millironx/nf-core_modules
1
0
Fork 0
mirror of https://github.com/MillironX/nf-core_modules.git synced 2024-09-21 07:42:05 +00:00
Code Issues Releases Packages Activity

Completed slop module for modules with test directory and updated meta.yml file

Browse source
This commit is contained in:
Sruthi Suresh 2020-11-11 16:45:44 -06:00 committed by sruthipsuresh
parent 5205ce286a
commit 709970e9af
31 changed files with 509 additions and 10676 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

470
nextflow Executable file
View file

@ -0,0 +1,470 @@
#!/usr/bin/env bash
#
# Copyright 2020, Seqera Labs
# Copyright 2013-2019, Centre for Genomic Regulation (CRG)
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
[[ "$NXF_DEBUG" == 'x' ]] && set -x
NXF_VER=${NXF_VER:-'20.10.0'}
NXF_ORG=${NXF_ORG:-'nextflow-io'}
NXF_HOME=${NXF_HOME:-$HOME/.nextflow}
NXF_PROT=${NXF_PROT:-'https'}
NXF_BASE=${NXF_BASE:-$NXF_PROT://www.nextflow.io/releases}
NXF_TEMP=${NXF_TEMP:-$TMPDIR}
NXF_DIST=${NXF_DIST:-$NXF_HOME/framework}
NXF_CLI="$0 $@"
export NXF_CLI
export NXF_ORG
export NXF_HOME
if [[ $TERM && $TERM != 'dumb' ]]; then
if command -v tput &>/dev/null; then
GREEN=$(tput setaf 2; tput bold)
YELLOW=$(tput setaf 3)
RED=$(tput setaf 1)
NORMAL=$(tput sgr0)
fi
fi
function echo_red() {
>&2 echo -e "$RED$*$NORMAL"
}
function echo_green() {
echo -e "$GREEN$*$NORMAL"
}
function echo_yellow() {
>&2 echo -e "$YELLOW$*$NORMAL"
}
function die() {
echo_red "$*"
exit 1
}
function get_abs_filename() {
echo "$(cd "$(dirname "$1")" && pwd)/$(basename "$1")"
}
function get() {
if command -v curl &>/dev/null; then
GET="curl -fsSL '$1' -o '$2'"
elif command -v wget &>/dev/null; then
GET="wget -q '$1' -O '$2'"
else
echo_red "ERROR: Cannot find 'curl' nor 'wget' utility -- please install one of them"
exit 1
fi
printf "Downloading nextflow dependencies. It may require a few seconds, please wait .. "
eval $GET; status=$?
printf "\r\033[K"
if [ $status -ne 0 ]; then
echo_red "ERROR: Cannot download nextflow required file -- make sure you can connect to the internet"
echo ""
echo "Alternatively you can try to download this file:"
echo " $1"
echo ""
echo "and save it as:"
echo " ${3:-$2}"
echo ""
exit 1
fi
}
function make_temp() {
local base=${NXF_TEMP:=$PWD}
if [ "$(uname)" = 'Darwin' ]; then mktemp "${base}/nxf-tmp.XXXXXX" || exit $?
else mktemp -t nxf-tmp.XXXXXX -p "${base}" || exit $?
fi
}
function resolve_link() {
[[ ! -f $1 ]] && exit 1
if command -v realpath &>/dev/null; then
realpath "$1"
elif command -v readlink &>/dev/null; then
local target="$1"
cd $(dirname $target); target=$(basename $target)
while [ -L "$target" ]; do
target="$(readlink "$target")"
cd $(dirname $target); target=$(basename $target)
done
echo "$(cd "$(dirname "$target")"; pwd -P)/$target"
else
echo_yellow "WARN: Neither \`realpath\` nor \`readlink\` command can be found"
exit 1
fi
}
function current_ver() {
[[ $NXF_EDGE == 1 ]] && printf 'edge' || printf 'latest'
}
function install() {
local tmpfile=$(make_temp)
local version=$(set +u; [[ $NXF_VER ]] && printf "v$NXF_VER" || current_ver)
local action="a=${2:-default}"
get "$NXF_BASE/$version/nextflow?$action" "$tmpfile" "$1" || exit $?
mv "$tmpfile" "$1" || exit $?
chmod +x "$1" || exit $?
bash "$1" -download || exit $?
echo ''
echo -e $'Nextflow installation completed. Please note:'
echo -e $'- the executable file `nextflow` has been created in the folder:' $(dirname $1)
if [[ ! "$PATH" =~ (^|:)"$(dirname $1)"(:|$) ]]; then
echo -e $'- you may complete the installation by moving it to a directory in your $PATH'
fi
echo ''
}
function launch_nextflow() {
# the launch command line
local cmdline=()
# remove leading and trailing double-quotes
for x in "${launcher[@]}"; do
x="${x%\"}"
x="${x#\"}"
cmdline+=("$x")
done
if [[ $NXF_MPIRUN ]]; then
local rank=''
[[ $SLURM_PROCID ]] && rank=$SLURM_PROCID
[[ $OMPI_COMM_WORLD_RANK ]] && rank=$OMPI_COMM_WORLD_RANK
if [[ ! $rank ]]; then
echo_red 'It looks you are not running in a MPI enabled environment -- cannot find `$OMPI_COMM_WORLD_RANK` nor `$SLURM_PROCID` variable';
exit 1;
fi
if [[ $SLURM_CPUS_PER_TASK && $SLURM_MEM_PER_CPU ]]; then
export NXF_CLUSTER_MAXCPUS=$SLURM_CPUS_PER_TASK
export NXF_CLUSTER_MAXMEMORY="$(($SLURM_MEM_PER_CPU*$SLURM_CPUS_PER_TASK))MB"
fi
if [[ $rank == 0 ]]; then
# sleep a few seconds in order to wait worker daemons to bootstrap
sleep ${NXF_SLEEP:-10}
export NXF_EXECUTOR='ignite'
export NXF_CLUSTER_SHUTDOWNONCOMPLETE='true'
else
args=(-log .nextflow_node_${rank}.log node ignite)
fi
# start in daemon mode
elif [[ "$bg" ]]; then
local pid_file="${NXF_PID_FILE:-.nextflow.pid}"
cmdline+=("${args[@]}")
exec "${cmdline[@]}" &
disown
echo $! > "$pid_file"
exit 0
fi
cmdline+=("${args[@]}")
exec "${cmdline[@]}"
exit 1
}
# check self-install
if [ "$0" = "bash" ] || [ "$0" = "/bin/bash" ]; then
if [ -d nextflow ]; then
echo 'Please note:'
echo "- The install procedure needs to create a file named 'nextflow' in this folder, but a directory with this name already exists."
echo "- Please renamed/delete that directory, or execute the Nextflow install procedure in another folder."
echo ''
exit 1
fi
install "$PWD/nextflow" install
exit 0
fi
# parse the command line
bg=''
dockerize=''
declare -a jvmopts=()
declare -a args=("$@")
declare -a commands=(clone config drop help history info ls pull run view node console kuberun)
cmd=''
while [[ $# != 0 ]]; do
case $1 in
-D*)
if [[ ! "$cmd" ]]; then
jvmopts+=("$1")
fi
;;
-d|-dockerize)
if [[ ! "$cmd" && ! -f /.nextflow/dockerized ]]; then
dockerize=1
fi
;;
-bg)
if [[ ! -f /.nextflow/dockerized ]]; then
bg=1
fi
;;
-download)
if [[ ! "$cmd" ]]; then
rm -rf "$NXF_DIST/$NXF_VER" || exit $?
bash "$0" -version || exit $?
exit 0
fi
;;
-self-update|self-update)
if [[ ! "$cmd" ]]; then
[[ -z $NXF_EDGE && $NXF_VER = *-edge ]] && NXF_EDGE=1
unset NXF_VER
install "$0" update
exit 0
fi
;;
-process.executor|-executor.name)
if [[ $2 && $2 == 'ignite' ]]; then
[ ! $NXF_MODE ] && NXF_MODE='ignite'; shift;
fi
;;
-with-mpi)
[ ! $NXF_MODE ] && NXF_MODE='ignite'
NXF_MPIRUN='true'
;;
*)
[[ $1 && $1 != -* && ! "$cmd" && ${commands[*]} =~ $1 ]] && cmd=$1
;;
esac
shift
done
NXF_DOCKER_OPTS=${NXF_DOCKER_OPTS:=''}
if [[ "$dockerize" ]]; then
if [[ "$bg" ]]; then detach='--detach '; else detach=''; fi
NXF_ASSETS=${NXF_ASSETS:-${NXF_HOME:-$HOME/.nextflow}/assets}
mkdir -p "$NXF_ASSETS"
exec docker run $detach --rm --net host \
-e NXF_ANSI_LOG=false \
-e USER -e HOME -e NXF_ASSETS=$NXF_ASSETS -e NXF_USRMAP=$(id -u) -e NXF_DOCKER_OPTS='-u $(id -u)' \
-v /var/run/docker.sock:/var/run/docker.sock \
-v $HOME:$HOME:ro,Z -v $NXF_ASSETS:$NXF_ASSETS:Z -v $PWD:$PWD:Z -w $PWD $NXF_DOCKER_OPTS \
nextflow/nextflow:$NXF_VER nextflow "${args[@]}"
exit 1
fi
CAPSULE_LOG=${CAPSULE_LOG:=''}
CAPSULE_RESET=${CAPSULE_RESET:=''}
CAPSULE_CACHE_DIR=${CAPSULE_CACHE_DIR:="$NXF_HOME/capsule"}
NXF_PACK=one
NXF_MODE=${NXF_MODE:-''}
NXF_JAR=${NXF_JAR:-nextflow-$NXF_VER-$NXF_PACK.jar}
NXF_BIN=${NXF_BIN:-$NXF_DIST/$NXF_VER/$NXF_JAR}
NXF_PATH=$(dirname "$NXF_BIN")
NXF_URL=${NXF_URL:-$NXF_BASE/v$NXF_VER/$NXF_JAR}
NXF_GRAB=${NXF_GRAB:-''}
NXF_CLASSPATH=${NXF_CLASSPATH:-''}
NXF_MPIRUN=${NXF_MPIRUN:=''}
NXF_HOST=${HOSTNAME:-localhost}
[[ $NXF_LAUNCHER ]] || NXF_LAUNCHER=${NXF_HOME}/tmp/launcher/nextflow-${NXF_PACK}_${NXF_VER}/${NXF_HOST}
[ ! $NXF_MODE ] && [[ $NXF_CLOUD_DRIVER == google ]] && NXF_MODE='google'
[ ! $NXF_MODE ] && [[ $GOOGLE_APPLICATION_CREDENTIALS ]] && NXF_MODE='google'
if [[ $NXF_MODE == ignite ]]; then
# Fix JDK bug when there's a limit on the OS virtual memory
# https://bugs.openjdk.java.net/browse/JDK-8044054
# https://issues.apache.org/jira/browse/HADOOP-7154
export MALLOC_ARENA_MAX=4
fi
# Determine the path to this file
if [[ $NXF_PACK = all ]]; then
NXF_BIN=$(which "$0" 2>/dev/null)
[ $? -gt 0 -a -f "$0" ] && NXF_BIN="./$0"
fi
# use nextflow custom java home path
if [[ "$NXF_JAVA_HOME" ]]; then
JAVA_HOME="$NXF_JAVA_HOME"
unset JAVA_CMD
fi
# Determine the Java command to use to start the JVM.
if [ ! -x "$JAVA_CMD" ] ; then
if [ -d "$JAVA_HOME" ] ; then
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
# IBM's JDK on AIX uses strange locations for the executables
JAVA_CMD="$JAVA_HOME/jre/sh/java"
else
JAVA_CMD="$JAVA_HOME/bin/java"
fi
elif [ -x /usr/libexec/java_home ]; then
JAVA_CMD="$(/usr/libexec/java_home -v 1.8+)/bin/java"
else
JAVA_CMD="$(which java)" || JAVA_CMD=java
fi
fi
# Retrieve the java version from a NF local file
JAVA_KEY="$NXF_HOME/tmp/ver/$(resolve_link "$JAVA_CMD" | sed 's@/@.@g')"
if [ -f "$JAVA_KEY" ]; then
JAVA_VER="$(cat "$JAVA_KEY")"
else
JAVA_VER="$("$JAVA_CMD" $NXF_OPTS -version 2>&1)"
if [ $? -ne 0 ]; then
echo_red "${JAVA_VER:-Failed to launch the Java virtual machine}"
echo_yellow "NOTE: Nextflow is trying to use the Java VM defined by the following environment variables:\n JAVA_CMD: $JAVA_CMD\n NXF_OPTS: $NXF_OPTS\n"
exit 1
fi
JAVA_VER=$(echo "$JAVA_VER" | awk '/version/ {gsub(/"/, "", $3); print $3}')
# check NF version
if [[ ! $NXF_VER =~ ([0-9]+)\.([0-9]+)\.([0-9].*) ]]; then
echo_red "Not a valid Nextflow version: $NXF_VER"
exit 1
fi
major=${BASH_REMATCH[1]}
minor=${BASH_REMATCH[2]}
# legacy version - Java 7/8 only
if [ $major -eq 0 ] && [ $minor -lt 26 ]; then
version_check="^(1.7|1.8)"
version_message="Java 7 or 8"
else
version_check="^(1.8|9|10|11|12|13|14|15)"
version_message="Java 8 or later"
fi
if [[ ! $JAVA_VER =~ $version_check ]]; then
echo_red "ERROR: Cannot find Java or it's a wrong version -- please make sure that $version_message is installed"
if [[ "$NXF_JAVA_HOME" ]]; then
echo_yellow "NOTE: Nextflow is trying to use the Java VM defined by the following environment variables:\n JAVA_CMD: $JAVA_CMD\n NXF_JAVA_HOME: $NXF_JAVA_HOME\n"
else
echo_yellow "NOTE: Nextflow is trying to use the Java VM defined by the following environment variables:\n JAVA_CMD: $JAVA_CMD\n JAVA_HOME: $JAVA_HOME\n"
fi
exit 1
fi
if [[ ! $JAVA_VER =~ ^(1.8|9|10|11|12|13|14|15) ]]; then
echo_yellow "NOTE: Nextflow is not tested with Java $JAVA_VER -- It's recommended the use of version 8 up to 15\n"
elif [[ ! $JAVA_VER =~ ^(1.8|9|10|11) && $NXF_MODE == ignite ]]; then
echo_yellow "WARN: Apache Ignite executor is not tested with Java $JAVA_VER -- It's recommended the use of version 8 up to 11\n"
fi
mkdir -p $(dirname "$JAVA_KEY")
[[ -f $JAVA_VER ]] && echo $JAVA_VER > "$JAVA_KEY"
fi
# Verify nextflow jar is available
if [ ! -f "$NXF_BIN" ]; then
[ -f "$NXF_PATH" ] && rm "$NXF_PATH"
mkdir -p "$NXF_PATH" || exit $?
tmpfile=$(make_temp)
get "$NXF_URL" "$tmpfile" "$NXF_BIN"
mv "$tmpfile" "$NXF_BIN"
fi
[[ "$cmd" == "console" ]] && NXF_MODE='console'
[[ "$cmd" == "node" && ! "$NXF_MODE" ]] && NXF_MODE='ignite'
COLUMNS=${COLUMNS:-`tty -s && tput cols 2>/dev/null || true`}
declare -a JAVA_OPTS=()
JAVA_OPTS+=(-Dfile.encoding=UTF-8 -Dcapsule.trampoline -Dcapsule.java.cmd="$JAVA_CMD")
if [[ $cmd == console ]]; then bg=1;
else JAVA_OPTS+=(-Djava.awt.headless=true)
fi
[[ "$NXF_MODE" ]] && JAVA_OPTS+=(-Dcapsule.mode=$NXF_MODE)
[[ "$JAVA_HOME" ]] && JAVA_OPTS+=(-Dcapsule.java.home="$JAVA_HOME")
[[ "$CAPSULE_LOG" ]] && JAVA_OPTS+=(-Dcapsule.log=$CAPSULE_LOG)
[[ "$CAPSULE_RESET" ]] && JAVA_OPTS+=(-Dcapsule.reset=true)
[[ "$cmd" != "run" && "$cmd" != "node" ]] && JAVA_OPTS+=(-XX:+TieredCompilation -XX:TieredStopAtLevel=1)
[[ "$NXF_OPTS" ]] && JAVA_OPTS+=($NXF_OPTS)
[[ "$NXF_CLASSPATH" ]] && export NXF_CLASSPATH
[[ "$NXF_GRAB" ]] && export NXF_GRAB
[[ "$COLUMNS" ]] && export COLUMNS
[[ "$NXF_TEMP" ]] && JAVA_OPTS+=(-Djava.io.tmpdir="$NXF_TEMP")
[[ "${jvmopts[@]}" ]] && JAVA_OPTS+=("${jvmopts[@]}")
# use drip to speedup startup time -- https://github.com/ninjudd/drip
[[ "$NXF_DRIP" ]] && export DRIP_INIT='' && export DRIP_INIT_CLASS='nextflow.cli.DripMain'
export JAVA_CMD
export CAPSULE_CACHE_DIR
# lookup the a `md5` command
if hash md5sum 2>/dev/null; then MD5=md5sum;
elif hash gmd5sum 2>/dev/null; then MD5=gmd5sum;
elif hash md5 2>/dev/null; then MD5=md5;
else MD5=''
fi
# when no md5 command is available fallback on default execution
if [ ! "$MD5" ] || [ "$CAPSULE_RESET" ]; then
launcher=($("$JAVA_CMD" "${JAVA_OPTS[@]}" -jar "$NXF_BIN"))
launch_nextflow
exit 1
fi
# creates a md5 unique for the given variables
env_md5() {
cat <<EOF | $MD5 | cut -f1 -d' '
$JAVA_CMD
$JAVA_VER
${JAVA_OPTS[@]}
$NXF_HOME
$NXF_VER
$NXF_OPTS
$NXF_GRAB
$NXF_CLASSPATH
$NXF_DRIP
EOF
}
# checked if a cached classpath file exists and it newer that the nextflow boot jar file
if [[ -f /.nextflow/dockerized ]]; then
LAUNCH_FILE=/.nextflow/launch-classpath
else
LAUNCH_FILE="${NXF_LAUNCHER}/classpath-$(env_md5)"
fi
if [ -s "$LAUNCH_FILE" ] && [ "$LAUNCH_FILE" -nt "$NXF_BIN" ]; then
launcher=($(cat "$LAUNCH_FILE"))
else
# otherwise run the capsule and get the result classpath in the 'launcher' and save it to a file
cli=($("$JAVA_CMD" "${JAVA_OPTS[@]}" -jar "$NXF_BIN"))
[[ $? -ne 0 ]] && echo_red 'Unable to initialize nextflow environment' && exit 1
if [[ "$JAVA_VER" =~ ^(9|10|11|12|13|14|15) ]]; then
launcher=("${cli[@]:0:1}")
launcher+=(--add-opens=java.base/java.lang=ALL-UNNAMED)
launcher+=(--add-opens=java.base/java.io=ALL-UNNAMED)
launcher+=(--add-opens=java.base/java.nio=ALL-UNNAMED)
launcher+=(--add-opens=java.base/java.util=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.nio.ch=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.nio.fs=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.net.www.protocol.http=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.net.www.protocol.https=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.net.www.protocol.ftp=ALL-UNNAMED)
launcher+=(--add-opens=java.base/sun.net.www.protocol.file=ALL-UNNAMED)
launcher+=(--add-opens=java.base/jdk.internal.misc=ALL-UNNAMED)
launcher+=(--illegal-access=deny)
launcher+=("${cli[@]:1}")
else
launcher=("${cli[@]}")
fi
# Don't show errors if the LAUNCH_FILE can't be created
if mkdir -p "${NXF_LAUNCHER}" 2>/dev/null; then
STR=''
for x in "${launcher[@]}"; do
[[ "$x" != "\"-Duser.dir=$PWD\"" ]] && STR+="$x "
done
printf "$STR">"$LAUNCH_FILE"
else
echo_yellow "Warning: Couldn't create cached classpath folder: $NXF_LAUNCHER -- Maybe NXF_HOME is not writable?"
fi
fi
# finally run it
launch_nextflow

59
software/bedtools/ernas/functions.nf
View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

36
software/bedtools/ernas/main.nf
View file

@ -1,36 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process BEDTOOLS_ERNAS {
tag "$meta.id"
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
input:
tuple val(meta), path(nogenesbed)
path "H3K27ac"
path "H3K4me1"
output:
tuple val(meta), path("*.erna.bed"), emit: ernabed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
bedtools intersect -a $nogenesbed -b $nogenesbed $H3K27ac $H3K4me1 -sorted -u -bed > ${prefix}.erna.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

55
software/bedtools/ernas/meta.yml
View file

@ -1,55 +0,0 @@
name: bedtools_ernas
description: Takes in units with genes removed
Keeps anything that intersects with H3K27ac or H3K4me1
keywords:
- bed
- bedtoolsintersect
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

59
software/bedtools/histonestobed/functions.nf
View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

35
software/bedtools/histonestobed/main.nf
View file

@ -1,35 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process BEDTOOLS_HISTONESTOBED {
tag "$meta.id"
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
// In the case of use for cell lines, the second input can also be replaced with the tuple (val) format.
input:
tuple val(meta), path(bams)
output:
tuple val(meta), path("*.bed"), emit: bed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
bamToBed -i ${bams[0]} | sortBed -i > ${prefix}.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

53
software/bedtools/histonestobed/meta.yml
View file

@ -1,53 +0,0 @@
name: bedtools_histonestoned
description: Coverts Histone Bam files to BED format
keywords:
- bed
- bedtoolsintersect
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

59
software/bedtools/removegenes/functions.nf
View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

38
software/bedtools/removegenes/main.nf
View file

@ -1,38 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process BEDTOOLS_REMOVEGENES {
tag "$meta.id"
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
input:
tuple val(meta), path(slopbed)
path metatranscript
output:
tuple val(meta), path("*.nogenes.bed"), emit: nogenesbed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
// sorted via chromosome, then by start position
"""
bedtools intersect -a $metatranscript -b $slopbed -v \\
| sortBed > ${prefix}.nogenes.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

53
software/bedtools/removegenes/meta.yml
View file

@ -1,53 +0,0 @@
name: bedtools_removegenes
description: Removes the intergenic regions from GRO-Seq Transcripts
keywords:
- bed
- bedtoolsintersect
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

5
software/bedtools/slop/main.nf
View file

@ -1,9 +1,6 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [upstream: 1,
downstream: 10 ]
def options = initOptions(params.options)
process BEDTOOLS_SLOP {
@ -33,7 +30,7 @@ process BEDTOOLS_SLOP {
def beds_files = beds.sort()
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
slopBed -i ${beds[0]} -g $sizes -l ${params.upstream} -r ${params.downstream} > ${prefix}.slop.bed
slopBed -i ${beds[0]} -g $sizes -l ${params.l} -r ${params.r} > ${prefix}.slop.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

16
software/bedtools/slop/meta.yml
View file

@ -1,10 +1,8 @@
name: bedtools_slop
description: Adds 1 KB to the front of the genes and 10 KB to the end of the sequence.
description: Adds a specified number of bases in each direction (unique values may be specified for either -l or -r)
keywords:
- bed
- slopBed
- downstream
- upstream
tools:
- bedtools:
description: |
@ -12,6 +10,14 @@ tools:
documentation: https://bedtools.readthedocs.io/en/latest/
params:
- l:
type: integer
description:
The number of base pairs to subtract from the start coordinate
- r:
type: integer
description:
The number of base pairs to add to the end coordinate
- outdir:
type: string
description: |
@ -27,6 +33,7 @@ params:
description: |
Run the module with Conda using the software specified
via the `conda` directive
input:
- meta:
type: map
@ -46,7 +53,8 @@ output:
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
pattern: "*.{slopbed}"
- version:
type: file
description: File containing software version

0
software/bedtools/test/input/A.bed → software/bedtools/slop/test/input/A.bed
View file

0
software/bedtools/test/input/genome.sizes → software/bedtools/slop/test/input/genome.sizes
View file

25
software/bedtools/slop/test/main.nf Normal file
View file

@ -0,0 +1,25 @@
#!/usr/bin/env nextflow
nextflow.preview.dsl = 2
// Test -l, -r provided.
include { BEDTOOLS_SLOP } from '../main.nf' addParams( options: [publish_dir:'test_bed_file'] )
// Define input channels
// Run the workflow
workflow test_bed_file {
def input = []
input = [ [ id:'test', l:1, r:10 ],
[ file("${baseDir}/input/A.bed", checkIfExists: true),] ]
BEDTOOLS_SLOP(
input,
file("${baseDir}/input/genome.sizes", checkIfExists: true)
)
}
workflow {
test_bed_file()
}

0
software/bedtools/test/nextflow.config → software/bedtools/slop/test/nextflow.config
View file

1
software/bedtools/test/input/B.bed
View file

@ -1 +0,0 @@
chr1 999 1010

1
software/bedtools/test/input/B.metatranscripts
View file

@ -1 +0,0 @@
chr1 999 1010

5
software/bedtools/test/input/H3K27ac.bed
View file

@ -1,5 +0,0 @@
chr1 951 1061
chr1 1300 1420
chr1 1400 1500

5
software/bedtools/test/input/H3K4me1.bed
View file

@ -1,5 +0,0 @@
chr1 951 1061
chr1 1300 1420
chr1 1400 1500

BIN
software/bedtools/test/input/test.single_end.sorted.bam
View file

Binary file not shown.

55
software/bedtools/test/main.nf
View file

@ -1,55 +0,0 @@
#!/usr/bin/env nextflow
nextflow.preview.dsl = 2
include { BEDTOOLS_SLOP } from '../slop/main.nf' addParams( options: [publish_dir:'test_bed_file'])
include { BEDTOOLS_REMOVEGENES } from '../removegenes/main.nf' addParams( options: [publish_dir:'test_bed_file'])
include { BEDTOOLS_ERNAS } from '../ernas/main.nf' addParams( options: [publish_dir:'test_bed_file'])
include { BEDTOOLS_TESTERNA } from '../testerna/main.nf' addParams( options: [publish_dir:'test_bed_file'])
include { BEDTOOLS_HISTONESTOBED} from '../histonestobed/main.nf' addParams( options: [publish_dir:'test_histones_to_bed'])
include { BEDTOOLS_ERNAGENEGROUPS} from '../ernagenegroups/main.nf' addParams( options: [publish_dir:'test_erna_gene_groups'])
// Define input channels
// Run the workflow
workflow test_bed_file {
def input = []
input = [ [ id:'test', single_end:true ],
[ file("${baseDir}/input/A.bed", checkIfExists: true),] ]
BEDTOOLS_SLOP(
input,
file("${baseDir}/input/genome.sizes", checkIfExists: true)
)
BEDTOOLS_REMOVEGENES(
BEDTOOLS_SLOP.out.slopbed,
file("${baseDir}/input/B.metatranscripts", checkIfExists: true)
)
BEDTOOLS_ERNAS(
BEDTOOLS_REMOVEGENES.out.nogenesbed,
file("${baseDir}/input/H3K27ac.bed", checkIfExists: true),
file("${baseDir}/input/H3K4me1.bed", checkIfExists: true)
)
BEDTOOLS_TESTERNA(
BEDTOOLS_ERNAS.out.ernabed,
file("${baseDir}/input/B.bed", checkIfExists: true)
)
}
workflow test_histones_to_bed {
def input = []
input = [ [ id:'test', single_end:true ],
[ file("${baseDir}/input/test.single_end.sorted.bam", checkIfExists: true),] ]
BEDTOOLS_HISTONESTOBED( input )
}
workflow {
test_bed_file()
test_histones_to_bed()
}

0
software/bedtools/test/output/test_bed_file/test.erna.bed
View file

0
software/bedtools/test/output/test_bed_file/test.erna.overlaps.bed
View file

0
software/bedtools/test/output/test_bed_file/test.nogenes.bed
View file

3
software/bedtools/test/output/test_bed_file/test.slop.bed
View file

@ -1,3 +0,0 @@
chr1 951 1061
chr1 1300 1420
chr1 1400 1500

1
software/bedtools/test/output/test_erna_prediction/test.erna_overlaps.bed
View file

@ -1 +0,0 @@
chr1 999 1010

10000
software/bedtools/test/output/test_histones_to_bed/test.bed
View file

File diff suppressed because it is too large Load diff

59
software/bedtools/testerna/functions.nf
View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

37
software/bedtools/testerna/main.nf
View file

@ -1,37 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process BEDTOOLS_TESTERNA {
tag "$meta.id"
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
// In the case of use for cell lines, the second input can also be replaced with the tuple (val) format.
input:
tuple val(meta), path(ernabed)
path ernareferencebed
output:
tuple val(meta), path("*.erna.overlaps.bed"), emit: ernaoverlapsbed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
bedtools intersect -a $ernareferencebed -b $ernabed \\
-sorted -u > ${prefix}.erna.overlaps.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

53
software/bedtools/testerna/meta.yml
View file

@ -1,53 +0,0 @@
name: bedtools_testerna
description: Compares identified ernas across cell lines/across legacy ernas
keywords:
- bed
- bedtoolsintersect
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"