Merge pull request #29 from matt-sd-watson/rename_to_spora

Rename to spora

Author: matt-sd-watson

.github/workflows/main.yml

@@ -1,5 +1,5 @@
 
-name: outbreaker
+name: spora
 
 # Controls when the workflow will run
 on:
@@ -12,7 +12,7 @@ on:
 
 jobs:
   build:
-    name: Outbreaker test on ${{ matrix.os }}
+    name: spora test on ${{ matrix.os }}
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
@@ -22,20 +22,20 @@ jobs:
       - uses: conda-incubator/setup-miniconda@v2
         with:
           environment-file: environments/environment.yml
-          activate-environment: ncov_outbreaker
+          activate-environment: ncov_spora
           channels: conda-forge,bioconda,defaults,r
           mamba-version: "*"
-      - name: Install outbreaker
+      - name: Install spora
         run: pip install .
-      - name: Check outbreaker version
+      - name: Check spora version
         shell: bash -l {0}
-        run: outbreaker -v
-      - name: Run outbreaker test via CLI
+        run: spora -v
+      - name: Run spora test via CLI
         shell: bash -l {0}
-        run: outbreaker -f data/tests/focal_seqs.fa -b data/tests/background_seqs.fa -r data/reference/ncov_reference.gb -o outbreaker_test -p test --snps-only --report --rename --names-csv data/tests/names.csv
-      - name: Run outbreaker test via config
+        run: spora -f data/tests/focal_seqs.fa -b data/tests/background_seqs.fa -r data/reference/ncov_reference.gb -o outbreaker_test -p test --snps-only --report --rename --names-csv data/tests/names.csv
+      - name: Run spora test via config
         shell: bash -l {0}
-        run: outbreaker -c data/test_config.yaml
-      - name: Run pytest for outbreaker
+        run: spora -c data/test_config.yaml
+      - name: Run pytest for spora
         shell: bash -l {0}
         run: pytest tests/

.github/workflows/publish.yml

@@ -0,0 +1,31 @@
+name: Publish spora to PyPI on release tag
+
+on:
+  release:
+      types:
+          - "published"
+jobs:
+  pypi_publish:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v4.0.0
+        with:
+          python-version: 3.8
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine
+          pip install pandas>=1.1.5 numpy>=1.19 biopython>=1.79 pytest>=7.1.2 snakemake>=7.0.0 pypandoc>=1.8
+      - name: build package
+        run: |
+          pip install pandoc>=2.2
+          python setup.py sdist bdist_wheel 
+      - name: publish to PyPI
+        # only create relases from tagged commits to master:
+        if: startsWith(github.ref, 'refs/tags')
+        uses: pypa/gh-action-pypi-publish@v1.5.0
+        with:
+          # if no "user:" specified use pypi token instead of username/password
+          password: ${{ secrets.PUBLISH_PYPI_SPORA }} # use secret from github secrets

CHANGELOG.md

@@ -1,4 +1,4 @@
-# outbreaker Changelog
+# spora Changelog
 
 ## Version 0.1.0, 06-10-21
 - Initial workflow
@@ -66,3 +66,9 @@
  - Above fix changes fixes the error in the SNP distance plot in the HTML report when rename is used but no names CSV is supplied
  - Addition of pytests in the CI/CD workflow
 
+ ## Version 0.7.0, 15-06-22
+ 
+ - outbreaker is renamed to spora to be compatible with PyPi
+ - version change to dplyr dependency for conda env
+ - Addition of CD GA workflow to pudblish to PyPi on release
+ 

README.md

@@ -1,24 +1,24 @@
-# outbreaker
+# spora: Streamlined Phylogenomic Outbreak Report Analysis
 
-![example workflow](https://github.com/matt-sd-watson/outbreaker/actions/workflows/main.yml/badge.svg)
+![example workflow](https://github.com/matt-sd-watson/spora/actions/workflows/main.yml/badge.svg)
 
 snakemake and Python integrated workflow for intermediate file generation for COVID outbreak analysis
 
 ## Installation
 
 ```
-git clone https://github.com/matt-sd-watson/outbreaker.git
-conda env create -f ncov_outbreaker/environments/environment.yml
-conda activate ncov_outbreaker
-cd outbreaker
+git clone https://github.com/matt-sd-watson/spora.git
+conda env create -f ncov_spora/environments/environment.yml
+conda activate ncov_spora
+cd spora
 pip install . 
 ```
 
 ## Updating
 
 ```
-conda activate ncov_outbreaker
-cd ~/outbreaker
+conda activate ncov_spora
+cd ~/spora
 git checkout main
 git pull
 pip install . 
@@ -27,11 +27,11 @@ pip install .
 ## Usage
 ```
 usage: 
-    	outbreaker -c <config.yaml> 
+    	spora -c <config.yaml> 
     	OR
-    	outbreaker --focal_list ...<input args>
+    	spora --focal_list ...<input args>
 
-Outbreaker: Python and snakemake outbreak workflow for COVID-19
+spora: Streamlined Phylogenomic Outbreak Report Analysis
 
 optional arguments:
   -h, --help            Show the help output and exit.
@@ -42,16 +42,15 @@ optional arguments:
   -b BACKGROUND_SEQS, --background-sequences BACKGROUND_SEQS
                         Optional input .txt list or multi-FASTA background samples to add to analysis
   -m MASTER_FASTA, --master-fasta MASTER_FASTA
-                        Master FASTA of genomic sequences to select from. Required if either --focal-sequences or --background-sequences are not supplied in
-                        FASTA format
+                        Master FASTA of genomic sequences to select from. Required if either --focal-sequences or --background-sequences are not supplied in FASTA format
   -o OUTDIR, --output-directory OUTDIR
-                        Path to the desired output directory. If none is provided, a new folder named outbreaker will be created in the current directory
+                        Path to the desired output directory. If none is provided, a new folder named spora will be created in the current directory
   -r REFERENCE, --reference REFERENCE
                         .gb file containing the desired COVID-19 reference sequence. Required
   -p PREFIX, --prefix PREFIX
                         Prefix string to label all output files. Default: outbreak
   -t NTHREADS, --nthreads NTHREADS
-                        Number of threads to use for processing. Default: 4
+                        Number of threads to use for processing. Default: 2
   -s, --snps-only       Generate a snps-only FASTA from the input FASTA. Default: False
   -rn, --rename         Rename the FASTA headers to be compatible with NML standards. Default: False
   -nc NAMES_CSV, --names-csv NAMES_CSV
@@ -63,16 +62,16 @@ optional arguments:
                         Integer for the minimum genome completeness percentage for filtering. Default: 90
   -gl GENOME_LENGTH, --genome-length GENOME_LENGTH
                         Integer for the minimum genome length for filtering. Default: 29500
-  -rp, --report         Generate a summary output report for the outbreaker run. Default: Not enabled
-  -v, --version         Show the current outbreaker version then exit.
+  -rp, --report         Generate a summary output report for the spora run. Default: Not enabled
+  -v, --version         Show the current spora version then exit.
 ```
 
 ## Documentation
 
-More detailed documentation for outbreaker usage and functionality can be found [here](docs/0-OVERVIEW.md)
+More detailed documentation for spora usage and functionality can be found [here](docs/0-OVERVIEW.md)
 
 ## Acknowledgments
 
-Inspiration for code structure and design for outbreaker was inspired by [pangolin](https://github.com/cov-lineages/pangolin) and [civet](https://github.com/artic-network/civet), and minor code blocks were adopted from these software.
+Inspiration for code structure and design for spora was inspired by [pangolin](https://github.com/cov-lineages/pangolin) and [civet](https://github.com/artic-network/civet), and minor code blocks were adopted from these software.
 
 The **Background** section in the documentation describing outbreak definitions was written by Mark Horsman. 

data/test_config.yaml

@@ -4,7 +4,7 @@ background_seqs: tests/background_seqs.fa
 
 reference: reference/ncov_reference.gb
 
-outdir: outbreaker_test_config
+outdir: spora_test_config
 
 snps_only: True
 

docs/0-OVERVIEW.md

@@ -1,8 +1,8 @@
-# outbreaker
+# spora
 
 ## Overview
-outbreaker is a workflow written in snakemake and Python that aims to facilitate rapid generation of intermediate input files that are required for outbreak analysis for COVID-19 at PHO. The workflow is designed to be flexible with command line inputs, providing users with options that can be toggled depending on the nature of the outbreak request and the input files required for downstream outbreak analysis tools. 
-At its core, outbreaker is designed to accept only a small number of mandatory inputs from the user, and will use a standard set of bioinformatics tools to produce a number of output files such as alignments, trees, SNP matrices, etc., that are often the required inputs for downstream outbreak tools such as [ggtree](https://github.com/YuLab-SMU/ggtree) and/or [civet/civet3](https://github.com/snake-flu/civet3). 
+spora is a workflow written in snakemake and Python that aims to facilitate rapid generation of intermediate input files that are required for outbreak analysis for COVID-19 at PHO. The workflow is designed to be flexible with command line inputs, providing users with options that can be toggled depending on the nature of the outbreak request and the input files required for downstream outbreak analysis tools. 
+At its core, spora is designed to accept only a small number of mandatory inputs from the user, and will use a standard set of bioinformatics tools to produce a number of output files such as alignments, trees, SNP matrices, etc., that are often the required inputs for downstream outbreak tools such as [ggtree](https://github.com/YuLab-SMU/ggtree) and/or [civet/civet3](https://github.com/snake-flu/civet3). 
 
 
 ## Background
@@ -13,7 +13,7 @@ At the same time, WGS data from COVID-19 cases known to not be involved in the s
 ## Workflow
 
 <p align="center">
-    <img src="images/outbreaker_workflow.png">
+    <img src="images/spora_workflow.png">
 </p>
 
 

docs/1-INSTALLATION.md

@@ -8,34 +8,34 @@ The following tools/packages are required: \
 
 ## Basic installation from source
 
-The basic installation instructions for outbreaker are as follows: 
+The basic installation instructions for spora are as follows: 
 
 ```
-git clone https://github.com/matt-sd-watson/outbreaker.git
-conda env create -f outbreaker/environments/environment.yml
-conda activate ncov_outbreaker
-cd outbreaker
+git clone https://github.com/matt-sd-watson/spora.git
+conda env create -f spora/environments/environment.yml
+conda activate ncov_spora
+cd spora
 pip install .
 ```
 
 ## Usage
 
 Test that the installation was successful using the following commands: 
 ```
-outbreaker
+spora
 #OR
-outbreaker --help
+spora --help
 ```
 
 which should result in the following output: 
 
 ```
 usage: 
-    	outbreaker -c <config.yaml> 
+    	spora -c <config.yaml> 
     	OR
-    	outbreaker --focal_list ...<input args>
+    	spora --focal_list ...<input args>
 
-Outbreaker: Python and snakemake outbreak workflow for COVID-19
+spora: Python and snakemake outbreak workflow for COVID-19
 
 optional arguments:
   -h, --help            Show the help output and exit.
@@ -49,7 +49,7 @@ optional arguments:
                         Master FASTA of genomic sequences to select from. Required if either --focal-sequences or --background-sequences are not supplied in
                         FASTA format
   -o OUTDIR, --output-directory OUTDIR
-                        Path to the desired output directory. If none is provided, a new folder named outbreaker will be created in the current directory
+                        Path to the desired output directory. If none is provided, a new folder named spora will be created in the current directory
   -r REFERENCE, --reference REFERENCE
                         .gb file containing the desired COVID-19 reference sequence. Required
   -p PREFIX, --prefix PREFIX
@@ -67,8 +67,8 @@ optional arguments:
                         Integer for the minimum genome completeness percentage for filtering. Default: 90
   -gl GENOME_LENGTH, --genome-length GENOME_LENGTH
                         Integer for the minimum genome length for filtering. Default: 29500
-  -rp, --report         Generate a summary output report for the outbreaker run. Default: Not enabled
-  -v, --version         Show the current outbreaker version then exit.
+  -rp, --report         Generate a summary output report for the spora run. Default: Not enabled
+  -v, --version         Show the current spora version then exit.
   
 ```