Merge branch 'qiime2:dev' into st_fetch_busco_iss_74

q2_types/feature_data/_transformer.py

@@ -255,7 +255,7 @@ def _fastaformats_to_metadata(ff, constructor=skbio.DNA, lowercase=False):
 
 def _series_to_fasta_format(ff, data, sequence_type="DNA", lowercase=False):
     with ff.open() as f:
-        for id_, seq in data.iteritems():
+        for id_, seq in data.items():
             if sequence_type == "protein":
                 sequence = skbio.Protein(seq, metadata={'id': id_},
                                          lowercase=lowercase)

q2_types/feature_data_mag/__init__.py

@@ -22,6 +22,6 @@
         'OrthologAnnotationDirFmt', 'OrthologFileFmt', 'Contig'
         ]
 
-importlib.import_module('q2_types.feature_data._format')
-importlib.import_module('q2_types.feature_data._transformer')
-importlib.import_module('q2_types.feature_data._type')
+importlib.import_module('q2_types.feature_data_mag._format')
+importlib.import_module('q2_types.feature_data_mag._transformer')
+importlib.import_module('q2_types.feature_data_mag._type')

q2_types/feature_data_mag/_transformer.py

@@ -37,7 +37,7 @@ def _get_filename(full_path):
 def _series_to_fasta(series, ff, seq_type='DNA'):
     fp = os.path.join(str(ff), f'{series.name}.fasta')
     with open(fp, 'w') as fh:
-        for id_, seq in series.iteritems():
+        for id_, seq in series.items():
             if seq:
                 sequence = CONSTRUCTORS[seq_type](seq, metadata={'id': id_})
                 skbio.io.write(sequence, format='fasta', into=fh)

q2_types/feature_data_mag/_type.py

@@ -13,7 +13,8 @@
         )
 from qiime2.core.type import SemanticType
 
-from ..per_sample_sequences import ContigSequencesDirFmt
+from ..bowtie2 import Bowtie2IndexDirFmt
+from ..per_sample_sequences import ContigSequencesDirFmt, SingleBowtie2Index
 from ..plugin_setup import plugin
 
 
@@ -55,3 +56,8 @@
 plugin.register_artifact_class(
         FeatureData[KEGG],
         directory_format=OrthologAnnotationDirFmt)
+
+plugin.register_semantic_type_to_format(
+    FeatureData[SingleBowtie2Index],
+    artifact_format=Bowtie2IndexDirFmt
+)

q2_types/feature_data_mag/tests/test_type.py

@@ -8,14 +8,17 @@
 
 import unittest
 
+from q2_types.bowtie2 import Bowtie2IndexDirFmt
 from q2_types.feature_data import FeatureData
 from qiime2.plugin.testing import TestPluginBase
 
 from q2_types.feature_data_mag import (
         MAG, MAGSequencesDirFmt, OrthologAnnotationDirFmt,
         NOG, OG, KEGG, Contig
 )
-from q2_types.per_sample_sequences import ContigSequencesDirFmt
+from q2_types.per_sample_sequences import (
+    ContigSequencesDirFmt, SingleBowtie2Index
+)
 
 
 class TestTypes(TestPluginBase):
@@ -63,6 +66,12 @@ def test_kegg_registered_to_format(self):
                 FeatureData[KEGG],
                 OrthologAnnotationDirFmt)
 
+    def test_bowtie_index_semantic_type_to_format_registration(self):
+        self.assertSemanticTypeRegisteredToFormat(
+            FeatureData[SingleBowtie2Index],
+            Bowtie2IndexDirFmt
+        )
+
 
 if __name__ == '__main__':
     unittest.main()

q2_types/genome_data/_format.py

@@ -19,21 +19,21 @@ def _validate_(self, level):
 
 
 class GenesDirectoryFormat(model.DirectoryFormat):
-    genes = model.FileCollection(r'(.*\_)?genes[0-9]*\.(fa|fna|fasta)$',
+    genes = model.FileCollection(r'.+\.(fa|fna|fasta)$',
                                  format=DNAFASTAFormat)
 
     @genes.set_path_maker
     def genes_path_maker(self, genome_id):
-        return '%s_genes.fasta' % genome_id
+        return '%s.fasta' % genome_id
 
 
 class ProteinsDirectoryFormat(model.DirectoryFormat):
-    proteins = model.FileCollection(r'(.*\_)?proteins[0-9]*\.(fa|faa|fasta)$',
+    proteins = model.FileCollection(r'.+\.(fa|faa|fasta)$',
                                     format=ProteinFASTAFormat)
 
     @proteins.set_path_maker
     def proteins_path_maker(self, genome_id):
-        return '%s_proteins.fasta' % genome_id
+        return '%s.fasta' % genome_id
 
 
 class GFF3Format(model.TextFileFormat):
@@ -160,12 +160,12 @@ def _validate_(self, level):
 
 
 class LociDirectoryFormat(model.DirectoryFormat):
-    loci = model.FileCollection(r'(.*\_)?loci[0-9]*\.gff$',
+    loci = model.FileCollection(r'.+\.gff$',
                                 format=GFF3Format)
 
     @loci.set_path_maker
     def loci_path_maker(self, genome_id):
-        return '%s_loci.gff' % genome_id
+        return '%s.gff' % genome_id
 
 
 plugin.register_formats(

q2_types/genome_data/_transformer.py

@@ -42,7 +42,7 @@ def _8(ortholog_file: OrthologFileFmt) -> pd.DataFrame:
 def _series_to_fasta(series, ff, seq_type='DNA'):
     fp = os.path.join(ff.path, f'{series.name}.fasta')
     with open(fp, 'w') as fh:
-        for id_, seq in series.iteritems():
+        for id_, seq in series.items():
             if seq:
                 sequence = CONSTRUCTORS[seq_type](seq, metadata={'id': id_})
                 skbio.io.write(sequence, format='fasta', into=fh)

q2_types/genome_data/tests/test_format.py

@@ -54,77 +54,29 @@ def test_seed_ortholog_dir_fmt_collection(self):
             obj.validate()
 
     def test_genes_dirfmt_fa_with_suffix(self):
-        dirpath = self.get_data_path('genes-with-suffix')
+        dirpath = self.get_data_path('genes')
         fmt = GenesDirectoryFormat(dirpath, mode='r')
 
         fmt.validate()
 
-    def test_genes_dirfmt_fa_with_prefix(self):
-        dirpath = self.get_data_path('genes-with-prefix')
-        fmt = GenesDirectoryFormat(dirpath, mode='r')
-
-        fmt.validate()
-
-    def test_genes_dirfmt_fa_with_wrong_prefix(self):
-        dirpath = self.get_data_path('genes-with-wrong-prefix')
-        fmt = GenesDirectoryFormat(dirpath, mode='r')
-
-        with self.assertRaisesRegex(
-                ValidationError,
-                'Missing one or more files for GenesDirectoryFormat'
-        ):
-            fmt.validate()
-
     def test_proteins_dirfmt_fa_with_suffix(self):
-        dirpath = self.get_data_path('proteins-with-suffix')
-        fmt = ProteinsDirectoryFormat(dirpath, mode='r')
-
-        fmt.validate()
-
-    def test_proteins_dirfmt_fa_with_prefix(self):
-        dirpath = self.get_data_path('proteins-with-prefix')
+        dirpath = self.get_data_path('proteins')
         fmt = ProteinsDirectoryFormat(dirpath, mode='r')
 
         fmt.validate()
 
-    def test_proteins_dirfmt_fa_with_wrong_prefix(self):
-        dirpath = self.get_data_path('proteins-with-wrong-prefix')
-        fmt = ProteinsDirectoryFormat(dirpath, mode='r')
-
-        with self.assertRaisesRegex(
-            ValidationError,
-            'Missing one or more files for ProteinsDirectoryFormat'
-        ):
-            fmt.validate()
-
     def test_gff_format_positive_with_suffix(self):
-        filepath = self.get_data_path('loci-with-suffix/loci1.gff')
+        filepath = self.get_data_path('loci/loci1.gff')
         fmt = GFF3Format(filepath, mode='r')
 
         fmt.validate()
 
     def test_loci_dirfmt_with_suffix(self):
-        dirpath = self.get_data_path('loci-with-suffix')
-        fmt = LociDirectoryFormat(dirpath, mode='r')
-
-        fmt.validate()
-
-    def test_loci_dirfmt_with_prefix(self):
-        dirpath = self.get_data_path('loci-with-prefix')
+        dirpath = self.get_data_path('loci')
         fmt = LociDirectoryFormat(dirpath, mode='r')
 
         fmt.validate()
 
-    def test_loci_dirfmt_with_wrong_prefix(self):
-        dirpath = self.get_data_path('loci-with-wrong-prefix')
-        fmt = LociDirectoryFormat(dirpath, mode='r')
-
-        with self.assertRaisesRegex(
-                ValidationError,
-                'Missing one or more files for LociDirectoryFormat'
-        ):
-            fmt.validate()
-
     def test_gff_format_wrong_version(self):
         filepath = self.get_data_path('loci-invalid/loci-wrong-version.gff')
         with self.assertRaisesRegex(

q2_types/genome_data/tests/test_transformer.py

@@ -64,8 +64,8 @@ def seqs_to_df(seqs):
     def test_genes_to_dataframe(self):
         _, obs = self.transform_format(GenesDirectoryFormat, pd.DataFrame,
                                        filenames=[
-                                           'genes-with-suffix/genes1.fa',
-                                           'genes-with-suffix/genes2.fa'
+                                           'genes/genes1.fa',
+                                           'genes/genes2.fa'
                                        ])
         exp = self.seqs_to_df(self.genes)
         pd.testing.assert_frame_equal(exp, obs)
@@ -82,8 +82,8 @@ def test_proteins_to_dataframe(self):
             ProteinsDirectoryFormat,
             pd.DataFrame,
             filenames=[
-                'proteins-with-suffix/proteins1.faa',
-                'proteins-with-suffix/proteins2.faa'
+                'proteins/proteins1.faa',
+                'proteins/proteins2.faa'
             ])
         exp = self.seqs_to_df(self.proteins)
         pd.testing.assert_frame_equal(exp, obs)
@@ -100,7 +100,7 @@ def test_gff_to_interval_metadata_iterator(self):
         input, obs = self.transform_format(
             GFF3Format,
             IntervalMetadataIterator,
-            filename='loci-with-suffix/loci1.gff')
+            filename='loci/loci1.gff')
         exp = skbio.io.read(str(input), format='gff3')
 
         for o, e in zip(obs, exp):
@@ -109,7 +109,7 @@ def test_gff_to_interval_metadata_iterator(self):
     def test_interval_metadata_iterator_to_gff(self):
         transformer = self.get_transformer(IntervalMetadataIterator,
                                            GFF3Format)
-        filepath = self.get_data_path('loci-with-suffix/loci1.gff')
+        filepath = self.get_data_path('loci/loci1.gff')
         generator = skbio.io.read(filepath, format='gff3')
         input = IntervalMetadataIterator(generator)
 

q2_types/per_sample_sequences/_type.py

@@ -7,7 +7,7 @@
 # ----------------------------------------------------------------------------
 
 from q2_types.bowtie2 import Bowtie2IndexDirFmt
-from q2_types.feature_data import BLAST6
+from q2_types.feature_data import BLAST6, FeatureData
 from qiime2.plugin import SemanticType
 
 from ..genome_data import SeedOrthologDirFmt
@@ -31,11 +31,15 @@
 Contigs = SemanticType(
     'Contigs', variant_of=SampleData.field['type'])
 SingleBowtie2Index = SemanticType(
-    'SingleBowtie2Index', variant_of=SampleData.field['type'])
+    'SingleBowtie2Index',
+    variant_of=[SampleData.field['type'], FeatureData.field['type']]
+)
 MultiBowtie2Index = SemanticType(
     'MultiBowtie2Index', variant_of=SampleData.field['type'])
 AlignmentMap = SemanticType(
-    'AlignmentMap', variant_of=SampleData.field['type'])
+    'AlignmentMap',
+    variant_of=[SampleData.field['type'], FeatureData.field['type']]
+)
 MultiAlignmentMap = SemanticType(
     'MultiAlignmentMap', variant_of=SampleData.field['type'])
 
@@ -90,6 +94,10 @@
     SampleData[AlignmentMap],
     artifact_format=BAMDirFmt
 )
+plugin.register_semantic_type_to_format(
+    FeatureData[AlignmentMap],
+    artifact_format=BAMDirFmt
+)
 plugin.register_semantic_type_to_format(
     SampleData[MultiAlignmentMap],
     artifact_format=MultiBAMDirFmt