Merge pull request #44 from USDA-ARS-GBRU/ITSxpressV2_flankingregions…

…_trim_gh_issue

Itsxpress v2 flankingregions trim gh issue

changelog.md

@@ -1,3 +1,11 @@
+2.0.2 (2024-3-20)
+------------------
+- Fixed a bug where the 3' end of the ITS region was not being trimmed from both forward and reverse reads if the read extended past the ITS region. This was due to the trimming being done at the start of both forward and reverse reads and not the end of each read. Thus if the read overlaped the opposite end of the ITS read, part of the conserved region would still be found on the ends of the forward and reverse read. This was fixed by trimming to just the ITS region for both forward and reverse reads. This bug did not affect the results of ASV calling with Dada2 becasue Dada2 ignored sequecne beyond the ITS region.  This fix will make the output more consistent with expectation.
+
+- Fixed a bug for submodule logging, where submodules were not logging to the main log file. This was fixed by passing the log file to the submodules and having them write to the same log file. This issue was introduced in version 2.0.0.
+
+- Added unit test to confirm that the 3' end of the ITS region is being trimmed from both forward and reverse reads.
+
 2.0.1 (2023-11-07)
 ------------------
 Fix single-end logic bug, which looked for a reverse read file even if single-end reads were provided because the single_end flag wasn't indicated by user.
@@ -89,4 +97,4 @@ New Features:
 -----------------
 - Fixed an indexing error causing ITS trimming to be off by 1 base.
 - Fixed error when raising file not found exception
-- removed old readme
+- removed old readme

itsxpress/Dedup.py

@@ -1,4 +1,5 @@
 import logging
+logger = logging.getLogger(__name__)
 import gzip
 import pyzstd as zstd
 import os
@@ -97,7 +98,24 @@ def _map_func(ziprecord):
             repseq = self.matchdict[record1.id]
             start, stop, tlen = itspos.get_position(repseq)
             r2start = tlen - stop
-            return record1[start:], record2[r2start:]
+            r2end = tlen - start #calculate end of R2
+            try:
+                if stop > tlen:
+                    record1_return = record1[start:]
+                elif stop <= tlen:
+                    record1_return = record1[start:stop]
+                else: 
+                    raise ValueError("An error occurred when trimming the forward read of {}".format(record1.id))
+                if r2end > tlen:
+                    record2_return = record2[r2start:]
+                elif r2end <= tlen:
+                    record2_return = record2[r2start:r2end]
+                else:
+                    raise ValueError("An error occurred when trimming the reverse read of {}".format(record2.id))
+            except ValueError as e:
+                logging.exception(e)
+                raise e
+            return record1_return, record2_return
 
         def _split_gen(gen):
             gen_a, gen_b = tee(gen, 2)

itsxpress/ITSposition.py

@@ -1,4 +1,5 @@
 import logging
+logger = logging.getLogger(__name__)
 
 class ItsPosition:
     """Class for ITS positional information derived from hmmserach domtable files.

itsxpress/SeqSample.py

@@ -1,5 +1,6 @@
 import os
 import logging
+logger = logging.getLogger(__name__)
 import tempfile
 import subprocess
 

itsxpress/SeqSamplePaired.py

@@ -4,6 +4,7 @@
 
 import subprocess
 import logging
+logger = logging.getLogger(__name__)
 import os
 import pyzstd as zstd
 

itsxpress/plugin_setup.py

@@ -18,7 +18,7 @@
 
 plugin = Plugin(
     name='itsxpress',
-    version='2.0.1',
+    version='2.0.2',
     package='itsxpress',
     website='https://github.com/USDA-ARS-GBRU/q2_itsxpress             '
             'ITSxpress: https://github.com/USDA-ARS-GBRU/itsxpress',

meta.yaml

@@ -1,5 +1,5 @@
 {% set name = "itsxpress" %}
-{% set version = "2.0.1" %}
+{% set version = "2.0.2" %}
 {% set file_ext = "tar.gz" %}
 {% set hash_type = "sha256" %}
 {% set hash_value = "b5797107ee3f21cbaba0b9625aa931741babdee3eeb5a3218a8b8bc9783e2e72" %}