genome assembly

jellyfish_velvet.sh

@@ -71,4 +71,4 @@ echo \
  
 velvetg ${file}/ -cov_cutoff auto " > velvet_scripts/$file'_velg_slurm.sh'
 sbatch velvet_scripts/$file'_velg_slurm.sh'
-done
+done

quast.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+#specify paths to your working directory and your reads directory
+WORK_DIR='/home/dkiambi/ayb_results/'
+
+cd $WORK_DIR
+mkdir -p quast_scripts quast_logs
+for file in $(ls -I "*scripts" -I "*logs" -I "old*" -I "fast*" -I "jellyfish_out" -I "*\.*")
+        do
+
+echo \
+"#!/bin/bash -e
+#SBATCH -p batch
+#SBATCH -n 2
+#SBATCH -o quast_logs/quast.%N.%j.out
+#SBATCH -e quast_logs/quast.%N.%j.err
+
+# load approporate module
+
+ module load quast
+
+quast.py ./${file}/contigs.fa -o ./${file}/ -t 2 " > quast_scripts/$file'_slurm.sh'
+sbatch quast_scripts/$file'_slurm.sh'
+done

velvet.sh

@@ -0,0 +1,25 @@
+#!/bin/bash -e
+#SBATCH -p batch
+#SBATCH -n 4
+#SBATCH -w compute03
+#SBATCH -o ./jfm.%N.%j.out
+#SBATCH -e ./jfm.%N.%j.err
+#SBATCH -p highmem
+#SBATCH -n 4     
+#SBATCH -w mammoth
+# define paths
+READ_DIR1='/export/data/ilri/miseq/MiSeq2/MiSeq2Output2018/181128_M03021_0009_000000000-C3F6V_AYB_run1/'
+READ_DIR2='/export/data/ilri/miseq/MiSeq2/MiSeq2Output2018/181203_M03021_0010_000000000-C63KC_AYB_run2/'
+READ_DIR3='/var/scratch/African_Yam_Bean_TSS11-RUN3-106656809/FASTQ_Generation_2018-12-16_08_18_54Z-143723645/1_L001-ds.1fa37ed4a86a45f6b7f61c434c62fe41/'
+READ1='1_S1_L001_R1_001.fastq.gz'
+READ2='1_S1_L001_R2_001.fastq.gz'
+
+# load relevant module
+module load velvet
+#module load jellyfish
+# land at appropriate place
+cd /home/dkiambi/ayb_results/
+
+# run the the asmebly with the relavant runs, optimising for kmers from 41 to 61 with changes of 5
+
+velveth velvet_out 63 -shortPaired -fastq.gz -separate $READ_DIR2/$READ1 $READ_DIR2/$READ2