Bioinformatics_Project_Culbert_Arnold_Submission

bashproject.sh

@@ -0,0 +1,47 @@
+#This script can align reference proteome files that contain two specific genes within an entire proteome sequence
+#This script is a model for alignment and can search for matches
+#Matches will determine whether or not the proteomes carry both specific gene sets 
+
+#usage: bash bashproject.sh
+
+#make a hsp70ref file and mcrAref file each containting all the reference sequences
+cat ref_sequences/hsp70gene_*.fasta > hsp70ref
+cat ref_sequences/mcrAgene_*.fasta > mcrAref
+
+#align all the reference sequences for the two genes
+../tools/muscle -in hsp70ref -out hsp70musclealign
+../tools/muscle -in mcrAref -out mcrAmusclealign
+
+#generate two HMM profiles for hsp70 and mcrA genes
+../tools/hmmbuild --amino hsp70HMMbuild hsp70musclealign
+../tools/hmmbuild --amino mcrAHMMbuild mcrAmusclealign
+
+#search each proteome for matches
+cd proteomes
+for file in *.fasta
+do
+../../tools/hmmsearch --tblout hsp70_$file ../hsp70HMMbuild $file
+../../tools/hmmsearch --tblout mcrA_$file ../mcrAHMMbuild $file
+done
+
+#search each result file
+#print each proteome name and matches for each gene
+
+echo "proteome_number, hsp70_matches, mcrA_matches" > ../matches.txt
+
+for file in proteome_*.fasta
+do
+hsp70_match=$(cat hsp70_$file | grep -v '#' | wc -l)
+mcrA_match=$(cat mcrA_$file | grep -v '#' | wc -l)
+echo "$file, $hsp70_match, $mcrA_match" | sed 's/.fasta//g' >> ../matches.txt
+done
+
+cd ..
+
+#when choosing best candidates, we elimated proteomes that did not have matches for either hsp70 or mcrA
+#then the rankings of best candidates were determined by sorting the highest matches of hsp70
+#we determined that one mcrA was sufficient for a candidate and that more hsp70 matches was a more desirable candidate
+
+echo "Best candidate proteomes listed and sorted by greatest number of matches" > candidate_results.txt
+cat matches.txt | grep -v "proteome_number" | grep -v " 0" | sort -k 2nr | cut -d , -f 1 >> candidate_results.txt
+

candidate_results.txt

@@ -0,0 +1,16 @@
+Best candidate proteomes listed and sorted by greatest number of matches
+proteome_03
+proteome_42
+proteome_45
+proteome_50
+proteome_05
+proteome_07
+proteome_23
+proteome_24
+proteome_15
+proteome_16
+proteome_19
+proteome_38
+proteome_39
+proteome_44
+proteome_48

matches.txt

@@ -0,0 +1,51 @@
+proteome_number, hsp70_matches, mcrA_matches
+proteome_01, 4, 0
+proteome_02, 2, 0
+proteome_03, 3, 1
+proteome_04, 4, 0
+proteome_05, 2, 1
+proteome_06, 0, 0
+proteome_07, 2, 1
+proteome_08, 5, 0
+proteome_09, 1, 0
+proteome_10, 3, 0
+proteome_11, 6, 0
+proteome_12, 6, 0
+proteome_13, 3, 0
+proteome_14, 2, 0
+proteome_15, 1, 1
+proteome_16, 1, 1
+proteome_17, 4, 0
+proteome_18, 8, 0
+proteome_19, 1, 2
+proteome_20, 3, 0
+proteome_21, 5, 0
+proteome_22, 9, 0
+proteome_23, 2, 2
+proteome_24, 2, 1
+proteome_25, 5, 0
+proteome_26, 1, 0
+proteome_27, 1, 0
+proteome_28, 1, 0
+proteome_29, 0, 1
+proteome_30, 1, 0
+proteome_31, 7, 0
+proteome_32, 4, 0
+proteome_33, 0, 0
+proteome_34, 2, 0
+proteome_35, 1, 0
+proteome_36, 3, 0
+proteome_37, 1, 0
+proteome_38, 1, 1
+proteome_39, 1, 1
+proteome_40, 2, 0
+proteome_41, 1, 0
+proteome_42, 3, 1
+proteome_43, 3, 0
+proteome_44, 1, 1
+proteome_45, 3, 1
+proteome_46, 2, 0
+proteome_47, 1, 0
+proteome_48, 1, 1
+proteome_49, 3, 0
+proteome_50, 3, 1