Update SynetAdding-Diamond.sh

SynetAdding-Diamond.sh

@@ -1,12 +1,5 @@
 # !/bin/bash
-# declare an array called array and define 3 vales
-# Input files: *.bed/gff & *.pep of each species
-# Example: at.bed, at.pep
-# This is advanced version of SynNet, written by Tao
-# Starts from Rapsearch, data pretreatment, synteny detection, sort output 
-# Note the program path before use. ie, RAPsearch2 sara server: ../RAPsearch2/RAPSearch2.23_64bits/bin
-#	mary server: ./RAPSearch2.23_64bits/bin
-# You can change the filename in the Line129, to name your own network.
+
 
 #	Example:bash SynetAdding-Diamond.sh DiamondGenomesDB OUTPUT-name"
 
@@ -27,7 +20,7 @@ display_usage() {
         fi
 
 # check whether user had supplied -h or --help . If yes display usage
-        if [[ ( $# == "--help") ||  $# == "-h" ]]
+        if [[ ( $* == "--help") ||  $* == "-h" ]]
         then
                 display_usage
                 exit 0
@@ -37,11 +30,8 @@ display_usage() {
 #	Step_1: species list
 #########################
 
-#array=(xm tr pf on ol lo gm ga dr am tn pm)
-# Actually 36 species in total,  3 of them is not ok. Tni Sfo and Cca
-#array=(Tru Oni Ola Loc Cse Pre Dre Elu Ssa Nfu Ipu Lch Hbu Nbr Pny Xma Pfo Ame Cmi Spa Cva Nco Fhe Cha Lcr Ali Mze Pme Pla Sgr San Srh Kma ga gm pm)
-# Usage : bash synet-Diamond.sh $1(OUTPUT-NAME)
-#array=(ath tof osa lac hel)
+# The first array should includes old + new genomes
+# Do remember to include the new genomes in array
 
 array=(ath osa oth)
 addnew=(oth)
@@ -52,7 +42,6 @@ foldername=$(date +"AddGenomes"%Y%m%d_%H%M)
 mkdir "$foldername-$2"
 cd "$foldername-$2"
 
-#array=(tar)
 
 #############################################################
 #	Step_2: Lets's first generate database of each genome!
@@ -61,7 +50,7 @@ cd "$foldername-$2"
 for i in "${addnew[@]}";do
 echo make database for species_$i
 
-#../../Programs/RAPSearch2.23_64bits/bin/prerapsearch -d $i.pep -n $i.pep.db	
+
 diamond makedb --in ../$i.pep -d ../$ExistingPath/$i
 
 done
@@ -74,35 +63,19 @@ for i in "${array[@]}";do
 	for j in "${addnew[@]}";do
 
 	echo   blast "$i" against "$j" 
-#../../Programs/RAPSearch2.23_64bits/bin/rapsearch -q $i.pep -d $j.pep.db -o "$i"_"$j" -z 10 -b 0 -v 50 -t a -p f -a t
 
 # All against addnew ! Read the manual of Diamond! --max-target-seqs/-k 
 diamond blastp -q ../$i.pep -d ../$ExistingPath/$j -o "$i"_"$j" -p 10 --max-hsps 1 -k 6
 # addnew against All !
 diamond blastp -q ../$j.pep -d ../$ExistingPath/$i -o "$j"_"$i" -p 10 --max-hsps 1 -k 6
 
-
-# ../programs/RAPSearch2.23_64bits/bin/rapsearch
-
-
 
 	done
 done
 
-####################################################################
-#	Step_4: Now we need a module to alter the output and make it neat.
-####################################################################
-#	for f in *.m8; do sed '/#/d;s/\r//g' $f > $f.homo
-#.rd means remove duplicates
-#	awk '!a[$1$2]++' $f.homo > $f.rd
-# keep the top 6 or another number of hits!
-#	awk 'a[$1]++<6' $f.rd > $f.fix
-#	done
-
-#	rm *.rd *.homo *.m8
 
 ###################################################################
-#	Step_5.1: Now we combine corresponding files to prepare .blast 
+#	Step_4: Now we combine corresponding files to prepare .blast 
 #   This step is for intraspecies synteny detection!
 ##################################################################
 
@@ -126,12 +99,10 @@ for i in "${array[@]}";do
 	done
 done
 
-	# for inter species starts here!
-	# but you have to be careful
-	# to avoid duplications 
+
 
 #######################################################################
-# 	Step_5.2  Another loop	
+# 	Step_4.2  Another loop	
 # 	This step is for interspecies synteny detection 
 # 	How to avoid duplicates! A-B is the same as B-A, so keep only one
 # 	use my small program
@@ -141,7 +112,6 @@ done
 #n=1
 
 
-
 function pwait() {
     while [ $(jobs -p | wc -l) -ge $1 ]; do
         sleep 1
@@ -169,7 +139,7 @@ wait
 done
 
 #################################
-#	Step_6: Now sort .collinearity files!
+#	Step_5: Now sort .collinearity files!
 #	We are almost there!
 #	Keep up!
 ##################################
@@ -186,17 +156,13 @@ sed '/#/d' 2 > 3
 # replace unwanted letters
 
 sed 's/.collinearity//g; s/e_value//g; s/ //g; s/:/b/g' 3 > 4
-# Pay attention to the following command, replace with the corrected gene names 
-
-# The following sed command is for the previous Gene IDs, you should mute it.
-# sed 's/ca__\([0-9]\+\)/ca\1ca/g;s/[a-z][a-z]__//g;s/\(p5_sc[0-9]\+.V1.gene[0-9]\+\)/el\1el/g;s/\(evm.TU.supercontig_[0-9]\+.[0-9]\+\)/cp\1cp/g;s/\(scaffold[0-9]\+\.[0-9]\+\)/ar\1ar/g;s/\(Scf[0-9]\+.g[0-9]\+\)/ug\1ug/g' 4| 
 
 awk '{print $1"\t"$5"\t"$2"\t"$3}' 4 >  $2
 # delete middle files 
 
 rm 1 2 3 4
 
 ################################
-#	step_7: now we have a SynNet	
+#	step_6: now we have a SynNet	
 ################################