debian/changelog

+q2-demux (2019.10.0-1) UNRELEASED; urgency=medium
+
+  * New upstream version
+
+ -- Liubov Chuprikova <chuprikovalv@gmail.com>  Sun, 29 Dec 2019 18:12:25 +0300
+
 q2-demux (2019.4.1-1) unstable; urgency=medium
 
   * Initial release (Closes: #930152)

q2_demux/__init__.py

@@ -9,6 +9,7 @@
 from ._demux import emp_single, emp_paired
 from ._subsample import subsample_single, subsample_paired
 from ._summarize import summarize
+from ._filter import filter_samples
 from ._version import get_versions
 
 
@@ -16,4 +17,4 @@ __version__ = get_versions()['version']
 del get_versions
 
 __all__ = ['emp_single', 'emp_paired', 'summarize',
-           'subsample_single', 'subsample_paired']
+           'subsample_single', 'subsample_paired', 'filter_samples']

q2_demux/_filter.py

+# ----------------------------------------------------------------------------
+# Copyright (c) 2016-2019, QIIME 2 development team.
+#
+# Distributed under the terms of the Modified BSD License.
+#
+# The full license is in the file LICENSE, distributed with this software.
+# ----------------------------------------------------------------------------
+
+import os
+
+import pandas as pd
+
+from qiime2 import Metadata
+from qiime2.util import duplicate
+from q2_types.per_sample_sequences import \
+    CasavaOneEightSingleLanePerSampleDirFmt
+
+from ._summarize import _PlotQualView
+
+
+def filter_samples(demux: _PlotQualView, metadata: Metadata,
+                   where: str = None, exclude_ids: bool = False) \
+                   -> CasavaOneEightSingleLanePerSampleDirFmt:
+    results = CasavaOneEightSingleLanePerSampleDirFmt()
+
+    paired = demux.paired
+    samples = demux.directory_format
+
+    ids_to_keep = metadata.get_ids(where=where)
+    if not ids_to_keep:
+        raise ValueError('No filtering requested.')
+    manifest = samples.manifest.view(pd.DataFrame)
+
+    if exclude_ids:
+        ids_to_keep = set(manifest.index) - set(ids_to_keep)
+
+    try:
+        for id in ids_to_keep:
+            forward = manifest.loc[id].forward
+            duplicate(forward, os.path.join(str(results),
+                      os.path.split(forward)[1]))
+            if paired:
+                reverse = manifest.loc[id].reverse
+                duplicate(reverse, os.path.join(str(results),
+                          os.path.split(reverse)[1]))
+    except KeyError:
+        raise ValueError(f'{id!r} is not a sample present in the '
+                         'demultiplexed data.')
+
+    return results

q2_demux/_summarize/_visualizer.py

@@ -25,7 +25,7 @@ TEMPLATES = pkg_resources.resource_filename('q2_demux', '_summarize')
 
 def _decode_qual_to_phred33(qual_str):
     # this function is adapted from scikit-bio
-    qual = np.fromstring(qual_str, dtype=np.uint8) - 33
+    qual = np.frombuffer(qual_str.encode('ascii'), dtype=np.uint8) - 33
     return qual
 
 

q2_demux/_version.py

@@ -23,9 +23,9 @@ def get_keywords():
     # setup.py/versioneer.py will grep for the variable names, so they must
     # each be defined on a line of their own. _version.py will just call
     # get_keywords().
-    git_refnames = " (tag: 2019.4.1)"
-    git_full = "7d08f111ea34d99d7eb77a3583eaf839ecfde05b"
-    git_date = "2019-05-08 16:42:34 -0700"
+    git_refnames = " (tag: 2019.10.0)"
+    git_full = "aec76a7d22d7126b57b99da259d752e72e99f148"
+    git_date = "2019-11-01 01:04:23 +0000"
     keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
     return keywords
 

q2_demux/plugin_setup.py

@@ -9,8 +9,10 @@
 import importlib
 
 from qiime2.plugin import (
-    Plugin, MetadataColumn, Categorical, Bool, Int, Float, Range, Citations
+    Plugin, Metadata, MetadataColumn, Categorical, Bool, Str, Int, Float,
+    Range, Citations, TypeMatch
 )
+
 from q2_types.sample_data import SampleData
 from q2_types.per_sample_sequences import (
     SequencesWithQuality, PairedEndSequencesWithQuality,
@@ -228,4 +230,43 @@ plugin.methods.register_function(
                  'sequences after subsampling.')
 )
 
+T = TypeMatch([SequencesWithQuality, PairedEndSequencesWithQuality,
+               JoinedSequencesWithQuality])
+plugin.methods.register_function(
+    function=q2_demux.filter_samples,
+    inputs={'demux': SampleData[T]},
+    parameters={'metadata': Metadata,
+                'where': Str,
+                'exclude_ids': Bool},
+    outputs=[
+        ('filtered_demux', SampleData[T])
+    ],
+    input_descriptions={
+        'demux': 'The demultiplexed data from which samples should be '
+        'filtered.'
+    },
+    parameter_descriptions={
+        'metadata': 'Sample metadata indicating which sample ids to filter. '
+                    'The optional `where` parameter may be used to filter ids '
+                    'based on specified conditions in the metadata. The '
+                    'optional `exclude_ids` parameter may be used to exclude '
+                    'the ids specified in the metadata from the filter.',
+        'where': 'Optional SQLite WHERE clause specifying sample metadata '
+                 'criteria that must be met to be included in the filtered '
+                 'data. If not provided, all samples in `metadata` that are '
+                 'also in the demultiplexed data will be retained.',
+        'exclude_ids': 'Defaults to False. If True, the samples selected by '
+                       'the `metadata` and optional `where` parameter will be '
+                       'excluded from the filtered data.',
+    },
+    output_descriptions={
+        'filtered_demux': 'Filtered demultiplexed data.'
+    },
+    name='Filter samples out of demultiplexed data.',
+    description='Filter samples indicated in given metadata out of '
+                'demultiplexed data. Specific samples can be further selected '
+                'with the WHERE clause, and the `exclude_ids` parameter '
+                'allows for filtering of all samples not specified.',
+)
+
 importlib.import_module('q2_demux._transformer')

q2_demux/tests/data/filter_samples_paired_end/dir_fmt/MANIFEST

+sample-id,filename,direction
+sample1,sample1_1_L001_R1_001.fastq.gz,forward
+sample1,sample1_1_L001_R2_001.fastq.gz,reverse
+sample2,sample2_2_L001_R1_001.fastq.gz,forward
+sample2,sample2_2_L001_R2_001.fastq.gz,reverse

q2_demux/tests/data/filter_samples_paired_end/dir_fmt/metadata.yml

+phred-offset: 33

q2_demux/tests/data/filter_samples_paired_end/filter_all.tsv

+#SampleID	Study
+sample1	A
+sample2	B

q2_demux/tests/data/filter_samples_paired_end/filter_none.tsv

+#SampleID	Study
+1	A

q2_demux/tests/data/filter_samples_paired_end/filter_subset.tsv

+#SampleID	Study
+sample1	A

q2_demux/tests/data/filter_samples_single_end/dir_fmt/MANIFEST

+sample-id,filename,direction
+# direction is not meaningful in this file as these
+# data may be derived from forward, reverse, or
+# joined reads
+sample1,sample1_1_L001_R1_001.fastq.gz,forward
+sample2,sample2_2_L001_R1_001.fastq.gz,forward

q2_demux/tests/data/filter_samples_single_end/dir_fmt/metadata.yml

+phred-offset: 33

q2_demux/tests/data/filter_samples_single_end/filter_all.tsv

+#SampleID	Study
+sample1	A
+sample2	B