diff --git a/GC_content.R b/cross-species-analyses/GC_content.R
similarity index 100%
rename from GC_content.R
rename to cross-species-analyses/GC_content.R
diff --git a/GO_orthologous_peaks.R b/cross-species-analyses/GO_orthologous_peaks.R
similarity index 100%
rename from GO_orthologous_peaks.R
rename to cross-species-analyses/GO_orthologous_peaks.R
diff --git a/GO_plots.R b/cross-species-analyses/GO_plots.R
similarity index 100%
rename from GO_plots.R
rename to cross-species-analyses/GO_plots.R
diff --git a/README.md b/cross-species-analyses/README.md
similarity index 100%
rename from README.md
rename to cross-species-analyses/README.md
diff --git a/annotation_10M.R b/cross-species-analyses/annotation_10M.R
similarity index 100%
rename from annotation_10M.R
rename to cross-species-analyses/annotation_10M.R
diff --git a/biomart_compare_orthoG.R b/cross-species-analyses/biomart_compare_orthoG.R
similarity index 100%
rename from biomart_compare_orthoG.R
rename to cross-species-analyses/biomart_compare_orthoG.R
diff --git a/comparePeaks.sh b/cross-species-analyses/comparePeaks.sh
similarity index 100%
rename from comparePeaks.sh
rename to cross-species-analyses/comparePeaks.sh
diff --git a/compare_liftover_genes.R b/cross-species-analyses/compare_liftover_genes.R
similarity index 100%
rename from compare_liftover_genes.R
rename to cross-species-analyses/compare_liftover_genes.R
diff --git a/geneSet_upsetPlot.R b/cross-species-analyses/geneSet_upsetPlot.R
similarity index 100%
rename from geneSet_upsetPlot.R
rename to cross-species-analyses/geneSet_upsetPlot.R
diff --git a/genomicRegionsPlot.R b/cross-species-analyses/genomicRegionsPlot.R
similarity index 100%
rename from genomicRegionsPlot.R
rename to cross-species-analyses/genomicRegionsPlot.R
diff --git a/go_semantic_similarity.R b/cross-species-analyses/go_semantic_similarity.R
similarity index 100%
rename from go_semantic_similarity.R
rename to cross-species-analyses/go_semantic_similarity.R
diff --git a/go_similarity_clusters_heatmaps.R b/cross-species-analyses/go_similarity_clusters_heatmaps.R
similarity index 100%
rename from go_similarity_clusters_heatmaps.R
rename to cross-species-analyses/go_similarity_clusters_heatmaps.R
diff --git a/liftOverPeaks.R b/cross-species-analyses/liftOverPeaks.R
similarity index 100%
rename from liftOverPeaks.R
rename to cross-species-analyses/liftOverPeaks.R
diff --git a/mm9_vista.bed b/cross-species-analyses/mm9_vista.bed
similarity index 100%
rename from mm9_vista.bed
rename to cross-species-analyses/mm9_vista.bed
diff --git a/mm9_vista.fasta b/cross-species-analyses/mm9_vista.fasta
similarity index 100%
rename from mm9_vista.fasta
rename to cross-species-analyses/mm9_vista.fasta
diff --git a/mm9_vista.txt b/cross-species-analyses/mm9_vista.txt
similarity index 100%
rename from mm9_vista.txt
rename to cross-species-analyses/mm9_vista.txt
diff --git a/mouse_geneExp_clustering_TCseq.R b/cross-species-analyses/mouse_geneExp_clustering_TCseq.R
similarity index 100%
rename from mouse_geneExp_clustering_TCseq.R
rename to cross-species-analyses/mouse_geneExp_clustering_TCseq.R
diff --git a/peakFeature2.R b/cross-species-analyses/peakFeature2.R
similarity index 100%
rename from peakFeature2.R
rename to cross-species-analyses/peakFeature2.R
diff --git a/peakFeatures.R b/cross-species-analyses/peakFeatures.R
similarity index 100%
rename from peakFeatures.R
rename to cross-species-analyses/peakFeatures.R
diff --git a/peak_QC.R b/cross-species-analyses/peak_QC.R
similarity index 100%
rename from peak_QC.R
rename to cross-species-analyses/peak_QC.R
diff --git a/peak_metrics.R b/cross-species-analyses/peak_metrics.R
similarity index 100%
rename from peak_metrics.R
rename to cross-species-analyses/peak_metrics.R
diff --git a/peak_metrics_PCA.R b/cross-species-analyses/peak_metrics_PCA.R
similarity index 100%
rename from peak_metrics_PCA.R
rename to cross-species-analyses/peak_metrics_PCA.R
diff --git a/subsamplePeaks.R b/cross-species-analyses/subsamplePeaks.R
similarity index 100%
rename from subsamplePeaks.R
rename to cross-species-analyses/subsamplePeaks.R
diff --git a/dunnart/.DS_Store b/dunnart-chipseq/.DS_Store
similarity index 100%
rename from dunnart/.DS_Store
rename to dunnart-chipseq/.DS_Store
diff --git a/dunnart/README.md b/dunnart-chipseq/README.md
similarity index 100%
rename from dunnart/README.md
rename to dunnart-chipseq/README.md
diff --git a/dunnart/Snakefile b/dunnart-chipseq/Snakefile
similarity index 100%
rename from dunnart/Snakefile
rename to dunnart-chipseq/Snakefile
diff --git a/dunnart/Snakefile_10M b/dunnart-chipseq/Snakefile_10M
similarity index 100%
rename from dunnart/Snakefile_10M
rename to dunnart-chipseq/Snakefile_10M
diff --git a/dunnart/configs/.multiqc_config.yaml b/dunnart-chipseq/configs/.multiqc_config.yaml
similarity index 100%
rename from dunnart/configs/.multiqc_config.yaml
rename to dunnart-chipseq/configs/.multiqc_config.yaml
diff --git a/dunnart/configs/SRR.txt b/dunnart-chipseq/configs/SRR.txt
similarity index 100%
rename from dunnart/configs/SRR.txt
rename to dunnart-chipseq/configs/SRR.txt
diff --git a/dunnart/configs/cluster.json b/dunnart-chipseq/configs/cluster.json
similarity index 100%
rename from dunnart/configs/cluster.json
rename to dunnart-chipseq/configs/cluster.json
diff --git a/dunnart/configs/config.yaml b/dunnart-chipseq/configs/config.yaml
similarity index 100%
rename from dunnart/configs/config.yaml
rename to dunnart-chipseq/configs/config.yaml
diff --git a/dunnart/scripts/.DS_Store b/dunnart-chipseq/scripts/.DS_Store
similarity index 100%
rename from dunnart/scripts/.DS_Store
rename to dunnart-chipseq/scripts/.DS_Store
diff --git a/dunnart/scripts/GC_CpG_plots.R b/dunnart-chipseq/scripts/GC_CpG_plots.R
similarity index 99%
rename from dunnart/scripts/GC_CpG_plots.R
rename to dunnart-chipseq/scripts/GC_CpG_plots.R
index 418a54f6c50626597395888d8fbce0756810664c..8bdf5100091452139c9e765a7813c101402436bb 100644
--- a/dunnart/scripts/GC_CpG_plots.R
+++ b/dunnart-chipseq/scripts/GC_CpG_plots.R
@@ -1,5 +1,6 @@
# GC content and CpG % plots
+# Purpose
library(data.table)
library(tidyverse)
library(ggridges)
diff --git a/dunnart/scripts/GO_plots.R b/dunnart-chipseq/scripts/GO_plots.R
similarity index 100%
rename from dunnart/scripts/GO_plots.R
rename to dunnart-chipseq/scripts/GO_plots.R
diff --git a/dunnart/scripts/array_wrapper.slurm.sh b/dunnart-chipseq/scripts/array_wrapper.slurm.sh
similarity index 100%
rename from dunnart/scripts/array_wrapper.slurm.sh
rename to dunnart-chipseq/scripts/array_wrapper.slurm.sh
diff --git a/dunnart/scripts/count_peaks.py b/dunnart-chipseq/scripts/count_peaks.py
similarity index 100%
rename from dunnart/scripts/count_peaks.py
rename to dunnart-chipseq/scripts/count_peaks.py
diff --git a/dunnart/scripts/encode_frip.py b/dunnart-chipseq/scripts/encode_frip.py
similarity index 100%
rename from dunnart/scripts/encode_frip.py
rename to dunnart-chipseq/scripts/encode_frip.py
diff --git a/dunnart/scripts/genes.peaks_perScaffold.R b/dunnart-chipseq/scripts/genes.peaks_perScaffold.R
similarity index 100%
rename from dunnart/scripts/genes.peaks_perScaffold.R
rename to dunnart-chipseq/scripts/genes.peaks_perScaffold.R
diff --git a/dunnart/scripts/genomicRegionsPlot.R b/dunnart-chipseq/scripts/genomicRegionsPlot.R
similarity index 100%
rename from dunnart/scripts/genomicRegionsPlot.R
rename to dunnart-chipseq/scripts/genomicRegionsPlot.R
diff --git a/dunnart/scripts/homerAnnot.sh b/dunnart-chipseq/scripts/homerAnnot.sh
similarity index 100%
rename from dunnart/scripts/homerAnnot.sh
rename to dunnart-chipseq/scripts/homerAnnot.sh
diff --git a/dunnart/scripts/homerMotifEnrich_plot.R b/dunnart-chipseq/scripts/homerMotifEnrich_plot.R
similarity index 100%
rename from dunnart/scripts/homerMotifEnrich_plot.R
rename to dunnart-chipseq/scripts/homerMotifEnrich_plot.R
diff --git a/dunnart/scripts/homer_motifEnrich.sh b/dunnart-chipseq/scripts/homer_motifEnrich.sh
similarity index 100%
rename from dunnart/scripts/homer_motifEnrich.sh
rename to dunnart-chipseq/scripts/homer_motifEnrich.sh
diff --git a/dunnart/scripts/overlap_dunnart_peaks_with_ARs.sh b/dunnart-chipseq/scripts/overlap_dunnart_peaks_with_ARs.sh
similarity index 100%
rename from dunnart/scripts/overlap_dunnart_peaks_with_ARs.sh
rename to dunnart-chipseq/scripts/overlap_dunnart_peaks_with_ARs.sh
diff --git a/dunnart/scripts/overlap_peaks.py b/dunnart-chipseq/scripts/overlap_peaks.py
similarity index 100%
rename from dunnart/scripts/overlap_peaks.py
rename to dunnart-chipseq/scripts/overlap_peaks.py
diff --git a/dunnart/scripts/peakAnno.R b/dunnart-chipseq/scripts/peakAnno.R
similarity index 100%
rename from dunnart/scripts/peakAnno.R
rename to dunnart-chipseq/scripts/peakAnno.R
diff --git a/dunnart/scripts/peakFeatures.R b/dunnart-chipseq/scripts/peakFeatures.R
similarity index 100%
rename from dunnart/scripts/peakFeatures.R
rename to dunnart-chipseq/scripts/peakFeatures.R
diff --git a/dunnart/scripts/subsample.sh b/dunnart-chipseq/scripts/subsample.sh
similarity index 100%
rename from dunnart/scripts/subsample.sh
rename to dunnart-chipseq/scripts/subsample.sh
diff --git a/dunnart/scripts/trimfastq.py b/dunnart-chipseq/scripts/trimfastq.py
similarity index 100%
rename from dunnart/scripts/trimfastq.py
rename to dunnart-chipseq/scripts/trimfastq.py
diff --git a/dunnart/scripts/twars_in_dunnart_peaks_hyperTest.R b/dunnart-chipseq/scripts/twars_in_dunnart_peaks_hyperTest.R
similarity index 100%
rename from dunnart/scripts/twars_in_dunnart_peaks_hyperTest.R
rename to dunnart-chipseq/scripts/twars_in_dunnart_peaks_hyperTest.R
diff --git a/dunnart/scripts/convergentTFBS_enrichment.R b/dunnart/scripts/convergentTFBS_enrichment.R
deleted file mode 100755
index d5633b5adc93cc498297e4d0722bd72f508c2aee..0000000000000000000000000000000000000000
--- a/dunnart/scripts/convergentTFBS_enrichment.R
+++ /dev/null
@@ -1,168 +0,0 @@
-
-## Author: Davide Vespasiani 2020
-
-library(data.table);library(magrittr);library(dplyr)
-library(tidyr);library(openxlsx) ## this is for exporting tables in excel format
-library(wesanderson);library(RColorBrewer); library(viridis);library(viridisLite)## these are just for colors
-library(ggthemes);library(ggplot2);library(ggpubr)
-library(ggrepel)
-library(readxl)
-
-
-numb_threads=getDTthreads()
-threads=setDTthreads(numb_threads-1)
-
-setwd('/Users/lauracook/OneDrive - The University of Melbourne/PhD (2018-2021)/5-TFBS/4-Results/1-BioMotif/')
-
-plot_dir='~/Desktop'
-table_dir='~/Desktop/'
-
-input_file <- fread("motifs2.csv", sep=",", header=TRUE)
-
-## these lines count the number of twars per condition (i.e. lost/gained/conserved) in each cluster
-## this is done with data.table package (if you dont know and you'll need R my adise is to look for it, it's very nice)
-## in any case when you see object=object[,colname:=something] it basically creates a column (colname) with entries corresponding on the arguments on the right
-## or if you see object=object[,c('colname1,'colname2'...)], it subset the objects retaining only the columns specified
-input_file_counts=copy(input_file)
-input_file_counts=input_file_counts[,c('twar','gain.lost','vierstra_cluster_no.','vierstra_cluster_name')] %>%
- unique() ## ps: if you have a twar that disrupts the motif recognised by >1 tf belonging to the same cluster calling unique here will remove this duplicate and count it only once
-input_file_counts=input_file_counts[,tfs_in_cluster_percondition:=.N,by=.(vierstra_cluster_no.,gain.lost)][ ## this means count all rows (i.e. .N) by= factor level in specified column
- ,totTFs_percondition:=.N,by=.(gain.lost)
- ][,tfs_not_cluster_percondition:=totTFs_percondition-tfs_in_cluster_percondition] ## row-wise subtraction
-
-## this function returns you a simplified version of the df subsetting it for the specified condition
-simplify_table=function(x,condition){
- df=copy(x)[gain.lost%in%condition][
- ,c('vierstra_cluster_no.','vierstra_cluster_name','tfs_in_cluster_percondition','tfs_not_cluster_percondition')
- ] %>% unique()## this unique here simplifies the resulting table
-}
-
-input_file_counts_altered=simplify_table(input_file_counts,'Altered')
-input_file_counts_lost=simplify_table(input_file_counts,'Lost')
-input_file_counts_conserved=simplify_table(input_file_counts,'Conserved')
-
-concatenate_df=function(x){
- bgkr=input_file_counts_conserved
- test=copy(x)
- ## this line is an inner join, so it returns all rows of test where there is a matching value in bkgr for rows of the two columns specified in 'on' argument
- ## i.e. it returns the clusters in the test set that are also in the bkgr set so that u can create the matrix for fisher test
- test=test[bgkr,on=c('vierstra_cluster_no.','vierstra_cluster_name'),nomatch=0]%>%
- setnames(old=c('tfs_in_cluster_percondition','tfs_not_cluster_percondition','i.tfs_in_cluster_percondition','i.tfs_not_cluster_percondition'),
- new=c('test_in_cluster','test_not_cluster','bkgr_in_cluster','bkgr_not_cluster'))
-}
-
-input_altered_vs_conserved=concatenate_df(input_file_counts_altered)
-
-input_gained_vs_conserved=concatenate_df(input_file_counts_gained)
-input_lost_vs_conserved=concatenate_df(input_file_counts_lost)
-
-## this function computes the fisher.exact pvalues and fdr corrects them
-fisher_pvalues=function(x){
- pvals=copy(x)
- pvals=pvals[,c('vierstra_cluster_no.','vierstra_cluster_name'):=NULL]
- pvals=apply(pvals, 1,
- function(y) {
- tbl <- matrix(as.numeric(y), ncol=2, byrow=T)
- fisher.test(tbl)$p.value
- }) ## this function applies to every row in your df. for each row it creates the 2x2 matrix and perform fisher test and returns just the p.value as vector of characters
- ## ps if you are not sure how it works/dont believe me (i would understand it) just run this:
- ## pvals=copy(your_input); pvals=pvals[,c(1:2):=NULL][1,] take first row only and then matrix(as.numeric(pvals), ncol=2, byrow=T). you'll see how it makes the 2x2 table
-
- pvalues_table=data.table(pval=pvals) ## then this converts the list of pvalues into a column (orders are maintained, so the first pval refers to the fisrt row in the input dataframe and so on)
- pvalues_table=pvalues_table[
- ,adj_p:=p.adjust(pval,method = 'fdr')][ ## this creates another column with the adj_pvalues
- ,log10_p_adjust:=-log10(adj_p)
- ][
- ,significant_score:=ifelse(`adj_p`<=0.0001,'****',
- ifelse(`adj_p`>0.0001 &`adj_p`<=0.001,'***',
- ifelse(`adj_p`>0.001 & `adj_p`<=0.01,'**',
- ifelse(`adj_p`>0.01 & `adj_p`<=0.05,'*',' '))))
- ] ## this is just for quick visualisation/subsecting of only the significant ones
-
- return(pvalues_table)
-}
-
-input_altered_vs_conserved_pvals=fisher_pvalues(input_altered_vs_conserved)
-
-input_gained_vs_conserved_pvals=fisher_pvalues(input_gained_vs_conserved)
-input_lost_vs_conserved_pvals=fisher_pvalues(input_lost_vs_conserved)
-
-## now it creates final df with all columns you need
-altered_vs_conserved=cbind(input_altered_vs_conserved,input_altered_vs_conserved_pvals)
-
-gained_vs_conserved=cbind(input_gained_vs_conserved,input_gained_vs_conserved_pvals)
-lost_vs_conserved=cbind(input_lost_vs_conserved,input_lost_vs_conserved_pvals)
-
-## this computes fold enrichment of the number of twars lost/gained for each cluster over that of conserved ones for the same cluster
-## ps this is the way i have been calculating the fold enrichmnent(i.e. the ratio of your test set/bkgr set in the cluster over the mean of this ratio across all clusters) but you could change it
-fold_enrichment=function(x,group){
- df=copy(x)
- df=df[
- ,group:=group ## ps: i have created here a column that takes values specified in group argument (i.e. gained/lost) because this allows me at the end to combine the 2 df and use a single function to plot them together (in separate facets) -see below
- ][,ratio_twar_lostgain_cluster:=test_in_cluster/bkgr_in_cluster
- ][,mean_ratio:=mean(ratio_twar_lostgain_cluster)
- ][,log2_fold_enrichment:=log2(ratio_twar_lostgain_cluster/mean_ratio)
- ][,log10_numb_twars_incluster:=log10(test_in_cluster)
- ][,c('vierstra_cluster_no.','vierstra_cluster_name','log2_fold_enrichment','pval','adj_p',
- 'significant_score','log10_p_adjust','log10_numb_twars_incluster','group')
- ]%>% setorderv('log10_p_adjust',-1)
-}
-
-altered_vs_conserved_final=fold_enrichment(altered_vs_conserved,'Altered')
-
-gained_vs_conserved_final=fold_enrichment(gained_vs_conserved,'Gained')
-lost_vs_conserved_final=fold_enrichment(lost_vs_conserved,'Lost')
-
-## here i make a single dt
-final_table=rbind(gained_vs_conserved_final,lost_vs_conserved_final)
-
-
-final_table=rbind(lost_vs_conserved_final)
-
-
-## make volcano plot
-tf_enrich_plot=function(x){
- df=copy(x)[,'Log10 total TFs per Cluster':=log10_numb_twars_incluster]
- gradient=scale_colour_viridis(aes(`Log10 total TFs per cluster`),option="inferno",discrete = F)
- #text=ifelse(!df$significant_score%in%' ',df$vierstra_cluster_name,'') ## this wont report in the plot the name of the clusters that are not significantly enriched/depleted
-
- ggplot(df,aes(x=log2_fold_enrichment,log10_p_adjust,label = text, col=log10_numb_twars_incluster))+
- geom_point(size=2)+
- geom_vline(xintercept=0, linetype="dashed", color = "black",size=0.2)+
- geom_text_repel(size = 5,color='black',
- box.padding = unit(0.5, "lines"),
- point.padding = unit(0.5, "lines")
- )+
- gradient+
- xlab('\n Log2 fold enrichment \n')+
- ylab('-Log10 (P)')+
- xlim(-4,4)+
- facet_wrap(group~.,ncol = 2)+ ## so this is what i was saying above: the group column allows now to split the plots into 2 facets
- theme(strip.text.x = element_text(),
- strip.text.y = element_text(hjust = 0.5),
- strip.background = element_rect(color = 'black', linetype = 'solid'),
- strip.background.y = element_blank(),
- strip.background.x =element_blank(),
- panel.spacing=unit(1, "lines"),
- panel.background =element_rect(fill = 'white', colour = 'black',size=1),
- panel.grid.minor = element_blank(),
- panel.grid.major = element_blank(),
- legend.position = "bottom",
- legend.key = element_rect(fill = "white", colour = "black"),
- axis.line = element_blank())
-}
-
-
-pdf(paste(plot_dir,'TFBS_enrichment_fisher_test_volcano.pdf',sep=''),width = 10,height=6)
-tf_enrich_plot(final_table)
-dev.off()
-
-## This code below produces an excel file with gained/lost enrichment results in two ≠sheets
-
-excel_table=copy(final_table)
-excel_table=split(excel_table,as.factor(excel_table$group)) %>%lapply(function(y)y=y[
- ,c('group','vierstra_cluster_no.','vierstra_cluster_name','log2_fold_enrichment','log10_numb_twars_incluster','pval','adj_p','log10_p_adjust','significant_score')]%>%
- unique())
-names(excel_table)=c('altered') ## name of the sheets
-
-write.xlsx(excel_table,paste(table_dir,'Table_twars_fisher_pvalues.xlsx',sep=''))
\ No newline at end of file
diff --git a/mouse/.DS_Store b/mouse-chipseq/.DS_Store
similarity index 100%
rename from mouse/.DS_Store
rename to mouse-chipseq/.DS_Store
diff --git a/mouse/README.md b/mouse-chipseq/README.md
similarity index 100%
rename from mouse/README.md
rename to mouse-chipseq/README.md
diff --git a/mouse/Snakefile1_H3K4me3 b/mouse-chipseq/Snakefile1_H3K4me3
similarity index 100%
rename from mouse/Snakefile1_H3K4me3
rename to mouse-chipseq/Snakefile1_H3K4me3
diff --git a/mouse/Snakefile_H3K27ac b/mouse-chipseq/Snakefile_H3K27ac
similarity index 100%
rename from mouse/Snakefile_H3K27ac
rename to mouse-chipseq/Snakefile_H3K27ac
diff --git a/mouse/Snakefile_H3K4me3 b/mouse-chipseq/Snakefile_H3K4me3
similarity index 100%
rename from mouse/Snakefile_H3K4me3
rename to mouse-chipseq/Snakefile_H3K4me3
diff --git a/mouse/configs/.multiqc_config.yaml b/mouse-chipseq/configs/.multiqc_config.yaml
similarity index 100%
rename from mouse/configs/.multiqc_config.yaml
rename to mouse-chipseq/configs/.multiqc_config.yaml
diff --git a/mouse/configs/SRR_H3K27ac.txt b/mouse-chipseq/configs/SRR_H3K27ac.txt
similarity index 100%
rename from mouse/configs/SRR_H3K27ac.txt
rename to mouse-chipseq/configs/SRR_H3K27ac.txt
diff --git a/mouse/configs/SRR_H3K4me3.txt b/mouse-chipseq/configs/SRR_H3K4me3.txt
similarity index 100%
rename from mouse/configs/SRR_H3K4me3.txt
rename to mouse-chipseq/configs/SRR_H3K4me3.txt
diff --git a/mouse/configs/cluster.json b/mouse-chipseq/configs/cluster.json
similarity index 100%
rename from mouse/configs/cluster.json
rename to mouse-chipseq/configs/cluster.json
diff --git a/mouse/configs/config_H3K27ac.yaml b/mouse-chipseq/configs/config_H3K27ac.yaml
similarity index 100%
rename from mouse/configs/config_H3K27ac.yaml
rename to mouse-chipseq/configs/config_H3K27ac.yaml
diff --git a/mouse/configs/config_H3K4me3.yaml b/mouse-chipseq/configs/config_H3K4me3.yaml
similarity index 100%
rename from mouse/configs/config_H3K4me3.yaml
rename to mouse-chipseq/configs/config_H3K4me3.yaml
diff --git a/mouse/envs/chip_environment.yml b/mouse-chipseq/envs/chip_environment.yml
similarity index 100%
rename from mouse/envs/chip_environment.yml
rename to mouse-chipseq/envs/chip_environment.yml
diff --git a/mouse/scripts/count_peaks.py b/mouse-chipseq/scripts/count_peaks.py
similarity index 100%
rename from mouse/scripts/count_peaks.py
rename to mouse-chipseq/scripts/count_peaks.py
diff --git a/mouse/scripts/encode_frip.py b/mouse-chipseq/scripts/encode_frip.py
similarity index 100%
rename from mouse/scripts/encode_frip.py
rename to mouse-chipseq/scripts/encode_frip.py
diff --git a/mouse/scripts/overlap_peaks.py b/mouse-chipseq/scripts/overlap_peaks.py
similarity index 100%
rename from mouse/scripts/overlap_peaks.py
rename to mouse-chipseq/scripts/overlap_peaks.py
diff --git a/mouse/scripts/subsample.sh b/mouse-chipseq/scripts/subsample.sh
similarity index 100%
rename from mouse/scripts/subsample.sh
rename to mouse-chipseq/scripts/subsample.sh
diff --git a/dunnart/scripts/create_jobs.sh b/whole-genome-alignment/create_jobs.sh
similarity index 88%
rename from dunnart/scripts/create_jobs.sh
rename to whole-genome-alignment/create_jobs.sh
index 9329754edea39e4e3df6bbced86ae42c102aa6d5..303ea68ef52666e5d4c0beed0b65db58949f386b 100755
--- a/dunnart/scripts/create_jobs.sh
+++ b/whole-genome-alignment/create_jobs.sh
@@ -1,6 +1,7 @@
#!/usr/bin/env bash
-## This script loops through all files in a directory
+## Author: Laura E Cook, University of Melbourne
+## Purpose: This script loops through all files in a directory
## These commands are then used in a slurm array script to run jobs in parallel
TRA=($(for file in *.maf; do echo $file |cut -d "." -f 1-2;done)) # change this to whatever your file prefix is
@@ -14,7 +15,6 @@ do
# generate lastz commands
echo 'lastz_32 /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/mm10.fa[multiple] /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/smiCra1_RM/'${tr}.fa 'H=2000 K=2400 L=3000 Y=3400 --scores=/data/projects/punim0586/lecook/chipseq-pipeline/cross_species/bin/GenomeAlignmentTools/HoxD55.q --format=maf > /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/maf/'${tr}_mm10.smiCra1.maf
-
# generate convert maf to axt format commands
echo 'maf-convert psl '${tr}.maf' > '${tr}.psl