Commit 24837f5b authored by Sander van der Zeeuw's avatar Sander van der Zeeuw

Merge branch 'feature-gears' into 'develop'

Feature gears (metagenomics)

Metagenomics pipeline, start from bam or from FastQ files.

Dependencies:
- Sambamba (v0.5.1+)
- Kraken

See merge request !168
parents 8c08d89b 900ba26b
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.kraken
import java.io.File
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.util.matching.Regex
/** Extension for Kraken */
class Kraken(val root: Configurable) extends BiopetCommandLineFunction {
@Input(doc = "Input: FastQ or FastA")
var input: List[File] = _
var db: File = config("db")
var inputFastQ: Boolean = true
var compression: Boolean = false
var compressionGzip: Boolean = false
var compressionBzip: Boolean = false
var quick: Boolean = false
var min_hits: Option[Int] = config("min_hits")
@Output(doc = "Unidentified reads", required = false)
var unclassified_out: Option[File] = None
@Output(doc = "Identified reads", required = false)
var classified_out: Option[File] = None
@Output(doc = "Output with hits per sequence")
var output: File = _
var preload: Boolean = config("preload", default = true)
var paired: Boolean = config("paired", default = false)
executable = config("exe", default = "kraken")
override val versionRegex = """Kraken version ([\d\w\-\.]+)\n.*""".r
override val versionExitcode = List(0, 1)
override val defaultCoreMemory = 8.0
override val defaultThreads = 4
override def versionCommand = executable + " --version"
/** Sets readgroup when not set yet */
override def beforeGraph: Unit = {
super.beforeGraph
}
/** Returns command to execute */
def cmdLine = {
var cmd: String = required(executable) +
"--db" + required(db) +
optional("--threads", nCoresRequest) +
conditional(inputFastQ, "--fastq-input") +
conditional(inputFastQ == false, "--fasta-input") +
conditional(quick, "--quick")
min_hits match {
case Some(v) => cmd += "--min_hits " + v
case _ => cmd += ""
}
cmd += optional("--unclassified-out ", unclassified_out.get) +
optional("--classified-out ", classified_out.get) +
"--output" + required(output) +
conditional(preload, "--preload") +
conditional(paired, "--paired")
// finally the input files (R1 [R2])
cmd += input.mkString(" ")
cmd
}
}
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.kraken
import java.io.File
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
/** Extension for Kraken */
class KrakenReport(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "kraken-report")
override val versionRegex = """Kraken version (.*)""".r
override val versionExitcode = List(0, 1)
override val defaultCoreMemory = 4.0
override val defaultThreads = 1
override def versionCommand = new File(new File(executable).getParent, "kraken").getAbsolutePath + " --version"
var db: File = config("db")
var show_zeros: Boolean = config("show_zeros", default = false)
@Input(doc = "Input raw kraken analysis")
var input: File = _
@Output(doc = "Output path kraken report")
var output: File = _
def cmdLine: String = {
val cmd: String = "--db " + required(db) +
conditional(show_zeros, "--show-zeros") +
input.getAbsolutePath + ">" + output.getAbsolutePath
cmd
}
}
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.sambamba
import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import java.io.File
/** Extension for sambamba flagstat */
class SambambaView(val root: Configurable) extends Sambamba {
override val defaultThreads = 2
@Input(doc = "Bam File")
var input: File = _
@Output(doc = "output File")
var output: File = _
var filter: Option[String] = _
val format: Option[String] = config("format", default = "bam")
val regions: Option[File] = config("regions")
val compression_level: Option[Int] = config("compression_level", default = 6)
/** Returns command to execute */
def cmdLine = required(executable) +
required("view") +
optional("--filter", filter) +
optional("--nthreads", nCoresRequest) +
optional("--format", format.get) +
optional("--regions", regions) +
optional("--compression-level", compression_level) +
required("--output" + output) +
required(input)
}
......@@ -80,6 +80,11 @@
<artifactId>Kopisu</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>Gears</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>Bam2Wig</artifactId>
......
......@@ -30,7 +30,8 @@ object BiopetExecutablePublic extends BiopetExecutable {
def pipelines: List[MainCommand] = List(
nl.lumc.sasc.biopet.pipelines.shiva.Shiva,
nl.lumc.sasc.biopet.pipelines.shiva.ShivaVariantcalling,
nl.lumc.sasc.biopet.pipelines.basty.Basty
nl.lumc.sasc.biopet.pipelines.basty.Basty,
nl.lumc.sasc.biopet.pipelines.gears.Gears
) ::: protectedPipelines
def tools: List[MainCommand] = List(
......
<?xml version="1.0" encoding="UTF-8"?>
<!--
Biopet is built on top of GATK Queue for building bioinformatic
pipelines. It is mainly intended to support LUMC SHARK cluster which is running
SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
should also be able to execute Biopet tools and pipelines.
Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
Contact us at: sasc@lumc.nl
A dual licensing mode is applied. The source code within this project that are
not part of GATK Queue is freely available for non-commercial use under an AGPL
license; For commercial users or users who do not want to follow the AGPL
license, please contact us to obtain a separate license.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>Biopet</artifactId>
<groupId>nl.lumc.sasc</groupId>
<version>0.4.0-DEV</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<inceptionYear>2015</inceptionYear>
<artifactId>Gears</artifactId>
<dependencies>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>BiopetFramework</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
<artifactId>Mapping</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.testng</groupId>
<artifactId>testng</artifactId>
<version>6.8</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_2.11</artifactId>
<version>2.2.1</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.pipelines.gears
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.PipelineCommand
import org.broadinstitute.gatk.queue.QScript
class Gears(val root: Configurable) extends QScript with GearsTrait {
def this() = this(null)
}
/** This object give a default main method to the pipelines */
object Gears extends PipelineCommand
\ No newline at end of file
#
# Biopet is built on top of GATK Queue for building bioinformatic
# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
# should also be able to execute Biopet tools and pipelines.
#
# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
#
# Contact us at: sasc@lumc.nl
#
# A dual licensing mode is applied. The source code within this project that are
# not part of GATK Queue is freely available for non-commercial use under an AGPL
# license; For commercial users or users who do not want to follow the AGPL
# license, please contact us to obtain a separate license.
#
# Set root logger level to DEBUG and its only appender to A1.
log4j.rootLogger=ERROR, A1
# A1 is set to be a ConsoleAppender.
log4j.appender.A1=org.apache.log4j.ConsoleAppender
# A1 uses PatternLayout.
log4j.appender.A1.layout=org.apache.log4j.PatternLayout
log4j.appender.A1.layout.ConversionPattern=%-5p [%d] [%C{1}] - %m%n
\ No newline at end of file
......@@ -34,6 +34,7 @@
<module>sage</module>
<module>kopisu</module>
<module>yamsvp</module>
<module>gears</module>
<module>bam2wig</module>
<module>carp</module>
<module>toucan</module>
......@@ -202,6 +203,7 @@
<exclude>**/*.bed</exclude>
<exclude>**/*.refFlat</exclude>
<exclude>**/*.R</exclude>
<exclude>**/*.rscript</exclude>
</excludes>
</configuration>
</plugin>
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment