def occ_to_roles(roles):
"""
Convert roles to a dict of roles and the pegs they do
:param roles:
:type roles:
:return:
:rtype:
"""
sv = SAPserver()
result = sv.occ_of_role({'-roles' : roles})
return result
def occ_to_roles(roles):
"""
Convert roles to a dict of roles and the pegs they do
:param roles:
:type roles:
:return:
:rtype:
"""
sv = SAPserver()
result = sv.occ_of_role({'-roles': roles})
return result
import sys
from servers.SAP import SAPserver
server=SAPserver()
genomeID = '83333.1'
sys.stderr.write("Genome: " + str(genomeID) + "\n")
prots = server.all_proteins( {"-id" : genomeID} )
print("protein length " + str(len(prots)))
import sys
from servers.SAP import SAPserver
server = SAPserver()
genomeID = '83333.1'
sys.stderr.write("Genome: " + str(genomeID) + "\n")
prots = server.all_proteins({"-id": genomeID})
print("protein length " + str(len(prots)))
"""
Get a list of neighboring reactions and the number of genomes that have
that reaction in it. This will allow us to gapfill our model with
some predicted reactions
"""
import os
import string
import sys
from servers.SAP import SAPserver
server=SAPserver()
def ascii_clean(s):
"""Remove non-ascii characters from a string"""
return filter(lambda x: x in string.printable, s)
def close_genera(genome_name):
res = server.all_genomes({'-complete' : True})
close = {}
for g in res:
if genome_name in res[g]:
close[g] = res[g]
return close
import sys
import os.path
from servers.SAP import SAPserver
#Make connection by instantiating SAPserver
server = SAPserver()
def regulon_evidence(genomeID, roles_and_fids, subs_and_fids, subs_and_roles)
# Get the regulons in the genome
regulons = server.atomic_regulons(genomeID)
# Loop through the roles
for r in roles_and_fids:
# Grab the role name and the fid for the role
role = r.keys()
fid = r.values()
# Loop through the regulons
for reg in regulons:
# Get the fids in the regulon
fids_in_reg = reg.values()
# Check if the fid for role is in the regulon
if fid in fids_in_reg:
# Get the other fids in its subsystem
other_fids = []
for s in subs_and_fids:
if fid in s.values():
other_fids.append(list((set(s.values) - set(fid))))
import sys
import os.path
import matplotlib.pyplot as plt
from servers.SAP import SAPserver
#Make connection by instantiating SAPserver
server = SAPserver()
genomeID = '83333.1'
# Read in the fids and protein sequences fom text file
fin = open('pegs_and_seqs.txt', 'r')
fids_seqs = {}
for line in fin:
fields = line.strip().split("\t")
fids_seqs[fields[0]] = fields[1]
fin.close()
print("# of fids: " + str(len(fids_seqs)))
# Create file to write out the role:fid:sequence to text file
fout = open('role_peg_seq.txt', 'w')
# Get the roles and subsystems for all of the fids
feature_hash = server.ids_to_subsystems({"-ids": fids_seqs.keys(), "-genome": genomeID})
# Some variables four counting roles and subsystems
role_fid_pairs = []
roles_w_fids = []
subs_w_fids = []
roles_per_fid = {}
subs_per_fid = {}
import sys
from servers.SAP import SAPserver
server = SAPserver()
genomes = server.all_genomes({'-complete': 1, '-prokaryotic': 1})
print("There are " + str(len(genomes)) + " genomes")
sys.exit(0)
for genomeID in genomes:
sys.stderr.write("Genome: " + genomes[genomeID] + " (" + str(genomeID) +
")\n")
prots = server.all_proteins({'-id': genomeID})
print("There are " + str(len(prots)) + " prots")
dna = server.ids_to_sequences({'-ids': list(prots.keys())})
print("There are " + str(len(dna)) + " sequences")
funcs = server.ids_to_functions({'-ids': list(prots.keys())})
print("There are " + str(len(funcs)) + " functions")
import sys
from servers.SAP import SAPserver
server=SAPserver()
genomes=server.all_genomes({'-complete':1, '-prokaryotic':1})
print("There are ", len(genomes), " genomes")
#sys.exit(0)
for genomeID in genomes:
sys.stderr.write("Genome: " + genomes[genomeID] + " (" + str(genomeID) + ")\n")
prots = server.all_proteins({'-id':genomeID})
print("There are ", len(prots), " prots")
dna = server.ids_to_sequences({'-ids':list(prots.keys())})
print("There are ", len(dna), " sequences")
funcs = server.ids_to_functions({'-ids':list(prots.keys())})
print("There are ", len(funcs), " functions")
import sys
from servers.SAP import SAPserver
server=SAPserver()
genomes = server.all_genomes({'-complete':1, '-prokaryotic':1})
allss = server.all_subsystems(None)
ss = list(allss.keys())
ss.sort()
subsystems = server.genomes_to_subsystems( {'-ids':list(genomes.keys()), '-all':1} )
gHasSS={}
for g in subsystems:
gHasSS[g]={}
for tpl in subsystems[g]:
if tpl[1] == '0':
continue
gHasSS[g][tpl[0]]=tpl[1]
print("", "", *ss, sep='\t')
for g in genomes:
print(genomes[g], g, sep='\t', end="")
for s in ss:
if s in gHasSS[g]:
print("\t", gHasSS[g][s], end="")
else:
print("\t", end="")
print()
