sequana-lora 1.0.0__tar.gz

sequana_lora-1.0.0/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2016-2019, Sequana Development Team 
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

sequana_lora-1.0.0/PKG-INFO

@@ -0,0 +1,177 @@
+Metadata-Version: 2.3
+Name: sequana-lora
+Version: 1.0.0
+Summary: Run assembler (Canu, Flye, Hifiasm) on a set of long read files
+License: BSD-3
+Keywords: pacbio,nanopore,snakemake,sequana,assembly
+Author: Sequana Team
+Author-email: thomas.cokelaer@pasteur.fr
+Requires-Python: >=3.9,<4.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Dist: Jinja2 (>=3.1.2)
+Requires-Dist: click (>=8.1.7)
+Requires-Dist: click-completion (>=0.5.2)
+Requires-Dist: pandas (>=2.0.0)
+Requires-Dist: sequana-pipetools (>=1.2.0)
+Description-Content-Type: text/x-rst
+
+This is is the **lora** pipeline from the `Sequana <https://sequana.readthedocs.org>`_ project
+
+:Overview: Run assembler (Canu, flye, hifiasm) on a set of long read files
+:Input: A set of BAM files from Pacbio sequencers, or FastQ files for Nanopore sequencers.
+:Output: HTML reports with assemblies for each sample.
+:Status: prod
+:Citation: Cokelaer et al, (2017), ‘Sequana’: a Set of Snakemake NGS pipelines, Journal of Open Source Software, 2(16), 352, JOSS DOI doi:10.21105/joss.00352
+
+
+Installation
+~~~~~~~~~~~~
+
+Install Lora with pip command::
+
+    pip install sequana-lora
+
+To update your installed version, type::
+
+    pip install sequana-lora --upgrade
+
+Usage
+~~~~~
+
+::
+
+    sequana_lora --help
+    sequana_lora --input-directory DATAPATH --assembler flye
+
+This creates a directory with the pipeline and configuration file. You will then need
+to execute the pipeline::
+
+    cd lora
+    sh lora.sh  # for a local run
+
+This launch a snakemake pipeline. If you are familiar with snakemake, you can
+retrieve the pipeline itself and its configuration files and then execute the pipeline yourself with specific parameters::
+
+    snakemake -s lora.rules --cores 4 --stats stats.txt
+
+Or use `sequanix <https://sequana.readthedocs.io/en/master/sequanix.html>`_ interface.
+
+Example 1 Pacbio subreads
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+::
+
+    sequana_lora --input-directory . --pacbio
+    cd lora
+
+**Do you need to build CCS ?**
+
+Look at the config file and the CCS section. Check that the parameters are as expected.
+If you wish to build so-called HiFi reads, set the min-passes to 10 and min-rq to 0.99.
+
+**do you have a blast DB**
+
+You may also edit the config file to set blast to true (you must handle the blast databases yourself)
+
+**Do you need an annotation from your contigs?**
+
+Set prokka to True (for bacterial annotation)
+
+**Want to check the core genome?**
+
+You may set busco to true to detect the core genome (you must provide a path to a valid lineage).
+
+
+Requirements
+~~~~~~~~~~~~
+
+This pipelines requires the following executable(s):
+
+- canu
+- hifiasm
+- flye
+- blastn
+- busco
+- bwa
+- ccs
+- circlator
+- checkm
+- medaka
+- minimap2
+- pbindex
+- polypolish
+- prokka
+- samtools
+- sequana
+
+
+.. image:: https://raw.githubusercontent.com/sequana/lora/master/sequana_pipelines/lora/dag.png
+
+
+Details
+~~~~~~~~~
+
+This pipeline runs **lora** in parallel on the input fastq files (paired or not).
+A brief sequana summary report is also produced.
+
+In practice, you may start from BAM files generated by Pacbio sequencers or
+Fastq files, or CCS files. CCS files can be built by the pipeline. Then, an
+assembler is used to build the draft assemblies (Canu, hifiasm, etc). From the
+draft, circularisation may be applied to generate circularised genome (useful
+for bacterial genomes). Finally, each contig is blasted and quality checks are
+performed using Busco, quast, etc.
+
+
+Rules and configuration details
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Here is the `latest documented configuration file <https://raw.githubusercontent.com/sequana/sequana_lora/master/sequana_pipelines/lora/config.yaml>`_
+to be used with the pipeline. Each rule used in the pipeline may have a section in the configuration file.
+
+Changelog
+~~~~~~~~~
+
+========= ====================================================================
+Version   Description
+========= ====================================================================
+1.0.0     * uniformised extension with other pipelines. fix regression on
+            schema file
+          * update sequana container to v0.16.5
+          * add unicyler apptainer
+          * add checkm module to help users chosing correct marker and name.
+          * replaces --pacbio and --nanopore with --data-type. pacbio is now
+            decompose into 3 sub-categories: pacbio-raw, pacbio-hifi and pacbio-corr
+          * add bandage if assembly graph is available
+          * fixed hifiasm container to use newest version
+          * improved report html
+          * make genome-size compulsary
+          * add fastp as preprocessing tool
+          * remove presets in favor of click options
+          * CCS defaults to hifi. pacbio presets in config set to pacbio-hifi
+          * blast removes from default. users must set blast DB themselves.
+          * busco lineage downloaded from the web.
+          * CANU preset changes: pacbio-->pacbio-hifi
+          * CANU-correction preset changes: pacbio-->pacbio-hifi
+          * FLYE preset changes: pacbio-raw-->pacbio-hifi
+0.3.0     * Use click instead of argparse
+          * added multiqc / checkm / unicycler
+0.2.0     * add apptainers in most rules
+          * remove utils.smk to move rulegraph inside main pipeline
+          * rename lora.smk into lora.rules for consistency with other
+            pipelines
+          * add checkm in the pipeline and HTML report
+0.1.0     **First release.**
+========= ====================================================================
+

sequana_lora-1.0.0/README.rst

@@ -0,0 +1,147 @@
+This is is the **lora** pipeline from the `Sequana <https://sequana.readthedocs.org>`_ project
+
+:Overview: Run assembler (Canu, flye, hifiasm) on a set of long read files
+:Input: A set of BAM files from Pacbio sequencers, or FastQ files for Nanopore sequencers.
+:Output: HTML reports with assemblies for each sample.
+:Status: prod
+:Citation: Cokelaer et al, (2017), ‘Sequana’: a Set of Snakemake NGS pipelines, Journal of Open Source Software, 2(16), 352, JOSS DOI doi:10.21105/joss.00352
+
+
+Installation
+~~~~~~~~~~~~
+
+Install Lora with pip command::
+
+    pip install sequana-lora
+
+To update your installed version, type::
+
+    pip install sequana-lora --upgrade
+
+Usage
+~~~~~
+
+::
+
+    sequana_lora --help
+    sequana_lora --input-directory DATAPATH --assembler flye
+
+This creates a directory with the pipeline and configuration file. You will then need
+to execute the pipeline::
+
+    cd lora
+    sh lora.sh  # for a local run
+
+This launch a snakemake pipeline. If you are familiar with snakemake, you can
+retrieve the pipeline itself and its configuration files and then execute the pipeline yourself with specific parameters::
+
+    snakemake -s lora.rules --cores 4 --stats stats.txt
+
+Or use `sequanix <https://sequana.readthedocs.io/en/master/sequanix.html>`_ interface.
+
+Example 1 Pacbio subreads
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+::
+
+    sequana_lora --input-directory . --pacbio
+    cd lora
+
+**Do you need to build CCS ?**
+
+Look at the config file and the CCS section. Check that the parameters are as expected.
+If you wish to build so-called HiFi reads, set the min-passes to 10 and min-rq to 0.99.
+
+**do you have a blast DB**
+
+You may also edit the config file to set blast to true (you must handle the blast databases yourself)
+
+**Do you need an annotation from your contigs?**
+
+Set prokka to True (for bacterial annotation)
+
+**Want to check the core genome?**
+
+You may set busco to true to detect the core genome (you must provide a path to a valid lineage).
+
+
+Requirements
+~~~~~~~~~~~~
+
+This pipelines requires the following executable(s):
+
+- canu
+- hifiasm
+- flye
+- blastn
+- busco
+- bwa
+- ccs
+- circlator
+- checkm
+- medaka
+- minimap2
+- pbindex
+- polypolish
+- prokka
+- samtools
+- sequana
+
+
+.. image:: https://raw.githubusercontent.com/sequana/lora/master/sequana_pipelines/lora/dag.png
+
+
+Details
+~~~~~~~~~
+
+This pipeline runs **lora** in parallel on the input fastq files (paired or not).
+A brief sequana summary report is also produced.
+
+In practice, you may start from BAM files generated by Pacbio sequencers or
+Fastq files, or CCS files. CCS files can be built by the pipeline. Then, an
+assembler is used to build the draft assemblies (Canu, hifiasm, etc). From the
+draft, circularisation may be applied to generate circularised genome (useful
+for bacterial genomes). Finally, each contig is blasted and quality checks are
+performed using Busco, quast, etc.
+
+
+Rules and configuration details
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Here is the `latest documented configuration file <https://raw.githubusercontent.com/sequana/sequana_lora/master/sequana_pipelines/lora/config.yaml>`_
+to be used with the pipeline. Each rule used in the pipeline may have a section in the configuration file.
+
+Changelog
+~~~~~~~~~
+
+========= ====================================================================
+Version   Description
+========= ====================================================================
+1.0.0     * uniformised extension with other pipelines. fix regression on
+            schema file
+          * update sequana container to v0.16.5
+          * add unicyler apptainer
+          * add checkm module to help users chosing correct marker and name.
+          * replaces --pacbio and --nanopore with --data-type. pacbio is now
+            decompose into 3 sub-categories: pacbio-raw, pacbio-hifi and pacbio-corr
+          * add bandage if assembly graph is available
+          * fixed hifiasm container to use newest version
+          * improved report html
+          * make genome-size compulsary
+          * add fastp as preprocessing tool
+          * remove presets in favor of click options
+          * CCS defaults to hifi. pacbio presets in config set to pacbio-hifi
+          * blast removes from default. users must set blast DB themselves.
+          * busco lineage downloaded from the web.
+          * CANU preset changes: pacbio-->pacbio-hifi
+          * CANU-correction preset changes: pacbio-->pacbio-hifi
+          * FLYE preset changes: pacbio-raw-->pacbio-hifi
+0.3.0     * Use click instead of argparse
+          * added multiqc / checkm / unicycler
+0.2.0     * add apptainers in most rules
+          * remove utils.smk to move rulegraph inside main pipeline
+          * rename lora.smk into lora.rules for consistency with other
+            pipelines
+          * add checkm in the pipeline and HTML report
+0.1.0     **First release.**
+========= ====================================================================

sequana_lora-1.0.0/pyproject.toml

@@ -0,0 +1,72 @@
+[build-system]
+requires = ["poetry-core>=2.0"]
+build-backend = "poetry.core.masonry.api"
+
+[project]
+name = "sequana-lora"
+version = "1.0.0"
+description = "Run assembler (Canu, Flye, Hifiasm) on a set of long read files"
+authors =[{name="Sequana Team", email="thomas.cokelaer@pasteur.fr"}]
+license = "BSD-3"
+repository = "https://github.com/sequana/lora"
+readme = "README.rst"
+keywords = ["pacbio", "nanopore", "snakemake", "sequana", "assembly"]
+classifiers = [
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Education",
+        "Intended Audience :: End Users/Desktop",
+        "Intended Audience :: Developers",
+        "Intended Audience :: Science/Research",
+        "License :: OSI Approved :: BSD License",
+        "Operating System :: POSIX :: Linux",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+        "Topic :: Scientific/Engineering :: Bio-Informatics",
+        "Topic :: Scientific/Engineering :: Information Analysis",
+]
+requires-python = ">=3.9,<4.0"
+dependencies = [
+    "sequana-pipetools >=1.2.0",
+    "pandas >= 2.0.0",
+    "Jinja2 >=3.1.2",
+    "click-completion >=0.5.2",
+    "click >=8.1.7"
+]
+
+[tool.poetry]
+packages = [
+    { include = "sequana_pipelines" }
+]
+
+[project.scripts]
+sequana_lora = "sequana_pipelines.lora.main:main"
+
+[tool.poetry.group.dev.dependencies]
+ruff = "^0.0.264"
+pytest = "^7.0.1"
+black = "^23.3.0"
+ipython = "^8.0.1"
+pytest-mock = "^3.7.0"
+pytest-asyncio = "^0.18.1"
+snakefmt = "^0.8.4"
+
+[tool.ruff]
+select = [
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # pyflakes
+    "I",  # isort
+    "C",  # flake8-comprehensions
+    "B",  # flake8-bugbear
+]
+ignore = [
+    "E501",  # line too long, handled by black
+    "B008",  # do not perform function calls in argument defaults
+    "C901",  # too complex
+]
+line-length = 120
+
+[tool.pytest.ini_options]
+asyncio_mode = "strict"

sequana_lora-1.0.0/sequana_pipelines/lora/__init__.py

@@ -0,0 +1,12 @@
+import importlib.metadata as metadata
+
+
+def get_package_version(package_name):
+    try:
+        version = metadata.version(package_name)
+        return version
+    except metadata.PackageNotFoundError:
+        return f"{package_name} not found"
+
+
+version = get_package_version("sequana-lora")