Therese Reisch, Tara Neufell, Kevin Buck bash project - Bioinformatics

genemachine.sh

@@ -0,0 +1,49 @@
+#therese reisch, tara neufell, and kevin buck bash project :))
+#start in the bioinformaticsProject, all of this code is assuming that our TA has the same directory structure as we do
+#usage: bash genemachine.sh
+
+#put all of the mcrA reference files into one file and all of the hsp gene reference files into another file
+touch  ref_sequences/mcrAmaster.fasta
+for index in {01..18}
+	do cat ref_sequences/mcrAgene_$index.fasta >> ref_sequences/mcrAmaster.fasta
+done
+
+touch ref_sequences/hsp70master.fasta
+for index in {01..22}
+	do cat ref_sequences/hsp70gene_$index.fasta >> ref_sequences/hsp70master.fasta
+done
+
+#aligning reference files using muscle tool
+~/Private/biocomputing2022/tools/muscle -in ref_sequences/mcrAmaster.fasta -out ref_sequences/mcrAmaster.aligned
+~/Private/biocomputing2022/tools/muscle -in ref_sequences/hsp70master.fasta -out ref_sequences/hsp70master.aligned
+
+#build hidden markov model with hmmer tool
+~/Private/biocomputing2022/tools/hmmbuild ref_sequences/mcrAmaster.build ref_sequences/mcrAmaster.aligned
+~/Private/biocomputing2022/tools/hmmbuild ref_sequences/hsp70master.build ref_sequences/hsp70master.aligned
+
+#search proteome sequences for mcrA with hmmr search tool
+for index in {01..50}
+	do ~/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome$index.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_$index.fasta
+done
+
+#search proteome sequences for hsp70 with hmmr search tool
+for index in {01..50}
+        do ~/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome$index.hsp70search ref_sequences/hsp70master.build proteomes/proteome_$index.fasta
+done 
+
+#making the summary table with headers
+touch proteomecounttable.txt
+echo proteome_name, mcrA_count, hsp70_count >> proteomecounttable.txt
+
+#counting gene matches and appending them to summary table
+for index in {01..50}
+	do mcrAcount=$(grep -v -c "#" proteomes/proteome$index.mcrAsearch)
+	hsp70count=$(grep -v -c "#" proteomes/proteome$index.hsp70search)
+	echo "proteome_$index, $mcrAcount, $hsp70count" >> proteomecounttable.txt
+done
+
+#making the recommendation list after removing proteomes with no mcrA genes and then sorting from highest to lowest hsp70 genes
+touch recommendationslist.txt
+echo proteome_name, mcrA_count, hsp70_count >> recommendationslist.txt
+cat proteomecounttable.txt | grep -E ", [1|2]," | sort -t , -k 3 -n -r >> recommendationslist.txt
+

proteomecounttable.txt

@@ -0,0 +1,51 @@
+proteome_name, mcrA_count, hsp70_count
+proteome_01, 0, 4
+proteome_02, 0, 1
+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, 1
+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, 5
+proteome_22, 0, 9
+proteome_23, 2, 2
+proteome_24, 1, 2
+proteome_25, 0, 5
+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, 1
+proteome_35, 0, 1
+proteome_36, 0, 3
+proteome_37, 0, 1
+proteome_38, 1, 1
+proteome_39, 1, 1
+proteome_40, 0, 1
+proteome_41, 0, 1
+proteome_42, 1, 3
+proteome_43, 0, 3
+proteome_44, 1, 1
+proteome_45, 1, 3
+proteome_46, 0, 1
+proteome_47, 0, 1
+proteome_48, 1, 1
+proteome_49, 0, 3
+proteome_50, 1, 3

proteomes/proteome01.hsp70search

@@ -0,0 +1,17 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_013362005.1       -          hsp70master          -           1.2e-296  982.1  30.7  1.4e-296  982.0  30.7   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_013360607.1       -          hsp70master          -           4.8e-129  428.6   0.2    7e-129  428.0   0.2   1.1   1   0   0   1   1   1   1 molecular chaperone HscC 
+WP_013362571.1       -          hsp70master          -            3.9e-12   42.4   6.1   1.9e-11   40.1   6.1   2.1   1   1   0   1   1   1   1 rod shape-determining protein 
+WP_013360481.1       -          hsp70master          -            3.4e-09   32.7   2.2   6.5e-05   18.5   0.6   2.7   2   1   1   3   3   3   2 ethanolamine utilization protein EutJ 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_01.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome01.hsp70search ref_sequences/hsp70master.build proteomes/proteome_01.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome01.mcrAsearch

@@ -0,0 +1,13 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_01.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome01.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_01.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome02.hsp70search

@@ -0,0 +1,14 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_010867429.1       -          hsp70master          -             0.0068   11.4   6.5    0.0083   11.1   6.5   1.1   1   0   0   1   1   1   1 transcriptional regulator 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_02.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome02.hsp70search ref_sequences/hsp70master.build proteomes/proteome_02.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome02.mcrAsearch

@@ -0,0 +1,13 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_02.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome02.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_02.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome03.hsp70search

@@ -0,0 +1,16 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_048118742.1       -          hsp70master          -                  0 1101.6  23.8         0 1101.4  23.8   1.0   1   0   0   1   1   1   1 MULTISPECIES: molecular chaperone DnaK 
+WP_048116754.1       -          hsp70master          -             1e-109  365.1   8.9  3.6e-100  333.6   3.7   2.0   2   0   0   2   2   2   2 MULTISPECIES: hypothetical protein 
+WP_048116752.1       -          hsp70master          -           1.3e-106  355.0  13.6   1.6e-99  331.5   6.5   2.0   2   0   0   2   2   2   2 MULTISPECIES: Hsp70 family protein 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_03.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome03.hsp70search ref_sequences/hsp70master.build proteomes/proteome_03.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome03.mcrAsearch

@@ -0,0 +1,14 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_048120720.1       -          mcrAmaster           -                  0 1114.8   2.5         0 1114.6   2.5   1.0   1   0   0   1   1   1   1 MULTISPECIES: coenzyme-B sulfoethylthiotransferase subunit alpha 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_03.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome03.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_03.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome04.hsp70search

@@ -0,0 +1,17 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_055360419.1       -          hsp70master          -           6.6e-262  867.6  31.1  1.5e-232  770.6  25.5   2.0   1   1   1   2   2   2   2 molecular chaperone DnaK 
+WP_055360541.1       -          hsp70master          -           7.7e-157  520.5  14.3  6.4e-144  477.8  13.0   2.0   2   0   0   2   2   2   2 Fe-S protein assembly chaperone HscA 
+WP_055359523.1       -          hsp70master          -            2.4e-14   49.9   0.5   1.7e-13   47.0   0.0   2.3   3   0   0   3   3   3   1 MULTISPECIES: rod shape-determining protein 
+WP_055361642.1       -          hsp70master          -            7.3e-06   21.8   3.5    0.0095   11.5   0.1   3.1   3   1   1   4   4   4   2 cell division protein FtsA 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_04.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome04.hsp70search ref_sequences/hsp70master.build proteomes/proteome_04.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome04.mcrAsearch

@@ -0,0 +1,13 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_04.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome04.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_04.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome05.hsp70search

@@ -0,0 +1,15 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_011447201.1       -          hsp70master          -           8.5e-303 1002.8  26.9  9.7e-303 1002.7  26.9   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_052288776.1       -          hsp70master          -             6e-147  488.1   3.1  8.9e-147  487.5   3.1   1.2   1   1   0   1   1   1   1 hypothetical protein 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_05.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome05.hsp70search ref_sequences/hsp70master.build proteomes/proteome_05.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome05.mcrAsearch

@@ -0,0 +1,14 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_011449112.1       -          mcrAmaster           -                  0 1017.8   0.1         0 1017.6   0.1   1.0   1   0   0   1   1   1   1 coenzyme-B sulfoethylthiotransferase subunit alpha 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_05.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome05.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_05.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome06.hsp70search

@@ -0,0 +1,13 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_06.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome06.hsp70search ref_sequences/hsp70master.build proteomes/proteome_06.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]

proteomes/proteome06.mcrAsearch

@@ -0,0 +1,13 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/mcrAmaster.build
+# Target file:     proteomes/proteome_06.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome06.mcrAsearch ref_sequences/mcrAmaster.build proteomes/proteome_06.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:54 2022
+# [ok]

proteomes/proteome07.hsp70search

@@ -0,0 +1,15 @@
+#                                                               --- full sequence ---- --- best 1 domain ---- --- domain number estimation ----
+# target name        accession  query name           accession    E-value  score  bias   E-value  score  bias   exp reg clu  ov env dom rep inc description of target
+#------------------- ---------- -------------------- ---------- --------- ------ ----- --------- ------ -----   --- --- --- --- --- --- --- --- ---------------------
+WP_012106756.1       -          hsp70master          -           5.1e-294  973.5  23.7  5.9e-294  973.3  23.7   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_012107167.1       -          hsp70master          -           2.8e-292  967.7  18.7  3.3e-292  967.5  18.7   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+#
+# Program:         hmmsearch
+# Version:         3.3.2 (Nov 2020)
+# Pipeline mode:   SEARCH
+# Query file:      ref_sequences/hsp70master.build
+# Target file:     proteomes/proteome_07.fasta
+# Option settings: /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/tools/hmmsearch --tblout proteomes/proteome07.hsp70search ref_sequences/hsp70master.build proteomes/proteome_07.fasta 
+# Current dir:     /afs/crc.nd.edu/user/t/treisch/Private/biocomputing2022/bioinformaticsProject
+# Date:            Wed Oct 12 21:06:55 2022
+# [ok]