documentation

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SPHINXPROJ    = coproID
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -0,0 +1,36 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+set SPHINXPROJ=coproID
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+
+:end
+popd

docs/source/conf.py

@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+from recommonmark.parser import CommonMarkParser
+
+source_parsers = {
+    '.md': CommonMarkParser,
+}
+
+source_suffix = ['.rst', '.md']
+
+# -- Project information -----------------------------------------------------
+
+project = 'coproID'
+copyright = '2018, Maxime Borry'
+author = 'Maxime Borry'
+
+# The short X.Y version
+version = ''
+# The full version, including alpha/beta/rc tags
+release = ''
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.mathjax',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path .
+exclude_patterns = []
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'alabaster'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'coproIDdoc'
+
+
+# -- Options for LaTeX output ------------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'coproID.tex', 'coproID Documentation',
+     'Maxime Borry', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'coproid', 'coproID Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output ----------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'coproID', 'coproID Documentation',
+     author, 'coproID', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Extension configuration -------------------------------------------------

docs/source/index.rst

@@ -0,0 +1,25 @@
+.. coproID documentation master file, created by
+   sphinx-quickstart on Wed Sep 26 10:48:05 2018.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to coproID's documentation!
+===================================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   intro
+   installation
+   usage
+   output
+   troubleshooting
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/source/installation.md

@@ -0,0 +1,15 @@
+Installation
+============
+
+## Requirements
+
+- **OS:** Unix based operating system such as Ubuntu or Mac OS X
+- **conda:** Install miniconda using the appropriated installers (no root permission required) [conda.io/miniconda.html](https://conda.io/miniconda.html)
+- **Nextflow:** Install nextflow with conda by issuing the following command in your terminal: `conda install -c bioconda nextflow`
+
+## Installation
+
+Install **coproID** by issuing the following command in your terminal:
+```
+nextflow pull maxibor/coproid
+```

docs/source/intro.md

@@ -0,0 +1,67 @@
+Introduction
+============
+
+<img src="_static/_img/logo.png" height="150">
+
+**coproID** (**CO**prolite **ID**entification) is a tool developed at the [Max Planck insitute for the Science of Human History](http://www.shh.mpg.de/en) by [Maxime Borry](https://github.com/maxibor)
+
+The purpose of **coproID** is to help identify the host of given sequenced microbiome when there is a doubt between two species.
+
+**coproID** is a pipeline developed using [Nextflow](https://www.nextflow.io/) and [Conda](https://conda.io/docs/) to ensure scalability and reproducibility.
+
+Even though it was developed with coprolite host identification in mind, it can be applied to any microbiome, provided they contain host DNA.
+
+To run **coproID** you need to provide as input:
+- microbiome sequencing paired end `fastq` files
+- **two** reference genomes (either in `fasta` format, or already `bowtie2` indexed)
+- the names of the two reference species
+- if you choose to give the reference genomes as indexed `bowtie2` files, you also need to provide the genomes sizes.
+
+## Quick start
+
+Example:
+```
+nextflow run maxibor/coproid --genome1 'genome1.fa' --genome2 'genome2.fa' --name1 'Homo_sapiens' --name2 'Canis_familiaris' --reads '*_R{1,2}.fastq.gz'
+```
+
+## coproID help menu
+
+```
+$ nextflow run maxibor/coproid --help
+N E X T F L O W  ~  version 0.31.1
+Launching `maxibor/coproid` [stupefied_borg] - revision: f062739210
+
+=========================================
+ coproID: Coprolite Identification
+ Homepage / Documentation: https://github.com/maxibor/coproid
+ Author: Maxime Borry <borry@shh.mpg.de>
+ Version 0.4
+ Last updated on September 26th, 2018
+=========================================
+Usage:
+The typical command for running the pipeline is as follows:
+nextflow run maxibor/coproid --genome1 'genome1.fa' --genome2 'genome2.fa' --name1 'Homo_sapiens' --name2 'Canis_familiaris' --reads '*_R{1,2}.fastq.gz'
+Mandatory arguments:
+  --reads                       Path to input data (must be surrounded with quotes)
+  --name1                       Name of candidate 1. Example: "Homo sapiens"
+  --name2                       Name of candidate 2. Example: "Canis familiaris"
+
+Options:
+  --phred                       Specifies the fastq quality encoding (33 | 64). Defaults to 33
+  --genome1                     Path to candidate 1 Coprolite maker's genome fasta file (must be surrounded with quotes) - If index1 is not set
+  --index1                      Path to Bowtie2 index genome andidate 1 Coprolite maker's genome, in the form of /path/to/*.bt2 - If genome1 is not set
+  --genome1Size                 Size of candidate 1 Coprolite maker's genome in bp - If genome1 is not set
+  --genome2                     Path to candidate 2 Coprolite maker's genome fasta file (must be surrounded with quotes)- If index2 is not set
+  --index2                      Path to Bowtie2 index genome andidate 2 Coprolite maker's genome, in the form of /path/to/*.bt2 - If genome2 is not set
+  --genome2Size                 Size of candidate 2 Coprolite maker's genome in bp - If genome2 is not set
+  --identity                    Identity threshold to retain read alignment. Default = 0.85
+  --bowtie                      Bowtie settings for sensivity (very-fast | very-sensitive). Default = very-sensitive
+
+Other options:
+  --results                     Name of result directory. Defaults to ./results
+  --help  --h                   Shows this help page
+```
+
+## coproID example workFlow
+
+![](_static/_img/dag.png)

docs/source/output.md

@@ -0,0 +1,21 @@
+Output
+======
+
+## coproID results
+
+ `results/{fastq_file_basename}.html`  
+
+ This file is the report of **coproID** and contains explanations on how the calculation was performed, the files used, and your result.
+
+ An example **coproID** output file file can be found [here](_static/simulated_coprolyte.html)
+
+## coproID logs
+
+You can generate a log file report of coproID run by using nextflow reporting option `-with-report`
+
+Example:
+```
+nextflow run maxibor/coproid --genome1 'path/to/data/genomes/hsapiens.fa' --genome2 'path/to/data/genomes/cfamiliaris.fa' --name1 'data/genomes/Homo_sapiens' --name2 'Canis_familiaris' --reads '*_R{1,2}.fastq.gz' -with-report report.html
+```
+
+The log file will be saved in `report.html`

docs/source/troubleshooting.md

@@ -0,0 +1,8 @@
+Troubleshooting
+===============
+
+## Known issues
+On Mac OS X, the nextflow log reporting (`-with-report`) may not work with Nextflow v0.31.1. This should be fixed in future Nextflow releases
+
+## Other issues
+If you find a specific issue, please open an [issue](https://github.com/maxibor/coproid/issues) on [GitHub](https://github.com/maxibor/coproid/issues)