minor updates to bit-assemble, bit-gen-reads, and bit-cov-analyzer; see changelog

Author: Mike Lee

CHANGELOG.md

@@ -13,6 +13,18 @@
 
 -->
 
+## v1.13.15 (13-Mar-2026)
+
+### Changed
+- `bit-assemble`
+  - the threads parameter is now passed to bbnorm and fastp (if run) in addition to the assemblers
+- `bit-gen-reads`
+  - `--type long` will no longer preferentially start reads at position 0 if the requested read size is larger than the contig; now it will start randomly and just produce a read that ends where the contig ends (unless `--circularize` is added)
+- `bit-cov-analyzer`
+  - no longer writes out individual window stats by default (to save spacetime), it needs to be turned on with the `--write-window-stats` now if wanted
+
+---
+
 ## v1.13.14 (13-Mar-2026)
 
 ### Fixed

bit/cli/assemble.py

@@ -62,6 +62,14 @@ def build_parser():
         type=Path,
         default=Path("assembly"),
     )
+    general.add_argument(
+        "-t",
+        "--threads",
+        metavar="<INT>",
+        help=wrap_help("Number of threads/cpus to pass to QC and assembly commands (default: 1; may be multiplied by number of snakemake jobs)"),
+        default=1,
+        type=int,
+    )
     general.add_argument(
         "--run-fastp",
         action="store_true",
@@ -82,14 +90,6 @@ def build_parser():
         help=wrap_help("Assembler to use (default: megahit)"),
         default="megahit",
     )
-    assembly.add_argument(
-        "-t",
-        "--threads",
-        metavar="<INT>",
-        help=wrap_help("Number of threads/cpus to pass as an assembler parameter (default: 1; may be multiplied by number of snakemake jobs)"),
-        default=1,
-        type=int,
-    )
     assembly.add_argument(
         "--min-contig-len",
         metavar="<INT>",

bit/cli/cov_analyzer.py

@@ -124,8 +124,8 @@ def main():
         default=100,
     )
     optional.add_argument(
-        "--no-window-stats",
-        help='Add this flag to skip writing out individual window stats (saves spacetime)',
+        "--write-window-stats",
+        help='Add this flag to also write out individual window stats (saves spacetime by not doing so)',
         action="store_true",
     )
 
@@ -153,7 +153,7 @@ def main():
         step_size = args.step_size,
         allowed_gap = args.allowed_gap,
         buffer = args.buffer,
-        no_window_stats = args.no_window_stats,
+        write_window_stats = args.write_window_stats,
         log_file = f"{args.output_dir}/runlog.txt",
         full_cmd_executed = full_cmd_executed
     )

bit/modules/cov_analyzer.py

@@ -30,7 +30,7 @@ def run_cov_analyzer(
     step_size: int,
     allowed_gap: int,
     buffer: int,
-    no_window_stats: bool,
+    write_window_stats: bool,
     log_file = str,
     full_cmd_executed: str = None
 ):
@@ -65,7 +65,7 @@ def run_cov_analyzer(
     low_merged_regions = annotate_zero_cov_bases(low_merged_regions, bam_file)
 
     generate_outputs(reference_fasta, high_merged_regions, low_merged_regions,
-                     cov_df, cov_stats, buffer, output_dir, contig_lengths, no_window_stats,
+                     cov_df, cov_stats, buffer, output_dir, contig_lengths, write_window_stats,
                      log_file)
 
 
@@ -345,12 +345,12 @@ def annotate_zero_cov_bases(merged_regions, bam_file):
 
 
 def generate_outputs(reference_fasta, high_merged_regions, low_merged_regions,
-                     cov_df, cov_stats, buffer, output_dir, contig_lengths, no_window_stats,
+                     cov_df, cov_stats, buffer, output_dir, contig_lengths, write_window_stats,
                      log_file):
 
     print()
     write_window_cov_stats(cov_stats, output_dir, contig_lengths, log_file)
-    if not no_window_stats:
+    if write_window_stats:
         write_windows_table(cov_stats, output_dir, log_file)
     write_window_plot_cov_histogram(cov_df, output_dir, log_file)
 

bit/modules/gen_reads.py

@@ -72,6 +72,11 @@ def extract_subsequence(sequence, seq_length, subseq_len, circularize):
             subseq = sequence[start:end]
         else:
             subseq = sequence[start:] + sequence[: end - seq_length]
+    elif subseq_len >= seq_length:
+        # when the requested length meets or exceeds the contig length,
+        # pick any start position and truncate at the contig end
+        start = random.randint(0, seq_length - 1)
+        subseq = sequence[start:]
     else:
         start = random.randint(0, seq_length - subseq_len)
         subseq = sequence[start:start + subseq_len]

bit/smk/assemble.smk

@@ -47,7 +47,8 @@ if run_fastp:
         params:
             output_dir=output_dir + "/{sample}/filtered-reads",
             html=output_dir + "/{sample}/filtered-reads/{sample}-fastp.html",
-            json=output_dir + "/{sample}/filtered-reads/{sample}-fastp.json"
+            json=output_dir + "/{sample}/filtered-reads/{sample}-fastp.json",
+            threads=threads
         log:
             log_files_dir + "/{sample}-fastp.log"
         shell:
@@ -56,7 +57,7 @@ if run_fastp:
 
             fastp -i {input.R1} -I {input.R2} -o {output.R1} -O {output.R2} \
                   --html {params.html} --json {params.json} \
-                  --thread 8 --detect_adapter_for_pe > {log} 2>&1
+                  --thread {params.threads} --detect_adapter_for_pe > {log} 2>&1
             """
 else:
     post_fastp_reads_dict = reads_dict
@@ -81,15 +82,16 @@ if run_bbnorm:
             R2=output_dir + "/{sample}/bbnormd-reads/{sample}-bbnormd-R2.fastq.gz"
         params:
             output_dir=output_dir + "/{sample}/bbnormd-reads",
-            target="100"
+            target="100",
+            threads=threads,
         log:
             log_files_dir + "/{sample}-bbnorm.log"
         shell:
             """
             mkdir -p {params.output_dir}
 
             bbnorm.sh in={input.R1} in2={input.R2} out={output.R1} out2={output.R2} \
-                     threads=8 target={params.target} > {log} 2>&1
+                     threads={params.threads} target={params.target} > {log} 2>&1
             """
 else:
     post_bbnorm_reads_dict = post_fastp_reads_dict

bit/tests/test_cov_analyzer.py

@@ -135,7 +135,7 @@ def fake_run_mosdepth(bam_file, window_bed_path, output_dir):
         step_size=50,
         allowed_gap=0,
         buffer=10,
-        no_window_stats=False,
+        write_window_stats=True,
         log_file=None,
         full_cmd_executed="pytest-run",
     )

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "bit"
-version = "1.13.14"
+version = "1.13.15"
 description = "A set of bioinformatics scripts and workflows"
 readme = "README.md"
 license = { text = "GPLv3" }