From d331db1734e0ec5e20388d27e53e8dfecafa9a61 Mon Sep 17 00:00:00 2001
From: Emily Chen <echen5@crcfe01.crc.nd.edu>
Date: Thu, 14 Oct 2021 08:49:06 -0400
Subject: [PATCH 1/2] This is the script for our final project (Emily Chen and
 Sanjna Chetan).

---
 .../ref_sequences/finalscript.sh              | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 bioinformaticsProject/ref_sequences/finalscript.sh

diff --git a/bioinformaticsProject/ref_sequences/finalscript.sh b/bioinformaticsProject/ref_sequences/finalscript.sh
new file mode 100644
index 0000000..faa1ba3
--- /dev/null
+++ b/bioinformaticsProject/ref_sequences/finalscript.sh
@@ -0,0 +1,34 @@
+#This script is for the final project of Biocomputing
+#Usage: bash finalscript.sh
+
+#STEP 1a: combine all hsp files in ref_sequences into a total file called HSP_file.fasta
+cat hsp*.fasta >> HSP_file.fasta
+#STEP 1b: combine all mcrA files in ref_sequences into a total file called mcrA_file.fasta
+cat mcrA*.fasta >> mcrA_file.fasta
+
+#STEP 2a: Search for HSP in each proteome
+./muscle -in HSP_file.fasta -out HSP_Muscle.afasta
+#STEP 2b: Search for mcrA in each proteome
+./muscle -in mcrA_file.fasta -out MCRA_Muscle.afasta
+
+#STEP 3a: Build hmm profile
+~/Private/bin/bin/hmmbuild HSP_hmm.txt HSP_Muscle.afasta
+#STEP 3b: Build mcrA profile
+~/Private/bin/bin/hmmbuild MCRA_hmm.txt MCRA_Muscle.afasta
+
+#STEP 4: Count matches for HSP and MCRA (against  each proteome)
+for number in proteome*.fasta
+do
+name=$(echo $number | cut -d_ -f 2| cut -d. -f 1)
+~/Private/bin/bin/hmmsearch --tblout match${name}resultsHSP.search HSP_hmm.txt $number
+~/Private/bin/bin/hmmsearch --tblout match${name}resultsMCRA.search MCRA_hmm.txt $number
+done
+
+#STEP 5: Make table with proteome number in first column, number of HSP matches in second column, and number of MCRA matches in third column
+for i in {01..50}
+do
+coltwo=$(cat match"$i"resultsHSP.search | grep -v "#" | wc -l)
+colthree=$(cat match"$i"resultsMCRA.search | grep -v "#" | wc -l)
+echo "Proteome $i   $coltwo"   "$colthree"
+done
+

From 9d798f88996812e22e5b7b0a81112b48395e54c2 Mon Sep 17 00:00:00 2001
From: Emily Chen <echen5@crcfe01.crc.nd.edu>
Date: Thu, 14 Oct 2021 08:59:11 -0400
Subject: [PATCH 2/2] This is the text file of final candidates that are pH
 resistant methanogens.

---
 .../ref_sequences/finalcandidates.txt             | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 bioinformaticsProject/ref_sequences/finalcandidates.txt

diff --git a/bioinformaticsProject/ref_sequences/finalcandidates.txt b/bioinformaticsProject/ref_sequences/finalcandidates.txt
new file mode 100644
index 0000000..784dad6
--- /dev/null
+++ b/bioinformaticsProject/ref_sequences/finalcandidates.txt
@@ -0,0 +1,15 @@
+Proteome 03 = 3 HSP, 1 MCRA
+Proteome 05 = 2 HSP, 1 MCRA
+Proteome 07 = 2 HSP, 1 MCRA
+Proteome 15 = 1 HSP, 1 MCRA
+Proteome 16 = 1 HSP, 1 MCRA
+Proteome 19 = 1 HSP, 2 MCRA
+Proteome 23 = 2 HSP, 2 MCRA
+Proteome 24 = 2 HSP, 1 MCRA
+Proteome 38 = 1 HSP, 1 MCRA
+Proteome 39 = 1 HSP, 1 MCRA
+Proteome 42 = 3 HSP, 1 MCRA
+Proteome 44 = 1 HSP, 1 MCRA
+Proteome 45 = 3 HSP, 1 MCRA
+Proteome 48 = 1 HSP, 1 MCRA
+Proteome 50 = 3 HSP, 1 MCRA