Updating to v0.9.96

- Fixed indentation bugs that prevented Falco or FastQC from running during the `clean` step and the subsampling of reads during the `assemble` step - Secret feature, coding genes databases can also be extracted as nucleotide Former-commit-id: bd8927c
edgardomortiz · Aug 23, 2023 · e1b37c1 · e1b37c1
1 parent 037b4ce
commit e1b37c1
Show file tree

Hide file tree

Showing 5 changed files with 40 additions and 35 deletions.
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@
 
 [![Install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat)](http://bioconda.github.io/recipes/captus/README.html) [![Bioconda downloads](https://anaconda.org/bioconda/captus/badges/downloads.svg)](https://anaconda.org/bioconda/captus) [![Version in Bioconda](https://anaconda.org/bioconda/captus/badges/version.svg)](https://anaconda.org/bioconda/captus) [![Last updated](https://anaconda.org/bioconda/captus/badges/latest_release_date.svg)](https://github.com/edgardomortiz/Captus/releases)
 ___
-## Installation
+## INSTALLATION
 ### Using micromamba
 The fastest way to install `Captus` is to create an isolated software environment using `micromamba` (https://mamba.readthedocs.io/en/latest/installation.html), if you don't have `micromamba` it can very easily be installed:
 For linux with `bash` shell:
@@ -79,23 +79,25 @@ And if the program was correctly installed you will see the main help page of Ca
 ```text
 usage: captus_assembly command [options]
 
-Captus 0.9.90: Assembly of Phylogenomic Datasets from High-Throughput Sequencing data
+Captus 0.9.96: Assembly of Phylogenomic Datasets from High-Throughput Sequencing data
 
 Captus-assembly commands:
   command     Program commands (in typical order of execution)
-                clean = Trim adaptors and quality filter reads with BBTools, run
-                        FastQC on the raw and cleaned reads
-                assemble = Perform de novo assembly with MEGAHIT: Assembling reads
-                           that were cleaned with the 'clean' command is
-                           recommended, but reads cleaned elsewhere are also allowed
-                extract = Recover targeted markers with BLAT and Scipio: Extracting
-                          markers from the assembly obtained with the 'assemble'
-                          command is recommended, but any other assemblies in FASTA
-                          format are also allowed.
-                align = Align extracted markers across samples with MAFFT or MUSCLE:
-                        Marker alignment depends on the directory structure created
-                        by the 'extract' command. This step also performs paralog
-                        filtering and alignment trimming using ClipKIT
+                clean = Trim adaptors and quality filter reads with BBTools,
+                        run FastQC on the raw and cleaned reads
+                assemble = Perform de novo assembly with MEGAHIT: Assembling
+                           reads that were cleaned with the 'clean' command is
+                           recommended, but reads cleaned elsewhere are also
+                           allowed
+                extract = Recover targeted markers with BLAT and Scipio:
+                          Extracting markers from the assembly obtained with
+                          the 'assemble' command is recommended, but any other
+                          assemblies in FASTA format are also allowed
+                align = Align extracted markers across samples with MAFFT or
+                        MUSCLE: Marker alignment depends on the directory
+                        structure created by the 'extract' command. This step
+                        also performs paralog filtering and alignment trimming
+                        using ClipKIT
 
 Help:
   -h, --help  Show this help message and exit
@@ -105,7 +107,6 @@ For help on a particular command: captus_assembly command -h
 
 ERROR: Missing command
 ```
-
-## Usage
+## USAGE
 
 Documentation and tutorials available at https://edgardomortiz.github.io/captus.docs/
diff --git a/captus/assemble.py b/captus/assemble.py
@@ -62,6 +62,7 @@ def assemble(full_command, args):
             " single-end. Sample names are derived from the text found before the '_R1' string."
         )
     skipped_subsample = []
+    skipped_assemble = []
     if args.sample_reads_target > 0:
         fastqs_to_subsample, skipped_subsample = find_and_match_fastqs(args.reads)
         skip_subsampling = False
@@ -152,11 +153,11 @@ def assemble(full_command, args):
         log.log(f'{"":>{mar}}  {dim("A directory will be created for every sample")}')
         log.log("")
 
-    if skipped_subsample:
-        log.log(f'{bold("WARNING:")} {len(skipped_subsample)} sample(s) will be skipped')
-        for msg in skipped_subsample:
-            log.log(msg)
-        log.log("")
+        if skipped_subsample:
+            log.log(f'{bold("WARNING:")} {len(skipped_subsample)} sample(s) will be skipped')
+            for msg in skipped_subsample:
+                log.log(msg)
+            log.log("")
 
         subsample_reads_params = []
         for fastq_r1 in sorted(fastqs_to_subsample):

diff --git a/captus/clean.py b/captus/clean.py
@@ -340,17 +340,17 @@ def clean(full_command, args):
             log.log(msg)
         log.log("")
 
-        if args.debug:
-            tqdm_serial_run(qc_stats, qc_stats_params,
-                            f"Running {args.qc_program}",
-                            f"{args.qc_program} analysis completed",
-                            "file", args.show_less)
-        else:
-            tqdm_parallel_async_run(qc_stats, qc_stats_params,
-                                    f"Running {args.qc_program}",
-                                    f"{args.qc_program} analysis completed",
-                                    "file", concurrent, args.show_less)
-        log.log("")
+    if args.debug:
+        tqdm_serial_run(qc_stats, qc_stats_params,
+                        f"Running {args.qc_program}",
+                        f"{args.qc_program} analysis completed",
+                        "file", args.show_less)
+    else:
+        tqdm_parallel_async_run(qc_stats, qc_stats_params,
+                                f"Running {args.qc_program}",
+                                f"{args.qc_program} analysis completed",
+                                "file", concurrent, args.show_less)
+    log.log("")
 
 
     ################################################################################################

diff --git a/captus/settings.py b/captus/settings.py
@@ -269,7 +269,10 @@
 
 # Bundled miscellaneous DNA references
 DNA_REFS = {
-    "": Path("")
+    "angiosperms353": Path(DATA_DIR, "Angiosperms353.FNA"),
+    "mega353": Path(DATA_DIR, "Mega353.FNA"),
+    "seedplantsptd": Path(DATA_DIR, "SeedPlantsPTD.FNA"),
+    "seedplantsmit": Path(DATA_DIR, "SeedPlantsMIT.FNA"),
 }
 
 # Bundled dependencies directory

diff --git a/captus/version.py b/captus/version.py
@@ -14,4 +14,4 @@
 not, see <http://www.gnu.org/licenses/>.
 """
 
-__version__ = '0.9.95'
+__version__ = '0.9.96'