faidx function can now search for multiple sequences in one execution

Author: JLSteenwyk

docs/usage/index.rst

@@ -377,7 +377,12 @@ Command line interface: pk_faidx; pk_get_entry; pk_ge
 Extracts sequence entry from fasta file.
 
 This function works similarly to the faidx function 
-in samtools, but does not requiring an indexing function.
+in samtools, but does not requiring an indexing step.
+
+To obtain multiple entries, input multiple entries separated
+by a comma (,). For example, if you want entries 
+named "seq_0" and "seq_1", the string "seq_0,seq_1"
+should be associated with the -e argument.
 
 .. code-block:: shell
 

phykit/phykit.py

@@ -738,7 +738,12 @@ def faidx(argv):
                 Extracts sequence entry from fasta file.
 
                 This function works similarly to the faidx function 
-                in samtools, but does not requiring an indexing function.
+                in samtools, but does not requiring an indexing step.
+
+                To obtain multiple entries, input multiple entries separated
+                by a comma (,). For example, if you want entries 
+                named "seq_0" and "seq_1", the string "seq_0,seq_1"
+                should be associated with the -e argument.
 
                 Aliases:
                   faidx, get_entry; ge

phykit/services/alignment/faidx.py

@@ -9,7 +9,9 @@ def __init__(self, args) -> None:
 
     def run(self):
         record_dict = SeqIO.index(self.fasta, "fasta")
-        print(f">{record_dict[self.entry].name}\n{record_dict[self.entry].seq}")
+        entry = self.entry.split(',')
+        for e in entry:
+            print(f">{record_dict[e].name}\n{record_dict[e].seq}")
 
     def process_args(self, args):
         return dict(fasta=args.fasta, entry=args.entry)

phykit/version.py

@@ -1 +1 @@
-__version__ = "1.19.7"
+__version__ = "1.19.8"

tests/integration/alignment/test_faidx.py

@@ -65,4 +65,22 @@ def test_faidx_alias1(self, mocked_print):
         ]
         with patch.object(sys, "argv", testargs):
             Phykit()
-        assert mocked_print.mock_calls == [call(expected_result)]
+        assert mocked_print.mock_calls == [call(expected_result)]
+
+    @patch("builtins.print")
+    def test_faidx_multiple_entries(self, mocked_print):
+        expected_result0 = ">1\nA-GTAT"
+        expected_result1 = ">2\nA-G-AT"
+        testargs = [
+            "phykit",
+            "faidx",
+            f"{here.parent.parent.parent}/sample_files/simple.fa",
+            '-e',
+            '1,2'
+        ]
+        with patch.object(sys, "argv", testargs):
+            Phykit()
+        assert mocked_print.mock_calls == [
+            call(expected_result0),
+            call(expected_result1)
+        ]