better naming

pdimens · Jul 4, 2024 · eafe4ac · eafe4ac
1 parent 457771a
commit eafe4ac
Show file tree

Hide file tree

Showing 10 changed files with 45 additions and 44 deletions.
diff --git a/src/harpy/align.py b/src/harpy/align.py
@@ -34,7 +34,7 @@ def align():
             "options": ["--extra-params", "--genome", "--molecule-distance", "--quality-filter"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--depth-window", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ],
@@ -44,7 +44,7 @@ def align():
             "options": ["--ema-bins", "--extra-params", "--genome", "--platform", "--quality-filter", "--whitelist"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--depth-window", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ],
@@ -54,7 +54,7 @@ def align():
             "options": ["--extra-params", "--genome", "--molecule-distance", "--quality-filter", "--read-length"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--depth-window", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ]
@@ -70,7 +70,7 @@ def align():
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Align/bwa", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')
@@ -145,7 +145,7 @@ def bwa(inputs, output_dir, genome, depth_window, threads, extra_params, quality
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Align/ema", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')
@@ -237,7 +237,7 @@ def ema(inputs, output_dir, platform, whitelist, genome, depth_window, threads,
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Align/strobealign", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')

diff --git a/src/harpy/deconvolve.py b/src/harpy/deconvolve.py
@@ -17,7 +17,7 @@
             "options": ["--density", "--dropout", "--kmer-length", "--window-size"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--hpc", "--output-dir", "--quiet", "--snakemake", "--threads", "--help"],
         },
     ]
@@ -27,24 +27,24 @@
 @click.option('-k', '--kmer-length', default = 21, show_default = True, type=int, help = 'Size of kmers')
 @click.option('-w', '--window-size', default = 40, show_default = True, type=int, help = 'Size of window guaranteed to contain at least one kmer')
 @click.option('-d', '--density', default = 3, show_default = True, type = click.IntRange(min = 1, max_open = True), help = 'On average, 1/2^d kmers are indexed')
-@click.option('-m', '--min-reads', default = 1, show_default = True, type = click.IntRange(min = 1, max_open = True), help = 'Minimum cloud size to deconvolve')
+@click.option('-a', '--dropout', default = 0, show_default = True, type = click.IntRange(min = 0, max_open = True), help = 'Minimum cloud size to deconvolve')
 @click.option('-t', '--threads', default = 4, show_default = True, type = click.IntRange(min = 1, max_open = True), help = 'Number of threads to use')
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Deconvolve", show_default=True,  help = 'Output directory name')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
 @click.option('--config-only',  is_flag = True, hidden = True, show_default = True, default = False, help = 'Create the config.yaml file and exit')
 @click.argument('inputs', required=True, type=click.Path(exists=True, readable=True), nargs=-1)
-def deconvolve(inputs, output_dir, kmer_length, window_size, density, min_reads, threads, snakemake, quiet, hpc, conda, config_only):
+def deconvolve(inputs, output_dir, kmer_length, window_size, density, dropout, threads, snakemake, quiet, hpc, conda, config_only):
     """
     Resolve clashing barcodes from different molecules
 
     Provide the input fastq files and/or directories at the end of the command
     as individual files/folders, using shell wildcards (e.g. `data/acronotus*.fq`), or both.
     
     The term "cloud" refers to the collection of all sequences that feature the same barcode. By default,
-    `dropout` is set to `1`, meaning it will consider all barcodes, even clouds with singleton.
+    `dropout` is set to `0`, meaning it will consider all barcodes, even clouds with singleton.
     """
     output_dir = output_dir.rstrip("/")
     workflowdir = f"{output_dir}/workflow"
@@ -69,7 +69,7 @@ def deconvolve(inputs, output_dir, kmer_length, window_size, density, min_reads,
         config.write(f"kmer_length: {kmer_length}\n")       
         config.write(f"window_size: {window_size}\n")
         config.write(f"density: {density}\n")
-        config.write(f"dropout: {min_reads - 1}\n")
+        config.write(f"dropout: {dropout}\n")
         config.write(f"workflow_call: {command}\n")
         config.write("inputs:\n")
         for i in fqlist:

diff --git a/src/harpy/demultiplex.py b/src/harpy/demultiplex.py
@@ -29,7 +29,7 @@ def demultiplex():
             "options": ["--schema"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ]
@@ -42,7 +42,7 @@ def demultiplex():
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Demultiplex", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False,  help = 'Create the config.yaml file and exit')

diff --git a/src/harpy/impute.py b/src/harpy/impute.py
@@ -18,7 +18,7 @@
             "options": ["--extra-params",  "--parameters", "--vcf", "--vcf-samples"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ]
@@ -33,7 +33,7 @@
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Impute", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')

diff --git a/src/harpy/phase.py b/src/harpy/phase.py
@@ -17,7 +17,7 @@
             "options": ["--extra-params", "--genome", "--ignore-bx", "--molecule-distance", "--prune-threshold", "--vcf", "--vcf-samples"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },     
     ]
@@ -35,7 +35,7 @@
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Phase", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake',  type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--skipreports',  is_flag = True, show_default = True, default = False, help = 'Don\'t generate HTML reports')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')

diff --git a/src/harpy/preflight.py b/src/harpy/preflight.py
@@ -39,7 +39,7 @@ def preflight():
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Preflight/fastq", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')
 @click.argument('inputs', required=True, type=click.Path(exists=True), nargs=-1)
@@ -97,7 +97,7 @@ def fastq(inputs, output_dir, threads, snakemake, quiet, hpc, conda, config_only
 @click.option('-q', '--quiet',  is_flag = True, show_default = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "Preflight/bam", show_default=True,  help = 'Output directory name')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--config-only',  is_flag = True, hidden = True, default = False, help = 'Create the config.yaml file and exit')
 @click.argument('inputs', required=True, type=click.Path(exists=True, readable=True), nargs=-1)

diff --git a/src/harpy/qc.py b/src/harpy/qc.py
@@ -17,7 +17,7 @@
             "options": ["--deconvolve", "--deconvolve-params", "--deduplicate", "--extra-params", "--min-length", "--max-length", "--trim-adapters"],
         },
         {
-            "name": "Other Options",
+            "name": "Workflow Controls",
             "options": ["--conda", "--hpc", "--output-dir", "--quiet", "--skipreports", "--snakemake", "--threads", "--help"],
         },
     ]
@@ -34,7 +34,7 @@
 @click.option('-t', '--threads', default = 4, show_default = True, type = click.IntRange(min = 4, max_open = True), help = 'Number of threads to use')
 @click.option('-q', '--quiet',  is_flag = True, default = False, help = 'Don\'t show output text while running')
 @click.option('-o', '--output-dir', type = click.Path(exists = False), default = "QC", show_default=True,  help = 'Output directory name')
-@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission config.yaml file')
+@click.option('--hpc',  type = click.Path(exists = True, file_okay = False, readable=True), help = 'Directory with HPC submission `config.yaml` file')
 @click.option('--conda',  is_flag = True, default = False, help = 'Use conda/mamba instead of container')
 @click.option('--snakemake', type = str, help = 'Additional Snakemake parameters, in quotes')
 @click.option('--skipreports',  is_flag = True, default = False, help = 'Don\'t generate HTML reports')
@@ -47,13 +47,14 @@ def qc(inputs, output_dir, min_length, max_length, trim_adapters, deduplicate, d
     Provide the input fastq files and/or directories at the end of the command
     as individual files/folders, using shell wildcards (e.g. `data/acronotus*.fq`), or both.
     
-    By default, adapters will be automatically detected and removed (can be disabled with `-a`).
-    Use `--deconvolve` to resolve barcode clashing that may occur by unrelated sequences having the same barcode.
-    The parameters are described [here](https://github.com/RolandFaure/QuickDeconvolution?tab=readme-ov-file#usage). You
-    can also use the `harpy deconvolve` worklfow to perform this task separately.
     The input reads will be quality trimmed using:
     - a sliding window from front to tail
     - poly-G tail removal
+    - use `-a` to automatically detect and remove adapters
+    - use `-d` to find and remove PCR duplicates
+    - use `-c` to resolve barcode clashing that may occur by unrelated sequences having the same barcode
+      - the parameters for `-p` are described [here](https://github.com/RolandFaure/QuickDeconvolution?tab=readme-ov-file#usage).
+      - you can use `harpy deconvolve` to perform this task separately
     """
     output_dir = output_dir.rstrip("/")
     workflowdir = f"{output_dir}/workflow"