Add files via upload

Fig3_findHTRs.sh

@@ -26,4 +26,4 @@ bedtools makewindows -w ${window} -g ${referencegenome3}.bed > ${referencegenome
 ## output is tsv file with mean % similarity in 10kb windows and 2.5kb slide
 ## this is because it takes the mean of 7th col of cov.tsv (which is % similarity)
 
-ls *.fna | while read comparison; do comparisonstrain=$( echo $comparison | awk -F "/" '{print $NF}' | awk -F "." '{print $1.$2}' ); minimap2 -c --secondary=no --cs ${referencegenome} ${comparison} | sort -k6,6 -k8,8n > ${comparisonstrain}.minimap2_${referencestrain}.paf; paftools.js splice2bed ${comparisonstrain}.minimap2_${referencestrain}.paf > ${comparisonstrain}.minimap2_${referencestrain}.bed; bedtools makewindows -w 100 -s 100 -g ${referencegenome3}.bed > ${referencegenome3}.short.bed; bedtools coverage -a ${referencegenome3}.short.bed -b ${comparisonstrain}.minimap2_${referencestrain}.bed > ${comparisonstrain}.minimap2_${referencestrain}.cov.tsv; bedtools map -b ${comparisonstrain}.minimap2_${referencestrain}.cov.tsv -a ${referencegenome3}.${window2}kbwindow_${slide2}kbslide.bed -c 7 -o mean > ${comparisonstrain}.minimap2_${referencestrain}.cov.binned.tsv; done
+ls *.fna | while read comparison; do comparisonstrain=$( echo $comparison | awk -F "/" '{print $NF}' | awk -F "." '{print $1.$2}' ); minimap2 -cx asm10 --secondary=no --cs ${referencegenome} ${comparison} | sort -k6,6 -k8,8n > ${comparisonstrain}.minimap2_${referencestrain}.paf; paftools.js splice2bed ${comparisonstrain}.minimap2_${referencestrain}.paf > ${comparisonstrain}.minimap2_${referencestrain}.bed; bedtools makewindows -w 100 -s 100 -g ${referencegenome3}.bed > ${referencegenome3}.short.bed; bedtools coverage -a ${referencegenome3}.short.bed -b ${comparisonstrain}.minimap2_${referencestrain}.bed > ${comparisonstrain}.minimap2_${referencestrain}.cov.tsv; bedtools map -b ${comparisonstrain}.minimap2_${referencestrain}.cov.tsv -a ${referencegenome3}.${window2}kbwindow_${slide2}kbslide.bed -c 7 -o mean > ${comparisonstrain}.minimap2_${referencestrain}.cov.binned.tsv; done

Fig6_S11.Rmd

@@ -13,7 +13,7 @@ library(aplot)
 ```
 
 ```{r read in files and format them}
-
+### first run Fig6_findTEs.sh to identify TEs in genomes
 species.tree <- read.tree("./Data/Speciestree.treefile")
 mimps<-read.csv("./Data/mimps.csv", sep=",",header = 1)
 groups<-read.table("./Data/species.tree.tip.labelgroup.txt", sep="\t",header = 1)

Fig6_findTEs.sh

@@ -0,0 +1,38 @@
+##### first build the database then run repeatmodeler
+#PBS -l walltime=48:00:00
+#PBS -l select=1:ncpus=64:mem=244gb
+
+cd $PBS_O_WORKDIR
+
+module load anaconda3/personal
+source activate repeatmodeler
+
+singularity exec \
+ --bind $PWD:$PWD \
+ dfam-tetools-latest.sif BuildDatabase -name "ragtag.assemblies" -dir ragtag.assemblies
+
+singularity exec \
+ --bind $PWD:$PWD \
+ dfam-tetools-latest.sif RepeatModeler \
+ -database ragtag.assemblies \
+ -pa 32 -LTRStruct
+
+
+##### then run repeatmasker using customised TE library
+#PBS -l walltime=24:00:00
+#PBS -l select=1:ncpus=64:mem=124gb
+
+cd $PBS_O_WORKDIR
+
+module load anaconda3/personal
+source activate repeatmodeler
+
+ singularity exec \
+ --bind $PWD:$PWD \
+ dfam-tetools-latest.sif \
+ RepeatMasker -lib ragtag.assemblies-families.manual.mimps.schmidt.fa \
+ -pa 32 -s \
+ -dir RM_out \
+ -alignments \
+ -gff -no_is \
+ ragtag.assemblies/*.fasta