Merge pull request #75 from gbouras13/dev

Dev

Author: gbouras13

HISTORY.md

@@ -1,5 +1,26 @@
 # History
 
+1.8.1 (2025-09-27)
+------------------
+
+* Fixes minor issues with `--skip_qc` (#73) and `--no_chromosome` (#74)
+
+1.8.0 (2025-06-12)
+------------------
+
+* Fixes issues with `--skip_qc` when using non gzipped FASTQ reads (#60)
+* Fixes issue with fastp versions #64
+* Add skip_mash to run Plassembler without the database mash search #61
+
+1.8.0 (2025-06-23)
+------------------
+
+* Relaxes Python version dependency to >=3.8,<3.14 from >=3.8,<3.10
+* Minor change to log file error behaviour #69
+* Thanks @rrwick for both changes
+
+* Bug fix with `--force` for `plassembler download`, which will only remove the output directory if `--force` is specified (#49).
+
 1.6.2 (2024-03-08)
 ------------------
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "plassembler"
-version = "1.8.0" # change VERSION too
+version = "1.8.1" # change VERSION too
 description = "Quickly and accurately assemble plasmids in hybrid sequenced bacterial isolates"
 authors = ["George Bouras <george.bouras@adelaide.edu.au>"]
 license = "MIT"

src/plassembler/__init__.py

@@ -72,6 +72,9 @@ def begin_plassembler(outdir, force):
     # get start time
     start_time = time.time()
 
+    # ensure sys exit if error
+    logger.add(lambda _: sys.exit(1), level="ERROR")
+
     # instantiate the outdir
     # remove outdir on force
     if force is True:
@@ -94,8 +97,6 @@ def begin_plassembler(outdir, force):
     log_file = os.path.join(outdir, f"plassembler_{start_time}.log")
     # adds log file
     logger.add(log_file)
-    # ensure sys exit if error
-    logger.add(lambda _: sys.exit(1), level="ERROR")
 
     logger.info(f"You are using Plassembler version {get_version()}")
     logger.info("Repository homepage is https://github.com/gbouras13/plassembler")
@@ -1276,6 +1277,11 @@ def long_options(func):
             help="Use --nano-raw for Flye. \nDesigned for Guppy fast configuration reads. \nBy default, Flye will assume SUP or HAC reads and use --nano-hq.",
             is_flag=True,
         ),
+        click.option(
+            "--keep_fastqs",
+            help="Whether you want to keep FASTQ files containing putative plasmid reads \nand long reads that map to multiple contigs (plasmid and chromosome).",
+            is_flag=True,
+        ),
         click.option(
             "--keep_chromosome",
             help="If you want to keep the chromosome assembly.",
@@ -1341,6 +1347,7 @@ def long(
     pacbio_model,
     skip_qc,
     raw_flag,
+    keep_fastqs,
     keep_chromosome,
     flye_directory,
     flye_assembly,
@@ -1371,6 +1378,7 @@ def long(
     logger.info(f"--force is {force}")
     logger.info(f"--skip_qc is {skip_qc}")
     logger.info(f"--raw_flag is {raw_flag}")
+    logger.info(f"--keep_fastqs is {keep_fastqs}")
     logger.info(f"--pacbio_model is {pacbio_model}")
     logger.info(f"--keep_chromosome is {keep_chromosome}")
     logger.info(f"--flye_directory is {flye_directory}")
@@ -1518,7 +1526,7 @@ def long(
             outdir,
             prefix,
             False,  # unicycler success
-            False,  # keep fastqs
+            False,  # keep fastqs will be false here as no chromosome
             False,  # assembled mode
             True,  # long only
             False,  # raven false
@@ -1730,7 +1738,7 @@ def long(
         outdir,
         prefix,
         unicycler_success,  # unicycler success
-        False,  # keep fastqs
+        keep_fastqs,  # keep fastqs
         False,  # assembled mode
         True,  # long only
         False,  # no raven

src/plassembler/utils/VERSION

@@ -1 +1 @@
-1.8.0
+1.8.1

src/plassembler/utils/cleanup.py

@@ -81,6 +81,7 @@ def move_and_copy_files(
     :param out_dir:  Output Directory
     :param prefix: prefix
     :param unicycler_success_flag: whether or not unicycler worked
+    :param keep_fastqs: whether to keep FASTQs
     :param assembled_mode: whether or not unicycler worked
     :param long_only: whether or not unicycler worked
     :param use_raven: whether or not unicycler worked

src/plassembler/utils/no_assembly.py

@@ -39,4 +39,4 @@ def create_fake_flye_chromosome_info(assembly_info_file: Path) -> None:
     }
 
     flye_info_df = pd.DataFrame(data)
-    flye_info_df.to_csv(assembly_info_file, index=False)
+    flye_info_df.to_csv(assembly_info_file, sep="\t", index=False)

tests/test_end_to_end.py

@@ -287,6 +287,15 @@ def test_plassembler_long(self):
         exec_command(cmd)
         remove_directory(outdir)
 
+    def test_plassembler_long_keep_fastqs(self):
+        """test plassembler long"""
+        longreads: Path = f"{end_to_end}/input_fastq.gz"
+        chromosome = 50000
+        outdir: Path = f"{end_to_end}/test_out_keep_fastqs"
+        cmd = f"plassembler long -l {longreads} -c {chromosome} -d {plassembler_db_dir} -o {outdir}  -t 8 -f --keep_fastqs"
+        exec_command(cmd)
+        remove_directory(outdir)
+
     def test_plassembler_long_skipmash(self):
         """test plassembler long --skip_mash - no need for -d"""
         longreads: Path = f"{end_to_end}/input_fastq.gz"