Merge pull request #18 from nf-core/dev

ready for first release

README.md

-# nf-core/hic
+# ![nf-core/hic](docs/images/nfcore-hic_logo.png)
 
 **Analysis of Chromosome Conformation Capture data (Hi-C)**.
 

Singularity

-From:nfcore/base
-Bootstrap:docker
-
-%labels
-    MAINTAINER Nicolas Servant
-    DESCRIPTION Singularity image containing all requirements for the nf-core/hic pipeline
-    VERSION 1.0dev
-
-%environment
-    PATH=/opt/conda/envs/nf-core-hic-1.0dev/bin:$PATH
-    export PATH
-
-%files
-    environment.yml /
-
-%post
-    /opt/conda/bin/conda env create -f /environment.yml
-    /opt/conda/bin/conda clean -a

docs/images/nfcore-hic_logo.svg

+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   enable-background="new 0 0 1150.9 517"
+   version="1.1"
+   viewBox="0 0 1456.7841 522.44342"
+   xml:space="preserve"
+   id="svg2"
+   inkscape:version="0.91 r13725"
+   sodipodi:docname="EmptyName_logo.svg"
+   width="1456.7842"
+   height="522.44342"><sodipodi:namedview
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1"
+     objecttolerance="10"
+     gridtolerance="10"
+     guidetolerance="10"
+     inkscape:pageopacity="0"
+     inkscape:pageshadow="2"
+     inkscape:window-width="1920"
+     inkscape:window-height="1015"
+     id="namedview75"
+     showgrid="false"
+     inkscape:zoom="0.35757767"
+     inkscape:cx="253.20897"
+     inkscape:cy="13.773735"
+     inkscape:window-x="1920"
+     inkscape:window-y="724"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="layer3"
+     fit-margin-left="62.25"
+     fit-margin-right="62.25"
+     fit-margin-top="62.25"
+     fit-margin-bottom="62.25" /><metadata
+     id="metadata4"><rdf:RDF><cc:Work
+         rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:title></dc:title></cc:Work></rdf:RDF></metadata><defs
+     id="defs6"><clipPath
+       id="e"><path
+         d="m 280.17,136.33 -21.5,-21.584 61,0 0,21.584 -39.5,0 z"
+         id="path9"
+         inkscape:connector-curvature="0" /></clipPath><linearGradient
+       id="f"
+       x2="1"
+       gradientTransform="matrix(37.935819,29.638391,-29.638391,37.935819,295.72019,166.19562)"
+       gradientUnits="userSpaceOnUse"><stop
+         stop-color="#0c542a"
+         offset="0"
+         id="stop12" /><stop
+         stop-color="#0c542a"
+         offset=".21472"
+         id="stop14" /><stop
+         stop-color="#25af64"
+         offset=".57995"
+         id="stop16" /><stop
+         stop-color="#25af64"
+         offset=".84663"
+         id="stop18" /><stop
+         stop-color="#25af64"
+         offset="1"
+         id="stop20" /></linearGradient></defs><style
+     type="text/css"
+     id="style22">
+	.st0{fill:#24AF63;}
+	.st1{font-family:'Maven Pro';}
+	.st1{font-weight:'bold';}
+	.st2{font-size:209.8672px;}
+	.st3{fill:#21AF62;}
+	.st4{fill:#ECDC86;}
+	.st5{fill:#A0918F;}
+	.st6{fill:#3F2B29;}
+	.st7{fill:#396E35;}
+	.st8{fill:url(#d);}
+</style><linearGradient
+     id="d"
+     x1="295.45999"
+     x2="333.34"
+     y1="150.75"
+     y2="180.35001"
+     gradientUnits="userSpaceOnUse"><stop
+       stop-color="#0D552B"
+       offset=".2147"
+       id="stop41" /><stop
+       stop-color="#176837"
+       offset=".311"
+       id="stop43" /><stop
+       stop-color="#1F8448"
+       offset=".4609"
+       id="stop45" /><stop
+       stop-color="#239A56"
+       offset=".604"
+       id="stop47" /><stop
+       stop-color="#24A860"
+       offset=".7361"
+       id="stop49" /><stop
+       stop-color="#25AF64"
+       offset=".8466"
+       id="stop51" /></linearGradient><g
+     inkscape:groupmode="layer"
+     id="layer2"
+     inkscape:label="Icon"
+     style="display:inline"
+     transform="translate(5.3761467,0)"><g
+       id="g4209"><path
+         style="fill:#24af63"
+         inkscape:connector-curvature="0"
+         id="path24"
+         d="m 1084.1,163.75 0,3.6 c -0.1,0 -0.1,0 -0.2,0.1 l -1.8,-1.5 c -4,-3.4 -8.3,-6.4 -13.1,-8.8 -0.8,-0.4 -1.6,-0.9 -2.5,-1.1 -0.1,-0.1 -0.2,-0.2 -0.3,-0.2 -1.8,-0.7 -3.6,-1.3 -5.5,-1.8 -4.1,-0.9 -8.2,-1 -12.3,-0.2 -5.3,1.1 -10,3.4 -14.5,6.4 -4.4,3 -8.4,6.5 -12.1,10.2 -0.7,0.7 -0.7,0.7 -1.1,-0.2 -2,-4.1 -4.2,-8.1 -6.9,-11.8 -2.1,-2.8 -4.4,-5.4 -7.4,-7.2 -3,-1.9 -6.3,-2.6 -9.8,-1.7 -4.3,1 -7.8,3.6 -11.1,6.4 -2,1.5 -3.8,3.3 -5.6,5 -1.7,1.5 -3.3,3 -5,4.5 -0.3,0.3 -0.5,0.3 -0.8,0 -1.7,-1.8 -3.5,-3.4 -5.6,-4.5 -3.1,-1.7 -6.3,-1.9 -9.6,-0.8 -2.8,0.9 -5.2,2.4 -7.7,4 -1,0.6 -1.9,1.3 -2.9,1.8 l 0,-0.2 c 0.1,-0.2 0.1,-0.4 0.1,-0.6 0.2,-4.4 0.5,-8.9 1.2,-13.3 1,-6.1 2.5,-12 5.2,-17.5 2,-4.1 4.7,-7.9 8.1,-11 4.5,-4.1 9.8,-6.7 15.6,-8.3 6.3,-1.8 12.7,-2.6 19.2,-2.9 2.6,-0.1 5.1,-0.2 7.7,-0.3 1.3,0.5 2.6,0.8 3.9,1.2 1.9,0.6 3.8,1.2 5.7,1.7 1,0.4 1.9,0.7 2.9,1.1 3.7,1.3 7.3,3 10.4,5.5 0.8,0.6 1.6,1.3 2.4,2 -0.2,-0.6 -0.4,-1.1 -0.6,-1.7 -1.4,-3.7 -3.5,-6.7 -6.9,-8.8 -1.4,-0.9 -2.9,-1.5 -4.4,-2.3 0.1,0 0.3,0 0.4,-0.1 4.5,-0.8 9.1,-1.2 13.7,-1.4 3.9,-0.2 7.9,-0.1 11.8,0.3 4.6,0.5 9.1,1.4 13.4,3 6.4,2.4 11.9,6.1 16.2,11.5 3.7,4.7 6.1,10.1 7.6,15.9 1.5,5.7 2.1,11.6 2.3,17.5 -0.1,2.1 -0.1,4.3 -0.1,6.5 z"
+         class="st0" /><path
+         style="fill:#ecdc86"
+         inkscape:connector-curvature="0"
+         id="path26"
+         d="m 1084.1,157.15 0.1,0 0,6.6 -0.1,0 0,-6.6 z"
+         class="st4" /><path
+         style="fill:#a0918f"
+         inkscape:connector-curvature="0"
+         id="path28"
+         d="m 1047.6,62.25 0,0.1 -4.5,0 0,-0.1 4.5,0 z"
+         class="st5" /><path
+         style="fill:#24af63"
+         inkscape:connector-curvature="0"
+         id="path30"
+         d="m 1050.5,250.65 c 2.5,-1 4.9,-2.3 7.3,-3.6 2.8,-1.7 5.4,-3.5 8,-5.4 2.2,-1.6 4.3,-3.3 6.4,-5.1 l 3.6,-3 c 0.2,-0.2 0.2,-0.1 0.3,0.1 0.4,1.6 0.7,3.3 1.1,5 0.5,2.3 0.8,4.6 1.1,6.9 0.3,2.7 0.4,5.3 0.2,8 -0.2,3.3 -0.8,6.6 -2,9.7 -0.7,1.9 -1.6,3.7 -2.7,5.4 -1.4,2.2 -3,4.2 -5,5.9 -2.3,2.1 -4.9,3.9 -7.7,5.4 -3.7,2.1 -7.7,3.6 -11.8,4.8 -3.9,1.2 -7.9,2 -11.9,2.7 -1.1,0.2 -2.2,0.4 -3.3,0.4 -2.3,-0.1 -4.6,-0.6 -6.8,-1.4 -3.3,-1.3 -6.2,-3.3 -9.5,-4.8 -1.8,-0.8 -3.6,-1.4 -5.5,-1.5 -2.5,-0.2 -4.6,0.7 -6.4,2.4 l -3.9,3.9 c -2.2,2.2 -4.8,3.7 -7.9,4.2 -2.1,0.3 -4.1,0.2 -6.2,-0.1 -2.9,-0.4 -5.7,-1.1 -8.4,-1.9 -4,-1.3 -7.7,-3.1 -11.1,-5.7 -3.2,-2.4 -5.7,-5.4 -7.8,-8.8 -2.1,-3.5 -3.3,-7.2 -4.2,-11.1 -0.4,-1.7 -0.6,-3.5 -0.8,-5.2 -0.3,-2.5 -0.4,-4.9 -0.3,-7.4 0.1,-3.5 0.4,-6.9 0.9,-10.4 0.4,0.4 0.8,0.7 1.1,1 2.2,2 4.7,3.8 7.3,5.4 2.9,1.7 6.1,3.1 9.4,4 2.2,0.6 4.5,1 6.8,1.1 1.9,0.2 3.8,0.2 5.7,0.1 2.2,-0.1 4.5,-0.3 6.7,-0.9 0.3,0 0.6,0 0.8,-0.1 2,-0.4 4,-0.9 6,-1.5 2.3,-0.7 4.5,-1.4 6.7,-2.2 2.1,-0.8 4.3,-1.7 6.4,-2.6 0.6,-0.3 1,-0.2 1.5,0.2 3.5,2.7 7.3,5 11.4,6.7 4.6,1.8 9.3,2.7 14.2,2.3 3.6,-0.7 7,-1.6 10.3,-2.9 z"
+         class="st0" /><path
+         style="fill:#ecdc86"
+         inkscape:connector-curvature="0"
+         id="path32"
+         d="m 1050.5,250.65 c -3.3,1.3 -6.7,2.2 -10.2,2.5 -4.9,0.4 -9.6,-0.5 -14.2,-2.3 -4.1,-1.6 -7.9,-3.9 -11.4,-6.7 -0.5,-0.4 -0.9,-0.5 -1.5,-0.2 -2.1,0.9 -4.2,1.8 -6.4,2.6 -2.2,0.8 -4.4,1.6 -6.7,2.2 -2,0.6 -4,1 -6,1.5 -0.3,0.1 -0.6,0.1 -0.8,0.1 0.7,-0.8 1.4,-1.6 2.1,-2.4 2.8,-3.2 4.8,-6.9 5.9,-11.1 1.6,-5.6 3.2,-11.3 4.6,-17 1,-4.2 1.8,-8.4 2.4,-12.7 0.4,-3.1 1,-14.9 0.8,-17.7 -0.5,-8.6 -2.4,-16.8 -5.9,-24.7 -2.1,-4.7 -5.7,-7.9 -10.7,-9.2 -2.2,-0.6 -4.4,-0.4 -6.5,0.3 -0.2,0.1 -0.3,0.2 -0.5,0.1 3.3,-2.8 6.7,-5.4 11.1,-6.4 3.5,-0.8 6.8,-0.2 9.8,1.7 3,1.9 5.3,4.4 7.4,7.2 2.7,3.7 4.9,7.7 6.9,11.8 0.4,0.9 0.4,0.9 1.1,0.2 3.7,-3.8 7.7,-7.3 12.1,-10.2 4.4,-3 9.2,-5.3 14.5,-6.4 4.1,-0.8 8.2,-0.7 12.3,0.2 1.9,0.4 3.7,1 5.5,1.8 0.1,0.1 0.3,0.1 0.3,0.2 -5.3,0.1 -9.8,2.1 -13.9,5.2 -2,1.5 -3.8,3.2 -5.2,5.3 -1.1,1.7 -2.1,3.6 -2.9,5.5 -1.8,3.8 -3.3,7.8 -4.4,11.9 -0.9,3.5 -1.5,7.1 -1.8,10.7 -0.2,2.8 -0.3,5.6 -0.2,8.4 0.1,3.4 0.5,6.8 0.9,10.3 0.7,5.7 1.7,11.4 2.7,17.1 0.5,3.1 0.9,6.3 1.5,9.5 0.7,4.6 3.3,8 7,10.6 0,-0.1 0.2,0 0.3,0.1 z"
+         class="st4" /><path
+         style="fill:#3f2b29"
+         inkscape:connector-curvature="0"
+         id="path34"
+         d="m 1043.1,62.35 4.5,0 c 3.6,0.2 7.2,0.8 10.6,2 2.7,0.9 3.3,2.7 1.7,5 -1.1,1.6 -2.7,2.8 -4.4,3.9 -2.1,1.4 -4.4,2.6 -6.9,3.5 -2.5,1 -4.9,0 -6.5,-2.5 -0.5,-0.8 -0.9,-1.6 -1.1,-2.5 -0.1,-0.3 -0.2,-0.4 -0.5,-0.4 -5.6,-1 -10.6,0.3 -14.7,4.3 -3.4,3.2 -5.4,7.3 -6.8,11.7 -1.3,4 -1.9,8 -2.1,12.2 -0.2,3.7 0.1,7.4 0.6,11 0.1,0.6 0.3,1.2 0.3,1.9 0.1,0.8 -0.2,1.5 -0.8,1.9 -0.7,0.5 -1.5,0.4 -2.3,0.4 -1.9,-0.6 -3.8,-1.2 -5.7,-1.7 l 0,-1.3 c 0,-2 0,-3.9 0.1,-5.9 0.4,-7.7 1.6,-15.3 4.6,-22.5 2.2,-5.4 5.4,-10.1 9.9,-13.8 3.7,-3.1 7.9,-5.1 12.6,-6.2 2.4,-0.6 4.6,-0.9 6.9,-1 z"
+         class="st6" /><path
+         style="fill:#396e35"
+         inkscape:connector-curvature="0"
+         id="path36"
+         d="m 1014.8,114.65 c 0.8,0 1.6,0.1 2.3,-0.4 0.7,-0.5 0.9,-1.2 0.8,-1.9 -0.1,-0.6 -0.2,-1.3 -0.3,-1.9 0.4,0 0.7,-0.1 1.1,-0.1 1.4,0.8 2.9,1.5 4.4,2.3 3.4,2.1 5.5,5.1 6.9,8.8 0.2,0.6 0.4,1.1 0.6,1.7 -0.8,-0.7 -1.6,-1.4 -2.4,-2 -3.2,-2.4 -6.7,-4.1 -10.4,-5.5 -1.1,-0.3 -2,-0.6 -3,-1 z"
+         class="st7" /><path
+         style="fill:#396e35"
+         inkscape:connector-curvature="0"
+         id="path38"
+         d="m 1009.1,111.65 0,1.3 c -1.3,-0.4 -2.6,-0.7 -3.9,-1.2 1.4,-0.1 2.7,-0.1 3.9,-0.1 z"
+         class="st7" /></g></g><g
+     inkscape:groupmode="layer"
+     id="layer3"
+     inkscape:label="Text"
+     style="display:inline"
+     transform="translate(5.3761467,0)"><text
+       x="48.898899"
+       y="241.24541"
+       font-size="209.87px"
+       font-weight="bold"
+       id="text53"
+       style="font-weight:bold;font-size:209.86999512px;font-family:'Maven Pro'"><tspan
+         class="st0 st1 st2"
+         x="48.898899"
+         y="241.24541"
+         font-size="209.87px"
+         font-weight="bold"
+         id="tspan55"
+         style="font-weight:bold;font-size:209.86720276px;font-family:'Maven Pro';fill:#24af63">nf-<tspan
+   id="tspan57"
+   style="fill:#000000" /></tspan></text>
+<text
+       x="357.14139"
+       y="241.24541"
+       font-size="209.87px"
+       font-weight="bold"
+       id="text69"
+       style="font-weight:bold;font-size:209.86999512px;font-family:'Maven Pro'"><tspan
+         class="st0 st1 st2"
+         x="357.14139"
+         y="241.24541"
+         font-size="209.87px"
+         font-weight="bold"
+         id="tspan71"
+         style="font-weight:bold;font-size:209.86720276px;font-family:'Maven Pro';fill:#24af63"><tspan
+           id="tspan73"
+           style="fill:#000000">core/</tspan></tspan></text>
+<text
+       x="-260.05042"
+       y="457.04541"
+       font-weight="bold"
+       id="text59"
+       style="font-weight:bold;font-family:'Maven Pro'"><tspan
+         class="st1 st2"
+         x="47.849564"
+         y="457.04541"
+         font-size="209.87px"
+         font-weight="bold"
+         id="tspan61"
+         style="font-weight:bold;font-size:209.86720276px;font-family:'Maven Pro'">hic</tspan></text>
+<path
+       d="m 300.43725,166.1155 -21.53224,21.61638 61.0915,0 0,-21.61638 -39.55926,0 z"
+       id="path67"
+       inkscape:connector-curvature="0"
+       style="fill:url(#f)" /></g></svg>
\ No newline at end of file

docs/usage.md

@@ -51,6 +51,11 @@
     * [`--splitFastq`](#--splitFastq)
     * [`--saveReference`](#--saveReference)
     * [`--saveAlignedIntermediates`](#--saveAlignedIntermediates)
+* [Skip options](#skip-options)
+  * [--skip_maps](#--skip_maps)
+  * [--skip_ice](#--skip_ice)
+  * [--skip_cool](#--skip_cool)
+  * [--skip_multiqc](#--skip_multiqc)  
 * [Job resources](#job-resources)
 * [Automatic resubmission](#automatic-resubmission)
 * [Custom resource requests](#custom-resource-requests)
@@ -457,6 +462,40 @@ If specified, all intermediate mapping files are saved and exported in the resul
 --saveReference
 ```
 
+## Skip options
+
+#### `--skip_maps`
+
+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
+```
+
+#### `--skip_ice`
+
+If defined, the ICE normalization is not run on the raw contact maps. Default: false
+
+```bash
+--skip_ice
+```
+
+#### `--skip_cool`
+
+If defined, cooler files are not generated. Default: false
+
+```bash
+--skip_cool
+```
+
+#### `--skip_multiqc`
+
+If defined, the MultiQC report is not generated. Default: false
+
+```bash
+--skip_multiqc
+```
+
 ## Job resources
 ### Automatic resubmission
 Each step in the pipeline has a default set of requirements for number of CPUs, memory and time. For most of the steps in the pipeline, if the job exits with an error code of `143` (exceeded requested resources) it will automatically resubmit with higher requests (2 x original, then 3 x original). If it still fails after three times then the pipeline is stopped.

main.nf

@@ -67,7 +67,7 @@ def helpMessage() {
     Step options:
       --skip_maps                           Skip generation of contact maps. Useful for capture-C
       --skip_ice			    Skip ICE normalization
-      --skip_cool			    Skip generation of cool files
+      --skip_cool			    Skip generation of cooler files
       --skip_multiQC			    Skip MultiQC
 
     AWSBatch options:
@@ -666,12 +666,17 @@ process remove_duplicates {
    if ( params.rm_dup ){
    """
    mkdir -p stats/${sample}
+
+   ## Sort valid pairs and remove read pairs with same starts (i.e duplicated read pairs)
    sort -T /tmp/ -S 50% -k2,2V -k3,3n -k5,5V -k6,6n -m ${vpairs} | \
    awk -F"\\t" 'BEGIN{c1=0;c2=0;s1=0;s2=0}(c1!=\$2 || c2!=\$5 || s1!=\$3 || s2!=\$6){print;c1=\$2;c2=\$5;s1=\$3;s2=\$6}' > ${sample}.allValidPairs
+
    echo -n "valid_interaction\t" > stats/${sample}/${sample}_allValidPairs.mergestat
    cat ${vpairs} | wc -l >> stats/${sample}/${sample}_allValidPairs.mergestat
    echo -n "valid_interaction_rmdup\t" >> stats/${sample}/${sample}_allValidPairs.mergestat
    cat ${sample}.allValidPairs | wc -l >> stats/${sample}/${sample}_allValidPairs.mergestat
+
+   ## Count short range (<20000) vs long range contacts
    awk 'BEGIN{cis=0;trans=0;sr=0;lr=0} \$2 == \$5{cis=cis+1; d=\$6>\$3?\$6-\$3:\$3-\$6; if (d<=20000){sr=sr+1}else{lr=lr+1}} \$2!=\$5{trans=trans+1}END{print "trans_interaction\\t"trans"\\ncis_interaction\\t"cis"\\ncis_shortRange\\t"sr"\\ncis_longRange\\t"lr}' ${sample}.allValidPairs >> stats/${sample}/${sample}_allValidPairs.mergestat
 
    """
@@ -683,6 +688,8 @@ process remove_duplicates {
    cat ${vpairs} | wc -l >> stats/${sample}/${sample}_allValidPairs.mergestat
    echo -n "valid_interaction_rmdup\t" >> stats/${sample}/${sample}_allValidPairs.mergestat
    cat ${sample}.allValidPairs | wc -l >> stats/${sample}/${sample}_allValidPairs.mergestat
+
+   ## Count short range (<20000) vs long range contacts 
    awk 'BEGIN{cis=0;trans=0;sr=0;lr=0} \$2 == \$5{cis=cis+1; d=\$6>\$3?\$6-\$3:\$3-\$6; if (d<=20000){sr=sr+1}else{lr=lr+1}} \$2!=\$5{trans=trans+1}END{print "trans_interaction\\t"trans"\\ncis_interaction\\t"cis"\\ncis_shortRange\\t"sr"\\ncis_longRange\\t"lr}' ${sample}.allValidPairs >> stats/${sample}/${sample}_allValidPairs.mergestat
    """
    }