RiboMetric 0.1.2__tar.gz

RiboMetric-0.1.2/AUTHORS.rst

@@ -0,0 +1,13 @@
+=======
+Credits
+=======
+
+Development Lead
+----------------
+
+* Jack Tierney <jackcurragh@gmail.com>
+
+Contributors
+------------
+
+None yet. Why not be the first?

RiboMetric-0.1.2/CONTRIBUTING.rst

@@ -0,0 +1,128 @@
+.. highlight:: shell
+
+============
+Contributing
+============
+
+Contributions are welcome, and they are greatly appreciated! Every little bit
+helps, and credit will always be given.
+
+You can contribute in many ways:
+
+Types of Contributions
+----------------------
+
+Report Bugs
+~~~~~~~~~~~
+
+Report bugs at https://github.com/JackCurragh/Ribosome/issues.
+
+If you are reporting a bug, please include:
+
+* Your operating system name and version.
+* Any details about your local setup that might be helpful in troubleshooting.
+* Detailed steps to reproduce the bug.
+
+Fix Bugs
+~~~~~~~~
+
+Look through the GitHub issues for bugs. Anything tagged with "bug" and "help
+wanted" is open to whoever wants to implement it.
+
+Implement Features
+~~~~~~~~~~~~~~~~~~
+
+Look through the GitHub issues for features. Anything tagged with "enhancement"
+and "help wanted" is open to whoever wants to implement it.
+
+Write Documentation
+~~~~~~~~~~~~~~~~~~~
+
+RiboMetric could always use more documentation, whether as part of the
+official RiboMetric docs, in docstrings, or even on the web in blog posts,
+articles, and such.
+
+Submit Feedback
+~~~~~~~~~~~~~~~
+
+The best way to send feedback is to file an issue at https://github.com/JackCurragh/RiboMetric/issues.
+
+If you are proposing a feature:
+
+* Explain in detail how it would work.
+* Keep the scope as narrow as possible, to make it easier to implement.
+* Remember that this is a volunteer-driven project, and that contributions
+  are welcome :)
+
+Get Started!
+------------
+
+Ready to contribute? Here's how to set up `RiboMetric` for local development.
+
+1. Fork the `RiboMetric` repo on GitHub.
+2. Clone your fork locally::
+
+    $ git clone git@github.com:your_name_here/RiboMetric.git
+
+3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development::
+
+    $ mkvirtualenv RiboMetric
+    $ cd RiboMetric/
+    $ python setup.py develop
+
+4. Create a branch for local development::
+
+    $ git checkout -b name-of-your-bugfix-or-feature
+
+   Now you can make your changes locally.
+
+5. When you're done making changes, check that your changes pass flake8 and the
+   tests, including testing other Python versions with tox::
+
+    $ flake8 RiboMetric tests
+    $ python setup.py test or pytest
+    $ tox
+
+   To get flake8 and tox, just pip install them into your virtualenv.
+
+6. Commit your changes and push your branch to GitHub::
+
+    $ git add .
+    $ git commit -m "Your detailed description of your changes."
+    $ git push origin name-of-your-bugfix-or-feature
+
+7. Submit a pull request through the GitHub website.
+
+Pull Request Guidelines
+-----------------------
+
+Before you submit a pull request, check that it meets these guidelines:
+
+1. The pull request should include tests.
+2. If the pull request adds functionality, the docs should be updated. Put
+   your new functionality into a function with a docstring, and add the
+   feature to the list in README.rst.
+3. The pull request should work for Python 3.5, 3.6, 3.7 and 3.8, and for PyPy. Check
+   https://travis-ci.com/JackCurragh/RiboMetric/pull_requests
+   and make sure that the tests pass for all supported Python versions.
+
+Tips
+----
+
+To run a subset of tests::
+
+$ pytest tests.test_RiboMetric
+
+
+Deploying
+---------
+
+A reminder for the maintainers on how to deploy.
+Make sure all your changes are committed (including an entry in HISTORY.rst).
+Then run::
+
+$ bump2version patch # possible: major / minor / patch
+$ git push
+$ git push --tags
+
+Travis will then deploy to PyPI if tests pass.

RiboMetric-0.1.2/HISTORY.rst

@@ -0,0 +1,8 @@
+=======
+History
+=======
+
+0.1.0 (2023-04-10)
+------------------
+
+* First release on PyPI.

RiboMetric-0.1.2/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2023, Jack Tierney
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

RiboMetric-0.1.2/MANIFEST.in

@@ -0,0 +1,12 @@
+include AUTHORS.rst
+include CONTRIBUTING.rst
+include HISTORY.rst
+include LICENSE
+include README.rst
+
+recursive-include tests *
+recursive-exclude * __pycache__
+recursive-exclude * *.py[co]
+recursive-exclude sample_data *
+
+recursive-include docs *.rst conf.py Makefile make.bat *.jpg *.png *.gif

RiboMetric-0.1.2/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.1
+Name: RiboMetric
+Version: 0.1.2
+Summary: A python command-line utility for the generation of comprehensive reports on the quality of ribosome profiling (Ribo-Seq) datasets
+Home-page: https://github.com/JackCurragh/RiboMetric
+Author: Jack Tierney
+Author-email: jackcurragh@gmail.com
+License: MIT license
+Keywords: RiboMetric
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.8
+License-File: LICENSE
+License-File: AUTHORS.rst

RiboMetric-0.1.2/README.rst

@@ -0,0 +1,41 @@
+================
+RiboMetric
+================
+
+
+.. image:: https://img.shields.io/pypi/v/RiboMetric.svg
+        :target: https://pypi.python.org/pypi/RiboMetric
+
+.. image:: https://readthedocs.org/projects/RiboMetric/badge/?version=latest
+        :target: https://RiboMetric.readthedocs.io/en/latest/?version=latest
+        :alt: Documentation Status
+
+
+.. image:: https://pyup.io/repos/github/JackCurragh/RiboMetric/shield.svg
+     :target: https://pyup.io/repos/github/JackCurragh/RiboMetric/
+     :alt: Updates
+
+
+
+ A python command-line utility for the generation of comprehensive reports on the quality of ribosome profiling (Ribo-Seq) datasets 
+
+
+* Free software: MIT license
+* Documentation: https://RiboMetric.readthedocs.io.
+
+
+Features
+--------
+
+There are a number of limitations to running RiboMetric at the moment. These include:
+
+  * Transciptomic alignments are required in BAM format 
+  * GFF annotations from Ensembl are also requried
+
+Credits
+-------
+
+This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.
+
+.. _Cookiecutter: https://github.com/audreyr/cookiecutter
+.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage

RiboMetric-0.1.2/RiboMetric/RiboMetric.py

@@ -0,0 +1,387 @@
+"""
+Main module for RiboMetric
+Handles the command line interface and calls the appropriate functions
+
+Many different input combinations are possible.
+
+Minimal Set:
+    -b, --bam <path> : Path to the bam file
+
+With this set the calculations will potentially less reliable and no gene
+feature information will be included in the output
+
+Standard Set:
+    -b, --bam <path> : Path to the bam file
+    -g, --gff <path> : Path to the gff file
+
+with this set the calculations will be more reliable and gene feature
+information will be included in the output
+
+Full Set:
+    -b, --bam <path> : Path to the bam file
+    -g, --gff <path> : Path to the gff file
+    -t, --transcriptome <path> : Path to the transcriptome fasta file
+
+with this set the calculations will contain the post information in its
+output but will take longest to run
+
+
+Optional Arguments:
+    -n, --name <str> : Name of the sample being analysed
+                        (default: filename of bam file)
+    -S, --subsample <int> : Number of reads to subsample from the bam file
+                        (default: 10000000)
+    -T, --transcripts <int> : Number of transcripts to consider
+                        (default: 100000)
+    -c, --config <path> : Path to the config file
+                        (default: config.yaml)
+
+Output:
+    --json : Output the results as a json file
+    --html : Output the results as an html file (default)
+    --pdf : Output the results as a pdf file (default)
+    --csv : Output the results as a csv file
+    --all : Output the results as all of the above
+"""
+
+import argparse
+from rich.console import Console
+from rich.text import Text
+from rich.table import Table
+from rich.emoji import Emoji
+
+import yaml
+
+from .file_parser import (
+    parse_bam,
+    parse_fasta,
+    parse_annotation,
+    prepare_annotation,
+)
+from .qc import annotation_free_mode, annotation_mode, sequence_mode
+from .plots import generate_plots
+from .modules import a_site_calculation
+from .html_report import generate_report
+from .json_output import generate_json
+
+
+def print_logo(console):
+    """
+    print the logo to the console
+    """
+    logo = Text(
+        """
+    ██████╗  ██╗ ██████╗  ██████╗ ███████╗ ██████╗ ███╗   ███╗███████╗
+    ██╔══██╗ ██║ ██╔══██╗██╔═══██╗██╔════╝██╔═══██╗████╗ ████║██╔════╝
+    ██████╔╝ ██║ ██████╔╝██║   ██║███████╗██║   ██║██╔████╔██║█████╗
+    ██╔══██╗ ██║ ██╔══██╗██║   ██║╚════██║██║   ██║██║╚██╔╝██║██╔══╝
+    ██║  ██║ ██║ ██████╔╝╚██████╔╝███████║╚██████╔╝██║ ╚═╝ ██║███████╗
+    ╚═╝  ╚═╝ ╚═╝ ══════╝  ╚═════╝ ╚══════╝ ╚═════╝ ╚═╝     ╚═╝╚══════╝
+    """,
+        style="bold blue",
+    )
+    logo += Text(
+        """
+    ██████╗  ██████╗  ██████╗ ███████╗██╗██╗    ███████╗██████╗
+    ██╔══██╗ ██╔══██╗██╔═══██╗██╔════╝██║██║    ██╔════╝██╔══██╗
+    ██████╔╝ ██████╔╝██║   ██║█████╗  ██║██║    █████╗  ██████╔╝
+    ██╔═══╝  ██╔══██╗██║   ██║██╔══╝  ██║██║    ██╔══╝  ██╔══██╗
+    ██║      ██║  ██║╚██████╔╝██║     ██║██████╗███████╗██║  ██║
+    ╚═╝      ╚═╝  ╚═╝ ╚═════╝ ╚═╝     ╚═╝╚═════╝╚══════╝╚═╝  ╚═╝
+    """,
+        style="bold red",
+    )
+    console.print(logo)
+
+
+def print_table_run(args, console, mode):
+    console = Console()
+
+    Inputs = Table(show_header=True, header_style="bold magenta")
+    Inputs.add_column("Parameters", style="dim", width=20)
+    Inputs.add_column("Values")
+    Inputs.add_row("Bam File:", args.bam)
+    Inputs.add_row("Gff File:", args.gff)
+    Inputs.add_row("Transcriptome File:", args.fasta)
+
+    Configs = Table(show_header=True, header_style="bold yellow")
+    Configs.add_column("Options", style="dim", width=20)
+    Configs.add_column("Values")
+    Configs.add_row("Mode:", mode)
+    Configs.add_row("# of reads:", str(args.subsample))
+    Configs.add_row("# of transcripts:", str(args.transcripts))
+    Configs.add_row("Config file:", args.config)
+
+    Output = Table(show_header=True, header_style="bold blue")
+    Output.add_column("Output Options", style="dim", width=20)
+    Output.add_column("Values")
+    Output.add_row("JSON:", str(args.json))
+    Output.add_row("HTML:", str(args.html))
+    Output.add_row("PDF:", str(args.pdf))
+    Output.add_row("CSV:", str(args.csv))
+    Output.add_row("All:", str(args.all))
+
+    # Print tables side by side
+    console.print(Inputs, Configs, Output, justify="inline", style="bold")
+
+
+def print_table_prepare(args, console, mode):
+    console = Console()
+
+    Inputs = Table(show_header=True, header_style="bold magenta")
+    Inputs.add_column("Parameters", style="dim", width=20)
+    Inputs.add_column("Values")
+    Inputs.add_row("Gff File:", args.gff)
+
+    Configs = Table(show_header=True, header_style="bold yellow")
+    Configs.add_column("Options", style="dim", width=20)
+    Configs.add_column("Values")
+    Configs.add_row("Mode:", mode)
+    Configs.add_row("# of transcripts:", str(args.transcripts))
+    Configs.add_row("Config file:", args.config)
+
+    # Print tables side by side
+    console.print(Inputs, Configs, justify="inline", style="bold")
+
+
+def argument_parser():
+    """
+    Parse the command line arguments and return the parser object
+
+    Inputs:
+        None
+
+    Outputs:
+        parser: ArgumentParser object containing the parsed arguments
+    """
+    parser = argparse.ArgumentParser(
+        description="""A python command-line utility for the generation
+                        of comprehensive reports on the quality of ribosome
+                        profiling (Ribo-Seq) datasets""",
+        epilog=f"""
+
+            Made with {Emoji('heart')} in LAPTI lab at University College Cork.
+            For more information, please visit:
+            https://RiboMetric.readthedocs.io/en/latest/
+            """,
+    )
+
+    subparsers = parser.add_subparsers(dest="command", title="subcommands")
+
+    # create the parser for the "run" command
+    run_parser = subparsers.add_parser(
+        "run", help="run RiboMetric in normal mode"
+    )
+    run_parser.add_argument(
+        "-b", "--bam", type=str, required=True, help="Path to bam file"
+    )
+    run_parser.add_argument(
+        "-a",
+        "--annotation",
+        type=str,
+        required=False,
+        help="Path to RiboMetric annotation file",
+    )
+    run_parser.add_argument(
+        "-g", "--gff", type=str, required=False, help="Path to gff file"
+    )
+    run_parser.add_argument(
+        "-f",
+        "--fasta",
+        type=str,
+        required=False,
+        help="Path to the transcriptome fasta file",
+    )
+    run_parser.add_argument(
+        "-n",
+        "--name",
+        type=str,
+        required=False,
+        help="""Name of the sample being analysed
+            (default: filename of bam file)""",
+    )
+    run_parser.add_argument(
+        "-o",
+        "--output",
+        type=str,
+        required=False,
+        default=".",
+        help="""Path to the output directory
+            (default: current directory)""",
+    )
+    run_parser.add_argument(
+        "-S",
+        "--subsample",
+        type=int,
+        required=False,
+        default=1000000,
+        help="""Number of reads to subsample from the bam file
+            (default: 10000000)""",
+    )
+    run_parser.add_argument(
+        "-T",
+        "--transcripts",
+        type=int,
+        required=False,
+        default=100000,
+        help="Number of transcripts to consider (default: 100000)",
+    )
+    run_parser.add_argument(
+        "-c",
+        "--config",
+        type=str,
+        required=False,
+        default="config.yml",
+        help="Path to the config file (default: config.yml)",
+    )
+    run_parser.add_argument(
+        "--json",
+        action="store_true",
+        default=False,
+        help="Output the results as a json file",
+    )
+    run_parser.add_argument(
+        "--html",
+        action="store_true",
+        default=True,
+        help="Output the results as an html file (default)",
+    )
+    run_parser.add_argument(
+        "--pdf",
+        action="store_true",
+        default=False,
+        help="Output the results as a pdf file (default)",
+    )
+    run_parser.add_argument(
+        "--csv",
+        action="store_true",
+        default=False,
+        help="Output the results as a csv file",
+    )
+    run_parser.add_argument(
+        "--all",
+        action="store_true",
+        default=False,
+        help="Output the results as all of the above",
+    )
+
+    # create the parser for the "prepare" command
+    prepare_parser = subparsers.add_parser(
+        "prepare", help="run RiboMetric in preparation mode"
+    )
+    prepare_parser.add_argument(
+        "-g", "--gff", type=str, required=True, help="Path to gff file"
+    )
+    prepare_parser.add_argument(
+        "-T",
+        "--transcripts",
+        type=int,
+        required=False,
+        default=10000000000,
+        help="Number of transcripts to consider (default: 100000)",
+    )
+    prepare_parser.add_argument(
+        "-o",
+        "--output",
+        type=str,
+        required=False,
+        default=".",
+        help="""Path to the output directory
+            (default: current directory)""",
+    )
+    prepare_parser.add_argument(
+        "-c",
+        "--config",
+        type=str,
+        required=False,
+        default="config.yml",
+        help="Path to the config file (default: config.yml)",
+    )
+    return parser
+
+
+def main(args):
+    """
+    Main function for the RiboMetric command line interface
+
+    Inputs:
+        args: Namespace object containing the parsed arguments
+
+    Outputs:
+        None
+    """
+    console = Console()
+    print_logo(console)
+
+    with open(args.config, "r") as ymlfile:
+        config = yaml.load(ymlfile, Loader=yaml.Loader)
+
+    if args.command == "prepare":
+        print_table_prepare(args, console, "Prepare Mode")
+        prepare_annotation(args.gff, args.output, args.transcripts, config)
+
+    else:
+        if args.all:
+            args.json = True
+            args.html = True
+            args.pdf = True
+            args.csv = True
+        print_table_run(args, console, "Run Mode")
+
+        if args.html:
+            if args.pdf:
+                report_export = "both"
+            else:
+                report_export = "html"
+        elif args.pdf:
+            report_export = "pdf"
+
+        read_df_pre = parse_bam(args.bam, args.subsample)
+        print("Reads parsed")
+
+        # Expand the dataframe to have one row per read
+        print("Expanding dataframe")
+        read_df = read_df_pre.loc[
+            read_df_pre.index.repeat(read_df_pre["count"])
+        ].reset_index(drop=True)
+        print("Dataframe expanded")
+        print("Calculating A site information")
+        read_df = a_site_calculation(read_df)
+
+        if args.gff is None and args.annotation is None:
+            results_dict = annotation_free_mode(read_df, config)
+
+        else:
+            if args.annotation is not None and args.gff is not None:
+                print("Both annotation and gff provided, using annotation")
+                annotation_df = parse_annotation(args.annotation)
+            elif args.annotation is None and args.gff is not None:
+                print("Gff provided, preparing annotation")
+                annotation_df = prepare_annotation(
+                    args.gff, args.output, args.transcripts, config
+                )
+                print("Annotation prepared")
+            elif args.annotation is not None and args.gff is None:
+                print("Annotation provided, parsing")
+                annotation_df = parse_annotation(args.annotation)
+                print("Annotation parsed")
+
+                print("Running annotation mode")
+                results_dict = annotation_mode(read_df, annotation_df, config)
+
+            if args.fasta is not None:
+                fasta_dict = parse_fasta(args.fasta)
+
+                results_dict = sequence_mode(results_dict, read_df, fasta_dict, config)
+        if args.html or args.pdf:
+            plots_list = generate_plots(results_dict, config)
+            generate_report(plots_list, config, report_export)
+        if args.json:
+            generate_json(results_dict, config)
+
+
+if __name__ == "__main__":
+    parser = argument_parser()
+    args = parser.parse_args()
+
+    main(args)

RiboMetric-0.1.2/RiboMetric/__init__.py

@@ -0,0 +1,5 @@
+"""Top-level package for RiboMetric."""
+
+__author__ = """Jack Tierney"""
+__email__ = "jackcurragh@gmail.com"
+__version__ = "0.1.0"

RiboMetric-0.1.2/RiboMetric/cli.py

@@ -0,0 +1,17 @@
+"""Console script for RiboMetric."""
+import sys
+
+from .RiboMetric import argument_parser as p, main as m
+
+
+def main():
+    """Console script for RiboMetric."""
+    parser = p()
+    args = parser.parse_args()
+
+    m(args)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())  # pragma: no cover