Added pickOtus step

public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/PickOtus.scala

+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class PickOtus(val root: Configurable) extends BiopetCommandLineFunction {
+  executable = config("exe", default = "pick_otus.py")
+
+  @Input(required = true)
+  var inputFasta: File = _
+
+  var outputDir: File = null
+
+  override def defaultThreads = 2
+
+  override def defaultCoreMemory = 5.0
+
+  var otu_picking_method: Option[String] = config("otu_picking_method")
+  var clustering_algorithm: Option[String] = config("clustering_algorithm")
+  var max_cdhit_memory: Option[Int] = config("max_cdhit_memory")
+  var refseqs_fp: Option[String] = config("refseqs_fp")
+  var blast_db: Option[String] = config("blast_db")
+  var max_e_value_blast: Option[String] = config("max_e_value_blast")
+  var sortmerna_db: Option[String] = config("sortmerna_db")
+  var sortmerna_e_value: Option[Double] = config("sortmerna_e_value")
+  var sortmerna_coverage: Option[Double] = config("sortmerna_coverage")
+  var sortmerna_tabular: Boolean = config("sortmerna_tabular", default = false)
+  var sortmerna_best_N_alignments: Option[Int] = config("sortmerna_best_N_alignments")
+  var sortmerna_max_pos: Option[Int] = config("sortmerna_max_pos")
+  var min_aligned_percent: Option[Double] = config("min_aligned_percent")
+  var similarity: Option[Double] = config("similarity")
+  var sumaclust_exact: Option[String] = config("sumaclust_exact")
+  var sumaclust_l: Boolean = config("sumaclust_l", default = false)
+  var denovo_otu_id_prefix: Option[String] = config("denovo_otu_id_prefix")
+  var swarm_resolution: Option[String] = config("swarm_resolution")
+  var trie_reverse_seqs: Boolean = config("trie_reverse_seqs", default = false)
+  var prefix_prefilter_length: Option[String] = config("prefix_prefilter_length")
+  var trie_prefilter: Option[String] = config("trie_prefilter")
+  var prefix_length: Option[String] = config("prefix_length")
+  var suffix_length: Option[String] = config("suffix_length")
+  var enable_rev_strand_match: Boolean = config("enable_rev_strand_match", default = false)
+  var suppress_presort_by_abundance_uclust: Boolean = config("suppress_presort_by_abundance_uclust", default = false)
+  var optimal_uclust: Boolean = config("optimal_uclust", default = false)
+  var exact_uclust: Boolean = config("exact_uclust", default = false)
+  var user_sort: Boolean = config("user_sort", default = false)
+  var suppress_new_clusters: Boolean = config("suppress_new_clusters", default = false)
+  var max_accepts: Option[String] = config("max_accepts")
+  var max_rejects: Option[String] = config("max_rejects")
+  var stepwords: Option[String] = config("stepwords")
+  var word_length: Option[String] = config("word_length")
+  var suppress_uclust_stable_sort: Boolean = config("suppress_uclust_stable_sort", default = false)
+  var suppress_prefilter_exact_match: Boolean = config("suppress_prefilter_exact_match", default = false)
+  var save_uc_files: Boolean = config("save_uc_files", default = false)
+  var percent_id_err: Option[String] = config("percent_id_err")
+  var minsize: Option[String] = config("minsize")
+  var abundance_skew: Option[String] = config("abundance_skew")
+  var db_filepath: Option[String] = config("db_filepath")
+  var perc_id_blast: Option[String] = config("perc_id_blast")
+  var de_novo_chimera_detection: Boolean = config("de_novo_chimera_detection", default = false)
+  var suppress_de_novo_chimera_detection: Boolean = config("suppress_de_novo_chimera_detection", default = false)
+  var reference_chimera_detection: Option[String] = config("reference_chimera_detection")
+  var suppress_reference_chimera_detection: Option[String] = config("suppress_reference_chimera_detection")
+  var cluster_size_filtering: Option[String] = config("cluster_size_filtering")
+  var suppress_cluster_size_filtering: Option[String] = config("suppress_cluster_size_filtering")
+  var remove_usearch_logs: Boolean = config("remove_usearch_logs", default = false)
+  var derep_fullseq: Boolean = config("derep_fullseq", default = false)
+  var non_chimeras_retention: Option[String] = config("non_chimeras_retention")
+  var minlen: Option[String] = config("minlen")
+  var usearch_fast_cluster: Boolean = config("usearch_fast_cluster", default = false)
+  var usearch61_sort_method: Option[String] = config("usearch61_sort_method")
+  var sizeorder: Boolean = config("sizeorder", default = false)
+
+  def cmdLine = executable +
+    required("-i", inputFasta) +
+    required("-o", outputDir) +
+    optional("-m", otu_picking_method) +
+    optional("-c", clustering_algorithm) +
+    optional("-M", max_cdhit_memory) +
+    optional("-r", refseqs_fp) +
+    optional("-b", blast_db) +
+    optional("-e", max_e_value_blast) +
+    optional("--sortmerna_db", sortmerna_db) +
+    optional("--sortmerna_e_value", sortmerna_e_value) +
+    optional("--sortmerna_coverage", sortmerna_coverage) +
+    conditional(sortmerna_tabular, "--sortmerna_tabular") +
+    optional("--sortmerna_best_N_alignments", sortmerna_best_N_alignments) +
+    optional("--sortmerna_max_pos", sortmerna_max_pos) +
+    optional("--min_aligned_percent", min_aligned_percent) +
+    optional("--similarity", similarity) +
+    optional("--sumaclust_exact", sumaclust_exact) +
+    conditional(sumaclust_l, "--sumaclust_l") +
+    optional("--denovo_otu_id_prefix", denovo_otu_id_prefix) +
+    optional("--swarm_resolution", swarm_resolution) +
+    conditional(trie_reverse_seqs, "--trie_reverse_seqs") +
+    optional("--prefix_prefilter_length", prefix_prefilter_length) +
+    optional("--trie_prefilter", trie_prefilter) +
+    optional("--prefix_length", prefix_length) +
+    optional("--suffix_length", suffix_length) +
+    conditional(enable_rev_strand_match, "--enable_rev_strand_match") +
+    conditional(suppress_presort_by_abundance_uclust, "--suppress_presort_by_abundance_uclust") +
+    conditional(optimal_uclust, "--optimal_uclust") +
+    conditional(exact_uclust, "--exact_uclust") +
+    conditional(user_sort, "--user_sort") +
+    conditional(suppress_new_clusters, "--suppress_new_clusters") +
+    optional("--max_accepts", max_accepts) +
+    optional("--max_rejects", max_rejects) +
+    optional("--stepwords", stepwords) +
+    optional("--word_length", word_length) +
+    conditional(suppress_uclust_stable_sort, "--suppress_uclust_stable_sort") +
+    conditional(suppress_prefilter_exact_match, "--suppress_prefilter_exact_match") +
+    conditional(save_uc_files, "--save_uc_files") +
+    optional("--percent_id_err", percent_id_err) +
+    optional("--minsize", minsize) +
+    optional("--abundance_skew", abundance_skew) +
+    optional("--db_filepath", db_filepath) +
+    optional("--perc_id_blast", perc_id_blast) +
+    conditional(de_novo_chimera_detection, "--de_novo_chimera_detection") +
+    conditional(suppress_de_novo_chimera_detection, "--suppress_de_novo_chimera_detection") +
+    optional("--reference_chimera_detection", reference_chimera_detection) +
+    optional("--suppress_reference_chimera_detection", suppress_reference_chimera_detection) +
+    optional("--cluster_size_filtering", cluster_size_filtering) +
+    optional("--suppress_cluster_size_filtering", suppress_cluster_size_filtering) +
+    conditional(remove_usearch_logs, "--remove_usearch_logs") +
+    conditional(derep_fullseq, "--derep_fullseq") +
+    optional("--non_chimeras_retention", non_chimeras_retention) +
+    optional("--minlen", minlen) +
+    optional("--usearch_fast_cluster", usearch_fast_cluster) +
+    optional("--usearch61_sort_method", usearch61_sort_method) +
+    conditional(sizeorder, "--sizeorder") +
+    optional("--threads", threads)
+}

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/ExtractUnmappedReads.scala

@@ -7,8 +7,8 @@ import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**
-  * Created by pjvanthof on 04/12/15.
-  */
+ * Created by pjvanthof on 04/12/15.
+ */
 class ExtractUnmappedReads(val root: Configurable) extends QScript with BiopetQScript {
 
   var bamFile: File = _

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala

 package nl.lumc.sasc.biopet.pipelines.gears
 
-import nl.lumc.sasc.biopet.core.{PipelineCommand, MultiSampleQScript}
+import nl.lumc.sasc.biopet.core.{ PipelineCommand, MultiSampleQScript }
 import nl.lumc.sasc.biopet.utils.Logging
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**
-  * Created by pjvanthof on 03/12/15.
-  */
+ * Created by pjvanthof on 03/12/15.
+ */
 class Gears(val root: Configurable) extends QScript with MultiSampleQScript { qscript =>
   def this() = this(null)
 
@@ -25,16 +25,16 @@ class Gears(val root: Configurable) extends QScript with MultiSampleQScript { qs
   }
 
   /**
-    * Method where the multisample jobs should be added, this will be executed only when running the -sample argument is not given.
-    */
+   * Method where the multisample jobs should be added, this will be executed only when running the -sample argument is not given.
+   */
   def addMultiSampleJobs(): Unit = {
   }
 
   /**
-    * Factory method for Sample class
-    * @param id SampleId
-    * @return Sample class
-    */
+   * Factory method for Sample class
+   * @param id SampleId
+   * @return Sample class
+   */
   def makeSample(id: String): Sample = new Sample(id)
 
   class Sample(sampleId: String) extends AbstractSample(sampleId) {
@@ -44,10 +44,10 @@ class Gears(val root: Configurable) extends QScript with MultiSampleQScript { qs
     }
 
     /**
-      * Factory method for Library class
-      * @param id SampleId
-      * @return Sample class
-      */
+     * Factory method for Library class
+     * @param id SampleId
+     * @return Sample class
+     */
     def makeLibrary(id: String): Library = new Library(id)
 
     class Library(libId: String) extends AbstractLibrary(libId) {

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsKraken.scala

@@ -2,14 +2,14 @@ package nl.lumc.sasc.biopet.pipelines.gears
 
 import nl.lumc.sasc.biopet.core.SampleLibraryTag
 import nl.lumc.sasc.biopet.core.summary.SummaryQScript
-import nl.lumc.sasc.biopet.extensions.kraken.{KrakenReport, Kraken}
+import nl.lumc.sasc.biopet.extensions.kraken.{ KrakenReport, Kraken }
 import nl.lumc.sasc.biopet.extensions.tools.KrakenReportToJson
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**
-  * Created by pjvanthof on 04/12/15.
-  */
+ * Created by pjvanthof on 04/12/15.
+ */
 class GearsKraken(val root: Configurable) extends QScript with SummaryQScript with SampleLibraryTag {
 
   var fastqR1: File = _
@@ -74,6 +74,6 @@ class GearsKraken(val root: Configurable) extends QScript with SummaryQScript wi
   /** Statistics shown in the summary file */
   def summaryFiles: Map[String, File] = outputFiles + ("input_R1" -> fastqR1) ++ (fastqR2 match {
     case Some(file) => Map("input_R1" -> file)
-    case _ => Map()
+    case _          => Map()
   })
 }

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRatx.scala

 package nl.lumc.sasc.biopet.pipelines.gears
 
 import nl.lumc.sasc.biopet.core.BiopetQScript
+import nl.lumc.sasc.biopet.extensions.qiime.PickOtus
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**
-  * Created by pjvan_thof on 12/4/15.
-  */
+ * Created by pjvan_thof on 12/4/15.
+ */
 class GearsQiimeRatx(val root: Configurable) extends QScript with BiopetQScript {
 
   var fastaR1: File = _
@@ -18,6 +19,9 @@ class GearsQiimeRatx(val root: Configurable) extends QScript with BiopetQScript
   }
 
   def biopetScript() = {
-
+    val pickOtus = new PickOtus(this)
+    pickOtus.inputFasta = fastaR1
+    pickOtus.outputDir = new File(outputDir, "pick_otus")
+    add(pickOtus)
   }
 }

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingle.scala

@@ -79,8 +79,8 @@ class GearsSingle(val root: Configurable) extends QScript with SummaryQScript wi
 
   /** Method to add jobs */
   def biopetScript(): Unit = {
-    val (r1: File, r2: Option[File]) = (fastqR1, fastqR2, bamFile) match {
-      case (Some(r1), r2, _) => (r1, r2)
+    val (r1, r2): (File, Option[File]) = (fastqR1, fastqR2, bamFile) match {
+      case (Some(r1), _, _) => (r1, fastqR2)
       case (_, _, Some(bam)) =>
         val extract = new ExtractUnmappedReads(this)
         extract.outputDir = outputDir
@@ -90,11 +90,11 @@ class GearsSingle(val root: Configurable) extends QScript with SummaryQScript wi
         extract.biopetScript()
         addAll(extract.functions)
         (extract.fastqUnmappedR1, Some(extract.fastqUnmappedR2))
-      case _ => Logging.addError("Missing input files")
+      case _ => throw new IllegalArgumentException("Missing input files")
     }
 
-    lazy val fastqR1 = fastqToFasta(r1, outputName + ".R1")
-    lazy val fastqR2 = r2.map(fastqToFasta(_, outputName + ".R2"))
+    lazy val fastaR1 = fastqToFasta(r1, outputName + ".R1")
+    lazy val fastaR2 = r2.map(fastqToFasta(_, outputName + ".R2"))
 
     if (gearsUseKraken) {
       val kraken = new GearsKraken(this)
@@ -110,7 +110,12 @@ class GearsSingle(val root: Configurable) extends QScript with SummaryQScript wi
 
     if (gearsUserQiimeRtax) {
       val qiimeRatx = new GearsQiimeRatx(this)
-
+      qiimeRatx.outputDir = new File(outputDir, "qiime_ratx")
+      qiimeRatx.fastaR1 = fastaR1
+      qiimeRatx.fastqR2 = fastaR2
+      qiimeRatx.init()
+      qiimeRatx.biopetScript()
+      addAll(qiimeRatx.functions)
     }
 
     addSummaryJobs()