Hide BiopythonDeprecationWarnings when reading certain sequence files

Biopython 1.85 shows a deprecation warning when using format='fasta'
with files that start with anything but '>'.

The warning as-is should not be exposed to Augur users. It is not
triggered when reading files with format='fasta-pearson', so this is the
easiest thing to do continue accepting such files for Biopython
>=1.85.

This way, Augur users get consistent, backwards compatible behavior no
matter the Biopython version they use.

augur/io/sequences.py

@@ -2,6 +2,8 @@
 import os
 
 from augur.errors import AugurError
+from importlib.metadata import version
+from packaging.version import Version
 from typing import Iterator, Iterable, Union
 from .file import open_file
 
@@ -11,8 +13,15 @@ def get_biopython_format(augur_format: str) -> str:
     supported_formats = {"fasta", "genbank"}
     if augur_format not in supported_formats:
         raise AugurError(f"Sequence file format {augur_format!r} is invalid. Must be one of {', '.join(repr(f) for f in sorted(supported_formats))}.")
+
     # Supported formats are valid Biopython formats
-    return augur_format
+    biopython_format = augur_format
+
+    # Allow comments in FASTA format using fasta-pearson in later biopython versions
+    if Version(version("biopython")) >= Version("1.85") and biopython_format == "fasta":
+        biopython_format = "fasta-pearson"
+
+    return biopython_format
 
 
 def read_sequence(

tests/io/test_sequences.py

@@ -81,7 +81,7 @@ def genbank_reference():
 class TestFormat:
     def test_fasta(self):
         biopython_format = augur.io.sequences.get_biopython_format("fasta")
-        assert biopython_format == "fasta"
+        assert biopython_format == "fasta" or biopython_format == "fasta-pearson"
 
     def test_genbank(self):
         biopython_format = augur.io.sequences.get_biopython_format("genbank")