removal of RESCRIPt RNA types, etc..

rescript/get_data.py

@@ -16,7 +16,7 @@
 import qiime2
 from urllib.request import urlretrieve
 from urllib.error import HTTPError
-from .types._format import RNAFASTAFormat
+from q2_types.feature_data import RNAFASTAFormat
 
 
 def get_silva_data(ctx,

rescript/plugin_setup.py

@@ -29,7 +29,7 @@
                             filter_taxa)
 from .orient import orient_seqs
 from q2_types.feature_data import (FeatureData, Taxonomy, Sequence,
-                                   AlignedSequence)
+                                   AlignedSequence, RNASequence)
 from q2_types.tree import Phylogeny, Rooted
 from q2_feature_classifier.classifier import (_parameter_descriptions,
                                               _classify_parameters)
@@ -39,8 +39,8 @@
 from rescript._utilities import _rank_handles
 from rescript.types._format import (
     SILVATaxonomyFormat, SILVATaxonomyDirectoryFormat, SILVATaxidMapFormat,
-    SILVATaxidMapDirectoryFormat, RNAFASTAFormat, RNASequencesDirectoryFormat)
-from rescript.types._type import SILVATaxonomy, SILVATaxidMap, RNASequence
+    SILVATaxidMapDirectoryFormat)
+from rescript.types._type import SILVATaxonomy, SILVATaxidMap
 from rescript.types.methods import reverse_transcribe
 from rescript.ncbi import get_ncbi_data, _default_ranks, _allowed_ranks
 
@@ -858,17 +858,13 @@
 )
 
 # Registrations
-plugin.register_semantic_types(SILVATaxonomy, SILVATaxidMap, RNASequence)
+plugin.register_semantic_types(SILVATaxonomy, SILVATaxidMap)
 plugin.register_semantic_type_to_format(
     FeatureData[SILVATaxonomy],
     artifact_format=SILVATaxonomyDirectoryFormat)
 plugin.register_semantic_type_to_format(
     FeatureData[SILVATaxidMap],
     artifact_format=SILVATaxidMapDirectoryFormat)
-plugin.register_semantic_type_to_format(
-    FeatureData[RNASequence],
-    artifact_format=RNASequencesDirectoryFormat)
 plugin.register_formats(SILVATaxonomyFormat, SILVATaxonomyDirectoryFormat,
-                        SILVATaxidMapFormat, SILVATaxidMapDirectoryFormat,
-                        RNAFASTAFormat, RNASequencesDirectoryFormat)
+                        SILVATaxidMapFormat, SILVATaxidMapDirectoryFormat)
 importlib.import_module('rescript.types._transformer')

rescript/tests/test_screenseq.py

@@ -9,10 +9,9 @@
 
 import qiime2
 from qiime2.plugin.testing import TestPluginBase
-from q2_types.feature_data import DNAFASTAFormat, DNAIterator
+from q2_types.feature_data import DNAFASTAFormat, DNAIterator, RNAFASTAFormat
 
 from rescript.screenseq import cull_seqs
-from rescript.types._format import RNAFASTAFormat
 
 
 import_data = qiime2.Artifact.import_data

rescript/types/__init__.py

@@ -7,12 +7,10 @@
 # ----------------------------------------------------------------------------
 
 from ._format import (SILVATaxonomyFormat, SILVATaxonomyDirectoryFormat,
-                      SILVATaxidMapFormat, SILVATaxidMapDirectoryFormat,
-                      RNAFASTAFormat, RNASequencesDirectoryFormat)
-from ._type import SILVATaxonomy, SILVATaxidMap, RNASequence
+                      SILVATaxidMapFormat, SILVATaxidMapDirectoryFormat)
+from ._type import SILVATaxonomy, SILVATaxidMap
 
 
 __all__ = ['SILVATaxonomyFormat', 'SILVATaxonomyDirectoryFormat',
            'SILVATaxidMapFormat', 'SILVATaxidMapDirectoryFormat',
-           'SILVATaxonomy', 'SILVATaxidMap', 'RNAFASTAFormat',
-           'RNASequencesDirectoryFormat', 'RNASequence']
+           'SILVATaxonomy', 'SILVATaxidMap']

rescript/types/_format.py

@@ -6,13 +6,9 @@
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
 
-import itertools
-
 import qiime2.plugin.model as model
 from qiime2.plugin import ValidationError
 
-from rescript._utilities import _read_rna_fasta
-
 
 def _validate_record_len(cells, current_line_number, exp_len):
     if len(cells) != exp_len:
@@ -128,21 +124,3 @@ def _validate_(self, level):
 SILVATaxidMapDirectoryFormat = model.SingleFileDirectoryFormat(
     'SILVATaxidMapDirectoryFormat', 'silva_taxmap.tsv',
     SILVATaxidMapFormat)
-
-
-class RNAFASTAFormat(model.TextFileFormat):
-    def _validate(self, n_records=None):
-        generator = _read_rna_fasta(str(self))
-        if n_records is not None:
-            generator = itertools.islice(generator, n_records)
-        # just loop over contents with skbio generator
-        # skbio will raise an error if any record is not an RNA sequence
-        [i for i in generator]
-
-    def _validate_(self, level):
-        record_count_map = {'min': 5, 'max': None}
-        self._validate(record_count_map[level])
-
-
-RNASequencesDirectoryFormat = model.SingleFileDirectoryFormat(
-    'RNASequencesDirectoryFormat', 'rna-sequences.fasta', RNAFASTAFormat)

rescript/types/_transformer.py

@@ -8,10 +8,10 @@
 
 import pandas as pd
 from q2_types.feature_data import (
-    DNAFASTAFormat, DNAIterator, AlignedDNAFASTAFormat)
+    DNAFASTAFormat, DNAIterator, AlignedDNAFASTAFormat, RNAFASTAFormat)
 
 from ..plugin_setup import plugin
-from ._format import SILVATaxonomyFormat, SILVATaxidMapFormat, RNAFASTAFormat
+from ._format import SILVATaxonomyFormat, SILVATaxidMapFormat
 from rescript._utilities import (
     _rna_to_dna, _read_dna_fasta, _dna_iterator_to_aligned_fasta)
 

rescript/types/_type.py

@@ -14,5 +14,3 @@
     'SILVATaxonomy', variant_of=FeatureData.field['type'])
 SILVATaxidMap = SemanticType(
     'SILVATaxidMap', variant_of=FeatureData.field['type'])
-
-RNASequence = SemanticType('RNASequence', variant_of=FeatureData.field['type'])

rescript/types/methods.py

@@ -6,9 +6,7 @@
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
 
-from q2_types.feature_data import DNAFASTAFormat
-
-from rescript.types._format import RNAFASTAFormat
+from q2_types.feature_data import DNAFASTAFormat, RNAFASTAFormat
 from rescript._utilities import _rna_to_dna
 
 

rescript/types/tests/test_types_formats_transformers.py

@@ -15,15 +15,13 @@
 from qiime2.plugin import ValidationError
 from qiime2.plugin.testing import TestPluginBase
 from q2_types.feature_data import (
-    FeatureData, DNAFASTAFormat, DNAIterator,
-    AlignedDNAFASTAFormat, AlignedDNAIterator)
+    FeatureData, DNAIterator, AlignedDNAFASTAFormat, AlignedDNAIterator,
+    DNAFASTAFormat, RNAFASTAFormat)
 
 from rescript._utilities import _read_dna_fasta, _read_dna_alignment_fasta
 from rescript.types import (SILVATaxonomyFormat, SILVATaxonomyDirectoryFormat,
                             SILVATaxidMapFormat, SILVATaxidMapDirectoryFormat,
-                            SILVATaxonomy, SILVATaxidMap,
-                            RNAFASTAFormat, RNASequencesDirectoryFormat,
-                            RNASequence)
+                            SILVATaxonomy, SILVATaxidMap)
 
 
 class RescriptTypesTestPluginBase(TestPluginBase):
@@ -151,9 +149,6 @@ def test_silva_taxonomy_semantic_type_registration(self):
     def test_silva_taxid_map_type_registration(self):
         self.assertRegisteredSemanticType(SILVATaxidMap)
 
-    def test_rna_sequence_type_registration(self):
-        self.assertRegisteredSemanticType(RNASequence)
-
     def test_silva_taxonomy_semantic_type_to_format_registration(self):
         self.assertSemanticTypeRegisteredToFormat(
             FeatureData[SILVATaxonomy], SILVATaxonomyDirectoryFormat)
@@ -162,10 +157,6 @@ def test_silva_taxid_map_semantic_type_to_format_registration(self):
         self.assertSemanticTypeRegisteredToFormat(
             FeatureData[SILVATaxidMap], SILVATaxidMapDirectoryFormat)
 
-    def test_rna_sequence_semantic_type_to_format_registration(self):
-        self.assertSemanticTypeRegisteredToFormat(
-            FeatureData[RNASequence], RNASequencesDirectoryFormat)
-
 
 class TestSILVATransformers(RescriptTypesTestPluginBase):
 
@@ -211,23 +202,6 @@ def test_silva_taxidmap_format_to_pd_dataframe(self):
         pdt.assert_frame_equal(self.taxmap, obs[:1], check_dtype=False)
 
 
-class TestRNAFASTAFormat(RescriptTypesTestPluginBase):
-
-    def test_rna_fasta_format_validate_positive(self):
-        filepath = self.get_data_path('derep-test-rna.fasta')
-        format = RNAFASTAFormat(filepath, mode='r')
-        # These should both just succeed
-        format.validate('min')
-        format.validate('max')
-
-    def test_rna_fasta_format_validate_negative_is_dna(self):
-        filepath = pkg_resources.resource_filename(
-            'rescript.tests', 'data/derep-test.fasta')
-        with self.assertRaisesRegex(ValueError, 'Invalid character.*\'T\''):
-            format = RNAFASTAFormat(filepath, mode='r')
-            format.validate('min')
-
-
 class TestRNATransformers(RescriptTypesTestPluginBase):
 
     def setUp(self):
@@ -257,6 +231,7 @@ def test_rna_fasta_format_to_dna_iterator(self):
             self.assertEqual(observed, expected)
 
 
+
 class TestDNAIteratorTransformers(RescriptTypesTestPluginBase):
     def setUp(self):
         super().setUp()