     """ Generates the VCF header line
     :param samples: list of samples, these will appear in the header line
@@ -627,23 +672,49 @@ def gvf_features_to_vcf_objects(gvf_lines_obj_list,
             # print("for ", key, " the number of vcf objects is: ", len(vcf_obj_list))
     return vcf_data_lines, list_of_vcf_objects
 
-def format_vcf_datalines(list_of_vcf_objects):
-    """ Iterates through a list of VCF objects and formats them as a VCF dataline.
+
+def populate_sample_formats(list_of_sample_names):
+    """ Populates a dictionary using a list of sample names. Dictionary key is sample name, value is the sample's format value.
+    :param list_of_sample_names: list of sample names
+    :return:sample_name_format_value: dictionary of sample names => sample format value
+    """
+    sample_name_format_value = {}
+    for sample in list_of_sample_names:
+        sample_name_format_value[sample] = "sampleFORMAThere" #TODO: fill this in
+    return sample_name_format_value
+
+def format_sample_values(sample_name_format_value):
+    """ Creates a partial vcf data line of sample format values.
+    :param sample_name_format_value: dictionary of sample names => sample format value
+    :return: sample_format_values_string: formatted string
+    """
+    sample_format_values_string = ""
+    for key in sample_name_format_value:
+        sample_format_values_string = sample_format_values_string + sample_name_format_value[key] + "\t"
+    return sample_format_values_string
+
+def format_vcf_datalines(list_of_vcf_objects, list_of_sample_names):
+    """ Iterates through a list of VCF objects and sample names and formats them as a VCF dataline.
     :param list_of_vcf_objects: list of vcf objects
+    :param list_of_sample_names: list of sample names
     :return: formatted_vcf_datalines: list of formatted vcf datalines
     """
+    sample_name_format_value = populate_sample_formats(list_of_sample_names)
+    sample_format_values_string = format_sample_values(sample_name_format_value)
+
     formatted_vcf_datalines = []
     for vcf_obj in list_of_vcf_objects:
         vcf_line = (f"{vcf_obj.chrom}\t"
-                    f"{vcf_obj.pos}\t"
-                    f"{vcf_obj.id}\t"
-                    f"{vcf_obj.ref}\t" #TODO: should this always be empty
-                    f"{vcf_obj.alt}\t" #TODO: should this always be empty
-                    f"{vcf_obj.qual}\t" #TODO: should this always be empty
-                    f"{vcf_obj.filter}\t" #TODO: should this always be empty
-                    f"{vcf_obj.info}\t"
-                    f"{vcf_obj.format}\tsampleFORMAThere" #TODO: fill this in
-                    )
+                        f"{vcf_obj.pos}\t"
+                        f"{vcf_obj.id}\t"
+                        f"{vcf_obj.ref}\t" #TODO: should this always be empty
+                        f"{vcf_obj.alt}\t" #TODO: should this always be empty
+                        f"{vcf_obj.qual}\t" #TODO: should this always be empty
+                        f"{vcf_obj.filter}\t" #TODO: should this always be empty
+                        f"{vcf_obj.info}\t"
+                        f"{vcf_obj.format}\t"
+                        f"{sample_format_values_string}"
+                        )
         formatted_vcf_datalines.append(vcf_line)
     return formatted_vcf_datalines
 
@@ -689,18 +760,17 @@ def main():
                                                                       all_possible_FILTER_lines,
                                                                       all_possible_FORMAT_lines)
 
-    # 10c
     print("Writing to the following VCF output: ", args.vcf_output)
     print("Generating the VCF header and the meta-information lines")
+
     with open(args.vcf_output, "w") as vcf_output:
-        unique_pragmas_to_add = generate_vcf_metainformation(lines_custom_unstructured, gvf_pragmas, list_of_vcf_objects)
+        unique_pragmas_to_add, samples = generate_vcf_metainformation(lines_custom_unstructured, gvf_pragmas, gvf_non_essential, list_of_vcf_objects)
         for pragma in unique_pragmas_to_add:
             vcf_output.write(f"{pragma}\n")
-        samples = ["samA"] # TODO: this is a placeholder, need to add a function to read gvf pragmas and collect the samples into a list
         header_fields = generate_vcf_header_line(samples)
         vcf_output.write(f"{header_fields}\n")
         print("Generating the VCF datalines")
-        formatted_vcf_datalines = format_vcf_datalines(list_of_vcf_objects)
+        formatted_vcf_datalines = format_vcf_datalines(list_of_vcf_objects, samples)
         for line in formatted_vcf_datalines:
             vcf_output.write(f"{line}\n")
     vcf_output.close()

tests/input/zebrafish.gvf

@@ -9,158 +9,15 @@
 #Publication: PMID=22203992;Journal=Proceedings of the National Academy of Sciences of the United States of America;Paper_title=Extensive genetic diversity and substructuring among zebrafish strains revealed through copy number variant analysis.;Publication_year=2012
 #Study: First_author=Kim Brown;Description=Comparative genomic hybridization analysis of 3 laboratory and one wild zebrafish populations for Copy Number Variants
 #Assembly_name: GRCz10
-#subject: subject_name=Zon5
-#subject: subject_name=Zon4
-#subject: subject_name=Enders4
-#subject: subject_name=Wilds1-7
-#subject: subject_name=DF6
-#subject: subject_name=Wilds2-6
-#subject: subject_name=Wilds1-1
-#subject: subject_name=Wilds1-5
-#subject: subject_name=DF7
-#subject: subject_name=Wilds2-5
-#subject: subject_name=Utah2
-#subject: subject_name=KarpMale4;subject_sex=Male
-#subject: subject_name=DF9
-#subject: subject_name=Wilds1-2
-#subject: subject_name=KarpMale6;subject_sex=Male
-#subject: subject_name=Enders2
-#subject: subject_name=Wilds1-6
-#subject: subject_name=Wilds2-9
-#subject: subject_name=Zon3
-#subject: subject_name=Utah5
-#subject: subject_name=Wilds2-10
-#subject: subject_name=ZIRC3
-#subject: subject_name=JenFemal3;subject_sex=Female
-#subject: subject_name=Zon1
-#subject: subject_name=ZIRC5
-#subject: subject_name=Utah9
-#subject: subject_name=Enders8
-#subject: subject_name=ZIRC1
-#subject: subject_name=ZIRC8
-#subject: subject_name=Wilds2-1
-#subject: subject_name=Wilds2-4
-#subject: subject_name=ZIRC7
-#subject: subject_name=Enders1
-#subject: subject_name=KarpMale5;subject_sex=Male
-#subject: subject_name=DF8
-#subject: subject_name=JenFemale10;subject_sex=Female
-#subject: subject_name=Utah3
-#subject: subject_name=JenFemal2;subject_sex=Female
-#subject: subject_name=Wilds1-6 orig
-#subject: subject_name=Enders3
-#subject: subject_name=KarpMale3;subject_sex=Male
-#subject: subject_name=JenFemale8;subject_sex=Female
-#subject: subject_name=JenMale6;subject_sex=Male
-#subject: subject_name=JenFemale9;subject_sex=Female
-#subject: subject_name=DF10
-#subject: subject_name=Wilds1-4
-#subject: subject_name=DF1
-#subject: subject_name=Zon2
-#subject: subject_name=Zon9
-#subject: subject_name=Wilds1-3
-#subject: subject_name=JenFemal1;subject_sex=Female
-#subject: subject_name=Zon10
 #subject: subject_name=Wilds2-3
-#subject: subject_name=JenMale2;subject_sex=Male
+#subject: subject_name=Zon9
 #subject: subject_name=JenMale7;subject_sex=Male
-#subject: subject_name=ZIRC4
-#subject: subject_name=Zon8
-#subject: subject_name=KarpMale2;subject_sex=Male
-#subject: subject_name=Wilds1-8
-#subject: subject_name=ZIRC9
-#subject: subject_name=Utah4
-#subject: subject_name=Zon7
-#subject: subject_name=Wilds2-2
-#subject: subject_name=DF5
-#subject: subject_name=DF2
-#subject: subject_name=Utah6
-#subject: subject_name=Wilds2-8
-#subject: subject_name=ZIRC6
-#subject: subject_name=ZIRC2
-#subject: subject_name=Wilds2-7
-#subject: subject_name=Utah8
-#subject: subject_name=DF3
-#subject: subject_name=Zon6
-#subject: subject_name=Utah7
-#subject: subject_name=Utah1
-#subject: subject_name=DF4
-#sample: sample_name=Wilds2-2;subject_name=Wilds2-2
-#sample: sample_name=DF5;subject_name=DF5
-#sample: sample_name=DF2;subject_name=DF2
-#sample: sample_name=Utah6;subject_name=Utah6
-#sample: sample_name=Wilds2-8;subject_name=Wilds2-8
-#sample: sample_name=ZIRC6;subject_name=ZIRC6
-#sample: sample_name=ZIRC2;subject_name=ZIRC2
-#sample: sample_name=Wilds2-7;subject_name=Wilds2-7
-#sample: sample_name=Utah8;subject_name=Utah8
-#sample: sample_name=DF3;subject_name=DF3
-#sample: sample_name=Zon6;subject_name=Zon6
-#sample: sample_name=Utah7;subject_name=Utah7
-#sample: sample_name=Utah1;subject_name=Utah1
-#sample: sample_name=DF4;subject_name=DF4
-#sample: sample_name=Zon5;subject_name=Zon5
-#sample: sample_name=Zon4;subject_name=Zon4
-#sample: sample_name=Enders4;subject_name=Enders4
-#sample: sample_name=Wilds1-7;subject_name=Wilds1-7
-#sample: sample_name=DF6;subject_name=DF6
-#sample: sample_name=Wilds2-6;subject_name=Wilds2-6
-#sample: sample_name=Wilds1-1;subject_name=Wilds1-1
-#sample: sample_name=Wilds1-5;subject_name=Wilds1-5
-#sample: sample_name=DF7;subject_name=DF7
-#sample: sample_name=Wilds2-5;subject_name=Wilds2-5
-#sample: sample_name=Utah2;subject_name=Utah2
-#sample: sample_name=KarpMale4;subject_name=KarpMale4
-#sample: sample_name=DF9;subject_name=DF9
-#sample: sample_name=Wilds1-2;subject_name=Wilds1-2
-#sample: sample_name=KarpMale6;subject_name=KarpMale6
-#sample: sample_name=Enders2;subject_name=Enders2
-#sample: sample_name=Wilds1-6;subject_name=Wilds1-6
-#sample: sample_name=Wilds2-9;subject_name=Wilds2-9
-#sample: sample_name=Zon3;subject_name=Zon3
-#sample: sample_name=Utah5;subject_name=Utah5
-#sample: sample_name=Wilds2-10;subject_name=Wilds2-10
-#sample: sample_name=ZIRC3;subject_name=ZIRC3
-#sample: sample_name=JenFemal3;subject_name=JenFemal3
-#sample: sample_name=Zon1;subject_name=Zon1
-#sample: sample_name=ZIRC5;subject_name=ZIRC5
-#sample: sample_name=Utah9;subject_name=Utah9
-#sample: sample_name=Enders8;subject_name=Enders8
-#sample: sample_name=ZIRC1;subject_name=ZIRC1
-#sample: sample_name=ZIRC8;subject_name=ZIRC8
-#sample: sample_name=Wilds2-1;subject_name=Wilds2-1
-#sample: sample_name=Wilds2-4;subject_name=Wilds2-4
-#sample: sample_name=ZIRC7;subject_name=ZIRC7
-#sample: sample_name=Enders1;subject_name=Enders1
-#sample: sample_name=KarpMale5;subject_name=KarpMale5
-#sample: sample_name=DF8;subject_name=DF8
-#sample: sample_name=JenFemale10;subject_name=JenFemale10
-#sample: sample_name=Utah3;subject_name=Utah3
-#sample: sample_name=JenFemal2;subject_name=JenFemal2
-#sample: sample_name=Wilds1-6 orig;subject_name=Wilds1-6 orig
-#sample: sample_name=Enders3;subject_name=Enders3
-#sample: sample_name=KarpMale3;subject_name=KarpMale3
-#sample: sample_name=JenFemale8;subject_name=JenFemale8
+#subject: subject_name=JenMale6;subject_sex=Male
 #sample: sample_name=JenMale6;subject_name=JenMale6
-#sample: sample_name=JenFemale9;subject_name=JenFemale9
-#sample: sample_name=DF10;subject_name=DF10
-#sample: sample_name=Wilds1-4;subject_name=Wilds1-4
-#sample: sample_name=DF1;subject_name=DF1
-#sample: sample_name=Zon2;subject_name=Zon2
-#sample: sample_name=Zon9;subject_name=Zon9
-#sample: sample_name=Wilds1-3;subject_name=Wilds1-3
-#sample: sample_name=JenFemal1;subject_name=JenFemal1
-#sample: sample_name=Zon10;subject_name=Zon10
 #sample: sample_name=Wilds2-3;subject_name=Wilds2-3
-#sample: sample_name=JenMale2;subject_name=JenMale2
+#sample: sample_name=Zon9;subject_name=Zon9
 #sample: sample_name=JenMale7;subject_name=JenMale7
-#sample: sample_name=ZIRC4;subject_name=ZIRC4
-#sample: sample_name=Zon8;subject_name=Zon8
-#sample: sample_name=KarpMale2;subject_name=KarpMale2
-#sample: sample_name=Wilds1-8;subject_name=Wilds1-8
-#sample: sample_name=ZIRC9;subject_name=ZIRC9
-#sample: sample_name=Utah4;subject_name=Utah4
-#sample: sample_name=Zon7;subject_name=Zon7
+#testing_unknown_pragma
 1	DGVa	copy_number_loss	776614	786127	.	+	.	ID=1;Name=nssv1412199;Alias=CNV28955;variant_call_so_id=SO:0001743;parent=nsv811094;Start_range=.,776614;End_range=786127,.;submitter_variant_call_id=CNV28955;sample_name=Wilds2-3;remap_score=.98857;Variant_seq=.
 1	DGVa	copy_number_loss	1277246	1320592	.	+	.	ID=12;Name=nssv1406143;Alias=CNV22899;variant_call_so_id=SO:0001743;parent=nsv811095;Start_range=.,1277246;End_range=1320592,.;submitter_variant_call_id=CNV22899;sample_name=Zon9;remap_score=.87402;Variant_seq=.
 1	DGVa	copy_number_gain	1284210	1320592	.	+	.	ID=13;Name=nssv1389474;Alias=CNV6230;variant_call_so_id=SO:0001742;parent=nsv811095;Start_range=.,1284210;End_range=1320592,.;submitter_variant_call_id=CNV6230;sample_name=JenMale7;remap_score=.69625;Variant_seq=.