diff --git a/.travis.yml b/.travis.yml
index b77371b03dae59b22b900792fe7f76b2d07faab1..2dd43f74a0f277205eeb13f0e52c970038c2c400 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -8,13 +8,12 @@ matrix:
fast_finish: true
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/hic: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/hic:dev nfcore/hic:1.1.0
+ - docker tag nfcore/hic:dev nfcore/hic:dev
install:
# Install Nextflow
@@ -30,7 +29,7 @@ install:
- 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='19.04.0' # Specify a minimum NF version that should be tested and work
- NXF_VER='' # Plus: get the latest NF version and check that it works
script:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7142fd883baa866d8d117030139d6261ef11a2d7..aac514667058a584d1fba7e70cd1a61a4ebd7540 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,13 +1,13 @@
# nf-core/hic: Changelog
-## v1.1dev
+## v1.1.0 - 2019-10-15
* Support 'N' base motif in restriction/ligation sites
-* Support multiple restriction enzymes/ligattion sites (comma separated) (#31)
+* Support multiple restriction enzymes/ligattion sites (comma separated) ([#31](https://github.com/nf-core/hic/issues/31))
* Add --saveInteractionBAM option
-* Add DOI (#29)
-* Fix bug for reads extension _1/_2 (#30)
-* Update manual (#28)
+* Add DOI ([#29](https://github.com/nf-core/hic/issues/29))
+* Fix bug for reads extension _1/_2 ([#30](https://github.com/nf-core/hic/issues/30))
+* Update manual ([#28](https://github.com/nf-core/hic/issues/28))
## v1.0 - 2019-05-06
diff --git a/Dockerfile b/Dockerfile
index bd89e7eed206414d6257f30f7ed2ebd91fb23971..4714783d6d4c757834980a200f109612ab56cd48 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,4 +1,4 @@
-FROM nfcore/base
+FROM nfcore/base:1.7
LABEL authors="Nicolas Servant" \
description="Docker image containing all requirements for nf-core/hic pipeline"
@@ -7,4 +7,4 @@ RUN apt-get update && apt-get install -y gcc g++ && apt-get clean -y
COPY environment.yml /
RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-hic-1.1.0dev/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-hic-1.1.1dev/bin:$PATH
diff --git a/README.md b/README.md
index 2227cb44fc2348a16c7b48a509eb9dafb2aa3a54..def8c35381f7dc28007dbf53de53bbde7a093b43 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
**Analysis of Chromosome Conformation Capture data (Hi-C)**.
[](https://travis-ci.com/nf-core/hic)
-[](https://www.nextflow.io/)
+[](https://www.nextflow.io/)
[](http://bioconda.github.io/)
[](https://hub.docker.com/r/nfcore/hic)
@@ -15,7 +15,7 @@
This pipeline is based on the
[HiC-Pro workflow](https://github.com/nservant/HiC-Pro).
-It was designed to process Hi-C data from raw fastq files (paired-end Illumina
+It was designed to process Hi-C data from raw FastQ files (paired-end Illumina
data) to normalized contact maps.
The current version supports most protocols, including digestion protocols as
well as protocols that do not require restriction enzymes such as DNase Hi-C.
@@ -39,24 +39,58 @@ sites (bowtie2)
6. Quality controls and report (MultiQC)
7. Addition export for visualisation and downstream analysis (cooler)
+## Quick Start
+
+i. Install [`nextflow`](https://nf-co.re/usage/installation)
+
+ii. Install one of [`docker`](https://docs.docker.com/engine/installation/),
+[`singularity`](https://www.sylabs.io/guides/3.0/user-guide/) or
+[`conda`](https://conda.io/miniconda.html)
+
+iii. Download the pipeline and test it on a minimal dataset with a single command
+
+```bash
+nextflow run nf-core/hic -profile test,<docker/singularity/conda/institute>
+```
+
+iv. Start running your own analysis!
+
+```bash
+nextflow run nf-core/hic -profile <docker/singularity/conda/institute> --reads '*_R{1,2}.fastq.gz' --genome GRCh37
+```
+
+See [usage docs](docs/usage.md) for all of the available options when running the pipeline.
+
## Documentation
The nf-core/hic pipeline comes with documentation about the pipeline, found in
the `docs/` directory:
-1. [Installation](docs/installation.md)
+1. [Installation](https://nf-co.re/usage/installation)
2. Pipeline configuration
- * [Local installation](docs/configuration/local.md)
- * [Adding your own system](docs/configuration/adding_your_own.md)
- * [Reference genomes](docs/configuration/reference_genomes.md)
+ * [Local installation](https://nf-co.re/usage/local_installation)
+ * [Adding your own system config](https://nf-co.re/usage/adding_own_config)
+ * [Reference genomes](https://nf-co.re/usage/reference_genomes)
3. [Running the pipeline](docs/usage.md)
4. [Output and how to interpret the results](docs/output.md)
-5. [Troubleshooting](docs/troubleshooting.md)
+5. [Troubleshooting](https://nf-co.re/usage/troubleshooting)
+
+## Contributions and Support
+
+If you would like to contribute to this pipeline, please see the
+[contributing guidelines](.github/CONTRIBUTING.md).
+
+For further information or help, don't hesitate to get in touch on
+[Slack](https://nfcore.slack.com/channels/hic).
+You can join with [this invite](https://nf-co.re/join/slack).
+
## Credits
nf-core/hic was originally written by Nicolas Servant.
+## Citation
+
If you use nf-core/hic for your analysis, please cite it using the following
doi: [10.5281/zenodo.2669513](https://doi.org/10.5281/zenodo.2669513)
diff --git a/conf/curie.config b/conf/curie.config
deleted file mode 100644
index ab85a2d9d778ac3ca875a273e9bbcb7eb966253d..0000000000000000000000000000000000000000
--- a/conf/curie.config
+++ /dev/null
@@ -1,16 +0,0 @@
-singularity {
- enabled = false
-}
-
-process {
- executor = 'pbs'
- queue = params.queue
- //beforeScript = 'export PATH=/bioinfo/pipelines/sandbox/dev/nfcore/rnaseq/modules/conda/envs/nf-core-rnaseq-1.2/bin:$PATH'
-}
-
-params {
- clusterOptions = false
- max_memory = 128.GB
- max_cpus = 4
- max_time = 240.h
-}
diff --git a/conf/multiqc_config.yaml b/conf/multiqc_config.yaml
deleted file mode 100644
index f2a738c43be4dae15db5075017559607c66c0542..0000000000000000000000000000000000000000
--- a/conf/multiqc_config.yaml
+++ /dev/null
@@ -1,7 +0,0 @@
-report_comment: >
- This report has been generated by the <a href="https://github.com/nf-core/hic" target="_blank">nf-core/hic</a>
- analysis pipeline. For information about how to interpret these results, please see the
- <a href="https://github.com/nf-core/hic" target="_blank">documentation</a>.
-report_section_order:
- nf-core/hic-software-versions:
- order: -1000
diff --git a/conf/test.config b/conf/test.config
index 592e3a40d8bce4cf22b5fe1ad9014ded48d439ce..00c47f85cd86d5d5a05ce3123024a37a9cc9e466 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -29,5 +29,5 @@ params {
min_mapq = 0
// Options
- skip_cool = true
+ skipCool = true
}
diff --git a/docs/README.md b/docs/README.md
index d7dbdac40b9452baa3d7d7747d264077276fb679..e160867d029e09c793168dd764f8a0ea01dcbd59 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -2,11 +2,11 @@
The nf-core/hic documentation is split into the following files:
-1. [Installation](installation.md)
+1. [Installation](https://nf-co.re/usage/installation)
2. Pipeline configuration
- * [Local installation](configuration/local.md)
- * [Adding your own system](configuration/adding_your_own.md)
- * [Reference genomes](configuration/reference_genomes.md)
+ * [Local installation](https://nf-co.re/usage/local_installation)
+ * [Adding your own system config](https://nf-co.re/usage/adding_own_config)
+ * [Reference genomes](https://nf-co.re/usage/reference_genomes)
3. [Running the pipeline](usage.md)
4. [Output and how to interpret the results](output.md)
-5. [Troubleshooting](troubleshooting.md)
+5. [Troubleshooting](https://nf-co.re/usage/troubleshooting)
diff --git a/docs/configuration/adding_your_own.md b/docs/configuration/adding_your_own.md
deleted file mode 100644
index b1703c1e10d064a0d989e2520642d6e77d742e66..0000000000000000000000000000000000000000
--- a/docs/configuration/adding_your_own.md
+++ /dev/null
@@ -1,126 +0,0 @@
-# nf-core/hic: Configuration for other clusters
-
-It is entirely possible to run this pipeline on other clusters, though you will
-need to set up your own config file so that the pipeline knows how to work with
-your cluster.
-
-> If you think that there are other people using the pipeline who would benefit
-from your configuration (eg. other common cluster setups), please let us know.
-We can add a new configuration and profile which can used by specifying
-`-profile <name>` when running the pipeline. The config file will then be
-hosted at `nf-core/configs` and will be pulled automatically before the pipeline
-is executed.
-
-If you are the only person to be running this pipeline, you can create your
-config file as `~/.nextflow/config` and it will be applied every time you run
-Nextflow. Alternatively, save the file anywhere and reference it when running
-the pipeline with `-c path/to/config` (see the
-[Nextflow documentation](https://www.nextflow.io/docs/latest/config.html)
-for more).
-
-A basic configuration comes with the pipeline, which loads the
-[`conf/base.config`](../../conf/base.config) by default. This means that you
-only need to configure the specifics for your system and overwrite any defaults
-that you want to change.
-
-## Cluster Environment
-
-By default, pipeline uses the `local` Nextflow executor - in other words, all
-jobs are run in the login session. If you're using a simple server, this may be
-fine. If you're using a compute cluster, this is bad as all jobs will run on
-the head node.
-
-To specify your cluster environment, add the following line to your config
-file:
-
-```nextflow
-process.executor = 'YOUR_SYSTEM_TYPE'
-```
-
-Many different cluster types are supported by Nextflow. For more information,
-please see the
-[Nextflow documentation](https://www.nextflow.io/docs/latest/executor.html).
-
-Note that you may need to specify cluster options, such as a project or queue.
-To do so, use the `clusterOptions` config option:
-
-```nextflow
-process {
- executor = 'SLURM'
- clusterOptions = '-A myproject'
-}
-```
-
-## Software Requirements
-
-To run the pipeline, several software packages are required. How you satisfy
-these requirements is essentially up to you and depends on your system.
-If possible, we _highly_ recommend using either Docker or Singularity.
-
-Please see the [`installation documentation`](../installation.md) for how to
-run using the below as a one-off. These instructions are about configuring a
-config file for repeated use.
-
-### Docker
-
-Docker is a great way to run nf-core/hic, as it manages all software
-installations and allows the pipeline to be run in an identical software
-environment across a range of systems.
-
-Nextflow has
-[excellent integration](https://www.nextflow.io/docs/latest/docker.html)
-with Docker, and beyond installing the two tools, not much else is required -
-nextflow will automatically fetch the
-[nfcore/hic](https://hub.docker.com/r/nfcore/hic/) image that we have created
-and is hosted at dockerhub at run time.
-
-To add docker support to your own config file, add the following:
-
-```nextflow
-docker.enabled = true
-process.container = "nfcore/hic"
-```
-
-Note that the dockerhub organisation name annoyingly can't have a hyphen,
-so is `nfcore` and not `nf-core`.
-
-### Singularity image
-
-Many HPC environments are not able to run Docker due to security issues.
-[Singularity](http://singularity.lbl.gov/) is a tool designed to run on such
-HPC systems which is very similar to Docker.
-
-To specify singularity usage in your pipeline config file, add the following:
-
-```nextflow
-singularity.enabled = true
-process.container = "shub://nf-core/hic"
-```
-
-If you intend to run the pipeline offline, nextflow will not be able to
-automatically download the singularity image for you.
-Instead, you'll have to do this yourself manually first, transfer the image
-file and then point to that.
-
-First, pull the image file where you have an internet connection:
-
-```bash
-singularity pull --name nf-core-hic.simg shub://nf-core/hic
-```
-
-Then transfer this file and point the config file to the image:
-
-```nextflow
-singularity.enabled = true
-process.container = "/path/to/nf-core-hic.simg"
-```
-
-### Conda
-
-If you're not able to use Docker or Singularity, you can instead use conda to
-manage the software requirements.
-To use conda in your own config file, add the following:
-
-```nextflow
-process.conda = "$baseDir/environment.yml"
-```
diff --git a/docs/configuration/local.md b/docs/configuration/local.md
deleted file mode 100644
index c3a047fbd856182b6ce823f8f91548b1a2bccc8a..0000000000000000000000000000000000000000
--- a/docs/configuration/local.md
+++ /dev/null
@@ -1,76 +0,0 @@
-# nf-core/hic: Local Configuration
-
-If running the pipeline in a local environment, we highly recommend using
-either Docker or Singularity.
-
-## Docker
-
-Docker is a great way to run `nf-core/hic`, as it manages all software
-installations and allows the pipeline to be run in an identical software
-environment across a range of systems.
-
-Nextflow has
-[excellent integration](https://www.nextflow.io/docs/latest/docker.html) with
-Docker, and beyond installing the two tools, not much else is required.
-The `nf-core/hic` profile comes with a configuration profile for docker, making
-it very easy to use. This also comes with the required presets to use the AWS
-iGenomes resource, meaning that if using common reference genomes you just
-specify the reference ID and it will be automatically downloaded from AWS S3.
-
-First, install docker on your system:
-[Docker Installation Instructions](https://docs.docker.com/engine/installation/)
-
-Then, simply run the analysis pipeline:
-
-```bash
-nextflow run nf-core/hic -profile docker --genome '<genome ID>'
-```
-
-Nextflow will recognise `nf-core/hic` and download the pipeline from GitHub.
-The `-profile docker` configuration lists the
-[nf-core/hic](https://hub.docker.com/r/nfcore/hic/) image that we have created
-and is hosted at dockerhub, and this is downloaded.
-
-For more information about how to work with reference genomes, see
-[`docs/configuration/reference_genomes.md`](reference_genomes.md).
-
-### Pipeline versions
-
-The public docker images are tagged with the same version numbers as the code,
-which you can use to ensure reproducibility. When running the pipeline,
-specify the pipeline version with `-r`, for example `-r 1.0`. This uses
-pipeline code and docker image from this tagged version.
-
-## Singularity image
-
-Many HPC environments are not able to run Docker due to security issues.
-[Singularity](http://singularity.lbl.gov/) is a tool designed to run on such
-HPC systems which is very similar to Docker. Even better, it can use create
-images directly from dockerhub.
-
-To use the singularity image for a single run, use `-with-singularity`.
-This will download the docker container from dockerhub and create a singularity
-image for you dynamically.
-
-If you intend to run the pipeline offline, nextflow will not be able to
-automatically download the singularity image for you. Instead, you'll have
-to do this yourself manually first, transfer the image file and then point to
-that.
-
-First, pull the image file where you have an internet connection:
-
-> NB: The "tag" at the end of this command corresponds to the pipeline version.
-> Here, we're pulling the docker image for version 1.0 of the nf-core/hic
-pipeline
-> Make sure that this tag corresponds to the version of the pipeline that
-you're using
-
-```bash
-singularity pull --name nf-core-hic-1.0.img docker://nf-core/hic:1.0
-```
-
-Then transfer this file and run the pipeline with this path:
-
-```bash
-nextflow run /path/to/nf-core-hic -with-singularity /path/to/nf-core-hic-1.0.img
-```
diff --git a/docs/configuration/reference_genomes.md b/docs/configuration/reference_genomes.md
deleted file mode 100644
index d584c0c8e0c9000b150406665f7d2edc33615edf..0000000000000000000000000000000000000000
--- a/docs/configuration/reference_genomes.md
+++ /dev/null
@@ -1,68 +0,0 @@
-# nf-core/hic: Reference Genomes Configuration
-
-The nf-core/hic pipeline needs a reference genome for alignment and annotation.
-
-These paths can be supplied on the command line at run time (see the
-[usage docs](../usage.md)),
-but for convenience it's often better to save these paths in a nextflow config
-file.
-See below for instructions on how to do this.
-Read [Adding your own system](adding_your_own.md) to find out how to set up
-custom config files.
-
-## Adding paths to a config file
-
-Specifying long paths every time you run the pipeline is a pain.
-To make this easier, the pipeline comes configured to understand reference
-genome keywords which correspond to preconfigured paths, meaning that you can
-just specify `--genome ID` when running the pipeline.
-
-Note that this genome key can also be specified in a config file if you always
-use the same genome.
-
-To use this system, add paths to your config file using the following template:
-
-```nextflow
-params {
- genomes {
- 'YOUR-ID' {
- fasta = '<PATH TO FASTA FILE>/genome.fa'
- }
- 'OTHER-GENOME' {
- // [..]
- }
- }
- // Optional - default genome. Ignored if --genome 'OTHER-GENOME' specified
- // on command line
- genome = 'YOUR-ID'
-}
-```
-
-You can add as many genomes as you like as long as they have unique IDs.
-
-## illumina iGenomes
-
-To make the use of reference genomes easier, illumina has developed a
-centralised resource called
-[iGenomes](https://support.illumina.com/sequencing/sequencing_software/igenome.html).
-Multiple reference index types are held together with consistent structure for
-multiple genomes.
-
-We have put a copy of iGenomes up onto AWS S3 hosting and this pipeline is
-configured to use this by default.
-The hosting fees for AWS iGenomes are currently kindly funded by a grant from
-Amazon.
-The pipeline will automatically download the required reference files when you
-run the pipeline.
-For more information about the AWS iGenomes, see
-[AWS-iGenomes](https://ewels.github.io/AWS-iGenomes/)
-
-Downloading the files takes time and bandwidth, so we recommend making a local
-copy of the iGenomes resource.
-Once downloaded, you can customise the variable `params.igenomes_base` in your
-custom configuration file to point to the reference location.
-For example:
-
-```nextflow
-params.igenomes_base = '/path/to/data/igenomes/'
-```
diff --git a/docs/installation.md b/docs/installation.md
deleted file mode 100644
index c3dc01893dd774c1cf5925ddbf441a26fdc24f93..0000000000000000000000000000000000000000
--- a/docs/installation.md
+++ /dev/null
@@ -1,148 +0,0 @@
-# nf-core/hic: Installation
-
-To start using the nf-core/hic pipeline, follow the steps below:
-
-1. [Install Nextflow](#1-install-nextflow)
-2. [Install the pipeline](#2-install-the-pipeline)
- * [Automatic](#21-automatic)
- * [Offline](#22-offline)
- * [Development](#23-development)
-3. [Pipeline configuration](#3-pipeline-configuration)
- * [Software deps: Docker and Singularity](#31-software-deps-docker-and-singularity)
- * [Software deps: Bioconda](#32-software-deps-bioconda)
- * [Configuration profiles](#33-configuration-profiles)
-4. [Reference genomes](#4-reference-genomes)
-
-## 1) Install NextFlow
-
-Nextflow runs on most POSIX systems (Linux, Mac OSX etc). It can be installed
-by running the following commands:
-
-```bash
-# Make sure that Java v8+ is installed:
-java -version
-
-# Install Nextflow
-curl -fsSL get.nextflow.io | bash
-
-# Add Nextflow binary to your PATH:
-mv nextflow ~/bin/
-# OR system-wide installation:
-# sudo mv nextflow /usr/local/bin
-```
-
-See [nextflow.io](https://www.nextflow.io/) for further instructions on how to
-install and configure Nextflow.
-
-## 2) Install the pipeline
-
-### 2.1) Automatic
-
-This pipeline itself needs no installation - NextFlow will automatically fetch
-it from GitHub if `nf-core/hic` is specified as the pipeline name.
-
-### 2.2) Offline
-
-The above method requires an internet connection so that Nextflow can download
-the pipeline files. If you're running on a system that has no internet
-connection, you'll need to download and transfer the pipeline files manually:
-
-```bash
-wget https://github.com/nf-core/hic/archive/master.zip
-mkdir -p ~/my-pipelines/nf-core/
-unzip master.zip -d ~/my-pipelines/nf-core/
-cd ~/my_data/
-nextflow run ~/my-pipelines/nf-core/hic-master
-```
-
-To stop nextflow from looking for updates online, you can tell it to run in
-offline mode by specifying the following environment variable in your
-~/.bashrc file:
-
-```bash
-export NXF_OFFLINE='TRUE'
-```
-
-### 2.3) Development
-
-If you would like to make changes to the pipeline, it's best to make a fork on
-GitHub and then clone the files. Once cloned you can run the pipeline directly
-as above.
-
-## 3) Pipeline configuration
-
-By default, the pipeline loads a basic server configuration
-[`conf/base.config`](../conf/base.config)
-This uses a number of sensible defaults for process requirements and is
-suitable for running on a simple (if powerful!) local server.
-
-Be warned of two important points about this default configuration:
-
-1. The default profile uses the `local` executor
- * All jobs are run in the login session. If you're using a simple server,
-this may be fine. If you're using a compute cluster, this is bad as all jobs
-will run on the head node.
- * See the
-[nextflow docs](https://www.nextflow.io/docs/latest/executor.html) for
-information about running with other hardware backends. Most job scheduler
-systems are natively supported.
-2. Nextflow will expect all software to be installed and available on the
-`PATH`
- * It's expected to use an additional config profile for docker, singularity
-or conda support. See below.
-
-### 3.1) Software deps: Docker
-
-First, install docker on your system:
-[Docker Installation Instructions](https://docs.docker.com/engine/installation/)
-
-Then, running the pipeline with the option `-profile docker` tells Nextflow to
-enable Docker for this run. An image containing all of the software
-requirements will be automatically fetched and used from
-[dockerhub](https://hub.docker.com/r/nfcore/hic).
-
-### 3.1) Software deps: Singularity
-
-If you're not able to use Docker then
-[Singularity](http://singularity.lbl.gov/) is a great alternative.
-The process is very similar: running the pipeline with the option
-`-profile singularity` tells Nextflow to enable singularity for this run.
-An image containing all of the software requirements will be automatically
-fetched and used from singularity hub.
-
-If running offline with Singularity, you'll need to download and transfer the
-Singularity image first:
-
-```bash
-singularity pull --name nf-core-hic.simg shub://nf-core/hic
-```
-
-Once transferred, use `-with-singularity` and specify the path to the image
-file:
-
-```bash
-nextflow run /path/to/nf-core-hic -with-singularity nf-core-hic.simg
-```
-
-Remember to pull updated versions of the singularity image if you update the
-pipeline.
-
-### 3.2) Software deps: conda
-
-If you're not able to use Docker _or_ Singularity, you can instead use conda to
-manage the software requirements.
-This is slower and less reproducible than the above, but is still better than
-having to install all requirements yourself!
-The pipeline ships with a conda environment file and nextflow has built-in
-support for this.
-To use it first ensure that you have conda installed (we recommend
-[miniconda](https://conda.io/miniconda.html)), then follow the same pattern
-as above and use the flag `-profile conda`
-
-### 3.3) Configuration profiles
-
-See [`docs/configuration/adding_your_own.md`](configuration/adding_your_own.md)
-
-## 4) Reference genomes
-
-See [`docs/configuration/reference_genomes.md`](configuration/reference_genomes.md)
diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md
deleted file mode 100644
index df43e8a755881b646991815e75e159069972c459..0000000000000000000000000000000000000000
--- a/docs/troubleshooting.md
+++ /dev/null
@@ -1,43 +0,0 @@
-# nf-core/hic: Troubleshooting
-
-## Input files not found
-
-If only no file, only one input file , or only read one and not read two is
-picked up then something is wrong with your input file declaration
-
-1. The path must be enclosed in quotes (`'` or `"`)
-2. The path must have at least one `*` wildcard character. This is even if
-you are only running one paired end sample.
-3. When using the pipeline with paired end data, the path must use `{1,2}` or
-`{R1,R2}` notation to specify read pairs.
-4. If you are running Single end data make sure to specify `--singleEnd`
-
-If the pipeline can't find your files then you will get the following error
-
-```bash
-ERROR ~ Cannot find any reads matching: *{1,2}.fastq.gz
-```
-
-Note that if your sample name is "messy" then you have to be very particular
-with your glob specification. A file name like
-`L1-1-D-2h_S1_L002_R1_001.fastq.gz` can be difficult enough for a human to
-read. Specifying `*{1,2}*.gz` wont work whilst `*{R1,R2}*.gz` will.
-
-## Data organization
-
-The pipeline can't take a list of multiple input files - it takes a glob
-expression. If your input files are scattered in different paths then we
-recommend that you generate a directory with symlinked files. If running
-in paired end mode please make sure that your files are sensibly named so
-that they can be properly paired. See the previous point.
-
-## Extra resources and getting help
-
-If you still have an issue with running the pipeline then feel free to
-contact us.
-Have a look at the [pipeline website](https://github.com/nf-core/hic) to
-find out how.
-
-If you have problems that are related to Nextflow and not our pipeline then
-check out the [Nextflow gitter channel](https://gitter.im/nextflow-io/nextflow)
-or the [google group](https://groups.google.com/forum/#!forum/nextflow).
diff --git a/docs/usage.md b/docs/usage.md
index 57f1e3edb293ca20830c41c145f06eb03c5e5d30..f1cd3a56a220a077cdd835c4d1e8e87e13cf726e 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -53,10 +53,10 @@
* [`--saveAlignedIntermediates`](#--saveAlignedIntermediates)
* [`--saveInteractionBAM`](#--saveInteractionBAM)
* [Skip options](#skip-options)
- * [--skip_maps](#--skip_maps)
- * [--skip_ice](#--skip_ice)
- * [--skip_cool](#--skip_cool)
- * [--skip_multiqc](#--skip_multiqc)
+ * [--skipMaps](#--skipMaps)
+ * [--skipIce](#--skipIce)
+ * [--skipCool](#--skipCool)
+ * [--skipMultiQC](#--skipMultiQC)
* [Job resources](#job-resources)
* [Automatic resubmission](#automatic-resubmission)
* [Custom resource requests](#custom-resource-requests)
@@ -561,38 +561,38 @@ dangling end, self-circle, etc.) and its tags.
## Skip options
-### `--skip_maps`
+### `--skipMaps`
If defined, the workflow stops with the list of valid interactions, and the
genome-wide maps are not built. Usefult for capture-C analysis. Default: false
```bash
---skip_maps
+--skipMaps
```
-### `--skip_ice`
+### `--skipIce`
If defined, the ICE normalization is not run on the raw contact maps.
Default: false
```bash
---skip_ice
+--skipIce
```
-### `--skip_cool`
+### `--skipCool`
If defined, cooler files are not generated. Default: false
```bash
---skip_cool
+--skipCool
```
-### `--skip_multiqc`
+### `--skipMultiQC`
If defined, the MultiQC report is not generated. Default: false
```bash
---skip_multiqc
+--skipMultiQC
```
## Job resources
diff --git a/environment.yml b/environment.yml
index 1a69ba7ac34662b5d0c7f808d50d7dd5b86899c3..271f3f5273246d63738d15c6f49cc7c07d1fdb94 100644
--- a/environment.yml
+++ b/environment.yml
@@ -1,10 +1,9 @@
# You can use this file to create a conda environment for this pipeline:
# conda env create -f environment.yml
-name: nf-core-hic-1.1.0
+name: nf-core-hic-1.1.1dev
channels:
- conda-forge
- bioconda
- - bioconda/label/cf201901
- defaults
dependencies:
- python=2.7.15
diff --git a/main.nf b/main.nf
index 2b8c2ecd67c164e95e61ae2451d2e0bf40f4d8f5..e531cb85226cf6615236624120e94ff39bd8d5c3 100644
--- a/main.nf
+++ b/main.nf
@@ -26,7 +26,7 @@ def helpMessage() {
-profile Configuration profile to use. Can use multiple (comma separated)
Available: conda, docker, singularity, awsbatch, test and more.
- References: If not specified in the configuration file or you wish to overwrite any of the references.
+ References If not specified in the configuration file or you wish to overwrite any of the references.
--genome Name of iGenomes reference
--bwt2_index Path to Bowtie2 index
--fasta Path to Fasta reference
@@ -35,12 +35,17 @@ def helpMessage() {
--saveReference Save reference genome to output folder. Default: False
--saveAlignedIntermediates Save intermediates alignment files. Default: False
- Options:
+ Alignments
--bwt2_opts_end2end Options for bowtie2 end-to-end mappinf (first mapping step). See hic.config for default.
--bwt2_opts_trimmed Options for bowtie2 mapping after ligation site trimming. See hic.config for default.
--min_mapq Minimum mapping quality values to consider. Default: 10
--restriction_site Cutting motif(s) of restriction enzyme(s) (comma separated). Default: 'A^AGCTT'
--ligation_site Ligation motifs to trim (comma separated). Default: 'AAGCTAGCTT'
+ --rm_singleton Remove singleton reads. Default: true
+ --rm_multi Remove multi-mapped reads. Default: true
+ --rm_dup Remove duplicates. Default: true
+
+ Contacts calling
--min_restriction_fragment_size Minimum size of restriction fragments to consider. Default: None
--max_restriction_fragment_size Maximum size of restriction fragments to consider. Default: None
--min_insert_size Minimum insert size of mapped reads to consider. Default: None
@@ -48,32 +53,29 @@ def helpMessage() {
--saveInteractionBAM Save BAM file with interaction tags (dangling-end, self-circle, etc.). Default: False
--dnase Run DNase Hi-C mode. All options related to restriction fragments are not considered. Default: False
-
--min_cis_dist Minimum intra-chromosomal distance to consider. Default: None
- --rm_singleton Remove singleton reads. Default: true
- --rm_multi Remove multi-mapped reads. Default: true
- --rm_dup Remove duplicates. Default: true
+ Contact maps
--bin_size Bin size for contact maps (comma separated). Default: '1000000,500000'
--ice_max_iter Maximum number of iteration for ICE normalization. Default: 100
--ice_filter_low_count_perc Percentage of low counts columns/rows to filter before ICE normalization. Default: 0.02
--ice_filter_high_count_perc Percentage of high counts columns/rows to filter before ICE normalization. Default: 0
--ice_eps Convergence criteria for ICE normalization. Default: 0.1
- Other options:
+
+ Workflow
+ --skipMaps Skip generation of contact maps. Useful for capture-C. Default: False
+ --skipIce Skip ICE normalization. Default: False
+ --skipCool Skip generation of cool files. Default: False
+ --skipMultiQC Skip MultiQC. Default: False
+
+ Other
--splitFastq Size of read chuncks to use to speed up the workflow. Default: None
--outdir The output directory where the results will be saved. Default: './results'
--email Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. Default: None
-name Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic. Default: None
- Step options:
-
- --skip_maps Skip generation of contact maps. Useful for capture-C. Default: False
- --skip_ice Skip ICE normalization. Default: False
- --skip_cool Skip generation of cool files. Default: False
- --skip_multiQC Skip MultiQC. Default: False
-
- AWSBatch options:
+ AWSBatch
--awsqueue The AWSBatch JobQueue that needs to be set when running on AWSBatch
--awsregion The AWS Region for your AWS Batch job to run on
""".stripIndent()
@@ -83,7 +85,7 @@ def helpMessage() {
* SET UP CONFIGURATION VARIABLES
*/
-// Show help emssage
+// Show help message
if (params.help){
helpMessage()
exit 0
@@ -243,6 +245,12 @@ summary['Restriction Motif']= params.restriction_site
summary['Ligation Motif'] = params.ligation_site
summary['DNase Mode'] = params.dnase
summary['Remove Dup'] = params.rm_dup
+summary['Min MAPQ'] = params.min_mapq
+summary['Min Fragment Size']= params.min_restriction_fragment_size
+summary['Max Fragment Size']= params.max_restriction_framgnet_size
+summary['Min Insert Size'] = params.min_insert_size
+summary['Max Insert Size'] = params.max_insert_size
+summary['Min CIS dist'] = params.min_cis_dist
summary['Maps resolution'] = params.bin_size
summary['Max Memory'] = params.max_memory
@@ -273,7 +281,7 @@ if(params.email) {
summary['MultiQC maxsize'] = params.maxMultiqcEmailFileSize
}
log.info summary.collect { k,v -> "${k.padRight(18)}: $v" }.join("\n")
-log.info "\033[2m----------------------------------------------------\033[0m"
+log.info "-\033[2m--------------------------------------------------\033[0m-"
// Check the hostnames against configured profiles
checkHostname()
@@ -403,36 +411,36 @@ process bowtie2_end_to_end {
saveAs: { params.saveAlignedIntermediates ? it : null }, mode: 'copy'
input:
- set val(sample), file(reads) from raw_reads
- file index from bwt2_index_end2end.collect()
+ set val(sample), file(reads) from raw_reads
+ file index from bwt2_index_end2end.collect()
output:
- set val(prefix), file("${prefix}_unmap.fastq") into unmapped_end_to_end
- set val(prefix), file("${prefix}.bam") into end_to_end_bam
+ set val(prefix), file("${prefix}_unmap.fastq") into unmapped_end_to_end
+ set val(prefix), file("${prefix}.bam") into end_to_end_bam
script:
- prefix = reads.toString() - ~/(\.fq)?(\.fastq)?(\.gz)?$/
- def bwt2_opts = params.bwt2_opts_end2end
-
- if (!params.dnase){
- """
- bowtie2 --rg-id BMG --rg SM:${prefix} \\
- ${bwt2_opts} \\
- -p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
- --un ${prefix}_unmap.fastq \\
- -U ${reads} | samtools view -F 4 -bS - > ${prefix}.bam
- """
- }else{
- """
- bowtie2 --rg-id BMG --rg SM:${prefix} \\
- ${bwt2_opts} \\
- -p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
- --un ${prefix}_unmap.fastq \\
- -U ${reads} > ${prefix}.bam
- """
- }
+ prefix = reads.toString() - ~/(\.fq)?(\.fastq)?(\.gz)?$/
+ def bwt2_opts = params.bwt2_opts_end2end
+
+ if (!params.dnase){
+ """
+ bowtie2 --rg-id BMG --rg SM:${prefix} \\
+ ${bwt2_opts} \\
+ -p ${task.cpus} \\
+ -x ${index}/${bwt2_base} \\
+ --un ${prefix}_unmap.fastq \\
+ -U ${reads} | samtools view -F 4 -bS - > ${prefix}.bam
+ """
+ }else{
+ """
+ bowtie2 --rg-id BMG --rg SM:${prefix} \\
+ ${bwt2_opts} \\
+ -p ${task.cpus} \\
+ -x ${index}/${bwt2_base} \\
+ --un ${prefix}_unmap.fastq \\
+ -U ${reads} > ${prefix}.bam
+ """
+ }
}
process trim_reads {
@@ -441,20 +449,20 @@ process trim_reads {
saveAs: { params.saveAlignedIntermediates ? it : null }, mode: 'copy'
when:
- !params.dnase
+ !params.dnase
input:
- set val(prefix), file(reads) from unmapped_end_to_end
+ set val(prefix), file(reads) from unmapped_end_to_end
output:
- set val(prefix), file("${prefix}_trimmed.fastq") into trimmed_reads
+ set val(prefix), file("${prefix}_trimmed.fastq") into trimmed_reads
script:
- """
- cutsite_trimming --fastq $reads \\
- --cutsite ${params.ligation_site} \\
- --out ${prefix}_trimmed.fastq
- """
+ """
+ cutsite_trimming --fastq $reads \\
+ --cutsite ${params.ligation_site} \\
+ --out ${prefix}_trimmed.fastq
+ """
}
process bowtie2_on_trimmed_reads {
@@ -463,24 +471,24 @@ process bowtie2_on_trimmed_reads {
saveAs: { params.saveAlignedIntermediates ? it : null }, mode: 'copy'
when:
- !params.dnase
+ !params.dnase
input:
- set val(prefix), file(reads) from trimmed_reads
- file index from bwt2_index_trim.collect()
+ set val(prefix), file(reads) from trimmed_reads
+ file index from bwt2_index_trim.collect()
output:
- set val(prefix), file("${prefix}_trimmed.bam") into trimmed_bam
+ set val(prefix), file("${prefix}_trimmed.bam") into trimmed_bam
script:
- prefix = reads.toString() - ~/(_trimmed)?(\.fq)?(\.fastq)?(\.gz)?$/
- """
- bowtie2 --rg-id BMG --rg SM:${prefix} \\
- ${params.bwt2_opts_trimmed} \\
- -p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
- -U ${reads} | samtools view -bS - > ${prefix}_trimmed.bam
- """
+ prefix = reads.toString() - ~/(_trimmed)?(\.fq)?(\.fastq)?(\.gz)?$/
+ """
+ bowtie2 --rg-id BMG --rg SM:${prefix} \\
+ ${params.bwt2_opts_trimmed} \\
+ -p ${task.cpus} \\
+ -x ${index}/${bwt2_base} \\
+ -U ${reads} | samtools view -bS - > ${prefix}_trimmed.bam
+ """
}
if (!params.dnase){
@@ -490,39 +498,38 @@ if (!params.dnase){
saveAs: { params.saveAlignedIntermediates ? it : null }, mode: 'copy'
input:
- set val(prefix), file(bam1), file(bam2) from end_to_end_bam.join( trimmed_bam )
+ set val(prefix), file(bam1), file(bam2) from end_to_end_bam.join( trimmed_bam )
output:
- set val(sample), file("${prefix}_bwt2merged.bam") into bwt2_merged_bam
- set val(oname), file("${prefix}.mapstat") into all_mapstat
+ set val(sample), file("${prefix}_bwt2merged.bam") into bwt2_merged_bam
+ set val(oname), file("${prefix}.mapstat") into all_mapstat
script:
- sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1$|_2)/
- tag = prefix.toString() =~/_R1|_val_1|_1/ ? "R1" : "R2"
- oname = prefix.toString() - ~/(\.[0-9]+)$/
-
- """
- samtools merge -@ ${task.cpus} \\
- -f ${prefix}_bwt2merged.bam \\
- ${bam1} ${bam2}
+ sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1$|_2)/
+ tag = prefix.toString() =~/_R1|_val_1|_1/ ? "R1" : "R2"
+ oname = prefix.toString() - ~/(\.[0-9]+)$/
+ """
+ samtools merge -@ ${task.cpus} \\
+ -f ${prefix}_bwt2merged.bam \\
+ ${bam1} ${bam2}
- samtools sort -@ ${task.cpus} -m 800M \\
+ samtools sort -@ ${task.cpus} -m 800M \\
-n -T /tmp/ \\
-o ${prefix}_bwt2merged.sorted.bam \\
${prefix}_bwt2merged.bam
- mv ${prefix}_bwt2merged.sorted.bam ${prefix}_bwt2merged.bam
-
- echo "## ${prefix}" > ${prefix}.mapstat
- echo -n "total_${tag}\t" >> ${prefix}.mapstat
- samtools view -c ${prefix}_bwt2merged.bam >> ${prefix}.mapstat
- echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${prefix}_bwt2merged.bam >> ${prefix}.mapstat
- echo -n "global_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
- echo -n "local_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam2} >> ${prefix}.mapstat
- """
+ mv ${prefix}_bwt2merged.sorted.bam ${prefix}_bwt2merged.bam
+
+ echo "## ${prefix}" > ${prefix}.mapstat
+ echo -n "total_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c ${prefix}_bwt2merged.bam >> ${prefix}.mapstat
+ echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${prefix}_bwt2merged.bam >> ${prefix}.mapstat
+ echo -n "global_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
+ echo -n "local_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam2} >> ${prefix}.mapstat
+ """
}
}else{
process dnase_mapping_stats{
@@ -531,27 +538,26 @@ if (!params.dnase){
saveAs: { params.saveAlignedIntermediates ? it : null }, mode: 'copy'
input:
- set val(prefix), file(bam1) from end_to_end_bam
+ set val(prefix), file(bam1) from end_to_end_bam
output:
- set val(sample), file(bam1) into bwt2_merged_bam
- set val(oname), file("${prefix}.mapstat") into all_mapstat
+ set val(sample), file(bam1) into bwt2_merged_bam
+ set val(oname), file("${prefix}.mapstat") into all_mapstat
script:
- sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1|_2)/
- tag = prefix.toString() =~/_R1|_val_1|_1/ ? "R1" : "R2"
- oname = prefix.toString() - ~/(\.[0-9]+)$/
-
- """
- echo "## ${prefix}" > ${prefix}.mapstat
- echo -n "total_${tag}\t" >> ${prefix}.mapstat
- samtools view -c ${bam1} >> ${prefix}.mapstat
- echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
- echo -n "global_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
- echo -n "local_${tag}\t0" >> ${prefix}.mapstat
- """
+ sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1|_2)/
+ tag = prefix.toString() =~/_R1|_val_1|_1/ ? "R1" : "R2"
+ oname = prefix.toString() - ~/(\.[0-9]+)$/
+ """
+ echo "## ${prefix}" > ${prefix}.mapstat
+ echo -n "total_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c ${bam1} >> ${prefix}.mapstat
+ echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
+ echo -n "global_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
+ echo -n "local_${tag}\t0" >> ${prefix}.mapstat
+ """
}
}
@@ -563,26 +569,26 @@ process combine_mapped_files{
saveAs: {filename -> filename.indexOf(".pairstat") > 0 ? "stats/$filename" : "$filename"}
input:
- set val(sample), file(aligned_bam) from bwt2_merged_bam.groupTuple()
+ set val(sample), file(aligned_bam) from bwt2_merged_bam.groupTuple()
output:
- set val(sample), file("${sample}_bwt2pairs.bam") into paired_bam
- set val(oname), file("*.pairstat") into all_pairstat
+ set val(sample), file("${sample}_bwt2pairs.bam") into paired_bam
+ set val(oname), file("*.pairstat") into all_pairstat
script:
- r1_bam = aligned_bam[0]
- r1_prefix = r1_bam.toString() - ~/_bwt2merged.bam$/
- r2_bam = aligned_bam[1]
- r2_prefix = r2_bam.toString() - ~/_bwt2merged.bam$/
- oname = sample.toString() - ~/(\.[0-9]+)$/
-
- def opts = "-t"
- opts = params.rm_singleton ? "${opts}" : "--single ${opts}"
- opts = params.rm_multi ? "${opts}" : "--multi ${opts}"
- if ("$params.min_mapq".isInteger()) opts="${opts} -q ${params.min_mapq}"
- """
- mergeSAM.py -f ${r1_bam} -r ${r2_bam} -o ${sample}_bwt2pairs.bam ${opts}
- """
+ r1_bam = aligned_bam[0]
+ r1_prefix = r1_bam.toString() - ~/_bwt2merged.bam$/
+ r2_bam = aligned_bam[1]
+ r2_prefix = r2_bam.toString() - ~/_bwt2merged.bam$/
+ oname = sample.toString() - ~/(\.[0-9]+)$/
+
+ def opts = "-t"
+ opts = params.rm_singleton ? "${opts}" : "--single ${opts}"
+ opts = params.rm_multi ? "${opts}" : "--multi ${opts}"
+ if ("$params.min_mapq".isInteger()) opts="${opts} -q ${params.min_mapq}"
+ """
+ mergeSAM.py -f ${r1_bam} -r ${r2_bam} -o ${sample}_bwt2pairs.bam ${opts}
+ """
}
@@ -597,34 +603,33 @@ if (!params.dnase){
saveAs: {filename -> filename.indexOf("*stat") > 0 ? "stats/$filename" : "$filename"}
input:
- set val(sample), file(pe_bam) from paired_bam
- file frag_file from res_frag_file.collect()
+ set val(sample), file(pe_bam) from paired_bam
+ file frag_file from res_frag_file.collect()
output:
- set val(sample), file("*.validPairs") into valid_pairs
- set val(sample), file("*.validPairs") into valid_pairs_4cool
- set val(sample), file("*.DEPairs") into de_pairs
- set val(sample), file("*.SCPairs") into sc_pairs
- set val(sample), file("*.REPairs") into re_pairs
- set val(sample), file("*.FiltPairs") into filt_pairs
- set val(sample), file("*RSstat") into all_rsstat
+ set val(sample), file("*.validPairs") into valid_pairs
+ set val(sample), file("*.validPairs") into valid_pairs_4cool
+ set val(sample), file("*.DEPairs") into de_pairs
+ set val(sample), file("*.SCPairs") into sc_pairs
+ set val(sample), file("*.REPairs") into re_pairs
+ set val(sample), file("*.FiltPairs") into filt_pairs
+ set val(sample), file("*RSstat") into all_rsstat
script:
- if (params.splitFastq){
- sample = sample.toString() - ~/(\.[0-9]+)$/
- }
-
- def opts = ""
- if ("$params.min_cis_dist".isInteger()) opts="${opts} -d ${params.min_cis_dist}"
- if ("$params.min_insert_size".isInteger()) opts="${opts} -s ${params.min_insert_size}"
- if ("$params.max_insert_size".isInteger()) opts="${opts} -l ${params.max_insert_size}"
- if ("$params.min_restriction_fragment_size".isInteger()) opts="${opts} -t ${params.min_restriction_fragment_size}"
- if ("$params.max_restriction_fragment_size".isInteger()) opts="${opts} -m ${params.max_restriction_fragment_size}"
- if (params.saveInteractionBAM) opts="${opts} --sam"
-
- """
- mapped_2hic_fragments.py -f ${frag_file} -r ${pe_bam} --all ${opts}
- """
+ if (params.splitFastq){
+ sample = sample.toString() - ~/(\.[0-9]+)$/
+ }
+
+ def opts = ""
+ if ("$params.min_cis_dist".isInteger()) opts="${opts} -d ${params.min_cis_dist}"
+ if ("$params.min_insert_size".isInteger()) opts="${opts} -s ${params.min_insert_size}"
+ if ("$params.max_insert_size".isInteger()) opts="${opts} -l ${params.max_insert_size}"
+ if ("$params.min_restriction_fragment_size".isInteger()) opts="${opts} -t ${params.min_restriction_fragment_size}"
+ if ("$params.max_restriction_fragment_size".isInteger()) opts="${opts} -m ${params.max_restriction_fragment_size}"
+ if (params.saveInteractionBAM) opts="${opts} --sam"
+ """
+ mapped_2hic_fragments.py -f ${frag_file} -r ${pe_bam} --all ${opts}
+ """
}
}
else{
@@ -634,23 +639,23 @@ else{
saveAs: {filename -> filename.indexOf("*stat") > 0 ? "stats/$filename" : "$filename"}
input:
- set val(sample), file(pe_bam) from paired_bam
+ set val(sample), file(pe_bam) from paired_bam
output:
- set val(sample), file("*.validPairs") into valid_pairs
- set val(sample), file("*.validPairs") into valid_pairs_4cool
- set val(sample), file("*RSstat") into all_rsstat
+ set val(sample), file("*.validPairs") into valid_pairs
+ set val(sample), file("*.validPairs") into valid_pairs_4cool
+ set val(sample), file("*RSstat") into all_rsstat
script:
- if (params.splitFastq){
- sample = sample.toString() - ~/(\.[0-9]+)$/
- }
-
- def opts = ""
- if ("$params.min_cis_dist".isInteger()) opts="${opts} -d ${params.min_cis_dist}"
- """
- mapped_2hic_dnase.py -r ${pe_bam} ${opts}
- """
+ if (params.splitFastq){
+ sample = sample.toString() - ~/(\.[0-9]+)$/
+ }
+
+ def opts = ""
+ if ("$params.min_cis_dist".isInteger()) opts="${opts} -d ${params.min_cis_dist}"
+ """
+ mapped_2hic_dnase.py -r ${pe_bam} ${opts}
+ """
}
}
@@ -665,12 +670,12 @@ process remove_duplicates {
saveAs: {filename -> filename.indexOf("*stat") > 0 ? "stats/$sample/$filename" : "$filename"}
input:
- set val(sample), file(vpairs) from valid_pairs.groupTuple()
+ set val(sample), file(vpairs) from valid_pairs.groupTuple()
output:
- set val(sample), file("*.allValidPairs") into all_valid_pairs
- set val(sample), file("*.allValidPairs") into all_valid_pairs_4cool
- file("stats/") into all_mergestat
+ set val(sample), file("*.allValidPairs") into all_valid_pairs
+ set val(sample), file("*.allValidPairs") into all_valid_pairs_4cool
+ file("stats/") into all_mergestat
script:
if ( params.rm_dup ){
@@ -710,21 +715,20 @@ process merge_sample {
publishDir "${params.outdir}/hic_results/stats/${sample}", mode: 'copy'
input:
- set val(prefix), file(fstat) from all_mapstat.groupTuple().concat(all_pairstat.groupTuple(), all_rsstat.groupTuple())
+ set val(prefix), file(fstat) from all_mapstat.groupTuple().concat(all_pairstat.groupTuple(), all_rsstat.groupTuple())
- output:
- file("mstats/") into all_mstats
+ output:
+ file("mstats/") into all_mstats
script:
- sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1|_2)/
- if ( (fstat =~ /.mapstat/) ){ ext = "mmapstat" }
- if ( (fstat =~ /.pairstat/) ){ ext = "mpairstat" }
- if ( (fstat =~ /.RSstat/) ){ ext = "mRSstat" }
-
- """
- mkdir -p mstats/${sample}
- merge_statfiles.py -f ${fstat} > mstats/${sample}/${prefix}.${ext}
- """
+ sample = prefix.toString() - ~/(_R1|_R2|_val_1|_val_2|_1|_2)/
+ if ( (fstat =~ /.mapstat/) ){ ext = "mmapstat" }
+ if ( (fstat =~ /.pairstat/) ){ ext = "mpairstat" }
+ if ( (fstat =~ /.RSstat/) ){ ext = "mRSstat" }
+ """
+ mkdir -p mstats/${sample}
+ merge_statfiles.py -f ${fstat} > mstats/${sample}/${prefix}.${ext}
+ """
}
@@ -733,15 +737,15 @@ process build_contact_maps{
publishDir "${params.outdir}/hic_results/matrix/raw", mode: 'copy'
when:
- !params.skip_maps
+ !params.skipMaps
input:
- set val(sample), file(vpairs), val(mres) from all_valid_pairs.combine(map_res)
- file chrsize from chromosome_size.collect()
+ set val(sample), file(vpairs), val(mres) from all_valid_pairs.combine(map_res)
+ file chrsize from chromosome_size.collect()
output:
- file("*.matrix") into raw_maps
- file "*.bed"
+ file("*.matrix") into raw_maps
+ file "*.bed"
script:
"""
@@ -758,14 +762,14 @@ process run_ice{
publishDir "${params.outdir}/hic_results/matrix/iced", mode: 'copy'
when:
- !params.skip_maps && !params.skip_ice
+ !params.skipMaps && !params.skipIce
input:
- file(rmaps) from raw_maps
- file "*.biases"
+ file(rmaps) from raw_maps
+ file "*.biases"
output:
- file("*iced.matrix") into iced_maps
+ file("*iced.matrix") into iced_maps
script:
prefix = rmaps.toString() - ~/(\.matrix)?$/
@@ -786,14 +790,14 @@ process generate_cool{
publishDir "${params.outdir}/export/cool", mode: 'copy'
when:
- !params.skip_cool
+ !params.skipCool
input:
- set val(sample), file(vpairs) from all_valid_pairs_4cool
- file chrsize from chromosome_size_cool.collect()
+ set val(sample), file(vpairs) from all_valid_pairs_4cool
+ file chrsize from chromosome_size_cool.collect()
output:
- file("*mcool") into cool_maps
+ file("*mcool") into cool_maps
script:
"""
@@ -803,51 +807,50 @@ process generate_cool{
/*
- * STEP 5 - MultiQC
+ * STEP 6 - MultiQC
*/
process multiqc {
- publishDir "${params.outdir}/MultiQC", mode: 'copy'
+ publishDir "${params.outdir}/MultiQC", mode: 'copy'
- when:
- !params.skip_multiqc
-
- input:
- file multiqc_config from ch_multiqc_config
- file ('input_*/*') from all_mstats.concat(all_mergestat).collect()
- file ('software_versions/*') from software_versions_yaml
- file workflow_summary from create_workflow_summary(summary)
+ when:
+ !params.skipMultiQC
- output:
- file "*multiqc_report.html" into multiqc_report
- file "*_data"
+ input:
+ file multiqc_config from ch_multiqc_config
+ file ('input_*/*') from all_mstats.concat(all_mergestat).collect()
+ file ('software_versions/*') from software_versions_yaml
+ file workflow_summary from create_workflow_summary(summary)
- script:
- rtitle = custom_runName ? "--title \"$custom_runName\"" : ''
- rfilename = custom_runName ? "--filename " + custom_runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" : ''
+ output:
+ file "*multiqc_report.html" into multiqc_report
+ file "*_data"
- """
- multiqc -f $rtitle $rfilename --config $multiqc_config .
- """
+ script:
+ rtitle = custom_runName ? "--title \"$custom_runName\"" : ''
+ rfilename = custom_runName ? "--filename " + custom_runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" : ''
+ """
+ multiqc -f $rtitle $rfilename --config $multiqc_config .
+ """
}
/*
- * STEP 3 - Output Description HTML
+ * STEP 7 - Output Description HTML
*/
process output_documentation {
- publishDir "${params.outdir}/pipeline_info", mode: 'copy'
+ publishDir "${params.outdir}/pipeline_info", mode: 'copy'
- input:
- file output_docs from ch_output_docs
+ input:
+ file output_docs from ch_output_docs
- output:
- file "results_description.html"
+ output:
+ file "results_description.html"
- script:
- """
- markdown_to_html.r $output_docs results_description.html
- """
+ script:
+ """
+ markdown_to_html.r $output_docs results_description.html
+ """
}
@@ -948,10 +951,10 @@ workflow.onComplete {
c_green = params.monochrome_logs ? '' : "\033[0;32m";
c_red = params.monochrome_logs ? '' : "\033[0;31m";
- if (workflow.stats.ignoredCountFmt > 0 && workflow.success) {
+ if (workflow.stats.ignoredCount > 0 && workflow.success) {
log.info "${c_purple}Warning, pipeline completed, but with errored process(es) ${c_reset}"
- log.info "${c_red}Number of ignored errored process(es) : ${workflow.stats.ignoredCountFmt} ${c_reset}"
- log.info "${c_green}Number of successfully ran process(es) : ${workflow.stats.succeedCountFmt} ${c_reset}"
+ log.info "${c_red}Number of ignored errored process(es) : ${workflow.stats.ignoredCount} ${c_reset}"
+ log.info "${c_green}Number of successfully ran process(es) : ${workflow.stats.succeedCount} ${c_reset}"
}
if(workflow.success){
@@ -976,14 +979,14 @@ def nfcoreHeader(){
c_cyan = params.monochrome_logs ? '' : "\033[0;36m";
c_white = params.monochrome_logs ? '' : "\033[0;37m";
- return """ ${c_dim}----------------------------------------------------${c_reset}
+ return """ -${c_dim}--------------------------------------------------${c_reset}-
${c_green},--.${c_black}/${c_green},-.${c_reset}
${c_blue} ___ __ __ __ ___ ${c_green}/,-._.--~\'${c_reset}
${c_blue} |\\ | |__ __ / ` / \\ |__) |__ ${c_yellow}} {${c_reset}
${c_blue} | \\| | \\__, \\__/ | \\ |___ ${c_green}\\`-._,-`-,${c_reset}
${c_green}`._,._,\'${c_reset}
- ${c_purple} nf-core/hic v${workflow.manifest.version}${c_reset}
- ${c_dim}----------------------------------------------------${c_reset}
+ ${c_purple} nf-core/atacseq v${workflow.manifest.version}${c_reset}
+ -${c_dim}--------------------------------------------------${c_reset}-
""".stripIndent()
}
diff --git a/nextflow.config b/nextflow.config
index 37a7d3c86ea1e5af718b17bfdd94f6b2bbe3795d..5d69802ee9402cae44e25e6880d3353e4d236561 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -16,10 +16,10 @@ params {
readPaths = false
chromosome_size = false
restriction_fragments = false
- skip_maps = false
- skip_ice = false
- skip_cool = false
- skip_multiqc = false
+ skipMaps = false
+ skipIce = false
+ skipCool = false
+ skipMultiQC = false
dnase = false
// Boilerplate options
@@ -45,7 +45,7 @@ params {
// Container slug. Stable releases should specify release tag!
// Developmental code should specify :dev
-process.container = 'nfcore/hic:1.1.0'
+process.container = 'nfcore/hic:dev'
// Load base.config by default for all pipelines
includeConfig 'conf/base.config'
@@ -101,8 +101,8 @@ manifest {
homePage = 'https://github.com/nf-core/hic'
description = 'Analysis of Chromosome Conformation Capture data (Hi-C)'
mainScript = 'main.nf'
- nextflowVersion = '>=0.32.0'
- version = '1.1.0'
+ nextflowVersion = '>=19.04.0'
+ version = '1.1.1dev'
}
// Function to ensure that resource requirements don't go beyond