cutseq 0.0.3__tar.gz → 0.0.4__tar.gz

{cutseq-0.0.3 → cutseq-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cutseq
-Version: 0.0.3
+Version: 0.0.4
 Summary: Automatically cut adapter / barcode / UMI from NGS data
 Home-page: https://github.com/y9c/cutseq
 License: MIT
@@ -19,9 +19,20 @@ Requires-Dist: cutadapt (>=4.8,<5.0)
 Project-URL: Repository, https://github.com/y9c/cutseq
 Description-Content-Type: text/markdown
 
-#✂️ CutSeq
+# ✂️ CutSeq
+
+[![Pypi Releases](https://img.shields.io/pypi/v/cutseq.svg)](https://pypi.python.org/pypi/cutseq)
+[![Downloads](https://pepy.tech/badge/cutseq)](https://pepy.tech/project/cutseq)
+
+# How to install?
+
+```bash
+pip install cutseq
+```
 
 ## How to use?
 
-`cutseq -a "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC" test_R1.fq.gz test_R2.fq.gz`
+```bash
+cutseq -a "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC" test_R1.fq.gz test_R2.fq.gz
+```
 

cutseq-0.0.4/README.md

@@ -0,0 +1,16 @@
+# ✂️ CutSeq
+
+[![Pypi Releases](https://img.shields.io/pypi/v/cutseq.svg)](https://pypi.python.org/pypi/cutseq)
+[![Downloads](https://pepy.tech/badge/cutseq)](https://pepy.tech/project/cutseq)
+
+# How to install?
+
+```bash
+pip install cutseq
+```
+
+## How to use?
+
+```bash
+cutseq -a "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC" test_R1.fq.gz test_R2.fq.gz
+```

cutseq-0.0.4/cutseq/run.py

@@ -0,0 +1,599 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright © 2024 Ye Chang yech1990@gmail.com
+# Distributed under terms of the GNU license.
+#
+# Created: 2024-04-19 18:57
+
+import argparse
+import logging
+import re
+import subprocess
+import sys
+
+from cutadapt.adapters import (
+    BackAdapter,
+    NonInternalBackAdapter,
+    NonInternalFrontAdapter,
+    PrefixAdapter,
+    RightmostFrontAdapter,
+)
+from cutadapt.files import InputPaths, OutputFiles
+from cutadapt.modifiers import (
+    AdapterCutter,
+    PairedEndRenamer,
+    QualityTrimmer,
+    Renamer,
+    SuffixRemover,
+    UnconditionalCutter,
+)
+from cutadapt.pipeline import PairedEndPipeline, SingleEndPipeline
+from cutadapt.predicates import IsUntrimmed, TooShort
+from cutadapt.runners import make_runner
+from cutadapt.steps import (
+    InfoFileWriter,
+    PairedEndFilter,
+    PairedEndSink,
+    PairedSingleEndStep,
+    SingleEndFilter,
+    SingleEndSink,
+)
+from cutadapt.utils import Progress
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s -  %(levelname)s - %(message)s",
+)
+
+
+def reverse_complement(b):
+    return "".join(
+        [dict(zip("ATGCNatgcn", "TACGNtacgn"))[x] for x in b[::-1] if x in "ATGCNatgcn"]
+    )
+
+
+def remove_fq_suffix(f):
+    suffixes_base = ["_R1_001", "_R2_001", "_R1", "_R2", ""]
+    suffixes = [
+        y + "." + x for x in ["fastq.gz", "fq.gz", "fastq", "fq"] for y in suffixes_base
+    ]
+    print(suffixes)
+    for suffix in suffixes:
+        if f.endswith(suffix):
+            return f.removesuffix(suffix)
+    return f
+
+
+class BarcodeSeq:
+    def __init__(self, seq):
+        self.fw = seq
+        self.rc = reverse_complement(seq)
+        self.len = len(seq)
+
+
+class BarcodeConfig:
+    """
+    Adapter scheme:
+    (p5)(inline5)(umi5)(mask5)(strand)(mask3)(umi3)(inline3)(p7)
+    """
+
+    def __init__(self, adapter=None):
+        self.strand = None
+        self.p5 = BarcodeSeq("")
+        self.p7 = BarcodeSeq("")
+        self.inline5 = BarcodeSeq("")
+        self.inline3 = BarcodeSeq("")
+        self.umi5 = BarcodeSeq("")
+        self.umi3 = BarcodeSeq("")
+        self.mask5 = BarcodeSeq("")
+        self.mask3 = BarcodeSeq("")
+        if adapter is not None:
+            self._parse_barcode(adapter)
+
+    def _parse_barcode(self, b):
+        m = re.match(
+            r"(?P<p5>[ATGCatgc]+)(\((?P<inline5>[ATGCatgc]+)\))?(?P<umi5>N*)(?P<mask5>X*)(?P<strand>-|>|<)(?P<mask3>X*)(?P<umi3>N*)(\((?P<inline3>[ATGCatgc]+)\))?(?P<p7>[ATGCatgc]+)",
+            b,
+        )
+        if m is None:
+            logging.error(f"barcode {b} is not valid")
+            sys.exit(1)
+        d = m.groupdict()
+        if d["inline5"] is None:
+            d["inline5"] = ""
+        if d["inline3"] is None:
+            d["inline3"] = ""
+        self.strand = "+" if d["strand"] == ">" else "-" if d["strand"] == "<" else None
+        self.p5 = BarcodeSeq(d["p5"])
+        self.p7 = BarcodeSeq(d["p7"])
+        self.inline5 = BarcodeSeq(d["inline5"])
+        self.inline3 = BarcodeSeq(d["inline3"])
+        self.umi5 = BarcodeSeq(d["umi5"])
+        self.umi3 = BarcodeSeq(d["umi3"])
+        self.mask5 = BarcodeSeq(d["mask5"])
+        self.mask3 = BarcodeSeq(d["mask3"])
+
+
+class CutadaptConfig:
+    def __init__(self):
+        self.rname_suffix = False
+        self.discarded_untrimmed = False
+        self.trim_polyA = False
+        self.min_length = 20
+        self.min_quality = 20
+        self.dry_run = False
+        self.threads = 1
+
+
+def run_steps(steps, dry_run=False):
+    if dry_run:
+        print(
+            " |\\\n".join([("    " + s if i > 0 else s) for i, s in enumerate(steps)])
+        )
+        process = subprocess.run("true", shell=True, capture_output=True)
+    else:
+        cmd = " | ".join(steps)
+        process = subprocess.run(cmd, shell=True, capture_output=True)
+    return process.stdout.decode(), process.stderr.decode()
+
+
+def pipeline_single(input1, output1, short1, untrimed1, barcode, settings):
+    modifiers = []
+    # step 1: remove suffix in the read name
+    modifiers.extend([SuffixRemover(".1"), SuffixRemover("/1")])
+    # step 2: remove adapter on the 5' end, artifact of template switching
+    modifiers.append(
+        AdapterCutter(
+            [
+                RightmostFrontAdapter(
+                    sequence=barcode.p5.fw, max_errors=0.25, min_overlap=10
+                )
+            ],
+            times=1,
+        )
+    )
+    # step 3: remove adapter on the 3' end, read though in the sequencing
+    modifiers.append(
+        AdapterCutter(
+            [BackAdapter(sequence=barcode.p7.fw, max_errors=0.2, min_overlap=3)],
+            times=2,
+        ),
+    )
+    # step 4: trim inline barcode
+    if barcode.inline5.len > 0:
+        modifiers.append(
+            AdapterCutter(
+                [PrefixAdapter(sequence=barcode.inline5.fw, max_errors=0.2)],
+                times=1,
+            )
+        )
+    if barcode.inline3.len > 0:
+        modifiers.append(UnconditionalCutter(-barcode.inline3.len))
+
+    # step 5: extract UMI
+    if barcode.umi5.len > 0:
+        modifiers.append(UnconditionalCutter(barcode.umi5.len))
+    if barcode.umi3.len > 0:
+        modifiers.append(UnconditionalCutter(-barcode.umi3.len))
+    if barcode.umi5.len + barcode.umi3.len > 0:
+        modifiers.append(Renamer("{id}_{cut_prefix}{cut_suffix}"))
+    else:
+        modifiers.append(Renamer("{id}"))
+
+    # step 6: mask tail in the RNA, which might be artifact of RT
+    if barcode.mask5.len > 0:
+        modifiers.append(UnconditionalCutter(barcode.mask5.len))
+    if barcode.mask3.len > 0:
+        modifiers.append(UnconditionalCutter(-barcode.mask3.len))
+    # step 7: trim polyA
+    if settings.trim_polyA:
+        if barcode.strand == "+":
+            modifiers.append(
+                AdapterCutter(
+                    [NonInternalBackAdapter(sequence="A" * 100, max_errors=0.15)]
+                )
+            )
+        elif barcode.strand == "-":
+            modifiers.append(
+                AdapterCutter(
+                    [NonInternalFrontAdapter(sequence="T" * 100, max_errors=0.15)]
+                )
+            )
+        else:
+            logging.info("No strand information provided, skip polyA trimming.")
+    # step 8: quality control, remove short reads
+    modifiers.append(
+        QualityTrimmer(cutoff_front=0, cutoff_back=settings.min_quality),
+    )
+
+    inpaths = InputPaths(input1)
+
+    with make_runner(inpaths, cores=settings.threads) as runner:
+        outfiles = OutputFiles(
+            proxied=settings.threads > 1,
+            qualities=runner.input_file_format().has_qualities(),
+            interleaved=False,
+        )
+        steps = [
+            # --info-file=info.txt
+            # PairedSingleEndStep(InfoFileWriter(outfiles.open_text("info.txt"))),
+            # -m 10
+            SingleEndFilter(
+                TooShort(settings.min_length), outfiles.open_record_writer(short1)
+            ),
+            # TODO: --max-n=0 support
+            # --discard-untrimmed
+            # SingleEndFilter( IsUntrimmed(), IsUntrimmed(), pair_filter_mode="any"),
+            # -o
+            SingleEndSink(outfiles.open_record_writer(output1, interleaved=False)),
+        ]
+        pipeline = SingleEndPipeline(modifiers, steps)
+        _stats = runner.run(pipeline, Progress(), outfiles)
+        # _ = stats.as_json()
+    outfiles.close()
+
+
+def pipeline_paired(
+    input1,
+    input2,
+    output1,
+    output2,
+    short1,
+    short2,
+    untrimed1,
+    untrimmed2,
+    barcode,
+    settings,
+):
+    modifiers = []
+    # step 1: remove suffix in the read name
+    modifiers.extend(
+        [
+            (SuffixRemover(".1"), SuffixRemover(".2")),
+            (SuffixRemover("/1"), SuffixRemover("/2")),
+        ]
+    )
+    # step 2: remove adapter on the 5' end, artifact of template switching
+    modifiers.append(
+        (
+            AdapterCutter(
+                [
+                    RightmostFrontAdapter(
+                        sequence=barcode.p5.fw, max_errors=0.25, min_overlap=10
+                    )
+                ],
+                times=1,
+            ),
+            AdapterCutter(
+                [
+                    RightmostFrontAdapter(
+                        sequence=barcode.p7.rc, max_errors=0.25, min_overlap=10
+                    )
+                ],
+                times=1,
+            ),
+        ),
+    )
+    # step 3: remove adapter on the 3' end, read though in the sequencing
+    modifiers.append(
+        (
+            AdapterCutter(
+                [BackAdapter(sequence=barcode.p7.fw, max_errors=0.2, min_overlap=3)],
+                times=2,
+            ),
+            AdapterCutter(
+                [BackAdapter(sequence=barcode.p5.rc, max_errors=0.2, min_overlap=3)],
+                times=2,
+            ),
+        ),
+    )
+    # step 4: trim inline barcode
+    if barcode.inline5.len > 0:
+        modifiers.append(
+            (
+                AdapterCutter(
+                    [PrefixAdapter(sequence=barcode.inline5.fw, max_errors=0.2)],
+                    times=1,
+                ),
+                UnconditionalCutter(-barcode.inline5.len),
+            )
+        )
+    if barcode.inline3.len > 0:
+        modifiers.append(
+            (
+                UnconditionalCutter(-barcode.inline3.len),
+                AdapterCutter(
+                    [BackAdapter(sequence=barcode.inline3.rc, max_errors=0.2)],
+                    times=1,
+                ),
+            )
+        )
+
+    # step 5: extract UMI
+    if barcode.umi5.len > 0:
+        modifiers.append(
+            (
+                UnconditionalCutter(barcode.umi5.len),
+                UnconditionalCutter(-barcode.umi5.len),
+            ),
+        )
+    if barcode.umi3.len > 0:
+        modifiers.append(
+            (
+                UnconditionalCutter(-barcode.umi3.len),
+                UnconditionalCutter(barcode.umi3.len),
+            )
+        )
+    if barcode.umi5.len + barcode.umi3.len > 0:
+        modifiers.append(PairedEndRenamer("{id}_{r1.cut_prefix}{r2.cut_prefix}"))
+    else:
+        modifiers.append(PairedEndRenamer("{id}"))
+
+    # step 6: mask tail in the RNA, which might be artifact of RT
+    if barcode.mask5.len > 0:
+        modifiers.append(
+            (
+                UnconditionalCutter(barcode.mask5.len),
+                UnconditionalCutter(-barcode.mask5.len),
+            )
+        )
+    if barcode.mask3.len > 0:
+        modifiers.append(
+            (
+                UnconditionalCutter(-barcode.mask3.len),
+                UnconditionalCutter(barcode.mask3.len),
+            )
+        )
+    # step 7: trim polyA
+    if settings.trim_polyA:
+        if barcode.strand == "+":
+            modifiers.append(
+                (
+                    AdapterCutter(
+                        [NonInternalBackAdapter(sequence="A" * 100, max_errors=0.15)]
+                    ),
+                    AdapterCutter(
+                        [NonInternalFrontAdapter(sequence="T" * 100, max_errors=0.15)]
+                    ),
+                )
+            )
+        elif barcode.strand == "-":
+            modifiers.append(
+                (
+                    AdapterCutter(
+                        [NonInternalFrontAdapter(sequence="T" * 100, max_errors=0.15)]
+                    ),
+                    AdapterCutter(
+                        [NonInternalBackAdapter(sequence="A" * 100, max_errors=0.15)]
+                    ),
+                )
+            )
+        else:
+            logging.info("No strand information provided, skip polyA trimming.")
+    # step 8: quality control, remove short reads
+    modifiers.append(
+        (
+            QualityTrimmer(cutoff_front=0, cutoff_back=settings.min_quality),
+            QualityTrimmer(cutoff_front=0, cutoff_back=settings.min_quality),
+        )
+    )
+
+    inpaths = InputPaths(input1, input2)
+
+    with make_runner(inpaths, cores=settings.threads) as runner:
+        outfiles = OutputFiles(
+            proxied=settings.threads > 1,
+            qualities=runner.input_file_format().has_qualities(),
+            interleaved=False,
+        )
+        steps = [
+            # --info-file=info.txt
+            # PairedSingleEndStep(InfoFileWriter(outfiles.open_text("info.txt"))),
+            # -m 10:10
+            PairedEndFilter(
+                TooShort(settings.min_length),
+                TooShort(settings.min_length),
+                outfiles.open_record_writer(short1, short2, interleaved=False),
+            ),
+            # TODO: --max-n=0 support
+            # --discard-untrimmed
+            # PairedEndFilter( IsUntrimmed(), IsUntrimmed(), pair_filter_mode="any"),
+            # -o ... -p ...
+            PairedEndSink(outfiles.open_record_writer(output1, output2)),
+        ]
+        pipeline = PairedEndPipeline(modifiers, steps)
+        _stats = runner.run(pipeline, Progress(), outfiles)
+        # _ = stats.as_json()
+    outfiles.close()
+
+
+def run_cutseq(args):
+    barcode_config = BarcodeConfig(args.adapter_scheme.upper())
+    settings = CutadaptConfig()
+    if args.with_rname_suffix:
+        settings.rname_suffix = True
+    if args.untrimmed_file is None:
+        settings.discarded_untrimmed = True
+    if args.trim_polyA:
+        settings.trim_polyA = True
+    settings.threads = args.threads
+    settings.min_length = args.min_length
+    settings.dry_run = args.dry_run
+    if len(args.input_file) == 1:
+        pipeline_single(
+            args.input_file[0],
+            args.output_file[0],
+            args.short_file[0],
+            args.untrimmed_file[0],
+            barcode_config,
+            settings,
+        )
+    else:
+        pipeline_paired(
+            args.input_file[0],
+            args.input_file[1],
+            args.output_file[0],
+            args.output_file[1],
+            args.short_file[0],
+            args.short_file[1],
+            args.untrimmed_file[0],
+            args.untrimmed_file[1],
+            barcode_config,
+            settings,
+        )
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Trim sequencing adapters from NGS data automatically."
+    )
+    # input file can be one or two for single or paired-end reads, but can not be more than two
+    parser.add_argument(
+        "input_file",
+        type=str,
+        nargs="+",
+        help="Input file path for NGS data, one or two files.",
+    )
+    # output file can be number of files matching the input files, if not provided it will generate based on the output prefix,
+    # if no output prefix provided it will generate based on the input file name
+    parser.add_argument(
+        "-a",
+        "--adapter-scheme",
+        type=str,
+        help="Adapter sequence configuration.",
+    )
+    parser.add_argument("-A", "--adapter-name", type=str, help="Built-in adapter name.")
+    parser.add_argument(
+        "-O",
+        "--output-prefix",
+        type=str,
+        help="Output file prefix for keep trimmed data.",
+    )
+    parser.add_argument(
+        "-o",
+        "--output-file",
+        type=str,
+        nargs="+",
+        help="Output file path for keep trimmed data.",
+    )
+
+    parser.add_argument(
+        "-q",
+        "--min-quality",
+        type=int,
+        default=20,
+        help="Minimum quality of the read tails in the reads to keep.",
+    )
+    # discard short reads
+    parser.add_argument(
+        "-S",
+        "--short-file",
+        type=str,
+        nargs="+",
+        help="Output file path for discarded too short data.",
+    )
+    parser.add_argument(
+        "-m",
+        "--min-length",
+        type=int,
+        default=20,
+        help="Minimum length of the reads to keep.",
+    )
+
+    parser.add_argument(
+        "--with-rname-suffix",
+        action="store_true",
+        help="R1 and R2 suffix cotains suffix. MGI platform.",
+    )
+    parser.add_argument(
+        "-U",
+        "--untrimmed-file",
+        type=str,
+        nargs="+",
+        help="Output file path for discarded reads without inline barcode.",
+    )
+
+    parser.add_argument("--trim-polyA", action="store_true", help="Trim polyA tail.")
+
+    parser.add_argument(
+        "-t",
+        "--threads",
+        type=int,
+        default=1,
+        help="Number of threads to use for trimming.",
+    )
+    parser.add_argument(
+        "-n",
+        "--dry-run",
+        action="store_true",
+        help="Print command instead of running it.",
+    )
+    args = parser.parse_args()
+
+    if args.adapter_name is not None:
+        if args.adapter_scheme is not None:
+            logging.info("Adapter scheme is provided, ignore adapter name.")
+        else:
+            if args.adapter_name.upper() == "TAKARAV2":
+                args.adapter_scheme = "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC"
+            elif args.adapter_name.upper() == "STRANDED":
+                args.adapter_scheme = "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC"
+            elif args.adapter_name.upper() == "TAKARAV3":
+                args.adapter_scheme = (
+                    "ACACGACGCTCTTCCGATCTXXX<XXXXXXNNNNNNNNAGATCGGAAGAGCACACGTC"
+                )
+            else:
+                logging.error("Adapter name is not valid.")
+                sys.exit(1)
+    elif args.adapter_scheme is None:
+        logging.error("Adapter scheme or name is required.")
+        sys.exit(1)
+
+    if len(args.input_file) > 2:
+        logging.error("Input file can not be more than two.")
+        sys.exit(1)
+
+    def validate_output_file(output_files, input_files, output_prefix, output_suffix):
+        default_format = ".fastq.gz"
+        r1 = "_" + output_suffix + "_R1" + default_format
+        r2 = "_" + output_suffix + "_R2" + default_format
+        if output_files:
+            if len(output_files) != len(input_files):
+                logging.error("Output file should be same as input file.")
+                sys.exit(1)
+            return output_files
+        elif output_prefix is not None:
+            if len(input_files) == 1:
+                return [output_prefix + r1]
+            else:
+                return [output_prefix + r1, output_prefix + r2]
+        else:
+            if len(input_files) == 1:
+                return [remove_fq_suffix(input_files[0]) + r1]
+            else:
+                return [
+                    remove_fq_suffix(input_files[0]) + r1,
+                    remove_fq_suffix(input_files[1]) + r2,
+                ]
+        return output_files
+
+    args.output_file = validate_output_file(
+        args.output_file, args.input_file, args.output_prefix, "trimmed"
+    )
+    args.short_file = validate_output_file(
+        args.short_file, args.input_file, args.output_prefix, "short"
+    )
+    args.untrimmed_file = (
+        validate_output_file(
+            args.untrimmed_file, args.input_file, args.output_prefix, "untrimmed"
+        )
+        if args.untrimmed_file is not None
+        else [None] * len(args.input_file)
+    )
+
+    run_cutseq(args)
+
+
+if __name__ == "__main__":
+    main()

cutseq-0.0.3/cutseq/run.py → cutseq-0.0.4/cutseq/run_cmd.py

@@ -40,23 +40,29 @@ def remove_fq_suffix(f):
     return f
 
 
+class BarcodeSeq:
+    def __init__(self, seq):
+        self.fw = seq
+        self.rc = reverse_complement(seq)
+        self.len = len(seq)
+
+
 class BarcodeConfig:
+    """
+    Adapter scheme:
+    (p5)(inline5)(umi5)(mask5)(strand)(mask3)(umi3)(inline3)(p7)
+    """
+
     def __init__(self, adapter=None):
         self.strand = None
-        self.p5_fw = ""
-        self.p5_rc = ""
-        self.p7_fw = ""
-        self.p7_rc = ""
-        self.inline5_fw = ""
-        self.inline5_rc = ""
-        self.inline5 = 0
-        self.inline3_fw = ""
-        self.inline3_rc = ""
-        self.inline3 = 0
-        self.umi5 = 0
-        self.umi3 = 0
-        self.mask5 = 0
-        self.mask3 = 0
+        self.p5 = BarcodeSeq("")
+        self.p7 = BarcodeSeq("")
+        self.inline5 = BarcodeSeq("")
+        self.inline3 = BarcodeSeq("")
+        self.umi5 = BarcodeSeq("")
+        self.umi3 = BarcodeSeq("")
+        self.mask5 = BarcodeSeq("")
+        self.mask3 = BarcodeSeq("")
         if adapter is not None:
             self._parse_barcode(adapter)
 
@@ -74,20 +80,14 @@ class BarcodeConfig:
         if d["inline3"] is None:
             d["inline3"] = ""
         self.strand = "+" if d["strand"] == ">" else "-" if d["strand"] == "<" else None
-        self.p5_fw = d["p5"]
-        self.p5_rc = reverse_complement(d["p5"])
-        self.p7_fw = d["p7"]
-        self.p7_rc = reverse_complement(d["p7"])
-        self.inline5_fw = d["inline5"] if d["inline5"] else ""
-        self.inline5_rc = reverse_complement(d["inline5"]) if d["inline5"] else ""
-        self.inline5 = len(d["inline5"])
-        self.inline3_fw = d["inline3"] if d["inline3"] else ""
-        self.inline3_rc = reverse_complement(d["inline3"]) if d["inline3"] else ""
-        self.inline3 = len(d["inline3"])
-        self.umi5 = len(d["umi5"])
-        self.umi3 = len(d["umi3"])
-        self.mask5 = len(d["mask5"])
-        self.mask3 = len(d["mask3"])
+        self.p5 = BarcodeSeq(d["p5"])
+        self.p7 = BarcodeSeq(d["p7"])
+        self.inline5 = BarcodeSeq(d["inline5"])
+        self.inline3 = BarcodeSeq(d["inline3"])
+        self.umi5 = BarcodeSeq(d["umi5"])
+        self.umi3 = BarcodeSeq(d["umi3"])
+        self.mask5 = BarcodeSeq(d["mask5"])
+        self.mask3 = BarcodeSeq(d["mask3"])
 
 
 class CutadaptConfig:
@@ -112,19 +112,19 @@ def run_cutadapt_PE(
     else:
         config_rname = ""
     steps.append(
-        f"{cutadapt}{config_rname} -e 0.25 -n 2 -O 10 -g '{barcode.p5_fw};rightmost' -G '{barcode.p7_rc};rightmost' --interleaved {input1} {input2}"
+        f"{cutadapt}{config_rname} -e 0.25 -n 2 -O 10 -g '{barcode.p5.fw};rightmost' -G '{barcode.p7.rc};rightmost' --interleaved {input1} {input2}"
     )
     # step 2: remove adapter on the 3' end, read though in the sequencing
     steps.append(
-        f"{cutadapt} -e 0.2 -n 2 -O 3 -a '{barcode.p7_fw}' -A '{barcode.p5_rc}' --interleaved -"
+        f"{cutadapt} -e 0.2 -n 2 -O 3 -a '{barcode.p7.fw}' -A '{barcode.p5.rc}' --interleaved -"
     )
     # step 3: trim inline barcode
     config_inline_args = []
-    if barcode.inline5 > 0:
-        config_inline_args.append(f"-g ^{barcode.inline5_fw} -U -{barcode.inline5}")
-    if barcode.inline3 > 0:
-        config_inline_args.append(f"-G ^{barcode.inline3_rc} -u -{barcode.inline3}")
-    if barcode.inline5 + barcode.inline3 > 0:
+    if barcode.inline5.len > 0:
+        config_inline_args.append(f"-g ^{barcode.inline5.fw} -U -{barcode.inline5.len}")
+    if barcode.inline3.len > 0:
+        config_inline_args.append(f"-G ^{barcode.inline3.rc} -u -{barcode.inline3.len}")
+    if barcode.inline5.len + barcode.inline3.len > 0:
         if settings.discarded_untrimmed:
             config_inline_args.append(
                 f"--untrimmed-output={discard1} --untrimmed-paired-output={discard2}"
@@ -132,16 +132,16 @@ def run_cutadapt_PE(
         config_inline = " ".join(config_inline_args)
         steps.append(f"{cutadapt} {config_inline} --interleaved -")
     # step 4: extract UMI
-    if barcode.umi5 + barcode.umi3 > 0:
+    if barcode.umi5.len + barcode.umi3.len > 0:
         steps.append(
-            f"{cutadapt} -u {barcode.umi5} -u -{barcode.umi3} -U {barcode.umi3} -U -{barcode.umi5} --rename='{{id}}_{{r1.cut_prefix}}{{r2.cut_prefix}}' --interleaved -"
+            f"{cutadapt} -u {barcode.umi5.len} -u -{barcode.umi3.len} -U {barcode.umi3.len} -U -{barcode.umi5.len} --rename='{{id}}_{{r1.cut_prefix}}{{r2.cut_prefix}}' --interleaved -"
         )
     else:
         steps.append(f"{cutadapt} --rename='{{id}}' --interleaved -")
     # step 5: mask tail in the RNA, which might be artifact of RT
-    if barcode.mask5 + barcode.mask3 > 0:
+    if barcode.mask5.len + barcode.mask3.len > 0:
         steps.append(
-            f"{cutadapt} -u {barcode.mask5} -u -{barcode.mask3} -U {barcode.mask3} -U -{barcode.mask5} --interleaved -"
+            f"{cutadapt} -u {barcode.mask5.len} -u -{barcode.mask3.len} -U {barcode.mask3.len} -U -{barcode.mask5.len} --interleaved -"
         )
     # step 6: trim polyA
     if settings.trim_polyA:
@@ -171,29 +171,29 @@ def run_cutadapt_SE(input1, output1, discard1, barcode, settings):
     else:
         config_rname = ""
     steps.append(
-        f"{cutadapt}{config_rname} -e 0.25 -n 2 -O 10 -g '{barcode.p5_fw};rightmost' {input1}"
+        f"{cutadapt}{config_rname} -e 0.25 -n 2 -O 10 -g '{barcode.p5.fw};rightmost' {input1}"
     )
     # step 2: remove adapter on the 3' end, read though in the sequencing
-    steps.append(f"{cutadapt} -e 0.2 -n 2 -O 3 -a '{barcode.p7_fw}' -")
+    steps.append(f"{cutadapt} -e 0.2 -n 2 -O 3 -a '{barcode.p7.fw}' -")
     # step 3: trim inline barcode
     config_inline_args = []
-    if barcode.inline3 > 0:
-        config_inline_args.append(f"-a {barcode.inline3_fw}$")
-    if barcode.inline5 > 0:
-        config_inline_args.append(f"-g ^{barcode.inline5_fw}")
-    if barcode.inline5 + barcode.inline3 > 0:
+    if barcode.inline3.len > 0:
+        config_inline_args.append(f"-a {barcode.inline3.fw}$")
+    if barcode.inline5.len > 0:
+        config_inline_args.append(f"-g ^{barcode.inline5.fw}")
+    if barcode.inline5.len + barcode.inline3.len > 0:
         if settings.discarded_untrimmed:
             config_inline_args.append(f"--untrimmed-output={discard1}")
 
         config_inline = " ".join(config_inline_args)
         steps.append(f"{cutadapt} {config_inline} -")
     # step 4: extract UMI
-    if barcode.umi5 + barcode.umi3 > 0:
+    if barcode.umi5.len + barcode.umi3.len > 0:
         steps.append(
-            f"{cutadapt} -u {barcode.umi5} -u -{barcode.umi3} --rename='{{id}}_{{cut_prefix}}{{cut_suffix}}' -"
+            f"{cutadapt} -u {barcode.umi5.len} -u -{barcode.umi3.len} --rename='{{id}}_{{cut_prefix}}{{cut_suffix}}' -"
         )
     # step 5: mask tail in the RNA, which might be artifact of RT
-    steps.append(f"{cutadapt} -u {barcode.mask5} -u -{barcode.mask3} -")
+    steps.append(f"{cutadapt} -u {barcode.mask5.len} -u -{barcode.mask3.len} -")
     # step 6: trim polyA
     if settings.trim_polyA:
         if barcode.strand == "+":
@@ -233,7 +233,6 @@ def run_cutseq(args):
     settings.threads = args.threads
     settings.min_length = args.min_length
     settings.dry_run = args.dry_run
-    # Example command setup, you'll need to expand this based on your actual requirements
     if len(args.input_file) == 1:
         steps = run_cutadapt_SE(
             args.input_file[0],

{cutseq-0.0.3 → cutseq-0.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cutseq"
-version = "0.0.3"
+version = "0.0.4"
 description = "Automatically cut adapter / barcode / UMI from NGS data"
 authors = ["Ye Chang <yech1990@gmail.com>"]
 license = "MIT"

cutseq-0.0.3/README.md

@@ -1,5 +0,0 @@
-#✂️ CutSeq
-
-## How to use?
-
-`cutseq -a "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC" test_R1.fq.gz test_R2.fq.gz`