Guan_bioinfoProj

final_result.txt

@@ -0,0 +1,51 @@
+proteomes 	 num of mcrA match 	 num of hsp70 match
+proteome_01 	 0 	 4
+proteome_02 	 0 	 2
+proteome_03 	 1 	 3
+proteome_04 	 0 	 4
+proteome_05 	 1 	 2
+proteome_06 	 0 	 0
+proteome_07 	 1 	 2
+proteome_08 	 0 	 5
+proteome_09 	 0 	 1
+proteome_10 	 0 	 3
+proteome_11 	 0 	 6
+proteome_12 	 0 	 6
+proteome_13 	 0 	 3
+proteome_14 	 0 	 2
+proteome_15 	 1 	 1
+proteome_16 	 1 	 1
+proteome_17 	 0 	 4
+proteome_18 	 0 	 8
+proteome_19 	 2 	 1
+proteome_20 	 0 	 3
+proteome_21 	 0 	 0
+proteome_22 	 0 	 0
+proteome_23 	 2 	 2
+proteome_24 	 1 	 2
+proteome_25 	 0 	 0
+proteome_26 	 0 	 1
+proteome_27 	 0 	 1
+proteome_28 	 0 	 1
+proteome_29 	 1 	 0
+proteome_30 	 0 	 1
+proteome_31 	 0 	 7
+proteome_32 	 0 	 4
+proteome_33 	 0 	 0
+proteome_34 	 0 	 2
+proteome_35 	 0 	 1
+proteome_36 	 0 	 3
+proteome_37 	 0 	 1
+proteome_38 	 1 	 1
+proteome_39 	 1 	 1
+proteome_40 	 0 	 2
+proteome_41 	 0 	 1
+proteome_42 	 1 	 3
+proteome_43 	 0 	 3
+proteome_44 	 1 	 1
+proteome_45 	 1 	 3
+proteome_46 	 0 	 2
+proteome_47 	 0 	 1
+proteome_48 	 1 	 1
+proteome_49 	 0 	 3
+proteome_50 	 1 	 3

orthogonal.sh

@@ -0,0 +1,35 @@
+# Identifying candidate pH-resistant methanogenic Archaea
+# Usage: bash orthogonal.sh $1 $2 $3 $4
+# $1 and $2 are the names of references gene, $3 is the name of genomes to be search, $4 is the result file.
+# Exp:  bash orthogonal.sh mcrA hsp70 proteome final_result.txt
+
+cat ref_sequences/$1* > tot_$1.fasta
+cat ref_sequences/$2* > tot_$2.fasta
+
+
+# Combine and align reference sequences
+~/Private/BioComputing2022/tools/muscle -in tot_$1.fasta -out $1_aligned.fasta
+~/Private/BioComputing2022/tools/muscle -in tot_$2.fasta -out $2_aligned.fasta
+
+# Build HMM profiles
+~/Private/BioComputing2022/tools/hmmbuild $1.hmm $1_aligned.fasta
+~/Private/BioComputing2022/tools/hmmbuild $2.hmm $2_aligned.fasta
+
+# Write headers for the final result file
+echo -e "proteomes" "\t" "num of $1 match" "\t" "num of $2 match" > $4
+
+for i in {01..50}
+do
+# Search ref sequences in proteomes, output in repo "before merged"
+~/Private/BioComputing2022/tools/hmmsearch --tblout befMerged/$1_match_$i $1.hmm proteomes/$3_$i.fasta
+~/Private/BioComputing2022/tools/hmmsearch --tblout befMerged/$2_match_$i $2.hmm proteomes/$3_$i.fasta
+
+# Count the matches
+numA=$(cat befMerged/$1_match_$i | grep -c WP)
+numB=$(cat befMerged/$2_match_$i | grep -c WP)
+
+# Output matches
+echo -e $3_$i "\t" $numA "\t" $numB >> $4
+
+done
+