added positive selection

7_positive-selection/10_meme_getResults.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+#get results for branches under selection according to hyphy absrel
+
+
+fileList="*output.txt"
+
+#outside of loop add file header
+echo "Hyphy MEME sites under episodic selection" > hyphy_meme_Results.txt
+echo "K. Castellano - 2024 January 8" >> hyphy_meme_Results.txt
+echo "------------------------------" >> hyphy_meme_Results.txt
+
+for file in ${fileList}
+do
+        prefix=$(echo ${file} | cut -d "_" -f 1)
+	echo ${prefix} >> hyphy_meme_Results.txt #print orthogroup ID
+	#this command below will print all lines after the string "###  For partition" which contain the sites under selection
+	sed -e '1,/### For partition/d' ${file} >> hyphy_meme_Results.txt
+	echo "" >> hyphy_meme_Results.txt #add empty line after each orthogroup in the output file to help make it clearer to read
+
+done

7_positive-selection/1_AGAT_filt.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+module load AGAT/v1.2.0
+
+agat_sp_keep_longest_isoform.pl -gff GCF_018143015.1_Lvar_3.0_genomic.gff \
+-out Lvariegatus_AGATfilt.gff 2>&1 | tee -a Lvariegatus_AGAT.log
+

7_positive-selection/2_OrthoFinder_MSA.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+#Run Orthofinder for Natural Selection Analysis
+#Kate Castellano
+
+#-f = path to fasta files for each species
+python3 /data/app/OrthoFinder/orthofinder.py -M msa -f ~/positive-selection/protein-files-urchinsOnly/

7_positive-selection/3_get_fasta_w_min_number.pl

@@ -0,0 +1,58 @@
+#!/usr/bin/perl
+#from Kevin Kocot
+#run by Kate Castellano
+
+use strict;
+use warnings;
+
+MAIN: {
+    my $indir = $ARGV[0] || usage();
+    my $outdir = $ARGV[1] || usage();
+    my $min  = $ARGV[2] || usage();
+    my $count = 0;
+
+    check_outdir($outdir);
+
+    opendir DIR, $indir or die "cannot open $indir:$!";
+    my @files = readdir DIR;
+    foreach my $f (@files) {
+        open IN, "$indir/$f" or die "cannot open $indir/$f:$!";
+        my $count = 0;
+        my $seqs = '';
+        my %species = ();
+        while (my $line = <IN>) {
+            $seqs .= $line;
+            next unless ($line =~ m/^>([^_]+)/);
+            my $sp = $1;
+            $count++ unless ($species{$sp});
+            $species{$sp}++;
+        }
+        write_seqs($outdir,$f,$seqs) if ($count == $min);
+    }
+}
+
+sub check_outdir {
+    my $outdir = shift;
+    if (-d $outdir) {
+        opendir OUTDIR, $outdir or die "cannot read $outdir:$!";
+        my @existing = grep {!/^\.\.?$/} readdir OUTDIR;
+        foreach my $e (@existing) {
+            warn "warning: $outdir exists and includes $e\n";
+        }
+    } else {
+        mkdir $outdir or die "cannot open $outdir";
+    }
+}
+
+sub write_seqs {
+    my $dir = shift;
+    my $file = shift;
+    my $seqs = shift;
+    open OUT, ">$dir/$file" or die "cannot open >$dir/$file:$!";
+    print OUT $seqs;
+    close OUT; 
+}
+
+sub usage {
+    die "usage: $0 INDIR OUTDIR MINIMUM_SEQS\n";    
+}

7_positive-selection/4_getCDS.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#Get Get CDS sequences for each orthogroup
+#Kate Castellano
+
+listFiles="*_headers.txt"
+cdsFile="/data/prj/urchin/red-urchin-genome/positive-selection/cds-files-urchinsOnly/AllSpecies.faa"
+
+for file in ${listFiles}
+do
+
+	prefix=$(echo ${file} | cut -d "_" -f 1,2)
+
+	seqtk subseq ${cdsFile} ${file} > ${prefix}_CDS.fa
+
+done

7_positive-selection/5_pal2nal.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+#this script will create phyllip format alignments for each orthogroup
+#the list.txt file contains the prefix for each file <orthogroup#>_1
+
+for i in `cat list.txt`
+do
+
+	/data/app/pal2nal.v14/pal2nal.pl ${i}.fa ${i}_CDS.fa -output paml -nomismatch -nogap -codontable 1 > ${i}_pal2nal.fa  2>&1 | tee -a pal2nal_log.txt
+
+done
+

7_positive-selection/6_editFiles.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+#edit pal2nal alignment files for hyphy
+
+#copy pal2nal files to this location
+#cp /data/prj/urchin/red-urchin-genome/positive-selection/protein-files-urchinsOnly/OrthoFinder/Results_Sep15/MultipleSequenceAlignments_AllSpecies/pal2nal/*.fa .
+
+
+fileList="*.fa"
+
+for file in ${fileList}
+do
+
+	prefix=$(echo ${file} | cut -d "." -f 1) 
+	sed '1d' ${file} > ${prefix}_edit.fa #remove first line which contains the number of aligned nucleotides
+
+	#add > in front of each header to turn it into a fasta file
+	sed -i 's/B/>B/' ${prefix}_edit.fa
+	sed -i 's/M/>M/' ${prefix}_edit.fa
+	sed -i 's/L/>L/' ${prefix}_edit.fa
+	sed -i 's/S/>S/' ${prefix}_edit.fa
+
+	rm ${file} #remove original pal2nal files we copied over to this location
+
+done

7_positive-selection/7_hyphy_absrel.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+#hyphy absrel
+
+
+module load hyphy/v2.5.58
+#ln -s /data/resources/app_modules/hyphy-2.5.58/res #only need to do this once; make symbolic link to batch files
+
+fileList="*.fa"
+treePath="/data/prj/urchin/red-urchin-genome/positive-selection/protein-files-urchinsOnly/OrthoFinder/Results_Sep15/Gene_Trees_edit/"
+
+for file in ${fileList}
+do
+
+        prefix=$(echo ${file} | cut -d "_" -f 1)
+	hyphy absrel --pvalue 0.05 --alignment ${file} --tree ${treePath}${prefix}_tree.txt --branches All >> ${prefix}_absrel_output.txt
+	#will ouput a .json file and the specificed .txt file
+
+done

7_positive-selection/8_absrel_getResults.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+#get results for branches under selection according to hyphy absrel
+
+
+fileList="*output.txt"
+
+#outside of loop add file header
+echo "Adaptive branch site random effects likelihood test Results - Urchins Only - Hyphy abSREL all branches" > hyphy_absrel_Results.txt
+echo "K. Castellano - 2024 January 4" >> hyphy_absrel_Results.txt
+echo "------------------------------------------------------------------------------------------------------" >> hyphy_absrel_Results.txt
+
+for file in ${fileList}
+do
+        prefix=$(echo ${file} | cut -d "_" -f 1)
+	echo ${prefix} >> hyphy_absrel_Results.txt #print orthogroup ID
+	#this command below will print all lines after the string "### Adaptive branch site random effects likelihood test" which contain the branches under selection
+	sed -e '1,/### Adaptive branch site random effects likelihood test/d' ${file} >> hyphy_absrel_Results.txt
+	echo "" >> hyphy_absrel_Results.txt #add empty line after each orthogroup in the output file to help make it clearer to read
+
+done
+
+sed -i '/tested./{N;s/\n$//}' hyphy_absrel_Results.txt #remove the empty line between the number of branches under selection and the lines with the p-value of the branches under selection; just makes it easier to read and see what data goes with which orthogroup

7_positive-selection/9_meme_hyphy.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+#run hyphy MEME on orthogroups that showed signatures of positive selection using hyphy absrel to identify sites under selection
+#K Castellano January 2024
+
+module load hyphy/v2.5.58
+
+treePath="/data/prj/urchin/red-urchin-genome/positive-selection/protein-files-urchinsOnly/OrthoFinder/Results_Sep15/Gene_Trees_edit/"
+
+for i in `cat meme_list.txt`
+do
+
+	hyphy meme --alignment ${i}_1_pal2nal_edit.fa --tree ${treePath}${i}_tree.txt >> ${i}_meme_output.txt
+
+done