Merge pull request #9 from USDA-ARS-GBRU/reversed_primers

Added support for reversed primers
USDA-ARS-GBRU · Dec 10, 2019 · a2a2e7b · a2a2e7b
2 parents debce44 + 672ae7b
commit a2a2e7b
Show file tree

Hide file tree

Showing 7 changed files with 36 additions and 58 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -1,7 +1,7 @@
 language: python
 dist: trusty
 sudo: false
-  
+
 # command to install dependencies
 before_install:
  - wget -q https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh
@@ -10,8 +10,8 @@ before_install:
  - export PATH="$MINICONDAS/bin:$PATH"
  - conda config --set always_yes yes
  - conda update -q conda
- - wget https://raw.githubusercontent.com/qiime2/environment-files/master/latest/staging/qiime2-latest-py35-linux-conda.yml
- - conda env create -n test-env --file qiime2-latest-py35-linux-conda.yml
+ - wget https://raw.githubusercontent.com/qiime2/environment-files/master/latest/staging/qiime2-latest-py36-linux-conda.yml
+ - conda env create -n test-env --file qiime2-latest-py36-linux-conda.yml
  - source activate test-env
 install:
   - conda config --add channels bioconda
@@ -28,5 +28,3 @@ script:
 
 after_success:
   - codecov
-
-
diff --git a/README.rst b/README.rst
@@ -52,7 +52,7 @@ Requirements/Dependencies
 -------------------------
 
 * Qiime2 is required to run Q2-itsxpress (for stand alone software see ITSxpress_)
-* To install Qiime2 follow these instructions: https://docs.qiime2.org/2018.8/install/
+* To install Qiime2 follow these instructions: https://docs.qiime2.org/2019.10/install/
 
 Q2_itsxpress Installation
 -------------------------
@@ -61,7 +61,7 @@ Q2_itsxpress Installation
 
 .. code-block:: bash
 
-  source activate qiime2-2018.8
+  source activate qiime2-2019.10
 
 2. Install Q2_itsxpress using BioConda_. Be sure to install Q2_itsxpres in the Qiime2 environment.
 

diff --git a/meta.yaml b/meta.yaml
diff --git a/q2_itsxpress/_itsxpress.py b/q2_itsxpress/_itsxpress.py
@@ -38,6 +38,7 @@ def _set_fastqs_and_check(fastq: str,
                           fastq2: str,
                           sample_id: str,
                           single_end: bool,
+                          reversed_primers: bool,
                           threads: int) -> object:
     """Checks and writes the fastqs as well as if they are paired end, interleaved and single end.
 
@@ -69,14 +70,16 @@ def _set_fastqs_and_check(fastq: str,
         # Create SeqSample objects and merge if needed.
     if paired_end and interleaved:
         sobj = itsxpress.SeqSamplePairedInterleaved(fastq=fastq,
-                                                    tempdir=None)
+                                                    tempdir=None,
+                                                    reversed_primers=reversed_primers)
         sobj._merge_reads(threads=threads)
         return sobj
 
     elif paired_end and not interleaved:
         sobj = itsxpress.SeqSamplePairedNotInterleaved(fastq=fastq,
                                                        fastq2=fastq2,
-                                                       tempdir=None)
+                                                       tempdir=None,
+                                                       reversed_primers=reversed_primers)
         sobj._merge_reads(threads=threads)
         return sobj
 
@@ -116,6 +119,7 @@ def trim_single(per_sample_sequences: SingleLanePerSampleSingleEndFastqDirFmt,
                    region=region,
                    paired_in=False,
                    paired_out=False,
+                   reversed_primers=False,
                    cluster_id=cluster_id)
     return results
 
@@ -125,13 +129,15 @@ def trim_pair(per_sample_sequences: SingleLanePerSamplePairedEndFastqDirFmt,
               region: str,
               taxa: str = "F",
               threads: int = 1,
+              reversed_primers: bool = False,
               cluster_id: float = default_cluster_id) -> CasavaOneEightSingleLanePerSampleDirFmt:
     results = main(per_sample_sequences=per_sample_sequences,
                    threads=threads,
                    taxa=taxa,
                    region=region,
                    paired_in=True,
                    paired_out=False,
+                   reversed_primers=reversed_primers,
                    cluster_id=cluster_id)
     return results
 
@@ -140,13 +146,15 @@ def trim_pair_output_unmerged(per_sample_sequences: SingleLanePerSamplePairedEnd
               region: str,
               taxa: str = "F",
               threads: int = 1,
+              reversed_primers: bool = False,
               cluster_id: float = default_cluster_id) -> CasavaOneEightSingleLanePerSampleDirFmt:
     results = main(per_sample_sequences=per_sample_sequences,
                    threads=threads,
                    taxa=taxa,
                    region=region,
                    paired_in=True,
                    paired_out=True,
+                   reversed_primers=reversed_primers,
                    cluster_id=cluster_id)
     return results
 # The ITSxpress handling
@@ -156,6 +164,7 @@ def main(per_sample_sequences,
          region: str,
          paired_in: bool,
          paired_out: bool,
+         reversed_primers: bool,
          cluster_id: float) -> CasavaOneEightSingleLanePerSampleDirFmt:
     """The main communication between the plugin and the ITSxpress program.
 
@@ -190,6 +199,7 @@ def main(per_sample_sequences,
             fastq2=sample.reverse if paired_in else None,
             sample_id=sample.Index,
             single_end=paired_out,
+            reversed_primers=reversed_primers,
             threads=threads)
         # Deduplicate
         if math.isclose(cluster_id, 1,rel_tol=1e-05):

diff --git a/q2_itsxpress/plugin_setup.py b/q2_itsxpress/plugin_setup.py
@@ -8,6 +8,7 @@
                            Int,
                            Float,
                            Range,
+                           Bool,
                            Citations)
 
 from q2_itsxpress._itsxpress import (trim_single,
@@ -17,19 +18,20 @@
 
 plugin = Plugin(
     name='itsxpress',
-    version='1.7.4',
+    version='1.8.0',
     package='q2_itsxpress',
     website='https://github.com/USDA-ARS-GBRU/q2_itsxpress             '
             'ITSxpress: https://github.com/USDA-ARS-GBRU/itsxpress',
-    description='ITSxpress trims amplicon reads down to the just their ITS region. '
+    description='ITSxpress trims amplicon reads down to their ITS region. '
                 'ITSxpress is designed to support the calling of exact sequence variants '
                 'rather than OTUs. This newer method of sequence error-correction requires '
                 'quality score data from each sequence, so each input sequence must be trimmed. '
                 'ITSxpress makes this possible by taking FASTQ data, de-replicating the '
                 'sequences then identifying the start and stop sites using HMMSearch. '
                 'Results are parsed and the trimmed files are returned. '
-                'The ITS 1, ITS2 or the entire ITS region including the 5.8s rRNA gene can be selected. '
-                'ITSxpress uses the hmm models from ITSx so results are comparable.',
+                'The ITS 1, ITS2 or the entire ITS region including the 5.8s rRNA'
+                'gene can be selected. ALL requires very long reads so it is not routinely'
+                'used with Illumina data. ITSxpress uses the hmm models from ITSx so results are comparable.',
     short_description='Plugin for using ITSxpress to rapidly trim the\n'
                       'internally transcribed spacer (ITS) region of FASTQ files.',
     citations=Citations.load('citations.bib', package='q2_itsxpress')
@@ -89,6 +91,7 @@
     parameters={'region': Str % Choices(['ITS2', 'ITS1', 'ALL']),
                 'taxa': Str % Choices(taxaList),
                 'threads': Int,
+                'reversed_primers': Bool,
                 'cluster_id': Float % Range(0.97, 1.0, inclusive_start=True, inclusive_end=True)},
     outputs=[('trimmed', SampleData[JoinedSequencesWithQuality])],
     input_descriptions={'per_sample_sequences': 'The artifact that contains the sequence file(s). '
@@ -98,7 +101,8 @@
         'region': ('\nThe regions ITS2, ITS1, and ALL that can be selected from.'),
         'taxa': ('\nThe selected taxonomic group sequenced that can be selected from.'),
         'threads': ('\nThe number of processor threads to use in the run.'),
-        'cluster_id': ('\nThe percent identity for clustering reads, set to 1 for exact dereplication.')
+        'cluster_id': ('\nThe percent identity for clustering reads, set to 1 for exact dereplication.'),
+        'reversed_primers': ('\n Primers are in reverse orientation as in Taylor et al. 2016, DOI:10.1128/AEM.02576-16.')
     },
     output_descriptions={'trimmed': 'The resulting trimmed sequences from ITSxpress'},
     name='Trim paired-end reads, output merged reads for use with Deblur',
@@ -136,6 +140,7 @@
     parameters={'region': Str % Choices(['ITS2', 'ITS1', 'ALL']),
                 'taxa': Str % Choices(taxaList),
                 'threads': Int,
+                'reversed_primers': Bool,
                 'cluster_id': Float % Range(0.97, 1.0, inclusive_start=True, inclusive_end=True)},
     outputs=[('trimmed', SampleData[PairedEndSequencesWithQuality])],
     input_descriptions={'per_sample_sequences': 'The artifact that contains the sequence file(s). '
@@ -145,7 +150,8 @@
         'region': ('\nThe regions ITS2, ITS1, and ALL that can be selected from.'),
         'taxa': ('\nThe selected taxonomic group sequenced that can be selected from.'),
         'threads': ('\nThe number of processor threads to use in the run.'),
-        'cluster_id': ('\nThe percent identity for clustering reads, set to 1 for exact dereplication.')
+        'cluster_id': ('\nThe percent identity for clustering reads, set to 1 for exact dereplication.'),
+        'reversed_primers': ('\n Primers are in reverse orientation as in Taylor et al. 2016, DOI:10.1128/AEM.02576-16.')
     },
     output_descriptions={'trimmed': 'The resulting trimmed sequences from ITSxpress'},
     name='Trim paired-end reads, output unmerged reads for use with Dada2',

diff --git a/setup.py b/setup.py
@@ -2,7 +2,7 @@
 
 setup(
     name='q2_itsxpress',
-    version='1.7.4',
+    version='1.8.0',
     packages=['q2_itsxpress'],
     author='Adam R. Rivers, Kyle C. Weber',
     author_email='adam.rivers@ars.usda.gov, kweber1@ufl.edu',
@@ -19,7 +19,7 @@
     python_requires=">3.5",
     include_package_data=True,
     install_requires=[
-        'itsxpress>=1.7.2',
+        'itsxpress>=1.8.0',
         'qiime2',
         'pandas',
     ],

diff --git a/tests/test_main.py b/tests/test_main.py
@@ -78,6 +78,7 @@ def test_single(self):
                                                    fastq2=None,
                                                    sample_id=sample.Index,
                                                    single_end=True,
+                                                   reversed_primers=False,
                                                    threads=1)
             self.assertTrue("4774-1-MSITS3" in obs.fastq)
 
@@ -88,6 +89,7 @@ def test_paired(self):
                                                    fastq2=sample.reverse,
                                                    sample_id=sample.Index,
                                                    single_end=True,
+                                                   reversed_primers=False,
                                                    threads=1)
             self.assertTrue("4774-1-MSITS3" in obs.fastq)
 
@@ -98,6 +100,7 @@ def test_paired_unmerged(self):
                                                    fastq2=sample.reverse,
                                                    sample_id=sample.Index,
                                                    single_end=False,
+                                                   reversed_primers=False,
                                                    threads=1)
             self.assertTrue("4774-1-MSITS3" in obs.fastq)
             self.assertTrue("4774-1-MSITS3" in obs.fastq2)
@@ -109,11 +112,13 @@ def test_trim_pair_no_bb(self):
                                                                         fastq2=sample.reverse,
                                                                         sample_id=sample.Index,
                                                                         single_end=False,
+                                                                        reversed_primers=False,
                                                                         threads=1))
             raises(ValueError, lambda: _itsxpress._set_fastqs_and_check(fastq=sample.forward,
                                                                         fastq2=sample.reverse,
                                                                         sample_id=sample.Index,
                                                                         single_end=True,
+                                                                        reversed_primers=False,
                                                                         threads=1))