cutseq 0.0.5__tar.gz → 0.0.7__tar.gz

{cutseq-0.0.5 → cutseq-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cutseq
-Version: 0.0.5
+Version: 0.0.7
 Summary: Automatically cut adapter / barcode / UMI from NGS data
 Home-page: https://github.com/y9c/cutseq
 License: MIT

{cutseq-0.0.5 → cutseq-0.0.7}/cutseq/run.py

@@ -7,6 +7,7 @@
 # Created: 2024-04-19 18:57
 
 import argparse
+import importlib.metadata
 import logging
 import re
 import subprocess
@@ -26,11 +27,13 @@ from cutadapt.modifiers import (
     PairedEndRenamer,
     QualityTrimmer,
     Renamer,
+    SingleEndModifier,
     SuffixRemover,
     UnconditionalCutter,
 )
 from cutadapt.pipeline import PairedEndPipeline, SingleEndPipeline
 from cutadapt.predicates import Predicate, TooShort
+from cutadapt.report import Statistics
 from cutadapt.runners import make_runner
 from cutadapt.steps import (
     PairedEndFilter,
@@ -40,6 +43,54 @@ from cutadapt.steps import (
 )
 from cutadapt.utils import Progress
 
+#  monkey patching ....
+original_method = Statistics._collect_modifier
+
+
+def patched_problematic_method(self, *args, **kwargs):
+    try:
+        return original_method(self, *args, **kwargs)
+    except AssertionError:
+        pass
+
+
+Statistics._collect_modifier = patched_problematic_method
+
+## Enhnace function for cutadapt
+
+
+class IsUntrimmedAny(Predicate):
+    """
+    Select reads for which no adapter match was found
+    """
+
+    def __init__(self, ref_adapters):
+        self.ref_adapters = ref_adapters
+
+    def __repr__(self):
+        return "IsUntrimmedAny()"
+
+    def test(self, read, info):
+        # check not all adapters with ref_adapters are exist in the matches
+        match_adapters = [match.adapter for match in info.matches]
+        if any([adapter not in match_adapters for adapter in self.ref_adapters]):
+            return True
+        return False
+
+
+class ReverseComplementConverter(SingleEndModifier):
+    def __init__(self):
+        self.rcd = False
+
+    def __repr__(self):
+        return f"UnconditionalCutter(length={self.length})"
+
+    def __call__(self, read, info):
+        return read.reverse_complement()
+
+
+__version__ = importlib.metadata.version(__package__ or __name__)
+
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s -  %(levelname)s - %(message)s",
@@ -125,25 +176,6 @@ class CutadaptConfig:
         self.threads = 1
 
 
-class IsUntrimmedRef(Predicate):
-    """
-    Select reads for which no adapter match was found
-    """
-
-    def __init__(self, ref_adapters):
-        self.ref_adapters = ref_adapters
-
-    def __repr__(self):
-        return "IsUntrimmedRef()"
-
-    def test(self, read, info):
-        # check not all adapters with ref_adapters are exist in the matches
-        match_adapters = [match.adapter for match in info.matches]
-        if any([adapter not in match_adapters for adapter in self.ref_adapters]):
-            return True
-        return False
-
-
 def run_steps(steps, dry_run=False):
     if dry_run:
         print(
@@ -222,6 +254,10 @@ def pipeline_single(input1, output1, short1, untrimmed1, barcode, settings):
         QualityTrimmer(cutoff_front=0, cutoff_back=settings.min_quality),
     )
 
+    # step 9: reverse complement the read
+    if settings.reverse_complement:
+        modifiers.append(ReverseComplementConverter())
+
     inpaths = InputPaths(input1)
 
     with make_runner(inpaths, cores=settings.threads) as runner:
@@ -251,7 +287,7 @@ def pipeline_single(input1, output1, short1, untrimmed1, barcode, settings):
             steps.append(
                 # TODO: --max-n=0 support
                 SingleEndFilter(
-                    IsUntrimmedRef(ref_adapters),
+                    IsUntrimmedAny(ref_adapters),
                     outfiles.open_record_writer(untrimmed1, interleaved=False),
                 ),
             )
@@ -406,6 +442,10 @@ def pipeline_paired(
         )
     )
 
+    # step 9: reverse complement the read
+    if settings.reverse_complement:
+        modifiers.append((ReverseComplementConverter(), ReverseComplementConverter()))
+
     inpaths = InputPaths(input1, input2)
 
     with make_runner(inpaths, cores=settings.threads) as runner:
@@ -432,10 +472,10 @@ def pipeline_paired(
             steps.append(
                 # TODO: --max-n=0 support
                 PairedEndFilter(
-                    IsUntrimmedRef([adapter_inline5])
+                    IsUntrimmedAny([adapter_inline5])
                     if barcode.inline5.len > 0
                     else None,
-                    IsUntrimmedRef([adapter_inline3])
+                    IsUntrimmedAny([adapter_inline3])
                     if barcode.inline3.len > 0
                     else None,
                     outfiles.open_record_writer(
@@ -463,6 +503,7 @@ def run_cutseq(args):
     settings.threads = args.threads
     settings.min_length = args.min_length
     settings.dry_run = args.dry_run
+    settings.reverse_complement = args.reverse_complement
     if len(args.input_file) == 1:
         pipeline_single(
             args.input_file[0],
@@ -565,6 +606,12 @@ def main():
 
     parser.add_argument("--trim-polyA", action="store_true", help="Trim polyA tail.")
 
+    parser.add_argument(
+        "--reverse-complement",
+        action="store_true",
+        help="Reverse complement the reads.",
+    )
+
     parser.add_argument(
         "-t",
         "--threads",
@@ -578,6 +625,11 @@ def main():
         action="store_true",
         help="Print command instead of running it.",
     )
+
+    parser.add_argument(
+        "-V", "--version", action="version", version=f"%(prog)s {__version__}"
+    )
+
     args = parser.parse_args()
 
     if args.adapter_name is not None:

{cutseq-0.0.5 → cutseq-0.0.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cutseq"
-version = "0.0.5"
+version = "0.0.7"
 description = "Automatically cut adapter / barcode / UMI from NGS data"
 authors = ["Ye Chang <yech1990@gmail.com>"]
 license = "MIT"