diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
index 26d2e7e9f9223900ddc066163f442f821d1a62f3..a43253198aa92a5832082dcd687516047b7af65b 100644
--- a/.github/workflows/awsfulltest.yml
+++ b/.github/workflows/awsfulltest.yml
@@ -20,7 +20,6 @@ jobs:
- name: Install awscli
run: conda install -c conda-forge awscli
- name: Start AWS batch job
- # TODO nf-core: You can customise AWS full pipeline tests as required
# Add full size test data (but still relatively small datasets for few samples)
# on the `test_full.config` test runs with only one set of parameters
# Then specify `-profile test_full` instead of `-profile test` on the AWS batch command
diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
index 78ee5bc67a2ad5565bca78f0de19cb639bf51998..94bca240004c28e2608c4e1a8c2a82bb054ce428 100644
--- a/.github/workflows/awstest.yml
+++ b/.github/workflows/awstest.yml
@@ -21,7 +21,6 @@ jobs:
- name: Install awscli
run: conda install -c conda-forge awscli
- name: Start AWS batch job
- # TODO nf-core: You can customise CI pipeline run tests as required
# For example: adding multiple test runs with different parameters
# Remember that you can parallelise this by using strategy.matrix
env:
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index fe636dd4fdc884d7ffc18dfc0b7ae81a186796f4..a8a8ba508df126c0af56f37daa5fe7e94a976875 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -34,13 +34,13 @@ jobs:
- name: Build new docker image
if: env.GIT_DIFF
- run: docker build --no-cache . -t nfcore/hic:dev
+ run: docker build --no-cache . -t nfcore/hic:1.2.2
- name: Pull docker image
if: ${{ !env.GIT_DIFF }}
run: |
docker pull nfcore/hic:dev
- docker tag nfcore/hic:dev nfcore/hic:dev
+ docker tag nfcore/hic:dev nfcore/hic:1.2.2
- name: Install Nextflow
run: |
@@ -48,8 +48,5 @@ jobs:
sudo mv nextflow /usr/local/bin/
- name: Run pipeline with test data
- # TODO nf-core: You can customise CI pipeline run tests as required
- # For example: adding multiple test runs with different parameters
- # Remember that you can parallelise this by using strategy.matrix
run: |
nextflow run ${GITHUB_WORKSPACE} -profile test,docker
diff --git a/Dockerfile b/Dockerfile
index 1f8dacfeed27d70458e18e57bd0aac77045df08c..3c8d019dc4fb85111fe16279257c734d8aeafd43 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -10,10 +10,10 @@ COPY environment.yml /
RUN conda env create --quiet -f /environment.yml && conda clean -a
# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-hic-1.2.1/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-hic-1.2.2/bin:$PATH
# Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-hic-1.2.1 > nf-core-hic-1.2.1.yml
+RUN conda env export --name nf-core-hic-1.2.2 > nf-core-hic-1.2.2.yml
# Instruct R processes to use these empty files instead of clashing with a local version
RUN touch .Rprofile
diff --git a/README.md b/README.md
index cde30f54178cda6f5a4cc4915d06795359c37f27..da5877743ea00743c8e3e50a01275dece0a2b1bd 100644
--- a/README.md
+++ b/README.md
@@ -104,8 +104,6 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
4. Start running your own analysis!
- <!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
-
```bash
nextflow run nf-core/hic -profile <docker/singularity/conda/institute> --input '*_R{1,2}.fastq.gz' --genome GRCh37
```
diff --git a/conf/hicpro.config b/conf/hicpro.config
index 01b755a955c5aee521a6cf43b00847cfbc8d0cd3..cd0cf0b5a54f860312f49ac193802d53964ce686 100644
--- a/conf/hicpro.config
+++ b/conf/hicpro.config
@@ -10,7 +10,6 @@
params {
// Alignment options
- splitFastq = false
bwt2_opts_end2end = '--very-sensitive -L 30 --score-min L,-0.6,-0.2 --end-to-end --reorder'
bwt2_opts_trimmed = '--very-sensitive -L 20 --score-min L,-0.6,-0.2 --end-to-end --reorder'
min_mapq = 10
@@ -35,9 +34,5 @@ params {
ice_filer_low_count_perc = 0.02
ice_filer_high_count_perc = 0
ice_eps = 0.1
-
- saveReference = false
- saveAlignedIntermediates = false
- saveInteractionBAM = false
}
diff --git a/conf/test_full.config b/conf/test_full.config
index 921372eec05fe6147c540a39463c54f0ebf09bce..47d31760585c66025666f112dcd03a23faeac543 100644
--- a/conf/test_full.config
+++ b/conf/test_full.config
@@ -12,11 +12,25 @@ params {
config_profile_description = 'Full test dataset to check pipeline function'
// Input data for full size test
- // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
- single_end = false
input_paths = [
- ['Testdata', ['https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R1.tiny.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R2.tiny.fastq.gz']],
- ['SRR389222', ['https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub2.fastq.gz']]
- ]
+ ['SRR4292758_00', ['https://github.com/nf-core/test-datasets/raw/hic/data/SRR4292758_00_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/data/SRR4292758_00_R2.fastq.gz']]
+ ]
+
+ // Annotations
+ fasta = 'https://github.com/nf-core/test-datasets/raw/hic/reference/W303_SGD_2015_JRIU00000000.fsa'
+ restriction_site = 'A^AGCTT'
+ ligation_site = 'AAGCTAGCTT'
+
+ min_mapq = 2
+ rm_dup = true
+ rm_singleton = true
+ rm_multi = true
+
+ min_restriction_fragment_size = 100
+ max_restriction_fragment_size = 100000
+ min_insert_size = 100
+ max_insert_size = 600
+
+ // Options
+ skip_cool = true
}
diff --git a/docs/README.md b/docs/README.md
index 67df846ef262b9918e55dff0147baf0d3cc03a9e..a6889549c7f27bda0aed81947685713781fe2d1b 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -2,8 +2,6 @@
The nf-core/hic documentation is split into the following pages:
-<!-- TODO nf-core: If you write more documentation pages, add them to the docs index page here -->
-
* [Usage](usage.md)
* An overview of how the pipeline works, how to run it and a description of all of the different command-line flags.
* [Output](output.md)
diff --git a/environment.yml b/environment.yml
index e8944c64299636c7796f9ff22ff64cc48a7fb22f..ccca9c3d12e94380287c1be0f9f34ca9813890ae 100644
--- a/environment.yml
+++ b/environment.yml
@@ -1,6 +1,6 @@
# You can use this file to create a conda environment for this pipeline:
# conda env create -f environment.yml
-name: nf-core-hic-1.2.1
+name: nf-core-hic-1.2.2
channels:
- conda-forge
- bioconda
diff --git a/main.nf b/main.nf
index f33f88c9c4c1d0920a9af77f3bec57f8063fb58d..0cfcbc67001461bd73d04d497056d11387c722aa 100644
--- a/main.nf
+++ b/main.nf
@@ -32,10 +32,10 @@ def helpMessage() {
--chromosome_size [file] Path to chromosome size file
--restriction_fragments [file] Path to restriction fragment file (bed)
--save_reference [bool] Save reference genome to output folder. Default: False
- --save_aligned_intermediates [bool] Save intermediates alignment files. Default: False
Alignments
--split_fastq [bool] Size of read chuncks to use to speed up the workflow. Default: None
+ --save_aligned_intermediates [bool] Save intermediates alignment files. Default: False
--bwt2_opts_end2end [str] Options for bowtie2 end-to-end mappinf (first mapping step). See hic.config for default.
--bwt2_opts_trimmed [str] Options for bowtie2 mapping after ligation site trimming. See hic.config for default.
--min_mapq [int] Minimum mapping quality values to consider. Default: 10
diff --git a/nextflow.config b/nextflow.config
index 24ff566a6356cdcadf02f951436b31d8fc29a55c..c598df934ea0bd8b61c414117332211b792a99f8 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -15,7 +15,8 @@ params {
outdir = './results'
genome = false
- readPaths = false
+ input_paths = false
+ split_fastq = false
chromosome_size = false
restriction_fragments = false
skip_maps = false
@@ -25,16 +26,28 @@ params {
save_reference = false
save_interaction_bam = false
save_aligned_intermediates = false
-
- dnase = false
- rm_dup = false
- rm_singleton = false
- rm_multi = false
+
+ bwt2_opts_end2end = '--very-sensitive -L 30 --score-min L,-0.6,-0.2 --end-to-end --reorder'
+ bwt2_opts_trimmed = '--very-sensitive -L 20 --score-min L,-0.6,-0.2 --end-to-end --reorder'
+ min_mapq = 10
+
+ // Digestion Hi-C
+ restriction_site = 'A^AGCTT'
+ ligation_site = 'AAGCTAGCTT'
min_restriction_fragment_size = false
max_restriction_fragment_size = false
min_insert_size = false
max_insert_size = false
- min_cis_dist = false
+ dnase = false
+ rm_dup = false
+ rm_singleton = false
+ rm_multi = false
+ bin_size = '1000000,500000'
+ ice_max_iter = 100
+ ice_filer_low_count_perc = 0.02
+ ice_filer_high_count_perc = 0
+ ice_eps = 0.1
+
publish_dir_mode = 'copy'
// Boilerplate options
@@ -65,7 +78,7 @@ params {
// Container slug. Stable releases should specify release tag!
// Developmental code should specify :dev
-process.container = 'nfcore/hic:1.2.1'
+process.container = 'nfcore/hic:1.2.2'
// Load base.config by default for all pipelines
includeConfig 'conf/base.config'
@@ -77,9 +90,6 @@ try {
System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
}
-// Load hic config file
-includeConfig 'conf/hicpro.config'
-
// Create profiles
profiles {
conda { process.conda = "$baseDir/environment.yml" }
@@ -138,7 +148,7 @@ manifest {
description = 'Analysis of Chromosome Conformation Capture data (Hi-C)'
mainScript = 'main.nf'
nextflowVersion = '>=19.10.0'
- version = '1.2.1'
+ version = '1.2.2'
}
// Function to ensure that resource requirements don't go beyond
diff --git a/nextflow_schema.json b/nextflow_schema.json
index ccbfe4b5162528808d9ffb5289a826e15ece76e7..bb4529597d769dc9e5b74ceed8ebcd2567b5ac8a 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -20,6 +20,17 @@
"description": "Input FastQ files.",
"help_text": "Use this to specify the location of your input FastQ files. For example:\n\n```bash\n--input 'path/to/data/sample_*_{1,2}.fastq'\n```\n\nPlease note the following requirements:\n\n1. The path must be enclosed in quotes\n2. The path must have at least one `*` wildcard character\n3. When using the pipeline with paired end data, the path must use `{1,2}` notation to specify read pairs.\n\nIf left unspecified, a default pattern is used: `data/*{1,2}.fastq.gz`"
},
+ "input_paths": {
+ "type": "string",
+ "hidden": true,
+ "description": "Input FastQ files for test only",
+ "default": "undefined"
+ },
+ "split_fastq": {
+ "type": "number",
+ "description": "Split the reads into chunks before running. Specify the number of reads per chuncks as --split_fastq 20000000.",
+ "fa_icon": "fas fa-dna"
+ },
"single_end": {
"type": "boolean",
"description": "Specifies that the input is single-end reads.",
@@ -72,6 +83,180 @@
"fa_icon": "fas fa-ban",
"hidden": true,
"help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
+ },
+ "bwt2_index": {
+ "type": "string",
+ "description": "Full path to directory containing Bowtie index including base name. i.e. `/path/to/index/base`.",
+ "fa_icon": "far fa-file-alt"
+ },
+ "chromosome_size": {
+ "type": "string",
+ "description": "Full path to file specifying chromosome sizes (tab separated with chromosome name and size)`.",
+ "fa_icon": "far fa-file-alt",
+ "help_text": "If not specified, the pipeline will build this file from the reference genome file"
+ },
+ "restriction_fragments": {
+ "type": "string",
+ "description": "Full path to restriction fragment (bed) file.",
+ "fa_icon": "far fa-file-alt",
+ "help_text": "This file depends on the Hi-C protocols and digestion strategy. If not provided, the pipeline will build it using the --restriction_site option"
+ },
+ "save_reference": {
+ "type": "boolean",
+ "description": "If generated by the pipeline save the annotation and indexes in the results directory.",
+ "help_text": "Use this parameter to save all annotations to your results folder. These can then be used for future pipeline runs, reducing processing times.",
+ "fa_icon": "fas fa-save"
+ }
+ }
+ },
+ "data_processing_options": {
+ "title": "Data processing",
+ "type": "object",
+ "description": "Parameters for Hi-C data processing",
+ "default": "",
+ "fa_icon": "fas fa-bahai",
+ "properties": {
+ "dnase": {
+ "type": "boolean",
+ "description": "For Hi-C protocols which are not based on enzyme digestion such as DNase Hi-C"
+ },
+ "restriction_site": {
+ "type": "string",
+ "default": "'A^AGCTT'",
+ "description": "Restriction motifs used during digestion. Several motifs (comma separated) can be provided."
+ },
+ "ligation_site": {
+ "type": "string",
+ "default": "'AAGCTAGCTT",
+ "description": "Expected motif after DNA ligation. Several motifs (comma separated) can be provided."
+ },
+ "rm_dup": {
+ "type": "boolean",
+ "description": "Remove duplicates"
+ },
+ "rm_multi": {
+ "type": "boolean",
+ "description": "Remove multi-mapped reads"
+ },
+ "rm_singleton": {
+ "type": "boolean",
+ "description": "Remove singleton"
+ },
+ "min_mapq": {
+ "type": "integer",
+ "default": "10",
+ "description": "Keep aligned reads with a minimum quality value"
+ },
+ "bwt2_opts_end2end": {
+ "type": "string",
+ "default": "'--very-sensitive -L 30 --score-min L,-0.6,-0.2 --end-to-end --reorder'",
+ "description": "Option for end-to-end bowtie mapping"
+ },
+ "bwt2_opts_trimmed": {
+ "type": "string",
+ "default": "'--very-sensitive -L 20 --score-min L,-0.6,-0.2 --end-to-end --reorder'",
+ "description": "Option for trimmed reads mapping"
+ },
+ "save_interaction_bam": {
+ "type": "boolean",
+ "description": "Save a BAM file where all reads are flagged by their interaction classes"
+ },
+ "save_aligned_intermediates": {
+ "type": "boolean",
+ "description": "Save all BAM files during two-steps mapping"
+ }
+ }
+ },
+ "contacts_calling_options": {
+ "title": "Contacts calling",
+ "type": "object",
+ "description": "Options to call significant interactions",
+ "default": "",
+ "fa_icon": "fas fa-signature",
+ "properties": {
+ "min_cis_dist": {
+ "type": "string",
+ "default": "undefined",
+ "description": "Minimum distance between loci to consider. Useful for --dnase mode to remove spurious ligation products"
+ },
+ "max_insert_size": {
+ "type": "string",
+ "default": "undefined",
+ "description": "Maximum fragment size to consider"
+ },
+ "min_insert_size": {
+ "type": "string",
+ "default": "undefined",
+ "description": "Minimum fragment size to consider"
+ },
+ "max_restriction_fragment_size": {
+ "type": "string",
+ "default": "undefined",
+ "description": "Maximum restriction fragment size to consider"
+ },
+ "min_restriction_fragment_size": {
+ "type": "string",
+ "default": "undefined",
+ "description": "Minimum restriction fragment size to consider"
+ }
+ }
+ },
+ "contact_maps_options": {
+ "title": "Contact maps",
+ "type": "object",
+ "description": "Options to build Hi-C contact maps",
+ "default": "",
+ "fa_icon": "fas fa-chess-board",
+ "properties": {
+ "bin_size": {
+ "type": "string",
+ "default": "'1000000,500000'",
+ "description": "Resolution to build the maps (comma separated)"
+ },
+ "ice_filer_low_count_perc": {
+ "type": "string",
+ "default": 0.02,
+ "description": "Filter low counts rows before normalization"
+ },
+ "ice_filer_high_count_perc": {
+ "type": "integer",
+ "default": "0",
+ "description": "Filter high counts rows before normalization"
+ },
+ "ice_eps": {
+ "type": "string",
+ "default": "0.1",
+ "description": "Threshold for ICE convergence"
+ },
+ "ice_max_iter": {
+ "type": "integer",
+ "default": "100",
+ "description": "Maximum number of iteraction for ICE normalization"
+ }
+ }
+ },
+ "skip_options": {
+ "title": "Skip options",
+ "type": "object",
+ "description": "Skip some steps of the pipeline",
+ "default": "",
+ "fa_icon": "fas fa-random",
+ "properties": {
+ "skip_maps": {
+ "type": "boolean",
+ "description": "Do not build contact maps"
+ },
+ "skip_ice": {
+ "type": "boolean",
+ "description": "Do not normalize contact maps"
+ },
+ "skip_cool": {
+ "type": "boolean",
+ "description": "Do not generate cooler file"
+ },
+ "skip_multiqc": {
+ "type": "boolean",
+ "description": "Do not generate MultiQC report"
}
}
},
@@ -246,6 +431,18 @@
{
"$ref": "#/definitions/reference_genome_options"
},
+ {
+ "$ref": "#/definitions/data_processing_options"
+ },
+ {
+ "$ref": "#/definitions/contacts_calling_options"
+ },
+ {
+ "$ref": "#/definitions/contact_maps_options"
+ },
+ {
+ "$ref": "#/definitions/skip_options"
+ },
{
"$ref": "#/definitions/generic_options"
},