nf-core · apeltzer · Dec 9, 2019 · Jun 23, 2019 · Jun 23, 2019 · Jun 23, 2019
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -6,7 +6,7 @@ We try to manage the required tasks for nf-core/scrnaseq using GitHub issues, yo
 
 However, don't be put off by this template - other more general issues and suggestions are welcome! Contributions to the code are even more welcome ;)
 
-> If you need help using or modifying nf-core/scrnaseq then the best place to ask is on the pipeline channel on [Slack](https://nf-core-invite.herokuapp.com/).
+> If you need help using or modifying nf-core/scrnaseq then the best place to ask is on the pipeline channel on [Slack](https://nfcore.slack.com/channels/scrnaseq).
 
 ## Contribution workflow
 
@@ -46,4 +46,4 @@ These tests are run both with the latest available version of Nextflow and also
 
 ## Getting help
 
-For further information/help, please consult the [nf-core/scrnaseq documentation](https://github.com/nf-core/scrnaseq#documentation) and don't hesitate to get in touch on the pipeline channel on [Slack](https://nf-core-invite.herokuapp.com/).
+For further information/help, please consult the [nf-core/scrnaseq documentation](https://github.com/nf-core/scrnaseq#documentation) and don't hesitate to get in touch on the pipeline channel on [Slack](https://nfcore.slack.com/channels/scrnaseq).
diff --git a/.github/markdownlint.yml b/.github/markdownlint.yml
@@ -1,9 +1,5 @@
 # Markdownlint configuration file
 default: true,
 line-length: false
-no-multiple-blanks: 0
-blanks-around-headers: false
-blanks-around-lists: false
-header-increment: false
 no-duplicate-header:
     siblings_only: true
diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml
@@ -0,0 +1,16 @@
+name: nfcore/scrnaseq branch protection
+# This workflow is triggered on PRs to master branch on the repository
+on:
+  pull_request:
+    branches:
+    - master
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      # PRs are only ok if coming from an nf-core dev branch
+      - uses: actions/checkout@v1
+      - name: Check PRs
+        run: |
+          [[ $(git remote get-url origin) == *nf-core/scrnaseq ]] && [ ${GITHUB_BASE_REF} = "master" ] && [ ${GITHUB_HEAD_REF} = "dev" ]
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -0,0 +1,26 @@
+name: scrnaseq CI
+# This workflow is triggered on pushes and PRs to the repository.
+on: [push, pull_request]  
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        nxf_ver: ['19.10.0', '']
+        profile: ['test,docker', 'test_kallisto,docker', 'test,docker --aligner star']
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          export NXF_VER=${{ matrix.nxf_ver }}
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - name: Download and tag image
+        run: |
+          docker pull nfcore/scrnaseq:dev
+          docker tag nfcore/scrnaseq:dev nfcore/scrnaseq:1.0.0
+      - name: "Test suites for all alignment methods"
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.profile }}
+
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
@@ -0,0 +1,53 @@
+name: nfcore/scrnaseq linting
+# This workflow is triggered on pushes and PRs to the repository.
+on: [push, pull_request]  
+
+jobs:
+  Markdown:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - uses: actions/setup-node@v1
+        with:
+          node-version: '10'
+      - name: Install markdownlint
+        run: |
+          npm install -g markdownlint-cli
+      - name: Run Markdownlint
+        run: |
+          markdownlint ${GITHUB_WORKSPACE} -c ${GITHUB_WORKSPACE}/.github/markdownlint.yml
+  YAML:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - uses: actions/setup-node@v1
+        with:
+          node-version: '10'
+      - name: Install yamllint
+        run: |
+          npm install -g yaml-lint
+      - name: Run yamllint
+        run: |
+          yamllint $(find ${GITHUB_WORKSPACE} -type f -name "*.yml")
+  nf-core:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - uses: actions/setup-python@v1
+        with:
+          python-version: '3.6'
+          architecture: 'x64'
+      - name: Install pip
+        run: |
+          sudo apt install python3-pip
+          pip install --upgrade pip
+      - name: Install nf-core tools
+        run: |
+          pip install nf-core
+      - name: Run nf-core lint
+        run: |
+          nf-core lint ${GITHUB_WORKSPACE}
diff --git a/.travis.yml b/.travis.yml
@@ -9,12 +9,12 @@ matrix:
 
 before_install:
   # PRs to master are only ok if coming from dev branch
-  - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && [ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ])'
+  - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && ([ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ] || [ $TRAVIS_PULL_REQUEST_BRANCH = "patch" ]))'
   # Pull the docker image first so the test doesn't wait for this
   - docker pull nfcore/scrnaseq:dev
   # Fake the tag locally so that the pipeline runs properly
   # Looks weird when this is :dev to :dev, but makes sense when testing code for a release (:dev to :1.0.1)
-  - docker tag nfcore/scrnaseq:dev nfcore/scrnaseq:dev
+  - docker tag nfcore/scrnaseq:dev nfcore/scrnaseq:1.0.0
 
 install:
   # Install Nextflow
@@ -24,19 +24,23 @@ install:
   # Install nf-core/tools
   - pip install --upgrade pip
   - pip install nf-core
+  # Install Conda 
+  - wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
+  - bash Miniconda3-latest-Linux-x86_64.sh -b -f -p $HOME/miniconda
+  - export PATH="$HOME/miniconda/bin:$PATH"
   # Reset
   - mkdir ${TRAVIS_BUILD_DIR}/tests && cd ${TRAVIS_BUILD_DIR}/tests
   # Install markdownlint-cli
   - sudo apt-get install npm && npm install -g markdownlint-cli
 
 env:
-  - NXF_VER='0.32.0' # Specify a minimum NF version that should be tested and work
-  - NXF_VER='' # Plus: get the latest NF version and check that it works
+  - NXF_VER='19.10.0' NXF_ANSI_LOG=0
+  - NXF_VER='' NXF_ANSI_LOG=0 
 
 script:
   # Lint the pipeline code
   - nf-core lint ${TRAVIS_BUILD_DIR}
-  # Lint the documentation
   - markdownlint ${TRAVIS_BUILD_DIR} -c ${TRAVIS_BUILD_DIR}/.github/markdownlint.yml
-  # Run the pipeline with the test profile
+  # REFERENCE: Run the basic pipeline with the test profile
   - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker
+  # All other tests run via GithUB Actions now
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,10 @@
 # nf-core/scrnaseq: Changelog
 
-## v1.0dev - [date]
+## v1.0.0 - 2019-11-28 "Tiny Aluminium Crab"
+
 Initial release of nf-core/scrnaseq, created with the [nf-core](http://nf-co.re/) template.
+This includes the following workflow options:
+
+* Salmon Alevin + AlevinQC
+* STARSolo
+* Kallisto / BUStools
diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md
@@ -34,7 +34,7 @@ This Code of Conduct applies both within project spaces and in public spaces whe
 
 ## Enforcement
 
-Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by contacting the project team on [Slack](https://nf-core-invite.herokuapp.com/). The project team will review and investigate all complaints, and will respond in a way that it deems appropriate to the circumstances. The project team is obligated to maintain confidentiality with regard to the reporter of an incident. Further details of specific enforcement policies may be posted separately.
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by contacting the project team on [Slack](https://nf-co.re/join/slack). The project team will review and investigate all complaints, and will respond in a way that it deems appropriate to the circumstances. The project team is obligated to maintain confidentiality with regard to the reporter of an incident. Further details of specific enforcement policies may be posted separately.
 
 Project maintainers who do not follow or enforce the Code of Conduct in good faith may face temporary or permanent repercussions as determined by other members of the project's leadership.
 

diff --git a/Dockerfile b/Dockerfile
@@ -1,7 +1,6 @@
-FROM nfcore/base
-LABEL authors="Peter J Bailey, Alexander Peltzer" \
+FROM nfcore/base:1.7
+LABEL authors="Peter J Bailey, Alexander Peltzer, Olga Botvinnik" \
       description="Docker image containing all requirements for nf-core/scrnaseq pipeline"
-
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-scrnaseq-1.0dev/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-scrnaseq-1.0.0/bin:$PATH
diff --git a/Makefile b/Makefile
diff --git a/README.md b/README.md
@@ -1,14 +1,17 @@
-# nf-core/scrnaseq
+# ![nf-core/scrnaseq](docs/images/nfcore-scrnaseq_logo.png)
 
-**A pipeline for the processing of single-cell rnaseq data**.
+**A fully automated Nextflow pipeline for Droplet-based (e.g. 10x Genomics) single-cell RNA-Seq data**.
 
-[![Build Status](https://travis-ci.com/nf-core/scrnaseq.svg?branch=master)](https://travis-ci.com/nf-core/scrnaseq)
-[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A50.32.0-brightgreen.svg)](https://www.nextflow.io/)
+[![Build Status](https://github.com/nf-core/scrnaseq/workflows/scrnaseq%20CI/badge.svg)](https://github.com/nf-core/scrnaseq/workflows/scrnaseq%20CI/badge.svg)
+[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A519.10.0-brightgreen.svg)](https://www.nextflow.io/)
 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](http://bioconda.github.io/)
 [![Docker](https://img.shields.io/docker/automated/nfcore/scrnaseq.svg)](https://hub.docker.com/r/nfcore/scrnaseq)
 
+[![Join us on Slack](https://img.shields.io/badge/slack-nfcore/scrnaseq-blue.svg)](https://nfcore.slack.com/channels/scrnaseq)
+
 ## Introduction
+
 The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It comes with docker containers making installation trivial and results highly reproducible.
 
 Work in progress - this is a community effort in building a pipeline capable to support:
@@ -30,15 +33,15 @@ The nf-core/scrnaseq pipeline comes with documentation about the pipeline, found
 4. [Output and how to interpret the results](docs/output.md)
 5. [Troubleshooting](https://nf-co.re/usage/troubleshooting)
 
-<!-- TODO nf-core: Add a brief overview of what the pipeline does and how it works -->
-
 ## Credits
 
-nf-core/scrnaseq was originally written by [Peter J. Bailey](https://github.com/PeterBailey) with some help from [Olga Botvinnik](https://github.com/olgabot) and [Alex Peltzer](https://github.com/apeltzer).
+The `nf-core/scrnaseq` was initiated by [Peter J. Bailey](https://github.com/PeterBailey) (Salmon Alevin, AlevinQC) with major contributions from [Olga Botvinnik](https://github.com/olgabot) (STARsolo, Testdata) and [Alex Peltzer](https://github.com/apeltzer) (Kallisto/BusTools workflow).
 
 ## Citation
 
-<!-- If you use nf-core/scrnaseq for your analysis, please cite it as follows: -->
-
 You can cite the `nf-core` pre-print as follows:  
 Ewels PA, Peltzer A, Fillinger S, Alneberg JA, Patel H, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. **nf-core: Community curated bioinformatics pipelines**. *bioRxiv*. 2019. p. 610741. [doi: 10.1101/610741](https://www.biorxiv.org/content/10.1101/610741v1).
+
+The basic benchmarks that were used as motivation for incorporating the three available modular workflows can be found in [this publication](https://www.biorxiv.org/content/10.1101/673285v2).
+
+We offer all three paths for the processing of scRNAseq data so it remains up to the user to decide which pipeline workflow is chosen for a particular analysis question.
diff --git a/bin/__pycache__/scrape_software_versions.cpython-36.pyc b/bin/__pycache__/scrape_software_versions.cpython-36.pyc
diff --git a/bin/alevin_qc.r b/bin/alevin_qc.r
@@ -7,17 +7,6 @@ if (length(args) < 3) {
   stop("Usage: alevin_qc.r <baseDir> <sampleId> <outDir>", call.=FALSE)
 }
 
-print(R.Version())
-
-if (!require("BiocManager")){
-    install.packages("BiocManager", dependencies=TRUE, repos='http://cloud.r-project.org/')
-    BiocManager::install()}
-
-if (!require("alevinQC")) {
-  BiocManager::install("alevinQC")
-}
-
-
 require(alevinQC)
 require(tximport)
 

diff --git a/bin/postprocessing.r b/bin/postprocessing.r
diff --git a/bin/scrape_software_versions.py b/bin/scrape_software_versions.py
@@ -3,19 +3,22 @@
 from collections import OrderedDict
 import re
 
-# TODO nf-core: Add additional regexes for new tools in process get_software_versions
 regexes = {
     'nf-core/scrnaseq': ['v_pipeline.txt', r"(\S+)"],
     'Nextflow': ['v_nextflow.txt', r"(\S+)"],
     'STAR': ['v_star.txt', r"(\S+)"],
     'Salmon': ['v_salmon.txt', r"salmon (\S+)"],
+    'Kallisto': ['v_kallisto.txt', r"kallisto, version (\S+)"],
+    'BUStools': ['v_bustools.txt', r"bustools (\S+)"],        
     'MultiQC': ['v_multiqc.txt', r"multiqc, version (\S+)"],
 }
 results = OrderedDict()
 results['nf-core/scrnaseq'] = '<span style="color:#999999;\">N/A</span>'
 results['Nextflow'] = '<span style="color:#999999;\">N/A</span>'
 results['STAR'] = '<span style="color:#999999;\">N/A</span>'
 results['Salmon'] = '<span style="color:#999999;\">N/A</span>'
+results['Kallisto'] = '<span style="color:#999999;\">N/A</span>'
+results['BUStools'] = '<span style="color:#999999;\">N/A</span>'
 results['MultiQC'] = '<span style="color:#999999;\">N/A</span>'
 
 # Search each file using its regex

diff --git a/bin/t2g.py b/bin/t2g.py
@@ -0,0 +1,99 @@
+#!/usr/bin/env python
+#This was downloaded on 2019-06-23 from https://github.com/bustools/getting_started/releases/ 
+#All credit goes to the original authors from the Kallisto/BUStools team!
+# BSD 2-Clause License
+# 
+# Copyright (c) 2017, Nicolas Bray, Harold Pimentel, Páll Melsted and Lior Pachter
+# 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.
+# 
+# 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.
+
+import sys, argparse
+
+def create_transcript_list(input, use_name = True, use_version = False):
+    r = {}
+    for line in input:
+        if len(line) == 0 or line[0] == '#':
+            continue
+        l = line.strip().split('\t')
+        if l[2] == 'transcript':
+            info = l[8]
+            d = {}
+            for x in info.split('; '):
+                x = x.strip()
+                p = x.find(' ')
+                if p == -1:
+                    continue
+                k = x[:p]
+                p = x.find('"',p)
+                p2 = x.find('"',p+1)
+                v = x[p+1:p2]
+                d[k] = v
+
+
+            if 'transcript_id' not in d or 'gene_id' not in d:
+                continue
+
+            tid = d['transcript_id'].split(".")[0]
+            gid = d['gene_id'].split(".")[0]
+            if use_version:
+                if 'transcript_version' not in d or 'gene_version' not in d:
+                    continue
+
+                tid += '.' + d['transcript_version']
+                gid += '.' + d['gene_version']
+            gname = None
+            if use_name:
+                if 'gene_name' not in d:
+                    continue
+                gname = d['gene_name']
+
+            if tid in r:
+                continue
+
+            r[tid] = (gid, gname)
+    return r
+
+
+
+def print_output(output, r, use_name = True):
+    for tid in r:
+        if use_name:
+            output.write("%s\t%s\t%s\n"%(tid, r[tid][0], r[tid][1]))
+        else:
+            output.write("%s\t%s\n"%(tid, r[tid][0]))
+
+
+if __name__ == "__main__":
+
+
+    parser = argparse.ArgumentParser(add_help=True, description='Creates transcript to gene info from GTF files\nreads from standard input and writes to standard output')
+    parser.add_argument('--use_version', '-v', action='store_true', help='Use version numbers in transcript and gene ids')
+    parser.add_argument('--skip_gene_names', '-s', action='store_true', help='Do not output gene names')
+    args = parser.parse_args()
+
+
+
+    input = sys.stdin
+    r = create_transcript_list(input, use_name = not args.skip_gene_names, use_version = args.use_version)
+    output = sys.stdout
+    print_output(output, r)