Add variant_length field

Author: tomwhite

bio2zarr/vcf2zarr/icf.py

@@ -212,6 +212,7 @@ def make_field_def(name, vcf_type, vcf_number):
         make_field_def("FILTERS", "String", "."),
         make_field_def("REF", "String", "1"),
         make_field_def("ALT", "String", "."),
+        make_field_def("rlen", "Integer", "1"),  # computed field
     ]
     return fields
 
@@ -1276,6 +1277,7 @@ def process_partition(self, partition_index):
                     tcw.append("FILTERS", variant.FILTERS)
                     tcw.append("REF", variant.REF)
                     tcw.append("ALT", variant.ALT)
+                    tcw.append("rlen", variant.end - variant.start)
                     for field in info_fields:
                         tcw.append(field.full_name, variant.INFO.get(field.name, None))
                     if has_gt:

bio2zarr/vcf2zarr/vcz.py

@@ -37,6 +37,7 @@ def inspect(path):
     "variant_contig": "An identifier from the reference genome or an angle-bracketed ID"
     " string pointing to a contig in the assembly file",
     "variant_position": "The reference position",
+    "variant_length": "The length of the variant measured in bases",
     "variant_id": "List of unique identifiers where applicable",
     "variant_allele": "List of the reference and alternate alleles",
     "variant_quality": "Phred-scaled quality score",
@@ -302,11 +303,12 @@ def fixed_field_spec(
         ]
         name_map = {field.full_name: field for field in icf.metadata.fields}
 
-        # Only two of the fixed fields have a direct one-to-one mapping.
+        # Only three of the fixed fields have a direct one-to-one mapping.
         array_specs.extend(
             [
                 spec_from_field(name_map["QUAL"], array_name="variant_quality"),
                 spec_from_field(name_map["POS"], array_name="variant_position"),
+                spec_from_field(name_map["rlen"], array_name="variant_length"),
             ]
         )
         array_specs.extend(

tests/test_icf.py

@@ -18,7 +18,7 @@ class TestSmallExample:
         'ALT', 'CHROM', 'FILTERS', 'FORMAT/DP', 'FORMAT/GQ',
         'FORMAT/GT', 'FORMAT/HQ', 'ID', 'INFO/AA', 'INFO/AC',
         'INFO/AF', 'INFO/AN', 'INFO/DB', 'INFO/DP', 'INFO/H2',
-        'INFO/NS', 'POS', 'QUAL', 'REF'
+        'INFO/NS', 'POS', 'QUAL', 'REF', 'rlen'
     )
     # fmt: on
 
@@ -117,6 +117,7 @@ class TestLocalAllelesExample:
         "POS",
         "QUAL",
         "REF",
+        "rlen",
     )
 
     @pytest.fixture(scope="class")
@@ -451,7 +452,7 @@ def icf(self, tmp_path_factory):
 
     def test_repr(self, icf):
         assert repr(icf).startswith(
-            "IntermediateColumnarFormat(fields=7, partitions=5, records=4665, path="
+            "IntermediateColumnarFormat(fields=8, partitions=5, records=4665, path="
         )
 
     def test_pos_repr(self, icf):

tests/test_vcf_examples.py

@@ -56,6 +56,9 @@ def test_position(self, ds):
             [111, 112, 14370, 17330, 1110696, 1230237, 1234567, 1235237, 10],
         )
 
+    def test_length(self, ds):
+        nt.assert_array_equal(ds["variant_length"], [1, 1, 1, 1, 1, 1, 1, 1, 2])
+
     def test_int_info_fields(self, ds):
         nt.assert_array_equal(
             ds["variant_NS"],
@@ -938,6 +941,7 @@ def test_info_fields(self, ds):
             "variant_filter",
             "variant_contig",
             "variant_position",
+            "variant_length",
             "variant_allele",
             "variant_id",
             "variant_id_mask",