From f56fe092114babc34d2b10be7712baf7d52f4beb Mon Sep 17 00:00:00 2001
From: nf-core-bot <core@nf-co.re>
Date: Tue, 30 Aug 2022 13:31:16 +0000
Subject: [PATCH] Template update for nf-core/tools version 2.5
---
.editorconfig | 2 +-
.github/PULL_REQUEST_TEMPLATE.md | 3 +-
.github/workflows/ci.yml | 23 ++------
.github/workflows/linting.yml | 38 +++++++++++--
CITATION.cff | 56 +++++++++++++++++++
README.md | 21 +++----
assets/email_template.txt | 1 -
bin/check_samplesheet.py | 41 +++++++-------
conf/base.config | 5 ++
docs/usage.md | 12 ++--
lib/WorkflowHic.groovy | 5 +-
lib/WorkflowMain.groovy | 9 ++-
main.nf | 2 +-
modules.json | 22 +++++---
.../templates/dumpsoftwareversions.py | 14 +++--
nextflow.config | 21 ++++++-
16 files changed, 184 insertions(+), 91 deletions(-)
create mode 100644 CITATION.cff
diff --git a/.editorconfig b/.editorconfig
index b6b3190..b78de6e 100644
--- a/.editorconfig
+++ b/.editorconfig
@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
indent_size = 4
indent_style = space
-[*.{md,yml,yaml,html,css,scss,js}]
+[*.{md,yml,yaml,html,css,scss,js,cff}]
indent_size = 2
# These files are edited and tested upstream in nf-core/modules
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 56233aa..c67458d 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -15,8 +15,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/hic/
- [ ] This comment contains a description of changes (with reason).
- [ ] If you've fixed a bug or added code that should be tested, add tests!
- - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/hic/tree/master/.github/CONTRIBUTING.md)
- - [ ] If necessary, also make a PR on the nf-core/hic _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/hic/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/hic _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
- [ ] Make sure your code lints (`nf-core lint`).
- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
- [ ] Usage Documentation in `docs/usage.md` is updated.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 738e174..f2fd348 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -10,7 +10,6 @@ on:
env:
NXF_ANSI_LOG: false
- CAPSULE_LOG: none
jobs:
test:
@@ -20,27 +19,17 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
- # Nextflow versions
- include:
- # Test pipeline minimum Nextflow version
- - NXF_VER: "21.10.3"
- NXF_EDGE: ""
- # Test latest edge release of Nextflow
- - NXF_VER: ""
- NXF_EDGE: "1"
+ NXF_VER:
+ - "21.10.3"
+ - "latest-everything"
steps:
- name: Check out pipeline code
uses: actions/checkout@v2
- name: Install Nextflow
- env:
- NXF_VER: ${{ matrix.NXF_VER }}
- # Uncomment only if the edge release is more recent than the latest stable release
- # See https://github.com/nextflow-io/nextflow/issues/2467
- # NXF_EDGE: ${{ matrix.NXF_EDGE }}
- run: |
- wget -qO- get.nextflow.io | bash
- sudo mv nextflow /usr/local/bin/
+ uses: nf-core/setup-nextflow@v1
+ with:
+ version: "${{ matrix.NXF_VER }}"
- name: Run pipeline with test data
# TODO nf-core: You can customise CI pipeline run tests as required
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
index 77358de..8a5ce69 100644
--- a/.github/workflows/linting.yml
+++ b/.github/workflows/linting.yml
@@ -35,6 +35,36 @@ jobs:
- name: Run Prettier --check
run: prettier --check ${GITHUB_WORKSPACE}
+ PythonBlack:
+ runs-on: ubuntu-latest
+ steps:
+ - uses: actions/checkout@v2
+
+ - name: Check code lints with Black
+ uses: psf/black@stable
+
+ # If the above check failed, post a comment on the PR explaining the failure
+ - name: Post PR comment
+ if: failure()
+ uses: mshick/add-pr-comment@v1
+ with:
+ message: |
+ ## Python linting (`black`) is failing
+
+ To keep the code consistent with lots of contributors, we run automated code consistency checks.
+ To fix this CI test, please run:
+
+ * Install [`black`](https://black.readthedocs.io/en/stable/): `pip install black`
+ * Fix formatting errors in your pipeline: `black .`
+
+ Once you push these changes the test should pass, and you can hide this comment :+1:
+
+ We highly recommend setting up Black in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help!
+
+ Thanks again for your contribution!
+ repo-token: ${{ secrets.GITHUB_TOKEN }}
+ allow-repeats: false
+
nf-core:
runs-on: ubuntu-latest
steps:
@@ -42,15 +72,11 @@ jobs:
uses: actions/checkout@v2
- name: Install Nextflow
- env:
- CAPSULE_LOG: none
- run: |
- wget -qO- get.nextflow.io | bash
- sudo mv nextflow /usr/local/bin/
+ uses: nf-core/setup-nextflow@v1
- uses: actions/setup-python@v3
with:
- python-version: "3.6"
+ python-version: "3.7"
architecture: "x64"
- name: Install dependencies
diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 0000000..4533e2f
--- /dev/null
+++ b/CITATION.cff
@@ -0,0 +1,56 @@
+cff-version: 1.2.0
+message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication"
+authors:
+ - family-names: Ewels
+ given-names: Philip
+ - family-names: Peltzer
+ given-names: Alexander
+ - family-names: Fillinger
+ given-names: Sven
+ - family-names: Patel
+ given-names: Harshil
+ - family-names: Alneberg
+ given-names: Johannes
+ - family-names: Wilm
+ given-names: Andreas
+ - family-names: Ulysse Garcia
+ given-names: Maxime
+ - family-names: Di Tommaso
+ given-names: Paolo
+ - family-names: Nahnsen
+ given-names: Sven
+title: "The nf-core framework for community-curated bioinformatics pipelines."
+version: 2.4.1
+doi: 10.1038/s41587-020-0439-x
+date-released: 2022-05-16
+url: https://github.com/nf-core/tools
+prefered-citation:
+ type: article
+ authors:
+ - family-names: Ewels
+ given-names: Philip
+ - family-names: Peltzer
+ given-names: Alexander
+ - family-names: Fillinger
+ given-names: Sven
+ - family-names: Patel
+ given-names: Harshil
+ - family-names: Alneberg
+ given-names: Johannes
+ - family-names: Wilm
+ given-names: Andreas
+ - family-names: Ulysse Garcia
+ given-names: Maxime
+ - family-names: Di Tommaso
+ given-names: Paolo
+ - family-names: Nahnsen
+ given-names: Sven
+ doi: 10.1038/s41587-020-0439-x
+ journal: nature biotechnology
+ start: 276
+ end: 278
+ title: "The nf-core framework for community-curated bioinformatics pipelines."
+ issue: 3
+ volume: 38
+ year: 2020
+ url: https://dx.doi.org/10.1038/s41587-020-0439-x
diff --git a/README.md b/README.md
index ff1e81d..700fdde 100644
--- a/README.md
+++ b/README.md
@@ -1,19 +1,14 @@
#  
-[](https://github.com/nf-core/hic/actions?query=workflow%3A%22nf-core+CI%22)
-[](https://github.com/nf-core/hic/actions?query=workflow%3A%22nf-core+linting%22)
-[](https://nf-co.re/hic/results)
-[](https://doi.org/10.5281/zenodo.XXXXXXX)
+[](https://nf-co.re/hic/results)[](https://doi.org/10.5281/zenodo.XXXXXXX)
[](https://www.nextflow.io/)
-[](https://docs.conda.io/en/latest/)
-[](https://www.docker.com/)
-[](https://sylabs.io/docs/)
+[](https://docs.conda.io/en/latest/)
+[](https://www.docker.com/)
+[](https://sylabs.io/docs/)
[](https://tower.nf/launch?pipeline=https://github.com/nf-core/hic)
-[](https://nfcore.slack.com/channels/hic)
-[](https://twitter.com/nf_core)
-[](https://www.youtube.com/c/nf-core)
+[](https://nfcore.slack.com/channels/hic)[](https://twitter.com/nf_core)[](https://www.youtube.com/c/nf-core)
## Introduction
@@ -25,7 +20,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
<!-- TODO nf-core: Add full-sized test dataset and amend the paragraph below if applicable -->
-On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/hic/results).
+On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources.The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/hic/results).
## Pipeline summary
@@ -42,7 +37,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
3. Download the pipeline and test it on a minimal dataset with a single command:
- ```console
+ ```bash
nextflow run nf-core/hic -profile test,YOURPROFILE --outdir <OUTDIR>
```
@@ -57,7 +52,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
<!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
- ```console
+ ```bash
nextflow run nf-core/hic --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
```
diff --git a/assets/email_template.txt b/assets/email_template.txt
index a951c5e..6905d6f 100644
--- a/assets/email_template.txt
+++ b/assets/email_template.txt
@@ -6,7 +6,6 @@
`._,._,'
nf-core/hic v${version}
----------------------------------------------------
-
Run Name: $runName
<% if (success){
diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py
index 3652c63..9a8b896 100755
--- a/bin/check_samplesheet.py
+++ b/bin/check_samplesheet.py
@@ -11,7 +11,6 @@ import sys
from collections import Counter
from pathlib import Path
-
logger = logging.getLogger()
@@ -79,13 +78,15 @@ class RowChecker:
def _validate_sample(self, row):
"""Assert that the sample name exists and convert spaces to underscores."""
- assert len(row[self._sample_col]) > 0, "Sample input is required."
+ if len(row[self._sample_col]) <= 0:
+ raise AssertionError("Sample input is required.")
# Sanitize samples slightly.
row[self._sample_col] = row[self._sample_col].replace(" ", "_")
def _validate_first(self, row):
"""Assert that the first FASTQ entry is non-empty and has the right format."""
- assert len(row[self._first_col]) > 0, "At least the first FASTQ file is required."
+ if len(row[self._first_col]) <= 0:
+ raise AssertionError("At least the first FASTQ file is required.")
self._validate_fastq_format(row[self._first_col])
def _validate_second(self, row):
@@ -97,36 +98,34 @@ class RowChecker:
"""Assert that read pairs have the same file extension. Report pair status."""
if row[self._first_col] and row[self._second_col]:
row[self._single_col] = False
- assert (
- Path(row[self._first_col]).suffixes[-2:] == Path(row[self._second_col]).suffixes[-2:]
- ), "FASTQ pairs must have the same file extensions."
+ if Path(row[self._first_col]).suffixes[-2:] != Path(row[self._second_col]).suffixes[-2:]:
+ raise AssertionError("FASTQ pairs must have the same file extensions.")
else:
row[self._single_col] = True
def _validate_fastq_format(self, filename):
"""Assert that a given filename has one of the expected FASTQ extensions."""
- assert any(filename.endswith(extension) for extension in self.VALID_FORMATS), (
- f"The FASTQ file has an unrecognized extension: {filename}\n"
- f"It should be one of: {', '.join(self.VALID_FORMATS)}"
- )
+ if not any(filename.endswith(extension) for extension in self.VALID_FORMATS):
+ raise AssertionError(
+ f"The FASTQ file has an unrecognized extension: {filename}\n"
+ f"It should be one of: {', '.join(self.VALID_FORMATS)}"
+ )
def validate_unique_samples(self):
"""
Assert that the combination of sample name and FASTQ filename is unique.
- In addition to the validation, also rename the sample if more than one sample,
- FASTQ file combination exists.
+ In addition to the validation, also rename all samples to have a suffix of _T{n}, where n is the
+ number of times the same sample exist, but with different FASTQ files, e.g., multiple runs per experiment.
"""
- assert len(self._seen) == len(self.modified), "The pair of sample name and FASTQ must be unique."
- if len({pair[0] for pair in self._seen}) < len(self._seen):
- counts = Counter(pair[0] for pair in self._seen)
- seen = Counter()
- for row in self.modified:
- sample = row[self._sample_col]
- seen[sample] += 1
- if counts[sample] > 1:
- row[self._sample_col] = f"{sample}_T{seen[sample]}"
+ if len(self._seen) != len(self.modified):
+ raise AssertionError("The pair of sample name and FASTQ must be unique.")
+ seen = Counter()
+ for row in self.modified:
+ sample = row[self._sample_col]
+ seen[sample] += 1
+ row[self._sample_col] = f"{sample}_T{seen[sample]}"
def read_head(handle, num_lines=10):
diff --git a/conf/base.config b/conf/base.config
index 598aec3..66977ff 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -26,6 +26,11 @@ process {
// adding in your local modules too.
// TODO nf-core: Customise requirements for specific processes.
// See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+ withLabel:process_single {
+ cpus = { check_max( 1 , 'cpus' ) }
+ memory = { check_max( 6.GB * task.attempt, 'memory' ) }
+ time = { check_max( 4.h * task.attempt, 'time' ) }
+ }
withLabel:process_low {
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
memory = { check_max( 12.GB * task.attempt, 'memory' ) }
diff --git a/docs/usage.md b/docs/usage.md
index e106ac9..d6b7122 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -12,7 +12,7 @@
You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below.
-```console
+```bash
--input '[path to samplesheet file]'
```
@@ -56,7 +56,7 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p
The typical command for running the pipeline is as follows:
-```console
+```bash
nextflow run nf-core/hic --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile docker
```
@@ -64,9 +64,9 @@ This will launch the pipeline with the `docker` configuration profile. See below
Note that the pipeline will create the following files in your working directory:
-```console
+```bash
work # Directory containing the nextflow working files
-<OUTIDR> # Finished results in specified location (defined with --outdir)
+<OUTDIR> # Finished results in specified location (defined with --outdir)
.nextflow_log # Log file from Nextflow
# Other nextflow hidden files, eg. history of pipeline runs and old logs.
```
@@ -75,7 +75,7 @@ work # Directory containing the nextflow working files
When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:
-```console
+```bash
nextflow pull nf-core/hic
```
@@ -251,6 +251,6 @@ Some HPC setups also allow you to run nextflow within a cluster job submitted yo
In some cases, the Nextflow Java virtual machines can start to request a large amount of memory.
We recommend adding the following line to your environment to limit this (typically in `~/.bashrc` or `~./bash_profile`):
-```console
+```bash
NXF_OPTS='-Xms1g -Xmx4g'
```
diff --git a/lib/WorkflowHic.groovy b/lib/WorkflowHic.groovy
index dbd0945..8e74472 100755
--- a/lib/WorkflowHic.groovy
+++ b/lib/WorkflowHic.groovy
@@ -10,6 +10,7 @@ class WorkflowHic {
public static void initialise(params, log) {
genomeExistsError(params, log)
+
if (!params.fasta) {
log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
System.exit(1)
@@ -41,9 +42,7 @@ class WorkflowHic {
yaml_file_text += "data: |\n"
yaml_file_text += "${summary_section}"
return yaml_file_text
- }
-
- //
+ }//
// Exit pipeline if incorrect --genome key provided
//
private static void genomeExistsError(params, log) {
diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy
index a86a891..30096e7 100755
--- a/lib/WorkflowMain.groovy
+++ b/lib/WorkflowMain.groovy
@@ -59,6 +59,7 @@ class WorkflowMain {
}
// Print parameter summary log to screen
+
log.info paramsSummaryLog(workflow, params, log)
// Check that a -profile or Nextflow config has been provided to run the pipeline
@@ -78,17 +79,15 @@ class WorkflowMain {
System.exit(1)
}
}
-
//
// Get attribute from genome config file e.g. fasta
//
- public static String getGenomeAttribute(params, attribute) {
- def val = ''
+ public static Object getGenomeAttribute(params, attribute) {
if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
if (params.genomes[ params.genome ].containsKey(attribute)) {
- val = params.genomes[ params.genome ][ attribute ]
+ return params.genomes[ params.genome ][ attribute ]
}
}
- return val
+ return null
}
}
diff --git a/main.nf b/main.nf
index 7dd9be5..c7ce044 100644
--- a/main.nf
+++ b/main.nf
@@ -4,7 +4,7 @@
nf-core/hic
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Github : https://github.com/nf-core/hic
- Website: https://nf-co.re/hic
+Website: https://nf-co.re/hic
Slack : https://nfcore.slack.com/channels/hic
----------------------------------------------------------------------------------------
*/
diff --git a/modules.json b/modules.json
index bd45115..97f1beb 100644
--- a/modules.json
+++ b/modules.json
@@ -3,14 +3,20 @@
"homePage": "https://github.com/nf-core/hic",
"repos": {
"nf-core/modules": {
- "custom/dumpsoftwareversions": {
- "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
- },
- "fastqc": {
- "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
- },
- "multiqc": {
- "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+ "git_url": "https://github.com/nf-core/modules.git",
+ "modules": {
+ "custom/dumpsoftwareversions": {
+ "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d",
+ "branch": "master"
+ },
+ "fastqc": {
+ "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d",
+ "branch": "master"
+ },
+ "multiqc": {
+ "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d",
+ "branch": "master"
+ }
}
}
}
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
index d139039..787bdb7 100644
--- a/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
@@ -1,9 +1,10 @@
#!/usr/bin/env python
-import yaml
import platform
from textwrap import dedent
+import yaml
+
def _make_versions_html(versions):
html = [
@@ -58,11 +59,12 @@ versions_by_module = {}
for process, process_versions in versions_by_process.items():
module = process.split(":")[-1]
try:
- assert versions_by_module[module] == process_versions, (
- "We assume that software versions are the same between all modules. "
- "If you see this error-message it means you discovered an edge-case "
- "and should open an issue in nf-core/tools. "
- )
+ if versions_by_module[module] != process_versions:
+ raise AssertionError(
+ "We assume that software versions are the same between all modules. "
+ "If you see this error-message it means you discovered an edge-case "
+ "and should open an issue in nf-core/tools. "
+ )
except KeyError:
versions_by_module[module] = process_versions
diff --git a/nextflow.config b/nextflow.config
index 7905a9a..bdd8ea9 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -13,11 +13,11 @@ params {
// Input options
input = null
+
// References
genome = null
igenomes_base = 's3://ngi-igenomes/igenomes'
igenomes_ignore = false
-
// MultiQC options
multiqc_config = null
multiqc_title = null
@@ -37,6 +37,7 @@ params {
schema_ignore_params = 'genomes'
enable_conda = false
+
// Config options
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
@@ -45,6 +46,7 @@ params {
config_profile_url = null
config_profile_name = null
+
// Max resource options
// Defaults only, expecting to be overwritten
max_memory = '128.GB'
@@ -72,6 +74,7 @@ try {
// }
+
profiles {
debug { process.beforeScript = 'echo $HOSTNAME' }
conda {
@@ -82,6 +85,15 @@ profiles {
shifter.enabled = false
charliecloud.enabled = false
}
+ mamba {
+ params.enable_conda = true
+ conda.useMamba = true
+ docker.enabled = false
+ singularity.enabled = false
+ podman.enabled = false
+ shifter.enabled = false
+ charliecloud.enabled = false
+ }
docker {
docker.enabled = true
docker.userEmulation = true
@@ -119,10 +131,16 @@ profiles {
podman.enabled = false
shifter.enabled = false
}
+ gitpod {
+ executor.name = 'local'
+ executor.cpus = 16
+ executor.memory = 60.GB
+ }
test { includeConfig 'conf/test.config' }
test_full { includeConfig 'conf/test_full.config' }
}
+
// Load igenomes.config if required
if (!params.igenomes_ignore) {
includeConfig 'conf/igenomes.config'
@@ -130,6 +148,7 @@ if (!params.igenomes_ignore) {
params.genomes = [:]
}
+
// Export these variables to prevent local Python/R libraries from conflicting with those in the container
// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.
--
GitLab