Switch to vcfpy

requirements.txt

@@ -2,6 +2,6 @@ click>=8.0.1
 flake8>=3.9.2
 jinja2>=3.0.1
 neo4j>=4.2.1
-pyvcf==0.6.8
+vcfpy>=0.13.0
 pytest>=6.2.4
 

setup.py

@@ -24,7 +24,7 @@
         "click",
         "neo4j",
         "jinja2",
-        "pyvcf",
+        "vcfpy",
     ],
     entry_points={"console_scripts": ["tbvcfreport=tbvcfreport.tbvcfreport:cli"]},
     project_urls={

tbvcfreport/report.py

@@ -79,7 +79,7 @@ def generate_txt_report(file_name, data):
         "GENE",
         "IDENTIFIER",
         "PRODUCT",
-        "TYPE",
+        "IS_SNV",
         "ANNOTATION",
         "POS",
         "REF",
@@ -95,7 +95,7 @@ def generate_txt_report(file_name, data):
             s[3],
             s[4],
             s[21]["protein"]["uniquename"] if "protein" in s[21] and s[21]["protein"] else "NOPROTEIN",
-            s[19],
+            str(s[19]),
             s[1],
             str(s[17]),
             s[18],

tbvcfreport/templates/report-layout.html

@@ -34,7 +34,7 @@
                 <th scope="col">GENE</th>
                 <th scope="col">LOCUS</th>
                 <th scope="col">PRODUCT</th>
-                <th scope="col">TYPE</th>
+                <th scope="col">IS_SNV</th>
                 <th scope="col">EFFECT</th>
                 <th scope="col">POS</th>
                 <th scope="col">REF</th>
@@ -68,7 +68,7 @@
                     <p>{{ "NA" }}</p>
                     {% endif %}
                 </td>
-                <td>{{ item[19] or "NA" }}</td>
+                <td>{{ item[19] }}</td>
                 <td>{{ item[1] or "NA" }}</td>
                 <td>
                     <a href="https://explorer.sanbi.ac.za/jbrowse/?loc=NC_000962.3%3A{{ item[20] }}&tracks=DNA%2CGenes&highlight=NC_000962.3%3A{{ item[20] }}"

tbvcfreport/vcfproc.py

@@ -1,5 +1,5 @@
 """Interface to handle VCF files."""
-import vcf
+import vcfpy
 
 from .dbconn import CombatTbDb
 
@@ -22,7 +22,7 @@ def parse(self):
         """Parse VCF."""
         variants, rv_tags = [], []
         with open(self.vcf_file) as _vcf:
-            vcf_reader = vcf.Reader(_vcf)
+            vcf_reader = vcfpy.Reader.from_stream(_vcf)
             for i, record in enumerate(vcf_reader):
                 if record.INFO.get("ANN"):
                     annotations = self.get_variant_ann(record=record)
@@ -35,12 +35,12 @@ def parse(self):
         rv_tags = list(set(rv_tags))
         gene_info = self.gene_info_to_dict(self.db.query_by_gene_list(rv_tags))
         with open(self.vcf_file) as _vcf:
-            vcf_reader = vcf.Reader(_vcf)
+            vcf_reader = vcfpy.Reader.from_stream(_vcf)
             for i, record in enumerate(vcf_reader):
-                if record.var_type == "snp":
-                    record.affected_start += 1
+                if record.is_snv():
+                    record.begin += 1
                 affected_region = "..".join(
-                    [str(record.affected_start), str(record.affected_end)]
+                    [str(record.begin), str(record.end)]
                 )
                 if record.INFO.get("ANN"):
                     annotations = self.get_variant_ann(record=record)
@@ -60,7 +60,7 @@ def parse(self):
                                 record.CHROM,
                                 record.POS,
                                 record.REF,
-                                record.var_type,
+                                record.is_snv(),
                                 affected_region,
                                 variant_data,
                             ]

tox.ini

@@ -4,7 +4,7 @@
 # and then run "tox" from this directory.
 
 [tox]
-envlist = py310,py311,py312
+envlist = py{310,311,312}
 
 [testenv]
 deps = -rrequirements.txt