add analysis_kraken script

STOMACH_ANALYSIS/analysis_kraken.sh

+#!/bin/bash
+################################################################################
+#                             analysis_kraken                                  #
+#                                                                              #
+# Script for taxonomic sequence classification of the using kraken             #
+#                                                                              #
+#                                                                              #
+# description: to be added                                                     #
+#                                                                              #
+#  Copyright (C) 2020 Rahma Amen (Potsdam University)                          #
+#                     amen@uni-potsdam.de                                      #
+#                                                                              #
+# Change History                                                               #
+#   29/10/2020  Rahma Amen  created the script                                 #
+#                                                                              #
+# ToDo:                                                                        #
+#     - Use kraken2                                                            #
+#                                                                              #
+################################################################################
+
+## Define in/out folders and variables
+
+DBNAME=/mnt/scratch/mathnat/ibb/amen/STOMACH_ANALYSIS/TEST_ANALYSIS/DATABASE_KRAKEN/
+DATA_TRIMMED=/mnt/scratch/mathnat/ibb/amen/STOMACH_ANALYSIS/TEST_ANALYSIS/DATA_TRIMMED
+OUT_DIR=/mnt/scratch/mathnat/ibb/amen/STOMACH_ANALYSIS/TEST_ANALYSIS/KRAKEN_ANALYSIS/
+
+## Creat custom database
+# to be written
+# http://ccb.jhu.edu/software/kraken/MANUAL.html#custom-databases
+#
+# Temporary fix for people using conda's version of kraken or kraken2: Run these commands prior to kraken-build --db . --download-taxonomy:
+# wget ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/nucl_gb.accession2taxid.gz
+# wget ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/nucl_wgs.accession2taxid.gz
+# touch accmap.dlflag
+# and put those files into the "taxonomy" folder
+#
+
+for fR in $DATA_TRIMMED/*R1_001_trimmed.fastq.gz
+
+do
+    # file stem (without extension or path)
+    fstem=$(echo $fR | sed 's/.*\///' | sed 's/1_001_trimmed.fastq.gz//')
+    fR1=$DATA_TRIMMED/$fstem"1_001_trimmed.fastq.gz"
+    fR2=$DATA_TRIMMED/$fstem"2_001_trimmed.fastq.gz"
+    fout=$OUT_DIR$fstem"_kraken"
+    frep=$OUT_DIR$fstem"_report"
+    ftrn=$OUT_DIR$fstem"_translate"
+    
+    kraken --paired $fR1 $fR2 --db $DBNAME > $fout
+    kraken-report $fout --db $DBNAME > $frep
+    kraken-translate $fout --db $DBNAME > $ftrn
+done