Final Biocomputing Project for Schmidt and Doktorczyk

bioinformaticsProject/proteomes/build.sh

@@ -0,0 +1,25 @@
+#
+for $i in proteome_**.fasta
+do
+	./muscle -in $i -out muscle$i
+	./hmmbuild build$i muscle$i
+	for j in ../ref_sequences/mrcAgene_**.fasta
+	do
+		./hmmsearch --tblout mrca$i build$i $j
+	done
+	cat mrca$i | grep "aligned" > hasmrcA$i
+
+	t=1
+	for p in ../ref_sequences/hsp70gene_**.fasta
+	do 
+		./hmmsearch --tblout $thsp$i hasmrcA$i $p
+		t=t+1	
+	done 
+		cat $thsp$i | grep "aligned" > $thas$i
+	#make file with all the names of the proteome that have hsp70 and mrc
+	for m in $thas$i
+	do
+		echo m > table.csv
+	done
+done
+cat table.csv | sed 's/_/ /' | sort -k 2

bioinformaticsProject/proteomes/sort.sh

@@ -0,0 +1,6 @@
+#file
+#for i in proteome_**.fasta
+#do
+	./muscle -in proteome_01.fasta -out muscleproteome_01.fasta
+
+#done

bioinformaticsProject/ref_sequences/build.sh

@@ -0,0 +1,25 @@
+#
+for i in *.fasta
+do
+	./muscle -in $i -out muscle$i
+	./hmmbuild build$i muscle$i
+	for j in ../proteomes/proteome_**.fasta
+	do
+		./hmmsearch --tblout mrca$i $j build$i
+	done
+	cat mrca$i | grep "aligned" > hasmrcA$i
+
+	#t=1
+	#for p in ../ref_sequences/hsp70gene_**.fasta
+	#do 
+	#	./hmmsearch --tblout $thsp$i hasmrcA$i $p
+		t=t+1	
+	#done 
+	#	cat $thsp$i | grep "aligned" > $thas$i
+	##make file with all the names of the proteome that have hsp70 and mrc
+	#for m in $thas$i
+	#do
+	#	echo m > table.csv
+	#done
+done
+#cat table.csv | sed 's/_/ /' | sort -k 2

bioinformaticsProject/ref_sequences/hashspgene.txt

@@ -0,0 +1,50 @@
+hspproteome_01.fasta   4
+hspproteome_02.fasta   1
+hspproteome_03.fasta   3
+hspproteome_04.fasta   4
+hspproteome_05.fasta   2
+hspproteome_06.fasta   0
+hspproteome_07.fasta   2
+hspproteome_08.fasta   5
+hspproteome_09.fasta   1
+hspproteome_10.fasta   3
+hspproteome_11.fasta   6
+hspproteome_12.fasta   6
+hspproteome_13.fasta   3
+hspproteome_14.fasta   1
+hspproteome_15.fasta   1
+hspproteome_16.fasta   1
+hspproteome_17.fasta   3
+hspproteome_18.fasta   8
+hspproteome_19.fasta   1
+hspproteome_20.fasta   3
+hspproteome_21.fasta   0
+hspproteome_22.fasta   0
+hspproteome_23.fasta   2
+hspproteome_24.fasta   2
+hspproteome_25.fasta   0
+hspproteome_26.fasta   1
+hspproteome_27.fasta   1
+hspproteome_28.fasta   1
+hspproteome_29.fasta   0
+hspproteome_30.fasta   1
+hspproteome_31.fasta   7
+hspproteome_32.fasta   4
+hspproteome_33.fasta   0
+hspproteome_34.fasta   1
+hspproteome_35.fasta   1
+hspproteome_36.fasta   3
+hspproteome_37.fasta   1
+hspproteome_38.fasta   1
+hspproteome_39.fasta   1
+hspproteome_40.fasta   1
+hspproteome_41.fasta   1
+hspproteome_42.fasta   3
+hspproteome_43.fasta   3
+hspproteome_44.fasta   1
+hspproteome_45.fasta   3
+hspproteome_46.fasta   1
+hspproteome_47.fasta   1
+hspproteome_48.fasta   1
+hspproteome_49.fasta   3
+hspproteome_50.fasta   3

bioinformaticsProject/ref_sequences/hasmcrAgene.txt

@@ -0,0 +1,16 @@
+mrcAproteome_24.fasta   1122.6
+mrcAproteome_50.fasta   1116.1
+mrcAproteome_45.fasta   1116.1
+mrcAproteome_42.fasta   1116.1
+mrcAproteome_03.fasta   1116.1
+mrcAproteome_29.fasta   1088.1
+mrcAproteome_48.fasta   1060.5
+mrcAproteome_44.fasta   1060.5
+mrcAproteome_39.fasta   1060.5
+mrcAproteome_38.fasta   1060.5
+mrcAproteome_16.fasta   1060.5
+mrcAproteome_23.fasta   1056.6
+mrcAproteome_19.fasta   1030.3
+mrcAproteome_15.fasta   1028.8
+mrcAproteome_05.fasta   1019.0
+mrcAproteome_07.fasta   1016.3

bioinformaticsProject/ref_sequences/hasmrcAgene.txt

@@ -0,0 +1,50 @@
+
+
+1114.3
+
+1017.3
+
+1014.7
+
+
+
+
+
+
+
+1027.2
+1058.8
+
+
+1028.7
+
+
+
+1055.0
+1120.8
+
+
+
+
+1086.3
+
+
+
+
+
+
+
+
+1058.8
+1058.8
+
+
+1114.3
+
+1058.8
+1114.3
+
+
+1058.8
+
+1114.3

bioinformaticsProject/ref_sequences/hspproteome_01.fasta

@@ -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       -          muscleallhsp         -           2.7e-296  981.0  30.7  3.1e-296  980.8  30.7   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_013360607.1       -          muscleallhsp         -           5.3e-129  428.4   0.2  7.8e-129  427.9   0.2   1.1   1   0   0   1   1   1   1 molecular chaperone HscC 
+WP_013362571.1       -          muscleallhsp         -            5.3e-12   42.0   6.5   2.5e-11   39.7   6.5   2.1   1   1   0   1   1   1   1 rod shape-determining protein 
+WP_013360481.1       -          muscleallhsp         -            3.3e-09   32.7   2.2   5.5e-05   18.8   0.5   2.7   2   1   1   3   3   3   2 ethanolamine utilization protein EutJ 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_01.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_01.fasta buildallhsp.fasta proteome_01.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:19 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_02.fasta

@@ -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       -          muscleallhsp         -             0.0069   11.4   6.5    0.0084   11.1   6.5   1.1   1   0   0   1   1   1   1 transcriptional regulator 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_02.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_02.fasta buildallhsp.fasta proteome_02.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:19 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_03.fasta

@@ -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       -          muscleallhsp         -                  0 1101.7  23.7         0 1101.6  23.7   1.0   1   0   0   1   1   1   1 MULTISPECIES: molecular chaperone DnaK 
+WP_048116754.1       -          muscleallhsp         -           1.1e-109  365.1   8.9  3.7e-100  333.6   3.7   2.0   2   0   0   2   2   2   2 MULTISPECIES: hypothetical protein 
+WP_048116752.1       -          muscleallhsp         -           1.3e-106  354.9  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:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_03.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_03.fasta buildallhsp.fasta proteome_03.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_04.fasta

@@ -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       -          muscleallhsp         -           8.3e-262  867.2  31.2  3.4e-259  858.6  31.2   2.0   1   1   0   1   1   1   1 molecular chaperone DnaK 
+WP_055360541.1       -          muscleallhsp         -           1.1e-156  520.0  14.1  8.9e-144  477.4  12.9   2.0   2   0   0   2   2   2   2 Fe-S protein assembly chaperone HscA 
+WP_055359523.1       -          muscleallhsp         -            2.4e-14   49.8   0.5   1.8e-13   47.0   0.0   2.3   3   0   0   3   3   3   1 MULTISPECIES: rod shape-determining protein 
+WP_055361642.1       -          muscleallhsp         -            7.5e-06   21.8   3.4    0.0096   11.5   0.1   3.1   3   1   1   4   4   4   2 cell division protein FtsA 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_04.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_04.fasta buildallhsp.fasta proteome_04.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_05.fasta

@@ -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       -          muscleallhsp         -           2.6e-302 1001.3  26.8    3e-302 1001.1  26.8   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_052288776.1       -          muscleallhsp         -           6.5e-147  488.0   3.2  9.6e-147  487.4   3.2   1.2   1   1   0   1   1   1   1 hypothetical protein 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_05.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_05.fasta buildallhsp.fasta proteome_05.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_06.fasta

@@ -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:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_06.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_06.fasta buildallhsp.fasta proteome_06.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_07.fasta

@@ -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       -          muscleallhsp         -           1.3e-293  972.2  23.8  1.5e-293  972.0  23.8   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+WP_012107167.1       -          muscleallhsp         -           2.4e-292  968.0  18.8  2.7e-292  967.8  18.8   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_07.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_07.fasta buildallhsp.fasta proteome_07.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_08.fasta

@@ -0,0 +1,18 @@
+#                                                               --- 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_062403955.1       -          muscleallhsp         -           5.2e-259  858.2  33.1  1.5e-229  760.8  27.1   2.0   1   1   1   2   2   2   2 molecular chaperone DnaK 
+WP_062405703.1       -          muscleallhsp         -           8.1e-153  507.4  12.2  1.2e-151  503.6  12.2   1.9   1   1   0   1   1   1   1 Fe-S protein assembly chaperone HscA 
+WP_062406926.1       -          muscleallhsp         -            7.7e-24   81.4   0.0   7.8e-19   64.8   0.0   2.0   2   0   0   2   2   2   2 Hsp70 family protein 
+WP_062408136.1       -          muscleallhsp         -            9.3e-14   48.1   0.5   7.2e-13   45.2   0.0   2.3   3   0   0   3   3   3   1 rod shape-determining protein 
+WP_062406075.1       -          muscleallhsp         -            1.3e-06   24.5   1.9    0.0028   13.5   0.1   3.1   3   1   0   4   4   4   2 cell division protein FtsA 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_08.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_08.fasta buildallhsp.fasta proteome_08.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_09.fasta

@@ -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_010902322.1       -          muscleallhsp         -                  0 1048.0  32.1         0 1047.8  32.1   1.0   1   0   0   1   1   1   1 molecular chaperone DnaK 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_09.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_09.fasta buildallhsp.fasta proteome_09.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_10.fasta

@@ -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_010937085.1       -          muscleallhsp         -           1.6e-280  928.1  26.6  7.6e-251  830.1  19.6   2.0   1   1   1   2   2   2   2 molecular chaperone DnaK 
+WP_010936122.1       -          muscleallhsp         -            0.00084   14.1   0.1    0.0013   13.4   0.1   1.4   1   0   0   1   1   1   1 cell division protein FtsA 
+WP_010936412.1       -          muscleallhsp         -              0.001   13.8   0.1    0.0018   12.9   0.1   1.3   1   0   0   1   1   1   1 cell division protein FtsA 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_10.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_10.fasta buildallhsp.fasta proteome_10.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]

bioinformaticsProject/ref_sequences/hspproteome_11.fasta

@@ -0,0 +1,19 @@
+#                                                               --- 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_015941672.1       -          muscleallhsp         -           1.7e-282  936.0  18.1  1.7e-280  929.4  18.1   2.0   1   1   0   1   1   1   1 molecular chaperone DnaK 
+WP_015941419.1       -          muscleallhsp         -           5.3e-278  921.2  13.0  4.7e-246  815.6   7.2   2.0   1   1   1   2   2   2   2 molecular chaperone DnaK 
+WP_015942306.1       -          muscleallhsp         -            1.7e-34  116.8   0.0   1.2e-19   67.8   0.0   3.0   2   1   1   3   3   3   3 Hsp70 family protein 
+WP_012616464.1       -          muscleallhsp         -            1.3e-11   41.3   6.0   2.6e-11   40.2   6.0   1.6   1   1   0   1   1   1   1 rod shape-determining protein 
+WP_012616267.1       -          muscleallhsp         -            4.4e-11   39.5   5.2   1.3e-09   34.7   5.2   2.6   1   1   0   1   1   1   1 rod shape-determining protein 
+WP_015941576.1       -          muscleallhsp         -            7.2e-05   19.0   1.1   0.00032   16.8   0.1   2.1   2   0   0   2   2   2   1 cell division protein FtsA 
+#
+# Program:         hmmsearch
+# Version:         3.3.1 (Jul 2020)
+# Pipeline mode:   SEARCH
+# Query file:      buildallhsp.fasta
+# Target file:     proteome_11.fasta
+# Option settings: ./hmmsearch --tblout hspproteome_11.fasta buildallhsp.fasta proteome_11.fasta 
+# Current dir:     /afs/crc.nd.edu/user/m/mschmi26/BiocompProject/Biocomputing_Project/bioinformaticsProject/ref_sequences
+# Date:            Fri Oct 15 10:54:20 2021
+# [ok]