# HG changeset patch
# User cpt
# Date 1685932865 0
# Node ID a99be535e99d1b8a4c36b472e3c4c73a6c905a9a
# Parent f3fc78cc4c43f4d33401c880a50a1fade369ab9d
planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
diff -r f3fc78cc4c43 -r a99be535e99d Disruptin_hydrophobicity_helicity_table_package.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/Disruptin_hydrophobicity_helicity_table_package.py Mon Jun 05 02:41:05 2023 +0000
@@ -0,0 +1,122 @@
+"""
+This program is intended to create the output table for the disruptin finder workflow
+"""
+from Bio import SeqIO
+from Bio.SeqUtils.ProtParam import ProteinAnalysis
+from Bio.SeqUtils import ProtParamData
+import csv
+import argparse
+import sys
+
+
+def disruptin_table(garnier_file, fasta_file):
+ # Iterable variables
+ position = 1
+ net_charge = 0
+ charge_res = 0
+ record_number = 0
+
+ # loop structures
+ names = []
+ sec_struct = []
+
+ # reading the lines from the garnier csv file
+ # with open(garnier_file,'r') as csvfile:
+ # garnierreader = csv.reader(csvfile)
+ for row in garnier_file:
+ if row[0] == "Sequence: ":
+ names += [row[1]]
+ elif row[0] in "HETC":
+ row = row.split("\t")
+ sec_struct += ["".join(row)]
+
+ record = []
+ p = []
+ r = []
+ c = []
+ h = []
+ s = []
+
+ # Parse the .fasta file and get the sequence
+ for rec in SeqIO.parse(fasta_file, "fasta"):
+ sequence = str(rec.seq)
+
+ # Set up the information vectors: for position #, residue, hydrophobic/charge/polar/nonpolar, and secondary
+ # structure
+ record += [rec.id]
+ position_vec = []
+ residue_vec = []
+ charge_sym_vec = []
+ sec_struct_vec = []
+
+ for aa in sequence:
+ position_vec += [str(position)]
+ residue_vec += [str(aa)]
+ sec_struct_vec += [str(sec_struct[record_number][position - 1])]
+
+ # For R and K residues a positive charge is given
+ if aa in "RK":
+ symbol = "+"
+ # For D and E residues a negative charge is given
+ elif aa in "DE":
+ symbol = "-"
+ elif aa in "AVMILPWFG":
+ symbol = "N"
+ elif aa in "HSYTCQN":
+ symbol = "P"
+ charge_sym_vec += symbol
+ position += 1
+
+ # Calculating hyrophobicity based on Kyte and Doolittle scale. Using binning value of 9. Since the binning
+ # is 9, the first 4 residues and last 4 residues as set blank so as to center the values to their
+ # approximate position on the sequence.
+ prot_ana_seq = ProteinAnalysis(sequence)
+ hydro = [0] * 4 + prot_ana_seq.protein_scale(ProtParamData.kd, 9) + [0] * 4
+
+ record_number += 1
+ position = 1
+
+ p += [position_vec]
+ r += [residue_vec]
+ c += [charge_sym_vec]
+ h += [hydro]
+ s += [sec_struct_vec]
+
+ # returns values for name of the sequence
+ return record, p, r, c, h, s
+
+
+if __name__ == "__main__":
+ # Grab all of the filters from our plugin loader
+ parser = argparse.ArgumentParser(description="Disruptin Table Output")
+ parser.add_argument(
+ "garnier_file", type=argparse.FileType("r"), help="csv file from garnier reader"
+ )
+ parser.add_argument(
+ "fasta_file",
+ type=argparse.FileType("r"),
+ help="fasta file of disruptin candidates",
+ )
+ args = parser.parse_args()
+
+ # Set up output location
+ # f = open(sys.stdout, 'w', newline='')
+ # writer1 = csv.writer(f)
+
+ iden, position, residue, charge, hydro, struct = disruptin_table(**vars(args))
+
+ for i in range(len(iden)):
+ # writer1.writerow(['Protein ID']+[iden[i]])
+ # writer1.writerow(['Position'] + [format(x, 's') for x in position[i]])
+ # writer1.writerow(['Residue'] + [format(x, 's') for x in residue[i]])
+ # writer1.writerow(['Charge'] + [format(x, 's') for x in charge[i]])
+ # writer1.writerow(['Hydrophobicity'] + [format(x, '.3f') for x in hydro[i]])
+ # writer1.writerow(['Secondary Structure'] + [format(x, 's') for x in struct[i]])
+ # writer1.writerow([''])
+
+ print(str(iden[i]))
+ print("Position \t " + "\t".join(position[i]))
+ print("Residue \t" + "\t".join(residue[i]))
+ print("Charge \t" + "\t".join(charge[i]))
+ print("Hydrophobicity \t" + "\t".join(format(x, ".3f") for x in hydro[i]))
+ print("Secondary Structure \t" + "\t".join(struct[i]))
diff -r f3fc78cc4c43 -r a99be535e99d Disruptin_hydrophobicity_helicity_table_package.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/Disruptin_hydrophobicity_helicity_table_package.xml Mon Jun 05 02:41:05 2023 +0000
@@ -0,0 +1,32 @@
+
+ makes table of disruptin candidates
+
+ macros.xml
+ cpt-macros.xml
+
+
+ $output]]>
+
+
+
+
+
+
+
+
+
+
diff -r f3fc78cc4c43 -r a99be535e99d cpt-macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt-macros.xml Mon Jun 05 02:41:05 2023 +0000
@@ -0,0 +1,115 @@
+
+
+
+ python
+ biopython
+ requests
+ cpt_gffparser
+
+
+
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+ @unpublished{galaxyTools,
+ author = {E. Mijalis, H. Rasche},
+ title = {CPT Galaxy Tools},
+ year = {2013-2017},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+
+ @unpublished{galaxyTools,
+ author = {E. Mijalis, H. Rasche},
+ title = {CPT Galaxy Tools},
+ year = {2013-2017},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+
+ @unpublished{galaxyTools,
+ author = {C. Ross},
+ title = {CPT Galaxy Tools},
+ year = {2020-},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+
+ @unpublished{galaxyTools,
+ author = {E. Mijalis, H. Rasche},
+ title = {CPT Galaxy Tools},
+ year = {2013-2017},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+ @unpublished{galaxyTools,
+ author = {A. Criscione},
+ title = {CPT Galaxy Tools},
+ year = {2019-2021},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+
+ @unpublished{galaxyTools,
+ author = {A. Criscione},
+ title = {CPT Galaxy Tools},
+ year = {2019-2021},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+
+
+ 10.1371/journal.pcbi.1008214
+
+ @unpublished{galaxyTools,
+ author = {C. Maughmer},
+ title = {CPT Galaxy Tools},
+ year = {2017-2020},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
+
+
+ @unpublished{galaxyTools,
+ author = {C. Maughmer},
+ title = {CPT Galaxy Tools},
+ year = {2017-2020},
+ note = {https://github.com/tamu-cpt/galaxy-tools/}
+ }
+
+
+
+
diff -r f3fc78cc4c43 -r a99be535e99d cpt_disruptin_table/Disruptin_hydrophobicity_helicity_table_package.py
--- a/cpt_disruptin_table/Disruptin_hydrophobicity_helicity_table_package.py Fri Jun 17 12:33:22 2022 +0000
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,122 +0,0 @@
-"""
-This program is intended to create the output table for the disruptin finder workflow
-"""
-from Bio import SeqIO
-from Bio.SeqUtils.ProtParam import ProteinAnalysis
-from Bio.SeqUtils import ProtParamData
-import csv
-import argparse
-import sys
-
-
-def disruptin_table(garnier_file, fasta_file):
- # Iterable variables
- position = 1
- net_charge = 0
- charge_res = 0
- record_number = 0
-
- # loop structures
- names = []
- sec_struct = []
-
- # reading the lines from the garnier csv file
-# with open(garnier_file,'r') as csvfile:
-# garnierreader = csv.reader(csvfile)
- for row in garnier_file:
- if row[0] == 'Sequence: ':
- names += [row[1]]
- elif row[0] in 'HETC':
- row = row.split('\t')
- sec_struct += [''.join(row)]
-
- record = []
- p = []
- r = []
- c = []
- h = []
- s = []
-
- # Parse the .fasta file and get the sequence
- for rec in SeqIO.parse(fasta_file, "fasta"):
- sequence = str(rec.seq)
-
- # Set up the information vectors: for position #, residue, hydrophobic/charge/polar/nonpolar, and secondary
- # structure
- record += [rec.id]
- position_vec = []
- residue_vec = []
- charge_sym_vec = []
- sec_struct_vec = []
-
- for aa in sequence:
- position_vec += [str(position)]
- residue_vec += [str(aa)]
- sec_struct_vec += [str(sec_struct[record_number][position - 1])]
-
- # For R and K residues a positive charge is given
- if aa in "RK":
- symbol = "+"
- # For D and E residues a negative charge is given
- elif aa in "DE":
- symbol = "-"
- elif aa in "AVMILPWFG":
- symbol = "N"
- elif aa in "HSYTCQN":
- symbol = "P"
- charge_sym_vec += symbol
- position += 1
-
- # Calculating hyrophobicity based on Kyte and Doolittle scale. Using binning value of 9. Since the binning
- # is 9, the first 4 residues and last 4 residues as set blank so as to center the values to their
- # approximate position on the sequence.
- prot_ana_seq = ProteinAnalysis(sequence)
- hydro = [0] * 4 + prot_ana_seq.protein_scale(ProtParamData.kd, 9) + [0] * 4
-
- record_number += 1
- position = 1
-
- p += [position_vec]
- r += [residue_vec]
- c += [charge_sym_vec]
- h += [hydro]
- s += [sec_struct_vec]
-
- # returns values for name of the sequence
- return record, p, r, c, h, s
-
-
-if __name__ == "__main__":
- # Grab all of the filters from our plugin loader
- parser = argparse.ArgumentParser(description="Disruptin Table Output")
- parser.add_argument(
- "garnier_file", type=argparse.FileType("r"), help="csv file from garnier reader"
- )
- parser.add_argument(
- "fasta_file",
- type=argparse.FileType("r"),
- help="fasta file of disruptin candidates",
- )
- args = parser.parse_args()
-
- # Set up output location
-# f = open(sys.stdout, 'w', newline='')
-# writer1 = csv.writer(f)
-
- iden, position, residue, charge, hydro, struct = disruptin_table(**vars(args))
-
- for i in range(len(iden)):
-# writer1.writerow(['Protein ID']+[iden[i]])
-# writer1.writerow(['Position'] + [format(x, 's') for x in position[i]])
-# writer1.writerow(['Residue'] + [format(x, 's') for x in residue[i]])
-# writer1.writerow(['Charge'] + [format(x, 's') for x in charge[i]])
-# writer1.writerow(['Hydrophobicity'] + [format(x, '.3f') for x in hydro[i]])
-# writer1.writerow(['Secondary Structure'] + [format(x, 's') for x in struct[i]])
-# writer1.writerow([''])
-
- print(str(iden[i]))
- print("Position \t " + "\t".join(position[i]))
- print("Residue \t" + "\t".join(residue[i]))
- print("Charge \t" + "\t".join(charge[i]))
- print("Hydrophobicity \t" + "\t".join(format(x, ".3f") for x in hydro[i]))
- print("Secondary Structure \t" + "\t".join(struct[i]))
diff -r f3fc78cc4c43 -r a99be535e99d cpt_disruptin_table/Disruptin_hydrophobicity_helicity_table_package.xml
--- a/cpt_disruptin_table/Disruptin_hydrophobicity_helicity_table_package.xml Fri Jun 17 12:33:22 2022 +0000
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,33 +0,0 @@
-
-
- makes table of disruptin candidates
-
- macros.xml
- cpt-macros.xml
-
-
- $output]]>
-
-
-
-
-
-
-
-
-
-
diff -r f3fc78cc4c43 -r a99be535e99d cpt_disruptin_table/cpt-macros.xml
--- a/cpt_disruptin_table/cpt-macros.xml Fri Jun 17 12:33:22 2022 +0000
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,115 +0,0 @@
-
-
-
-
- python
- biopython
- requests
-
-
-
-
-
-
-
- 10.1371/journal.pcbi.1008214
- @unpublished{galaxyTools,
- author = {E. Mijalis, H. Rasche},
- title = {CPT Galaxy Tools},
- year = {2013-2017},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
- 10.1371/journal.pcbi.1008214
-
- @unpublished{galaxyTools,
- author = {E. Mijalis, H. Rasche},
- title = {CPT Galaxy Tools},
- year = {2013-2017},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
-
-
- 10.1371/journal.pcbi.1008214
-
- @unpublished{galaxyTools,
- author = {C. Ross},
- title = {CPT Galaxy Tools},
- year = {2020-},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
-
-
- 10.1371/journal.pcbi.1008214
-
- @unpublished{galaxyTools,
- author = {E. Mijalis, H. Rasche},
- title = {CPT Galaxy Tools},
- year = {2013-2017},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
- @unpublished{galaxyTools,
- author = {A. Criscione},
- title = {CPT Galaxy Tools},
- year = {2019-2021},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
-
-
- 10.1371/journal.pcbi.1008214
-
- @unpublished{galaxyTools,
- author = {A. Criscione},
- title = {CPT Galaxy Tools},
- year = {2019-2021},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
-
-
- 10.1371/journal.pcbi.1008214
-
- @unpublished{galaxyTools,
- author = {C. Maughmer},
- title = {CPT Galaxy Tools},
- year = {2017-2020},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
-
-
- @unpublished{galaxyTools,
- author = {C. Maughmer},
- title = {CPT Galaxy Tools},
- year = {2017-2020},
- note = {https://github.com/tamu-cpt/galaxy-tools/}
- }
-
-
-
-
diff -r f3fc78cc4c43 -r a99be535e99d cpt_disruptin_table/macros.xml
--- a/cpt_disruptin_table/macros.xml Fri Jun 17 12:33:22 2022 +0000
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,23 +0,0 @@
-
-
-
-
- python
- biopython
- cpt_gffparser
-
-
-
-
-
-
-
-
-
-
- ln -s $genome_fasta genomeref.fa;
-
-
- genomeref.fa
-
-
diff -r f3fc78cc4c43 -r a99be535e99d macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Mon Jun 05 02:41:05 2023 +0000
@@ -0,0 +1,74 @@
+
+
+
+ progressivemauve
+
+ bcbiogff
+
+
+
+ 2.4.0
+
+ 10.1371/journal.pone.0011147
+
+
+ 10.1093/bioinformatics/btm039
+
+
+ '$xmfa'
+
+
+
+
+
+ '$sequences'
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ '$gff3_data'
+
+
+ #if str($reference_genome.reference_genome_source) == 'cached':
+ '${reference_genome.fasta_indexes.fields.path}'
+ #else if str($reference_genome.reference_genome_source) == 'history':
+ genomeref.fa
+ #end if
+
+
+ #if $reference_genome.reference_genome_source == 'history':
+ ln -s '$reference_genome.genome_fasta' genomeref.fa;
+ #end if
+
+
+ #if str($reference_genome.reference_genome_source) == 'cached':
+ '${reference_genome.fasta_indexes.fields.path}'
+ #else if str($reference_genome.reference_genome_source) == 'history':
+ genomeref.fa
+ #end if
+
+