update for release 2.0.1

culebrONT/containers/Dockerfile_test

@@ -0,0 +1,44 @@
+#INFORMATION
+#MAINTAINER Julie Orjuela & Francois Sabot (Docker)
+#version="1.0"
+#software="all Culebront dependencies"
+#description="All dependencies used to launch CulebrONT in LOCAL mode"
+#website="https://culebront-pipeline.readthedocs.io/en/latest/"
+
+FROM ubuntu:focal
+USER root
+
+# ENVIRONMENT
+
+# INSTALL, Global
+RUN apt update
+RUN DEBIAN_FRONTEND=noninteractive apt -y install keyboard-configuration git vim curl wget less locate graphviz python3-pip
+RUN DEBIAN_FRONTEND=noninteractive apt -y install python3.8 python3.8-dev python3.8-venv python3.8-full python3.8-distutils
+RUN DEBIAN_FRONTEND=noninteractive apt -y install python3.9 python3.9-dev python3.9-venv python3.9-full python3.9-distutils
+RUN ln -fs /usr/share/zoneinfo/Europe/Paris /etc/localtime
+RUN apt install -y tzdata
+RUN dpkg-reconfigure --frontend noninteractive tzdata
+
+# Install for Python
+RUN echo 'export LC_ALL=C.UTF-8' >> /environment
+RUN echo 'export LANG=C.UTF-8' >> /environment
+ENV LC_ALL=C.UTF-8
+ENV LANG=C.UTF-8
+RUN python3.8 -m pip install tox
+RUN python3.9 -m pip install tox
+
+# installing Singularity
+RUN wget https://dl.google.com/go/go1.16.4.linux-amd64.tar.gz
+RUN tar -C /usr/local -xzvf go1.16.4.linux-amd64.tar.gz 
+RUN rm go1.16.4.linux-amd64.tar.gz 
+ENV PATH=/usr/local/go/bin:$PATH
+
+## Install Singularity itself
+RUN wget https://github.com/sylabs/singularity/releases/download/v3.8.1/singularity-ce-3.8.1.tar.gz 
+RUN tar -xzf singularity-ce-3.8.1.tar.gz
+ENV PKG_CONFIG_PATH=/usr/lib/pkgconfig:/usr/lib/x86_64-linux-gnu/pkgconfig/
+RUN cd /singularity-ce-3.8.1 && ./mconfig -p /usr/local && make -C builddir && make -C builddir install
+
+# Download build singularity
+RUN mkdir -p /usr/local/culebrONT/Containers && cd /usr/local/culebrONT/Containers && wget --no-check-certificate -rm -nH --cut-dirs=2 --reject="index.html*" --no-parent https://itrop.ird.fr/culebront_utilities/singularity_build/
+

culebrONT/snakeWrapper/usefull_function.py

@@ -206,6 +206,7 @@ def check_and_download_singularity():
         url, path_install = imgs_list
         if not Path(path_install).exists():
             SINGULARITY_URL_FILES_DOWNLOAD.append(imgs_list)
+            click.secho(f"    File: {path_install} is download.", fg="yellow", nl=True)
         else:
             click.secho(f"    File: {path_install} already download, done.", fg="yellow", nl=True)
     results = multiprocessing_download(SINGULARITY_URL_FILES_DOWNLOAD)

culebrONT/snakefiles/Snakefile

@@ -426,13 +426,44 @@ rule stats_assembly:
     script:
         f"{SNAKEMAKE_SCRIPTS}/assembly-stats.py"
 
+
+rule copy_final_assemblies:
+    """ build stats on assembly"""
+    threads: get_threads('copy_final_assemblies', 1)
+    input:
+        fasta_list = rules.preparing_fasta_to_quality.output.renamed
+    output:
+        fasta_final = f"{output_dir}ASSEMBLIES/{{fastq}}-{{assemblers}}-{{quality_step}}{f'-{add_circular_name}' if add_circular_name else ''}.fasta"
+    params:
+        sample = '{fastq}'
+    log:
+        output = f"{output_dir}LOGS/copy_final_assemblies/{{fastq}}_{{assemblers}}_{{quality_step}}.o",
+        error = f"{output_dir}LOGS/copy_final_assemblies/{{fastq}}_{{assemblers}}_{{quality_step}}.e"
+    message:
+        """
+        Launching {rule}
+        threads : {threads}
+        input:
+             fasta_list : {input.fasta_list}
+        output:
+             fasta_final : {output.fasta_final}
+        log:
+            output : {log.output}
+            error: {log.error}
+        """
+    shell:
+        """
+        cp {input.fasta_list} {output.fasta_final}
+        """
+
 def output_final(wildcards):
     dico_final = {
         "fasta_list" : expand(rules.preparing_fasta_to_quality.output.renamed, fastq=FASTQ, assemblers=culebront.assembly_tools_activated, quality_step=culebront.quality_step),
         "bench_list" : expand(rules.run_benchmark_time.output.stat_time,fastq=FASTQ),
         "dag" : rules.rule_graph.output.dag,
         "versions" : rules.run_get_versions.output.csv,
-        "stats_assembly": expand(rules.stats_assembly.output.csv, fastq = FASTQ)
+        "stats_assembly": expand(rules.stats_assembly.output.csv, fastq = FASTQ),
+        "all_assemblies":  expand(rules.copy_final_assemblies.output.fasta_final, fastq=FASTQ,assemblers=culebront.assembly_tools_activated,quality_step=culebront.quality_step)
          # "report_snakemake" : rules.run_report_snakemake.output.report_snakemake,
         }
     if config['QUALITY']['QUAST']:

culebrONT/snakefiles/quality.snake

@@ -54,9 +54,9 @@ rule preparing_fasta_to_quality:
     input:
         fasta = fasta_to_busco
     output:
-        renamed =  f"{output_dir}{{fastq}}/AGGREGATED_QC/DATA/{{assemblers}}-{{quality_step}}-{add_circular_name}.fasta"
+        renamed =  f"{output_dir}{{fastq}}/AGGREGATED_QC/DATA/{{fastq}}-{{assemblers}}-{{quality_step}}{f'-{add_circular_name}' if add_circular_name else ''}.fasta"
     params:
-        index_mmi = f"{output_dir}{{fastq}}/AGGREGATED_QC/DATA/{{assemblers}}-{{quality_step}}-{add_circular_name}.fasta.mmi"
+        index_mmi = f"{output_dir}{{fastq}}/AGGREGATED_QC/DATA/{{fastq}}-{{assemblers}}-{{quality_step}}{f'-{add_circular_name}' if add_circular_name else ''}.fasta.mmi"
     log:
         output = f"{output_dir}{{fastq}}/LOGS/QUALITY/AGGREGATED_QC/{{fastq}}-{{assemblers}}-{{quality_step}}-preparing_DATA.o",
         error = f"{output_dir}{{fastq}}/LOGS/QUALITY/AGGREGATED_QC/{{fastq}}-{{assemblers}}-{{quality_step}}-preparing_DATA.e",

culebrONT/snakemake_scripts/assembly-stats.py

@@ -150,7 +150,7 @@ def calculate_stats(seq_lens, gc_cont):
 
     for assembly_file in sorted(files_list):
         assembly_file_path = Path(assembly_file)
-        assembler, step, _ = assembly_file_path.stem.split("-")
+        sample, assembler, step, _ = assembly_file_path.stem.split("-")
         step = replace_all({"STEP_": "", "_STARTFIXED": ""}, step)
         contig_lens, scaffold_lens, gc_cont = read_genome(assembly_file)
         scaffold_stats = calculate_stats(scaffold_lens, gc_cont)

docs/requirements.txt

@@ -1,16 +1,3 @@
-sphinx_copybutton==0.4.0
+sphinx_copybutton
 snakemake
-sphinx_click==3.0.2 
-setuptools>=45
-wheel>=0.37.1
-setuptools_scm>=6.2
-sphinx-rtd-theme==1.0.0
-sphinx==4.4.0
-sphinxcontrib-applehelp==1.0.2
-sphinxcontrib-devhelp==1.0.2
-sphinxcontrib-htmlhelp==2.0.0
-sphinxcontrib-jsmath==1.0.1
-sphinxcontrib-mermaid==0.7.1
-sphinxcontrib-qthelp==1.0.3
-sphinxcontrib-serializinghtml==1.1.5
-docutils==0.17.1
+sphinx_click

docs/source/ABOUT.rst

@@ -9,7 +9,7 @@ Due to the daily deluge of data sequences and the increasing number of released
 
 However a huge question remains:
 
-"\ *But which assembly tool will provide the best result for your favorite organism?*\ "
+*"But which assembly tool will provide the best result for your favorite organism?"*
 
 To that anguishing idea, we can answer: **CulebrONT can help you!**
 
@@ -22,11 +22,12 @@ Assembly, circularisation, polishing and correction steps are all included withi
    :depth: 2
    :backlinks: entry
 
+
 From assembly to correction
 ---------------------------
 
 CulebrONT is a really flexible tool to assemble, circularise (or not), polish and correct assemblies. You can give your own parameters in the *config.yaml* file to CulebrONT to generate a modular, dedicated pipeline for your own data.
-
+   
 .. warning::
    You must launch at least one of the assemblers included in CulebrONT to pipe it with the potential circularisation, polishing and correction steps or with the quality control pipeline.
 
@@ -83,7 +84,6 @@ Fixstart is always performed on the last draft sequenced obtained in the pipelin
    * Fixstart is launched after the polishing step if assembly+polishing are activated.
    * Fixstart is launched after the correction step if assembly+polishing+correction or assembly+correction are activated
 
-
 .. warning::
    In any case, Fixstart will be deactivated if CIRCULAR is set to False
 
@@ -100,12 +100,9 @@ Polishing step is ensured by Racon, that corrects raw contigs generated by rapid
 
 .. note::
    * Minipolish includes a Racon polishing round, so if polishing is deactivated for the other assemblers (Flye, Shasta, Raven, Smartdenovo and Canu), Miniasm will still polish anyway. Please take it into account when you are doing pipeline comparisons.
-
    * Raven parameter -p (for polishing) is by default of 0.
-
    * A control rotation of circular molecule is performed before every Racon step.
 
-
 Included tools :
 
 * Racon version >= 1.4.13 https://github.com/isovic/racon
@@ -122,7 +119,6 @@ Correction can improve the consensus sequence for a draft genome assembly coming
    * Polished segments are merged subsequently.
    * CulebrONT implemented parallelism following the `Medaka documentation <https://nanoporetech.github.io/medaka/installation.html#improving-parallelism>`_ and the `Nanopolish practices <https://nanopolish.readthedocs.io/en/latest/quickstart_consensus.html#compute-a-new-consensus-sequence-for-a-draft-assembly>`_.
 
-
 **If you have short reads, you can now use *Pilon* to correct assemblies. As for Racon, several recursive rounds of Pilon can be run.**
 
 Included tools :
@@ -153,11 +149,9 @@ CulebrONT checks the quality of the assemblies with using these optional tools:
    * Samtools flagstats: calculates remapping stats using Illumina reads over assemblies
    * Mauve: allows multiple alignment of several assembles (for small genome only).
 
-
 .. danger::
    Please, activate Mauve only for small genomes.
 
-
 Included tools :
 
 * BUSCO version >= 4.0.5

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools>=45", "wheel>=0.37.1", "setuptools_scm>=6.2"]
+requires = ["setuptools", "wheel", "setuptools_scm"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools_scm]
@@ -18,15 +18,23 @@ envlist = py{38,39}
 skip_missing_interpreters = True
 skipsdist=False
 
+[gh-actions]
+python = 3.8: py38
+
 [testenv:py{38,39}]
 description = Run the install in Python 3.8
 skip_install = False
 changedir={envdir}
+whitelist_externals =
+    bash
+    echo
 envdir =
     py38: {toxworkdir}/py38
     py39: {toxworkdir}/py39
 commands =
-    culebrONT --help
+    #culebrONT --help
+    bash -ec 'echo `pwd`'
+    bash -ec 'CPDIR="./lib/python3.8/site-packages/culebrONT/containers/"; DIR="/usr/local/culebrONT/Containers"; if [[ -d $DIR ]]; then ls $DIR;  echo "copy Containers files in $DIR to $CPDIR"; ln -sf $DIR/* $CPDIR; fi'
     culebrONT install_local