added new annotation format

q2_amr/amrfinderplus/types/__init__.py

@@ -7,12 +7,14 @@
 # ----------------------------------------------------------------------------
 from q2_amr.amrfinderplus.types._format import (
     AMRFinderPlusDatabaseDirectoryFormat,
+    ARMFinderPlusAnnotationFormat,
     BinaryFormat,
     TextFormat,
 )
 
 __all__ = [
     "AMRFinderPlusDatabaseDirectoryFormat",
+    "ARMFinderPlusAnnotationFormat",
     "TextFormat",
     "BinaryFormat",
 ]

q2_amr/amrfinderplus/types/_format.py

@@ -5,7 +5,9 @@
 #
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
+import pandas as pd
 from q2_types.feature_data import MixedCaseDNAFASTAFormat, ProteinFASTAFormat
+from qiime2.core.exceptions import ValidationError
 from qiime2.plugin import model
 
 
@@ -345,3 +347,45 @@ class AMRFinderPlusDatabaseDirectoryFormat(model.DirectoryFormat):
         "AMR_DNA-Streptococcus_pneumoniae.tab", format=TextFormat
     )
     AMR_DNA_Escherichia_tab = model.File("AMR_DNA-Escherichia.tab", format=TextFormat)
+
+
+class ARMFinderPlusAnnotationFormat(model.TextFileFormat):
+    def _validate(self, n_records=None):
+        header_coordinates = [
+            "Protein identifier",
+            "Contig id",
+            "Start",
+            "Stop",
+            "Strand",
+            "Gene symbol",
+            "Sequence name",
+            "Scope",
+            "Element type",
+            "Element subtype",
+            "Class",
+            "Subclass",
+            "Method",
+            "Target length",
+            "Reference sequence length",
+            "% Coverage of reference sequence",
+            "% Identity to reference sequence",
+            "Alignment length",
+            "Accession of closest sequence",
+            "Name of closest sequence",
+            "HMM id",
+            "HMM description",
+        ]
+        header = header_coordinates[:1] + header_coordinates[5:]
+        header_obs = pd.read_csv(str(self), sep="\t", nrows=0).columns.tolist()
+        if header != header_obs and header_coordinates != header_obs:
+            raise ValidationError(
+                "Header line does not match ARMFinderPlusAnnotation format. Must "
+                "consist of the following values: "
+                + ", ".join(header_coordinates)
+                + ".\nWhile Contig id, Start, Stop and Strand are optional."
+                + ".\n\nFound instead: "
+                + ", ".join(header_obs)
+            )
+
+    def _validate_(self, level):
+        self._validate()

q2_amr/amrfinderplus/types/_type.py

@@ -8,3 +8,4 @@
 from qiime2.core.type import SemanticType
 
 AMRFinderPlusDatabase = SemanticType("AMRFinderPlusDatabase")
+ARMFinderPlusAnnotation = SemanticType("ARMFinderPlusAnnotation")

q2_amr/amrfinderplus/types/tests/data/annotation/amr_annotation.tsv

@@ -0,0 +1,3 @@
+Protein identifier	Gene symbol	Sequence name	Scope	Element type	Element subtype	Class	Subclass	Method	Target length	Reference sequence length	% Coverage of reference sequence	% Identity to reference sequence	Alignment length	Accession of closest sequence	Name of closest sequence	HMM id	HMM description
+aph3pp-Ib_partial_5p_neg	aph(3'')-Ib	aminoglycoside O-phosphotransferase APH(3'')-Ib	core	AMR	AMR	AMINOGLYCOSIDE	STREPTOMYCIN	PARTIALP	225	267	81.27	100.00	217	WP_001082319.1	aminoglycoside O-phosphotransferase APH(3'')-Ib	NF032896.1	APH(3'') family aminoglycoside O-phosphotransferase
+blaOXA-436_partial	blaOXA	OXA-48 family class D beta-lactamase	core	AMR	AMR	BETA-LACTAM	BETA-LACTAM	PARTIALP	233	265	87.92	100.00	233	WP_058842180.1	OXA-48 family carbapenem-hydrolyzing class D beta-lactamase OXA-436	NF012161.0	class D beta-lactamase

q2_amr/amrfinderplus/types/tests/data/annotation/amr_annotation_coordiantes.tsv

@@ -0,0 +1,3 @@
+Protein identifier	Contig id	Start	Stop	Strand	Gene symbol	Sequence name	Scope	Element type	Element subtype	Class	Subclass	Method	Target length	Reference sequence length	% Coverage of reference sequence	% Identity to reference sequence	Alignment length	Accession of closest sequence	Name of closest sequence	HMM id	HMM description
+NA	contig01	101	958	+	blaTEM-156	class A beta-lactamase TEM-156	core	AMR	AMR	BETA-LACTAM	BETA-LACTAM	ALLELEX	286	286	100.00	100.00	286	WP_061158039.1	class A beta-lactamase TEM-156	NA	NA
+NA	contig02	1	1191	+	blaPDC	PDC family class C beta-lactamase	core	AMR	AMR	BETA-LACTAM	CEPHALOSPORIN	BLASTX	397	397	100.00	99.75	397	WP_061189306.1	class C beta-lactamase PDC-114	NA	NA

q2_amr/amrfinderplus/types/tests/data/annotation/amr_annotation_wrong.tsv

@@ -0,0 +1 @@
+Incorrect Header 1  Incorrect Header 2  Incorrect Header 3

q2_amr/amrfinderplus/types/tests/test_types_formats_transformers.py

@@ -5,16 +5,71 @@
 #
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
+from qiime2.core.exceptions import ValidationError
 from qiime2.plugin.testing import TestPluginBase
 
-from q2_amr.amrfinderplus.types._format import AMRFinderPlusDatabaseDirectoryFormat
+from q2_amr.amrfinderplus.types._format import (
+    AMRFinderPlusDatabaseDirectoryFormat,
+    ARMFinderPlusAnnotationFormat,
+)
 
 
-class TestAMRFinderPlusDatabaseTypesAndFormats(TestPluginBase):
+class TestAMRFinderPlusTypesAndFormats(TestPluginBase):
     package = "q2_amr.amrfinderplus.types.tests"
 
     def test_amrfinderplus_database_directory_format_validate_positive(self):
         format = AMRFinderPlusDatabaseDirectoryFormat(
             self.get_data_path("database"), mode="r"
         )
         format.validate()
+
+    def test_amrfinderplus_annotation_format_validate_positive(self):
+        filepath = self.get_data_path("annotation/amr_annotation.tsv")
+        format = ARMFinderPlusAnnotationFormat(filepath, mode="r")
+        format.validate()
+
+    def test_amrfinderplus_annotation_format_validate_positive_coordinates(self):
+        filepath = self.get_data_path("annotation/amr_annotation_coordiantes.tsv")
+        format = ARMFinderPlusAnnotationFormat(filepath, mode="r")
+        format.validate()
+
+    def test_amrfinderplus_annotation_format_validation_error(self):
+        with self.assertRaises(ValidationError) as context:
+            path = self.get_data_path("annotation/amr_annotation_wrong.tsv")
+            format = ARMFinderPlusAnnotationFormat(path, mode="r")
+            format.validate()
+
+            header_coordinates = [
+                "Protein identifier",
+                "Contig id",
+                "Start",
+                "Stop",
+                "Strand",
+                "Gene symbol",
+                "Sequence name",
+                "Scope",
+                "Element type",
+                "Element subtype",
+                "Class",
+                "Subclass",
+                "Method",
+                "Target length",
+                "Reference sequence length",
+                "% Coverage of reference sequence",
+                "% Identity to reference sequence",
+                "Alignment length",
+                "Accession of closest sequence",
+                "Name of closest sequence",
+                "HMM id",
+                "HMM description",
+            ]
+            expected_message = (
+                "Header line does not match ARMFinderPlusAnnotation format. Must "
+                "consist of the following values: "
+                + ", ".join(header_coordinates)
+                + ".\nWhile Contig id, Start, Stop and Strand are optional."
+                + "\n\nFound instead: "
+                + "Incorrect Header 1, Incorrect Header 2, Incorrect Header 3"
+            )
+
+            self.assertEqual(str(context.exception), expected_message)

q2_amr/plugin_setup.py

@@ -30,6 +30,7 @@
 from q2_amr import __version__
 from q2_amr.amrfinderplus.types._format import (
     AMRFinderPlusDatabaseDirectoryFormat,
+    ARMFinderPlusAnnotationFormat,
     BinaryFormat,
     TextFormat,
 )
@@ -1145,6 +1146,7 @@
     AMRFinderPlusDatabaseDirectoryFormat,
     TextFormat,
     BinaryFormat,
+    ARMFinderPlusAnnotationFormat,
 )
 
 importlib.import_module("q2_amr.card.types._transformer")