def compute_fasta_stats(formats, input_file, seqtype, priority):
MIN_LENGTH='MIN_LENGTH'
MAX_LENGTH='MAX_LENGTH'
NUMSEQ='NUMSEQ'
TOTAL_LENGTH='TOTAL_LENGTH'
AVG_LENGTH='AVG_LENGTH'
stats = {
MIN_LENGTH: 0,
MAX_LENGTH: 0,
NUMSEQ : 0,
TOTAL_LENGTH: 0,
AVG_LENGTH : 0
}
""" min length """
_MAX = 1000000000000
stats[MAX_LENGTH] = -(_MAX)
stats[MIN_LENGTH]= _MAX
fastareader= FastaReader(input_file)
""" process one fasta sequence at a time """
lengths_str=""
for record in fastareader:
seqname = record.name
seq = record.sequence
length = len(seq)
stats[NUMSEQ] += 1
stats[AVG_LENGTH] = stats[AVG_LENGTH] + length
if stats[MIN_LENGTH] > length:
stats[MIN_LENGTH] = length
if stats[MAX_LENGTH] < length:
stats[MAX_LENGTH] = length
if stats[NUMSEQ] > 0 :
stats[AVG_LENGTH] = stats[AVG_LENGTH]/stats[NUMSEQ]
else:
stats[AVG_LENGTH] = 0
# printf("%s\tNumber of sequences in input file BEFORE QC (%s)\t%s\n" %(str(priority), opts.seqtype, str(stats[NUMSEQ][BEFORE])) )
# printf("%s\tNumber of sequences AFTER QC (%s)\t%s\n" %(str(priority + 5), opts.seqtype, str(stats[NUMSEQ][AFTER])))
printf(formats %(str(priority + 5), str(stats[NUMSEQ])))
printf("%s\t-min length\t%s\n" %(str(priority + 6), str(stats[MIN_LENGTH])) )
printf("%s\t-avg length\t%s\n" %( str(priority + 7), str(int(stats[AVG_LENGTH]))))
printf("%s\t-max length\t%s\n" %( str(priority + 8), str(stats[MAX_LENGTH])) )
printf("%s\t-total base pairs (bp)\t%s\n" %( str(priority + 9), str(int(stats[AVG_LENGTH]* stats[NUMSEQ])) ))
def main(argv, errorlogger=None, runcommand=None, runstatslogger=None):
global parser
options, args = parser.parse_args(argv)
# is there a pathwaytools executable installed
if False and not path.exists(options.ptoolsExec):
eprintf("ERROR\tPathwayTools executable %s not found!\n",
options.ptoolsExec)
if errorlogger:
errorlogger.printf(
"ERROR\tPathwayTools executable %s not found!\n",
options.ptoolsExec)
exit_process("ERROR\tPathwayTools executable %s not found!\n" %
(options.ptoolsExec))
# command to build the ePGDB
command = "%s " % (options.ptoolsExec)
command += " -api"
pythonCyc = startPathwayTools(options.sample_name.lower(),
options.ptoolsExec, True)
#resultLines = pythonCyc.getReactionListLines()
resultLines = pythonCyc.getFlatFiles()
StopPathwayTools()
try:
if False:
pythonCyc = startPathwayTools(options.sample_name.lower(),
options.ptoolsExec, True)
pythonCyc.setDebug() # disable pathway debug statements
printf("INFO\tExtracting the reaction list from ePGDB " +
options.sample_name + "\n")
resultLines = pythonCyc.getReactionListLines()
#pythonCyc.stopPathwayTools()
reaction_list_file = open(options.reactions_list + ".tmp", 'w')
for line in resultLines:
fprintf(reaction_list_file, "%s\n", line.strip())
reaction_list_file.close()
StopPathwayTools()
except:
print traceback.print_exc(10)
eprintf("ERROR\tFailed to run extract pathways for %s : \n" %
(options.sample_name))
eprintf(
"INFO\tKill any other PathwayTools instance running on the machine and try again"
)
if errorlogger:
errorlogger.write(
"ERROR\tFailed to run extract pathways for %s : " %
(options.sample_name))
errorlogger.write(
"INFO\tKill any other PathwayTools instance running on the machine and try again\n"
)
StopPathwayTools()
def dry_run_status(commands):
for command in commands:
printf("%s", command[0])
if command[4] == True:
printf("%s", " Required")
else:
printf("%s", " Not Required")
printf("\n")
def dry_run_status( commands ):
for command in commands:
printf("%s", command[0])
if command[4] == True:
printf("%s", " Required")
else:
printf("%s", " Not Required")
printf("\n")
def main(argv, errorlogger = None, runcommand = None, runstatslogger = None):
global parser
options, args = parser.parse_args(argv)
# is there a pathwaytools executable installed
if False and not path.exists(options.ptoolsExec):
eprintf("ERROR\tPathwayTools executable %s not found!\n", options.ptoolsExec)
if errorlogger:
errorlogger.printf("ERROR\tPathwayTools executable %s not found!\n", options.ptoolsExec)
exit_process("ERROR\tPathwayTools executable %s not found!\n" %(options.ptoolsExec))
# command to build the ePGDB
command = "%s " %(options.ptoolsExec)
command += " -api"
pythonCyc = startPathwayTools(options.sample_name.lower(), options.ptoolsExec, True)
#resultLines = pythonCyc.getReactionListLines()
resultLines = pythonCyc.getFlatFiles()
StopPathwayTools()
try:
if False:
pythonCyc = startPathwayTools(options.sample_name.lower(), options.ptoolsExec, True)
pythonCyc.setDebug() # disable pathway debug statements
printf("INFO\tExtracting the reaction list from ePGDB " + options.sample_name + "\n")
resultLines = pythonCyc.getReactionListLines()
#pythonCyc.stopPathwayTools()
reaction_list_file = open(options.reactions_list + ".tmp", 'w')
for line in resultLines:
fprintf(reaction_list_file,"%s\n",line.strip())
reaction_list_file.close()
StopPathwayTools()
except:
print traceback.print_exc(10)
eprintf("ERROR\tFailed to run extract pathways for %s : \n" %(options.sample_name))
eprintf("INFO\tKill any other PathwayTools instance running on the machine and try again")
if errorlogger:
errorlogger.write("ERROR\tFailed to run extract pathways for %s : " %(options.sample_name))
errorlogger.write("INFO\tKill any other PathwayTools instance running on the machine and try again\n")
StopPathwayTools()
def ExtractPathway_WTD(options):
# Extract pathways and WTD
# place to store list of expected taxonomic range(s)
printf('INFO\tEntering the WTD calculations!\n')
serialized_metacyc_taxa_ranges = "/tmp/metacyc_pwy_taxa_range.pk"
serialized_metacyc_taxa_ranges_tmp = "/tmp/metacyc_pwy_taxa_range.pk.tmp"
try:
if options.wtd and not path.isfile(serialized_metacyc_taxa_ranges):
# get MetaCyc's expected taxonomic range(s) and serialize for later use in /tmp
# try:
printf('INFO\tGetting MetaCyc Expected Taxonomic Range(s)\n')
pythonCyc = startPathwayTools('meta', options.ptoolsExec, True)
pwys = pythonCyc.getAllPathways()
pwy_taxa_range = {} # hash from pwy to expected taxonomic range(s)
pwy_taxa_range_pk = open(serialized_metacyc_taxa_ranges_tmp, "w")
# get expected taxonomic ranges for each pathway
for pwy in pwys:
# printf(" " + pwy)
my_expected_taxonomic_range = pythonCyc.getExpectedTaxonomicRange(
pwy)
pwy_taxa_range[pwy] = my_expected_taxonomic_range
# printf(" " + pwy)
# write the pathway
pickle.dump(pwy_taxa_range, pwy_taxa_range_pk)
pwy_taxa_range_pk.close()
StopPathwayTools()
rename(serialized_metacyc_taxa_ranges_tmp,
serialized_metacyc_taxa_ranges)
else:
# read expected taxonomic range from serialized file
exepected_taxa_in = open(serialized_metacyc_taxa_ranges, "r")
pwy_taxa_range = pickle.load(exepected_taxa_in)
# create mapping of preferred NCBI to MEGAN taxonomy
megan_map = {}
if options.ncbi_megan_map:
with open(options.ncbi_megan_map) as megan_map_file:
for line in megan_map_file:
fields = line.split("\t")
fields = map(str.strip, fields)
megan_map[fields[0]] = fields[1]
# get ORF to taxa map from annotation_table
printf("INFO\tGetting ORF to Taxa Map from AnnotationTable\n")
orf_lca = {}
with open(options.annotation_table) as f:
for line in f:
fields = line.split("\t")
orf_lca[fields[0].strip()] = fields[8].strip()
# get pathway ORFs and Rxns
pwy_to_orfs = {}
pwy_to_long = {}
pwy_to_rxns = {}
try:
pythonCyc = startPathwayTools(options.sample_name.lower(),
options.ptoolsExec, True)
pwys = pythonCyc.getAllPathways()
for pwy in pwys:
# printf(" " + pwy)
genes = pythonCyc.getPathwayORFs(pwy)
rxns = pythonCyc.getPathwayReactionInfo(pwy)
pwy_to_orfs[pwy] = genes
pwy_to_long[pwy] = cleanup(
pythonCyc.get_slot_value(pwy, "common-name"))
pwy_to_rxns[pwy] = rxns
# printf("\n")
StopPathwayTools()
except:
print """
Problem connecting to Pathway Tools. Check the /tmp/ptools-socket file.
"""
except:
print """
Problem calculating WTD via Pathway Tools. Check the /tmp/ptools-socket file.
"""
# get LCA per pathway
pwy_lca = {}
# load NCBI taxonomy map
printf("INFO\tLoading NCBI Taxonomy Map\n")
lca = LCAComputation([options.ncbi_tree], )
for pwy in pwy_to_orfs:
orfs = pwy_to_orfs[pwy]
taxa_ids = []
for orf in orfs:
if orf in orf_lca:
# could strip out id here
res = re.search("(.+?)\(([0-9]+?)\)", orf_lca[orf])
if res:
taxa_annotation = res.group(1)
id = res.group(2)
else:
id = lca.get_a_Valid_ID([orf_lca[orf]])
taxa_ids.append(id)
pwy_lca_id = lca.get_lca(taxa_ids, True)
# print "In run_pathologic"
# print pwy_lca_id
# print pwy_lca_id
lca.clear_cells(taxa_ids)
pwy_lca[pwy] = [pwy_lca_id, lca.translateIdToName(pwy_lca_id)]
# calculate weighted taxonomic distance
pwy_to_wtd = {}
for pwy in pwy_lca:
C = [] # list of distances
C_taxa = [] # list of parallel observed-expected taxa pairs
C_pos = [] # list of non-negative distances
C_pos_taxa = [] # list of parallel observed-expected taxa pairs
C_neg = [] # list of negative distances
C_neg_taxa = [] # list of parallel observed-expected taxa pairs
if len(pwy_taxa_range[pwy]) > 0:
for expected in pwy_taxa_range[pwy]:
dist = lca.wtd(expected[0], pwy_lca[pwy][0])
if dist or dist == 0:
# valid distance
# add distance respective lists
C.append(dist) # add distance
C_taxa.append([expected[0], pwy_lca[pwy][0]])
if dist >= 0:
C_pos.append(dist) # add to non-negative list
C_pos_taxa.append([expected[0], pwy_lca[pwy][0]])
else:
C_neg.append(dist) # add to negative list
C_neg_taxa.append([expected[0], pwy_lca[pwy][0]])
else:
print "Not a valid distance"
continue
else:
# no expected taxonomy, set to root
min_taxa = "1"
dist = lca.wtd(min_taxa, pwy_lca[pwy][0])
# add distance respective lists
C.append(dist) # add distance
C_taxa.append([min_taxa, pwy_lca[pwy][0]])
if dist >= 0:
C_pos.append(dist) # add to non-negative list
C_pos_taxa.append([min_taxa, pwy_lca[pwy][0]])
else:
C_neg.append(dist) # add to negative list
C_neg_taxa.append([min_taxa, pwy_lca[pwy][0]])
# find index with max distance (closest to expected taxonomy)
max_index, max_dist = max(enumerate(C), key=operator.itemgetter(1))
max_taxa = C_taxa[max_index]
# remap to preferred names
observed = get_preferred_taxa_name(max_taxa[1], megan_map,
lca.id_to_name)
expected = get_preferred_taxa_name(max_taxa[0], megan_map,
lca.id_to_name)
pwy_to_wtd[pwy] = [max_dist, observed, expected]
# write out pathway table
table_out_tmp = options.table_out + ".tmp"
try:
out = open(table_out_tmp, "w")
except:
print "Had problems opening file: " + options.table_out
# write appropreate header
if options.wtd:
header = "SAMPLE\tPWY_NAME\tPWY_COMMON_NAME\tNUM_REACTIONS\tNUM_COVERED_REACTIONS\tORF_COUNT\tWTD\tOBSERVED\tEXPECTED\tORFS\n"
else:
header = "SAMPLE\tPWY_NAME\tPWY_COMMON_NAME\tNUM_REACTIONS\tNUM_COVERED_REACTIONS\tORF_COUNT\tORFS\n"
out.write(header)
sample = options.sample_name # sample name
for pwy in pwy_to_orfs:
# generate output line
line = []
line.append(sample) # sample name
line.append(pwy) # pathway name
line.append(pwy_to_long[pwy]) # pathway longname
line.append(pwy_to_rxns[pwy][0]) # pathway num reactions
line.append(pwy_to_rxns[pwy][1]) # pathway covered reactions
line.append(len(pwy_to_orfs[pwy])) # num orfs
if options.wtd:
line.append(pwy_to_wtd[pwy][0]) # wtd
line.append(pwy_to_wtd[pwy][1]) # wtd observed taxa
line.append(pwy_to_wtd[pwy][2]) # wtd expected taxa
line.append("[" + ",".join(pwy_to_orfs[pwy]) + "]") # list of ORFs
line = map(str, line) # cast all to string
out.write("\t".join(line) + "\n") # write out line
try:
out.close() # close file
rename(table_out_tmp, options.table_out)
except:
print "Had problems closing file: " + options.table_out
def main(argv, errorlogger=None, runcommand=None, runstatslogger=None):
global parser
options, args = parser.parse_args(argv)
if options.inputfolder == None:
parser.error('ERROR\tInput folder for Pathologic not found')
else:
# required files to be able to build ePGDB
files = [
options.inputfolder + PATHDELIM + '0.pf',
# options.inputfolder + PATHDELIM + '0.fasta',
options.inputfolder + PATHDELIM + 'genetic-elements.dat',
options.inputfolder + PATHDELIM + 'organism-params.dat'
]
if files_exist(files, errorlogger=errorlogger):
exit_process(
"ERROR\tCannot find all inputs for Pathologic in folder %s : "
% (options.inputfolder))
# is there a pathwaytools executable installed
if not path.exists(options.ptoolsExec):
eprintf("ERROR\tPathwayTools executable %s not found!\n",
options.ptoolsExec)
if errorlogger:
errorlogger.printf(
"ERROR\tPathwayTools executable %s not found!\n",
options.ptoolsExec)
exit_process("ERROR\tPathwayTools executable %s not found!\n" %
(options.ptoolsExec))
# command to build the ePGDB
command = "%s -patho %s" % (options.ptoolsExec, options.inputfolder)
if options.no_taxonomic_pruning:
command += " -no-taxonomic-pruning "
if options.no_web_cel_overview:
command += " -no-web-cel-overview"
command += " -api"
status = 0
fix_pgdb_input_files(options.pgdbdir, pgdbs=[])
if not path.exists(options.pgdbdir):
status = runPathologicCommand(runcommand=command)
fix_pgdb_input_files(options.pgdbdir, pgdbs=[])
if status != 0:
eprintf("ERROR\tFailed to run Pathologic on input %s : \n" %
(options.inputfolder))
eprintf(
"INFO\tKill any other PathwayTools instance running on the machine and try again\n"
)
if errorlogger:
errorlogger.write(
"ERROR\tFailed to run Pathologic on input %s : " %
(options.inputfolder))
errorlogger.write(
"INFO\tKill any other PathwayTools instance running on the machine and try again"
)
errorlogger.write(" : " + command)
exit_process("ERROR\tFailed to run Pathologic on input %s : " %
(options.inputfolder))
if not path.exists(options.reactions_list):
try:
pythonCyc = startPathwayTools(options.sample_name.lower(),
options.ptoolsExec, True)
pythonCyc.setDebug() # disable pathway debug statements
printf("INFO\tExtracting the reaction list from ePGDB " +
options.sample_name + "\n")
resultLines = pythonCyc.getReactionListLines()
#pythonCyc.stopPathwayTools()
reaction_list_file = open(options.reactions_list + ".tmp", 'w')
for line in resultLines:
fprintf(reaction_list_file, "%s\n", line.strip())
reaction_list_file.close()
rename(options.reactions_list + ".tmp", options.reactions_list)
StopPathwayTools()
except:
print traceback.print_exc(10)
eprintf("ERROR\tFailed to run extract pathways for %s : \n" %
(options.sample_name))
eprintf(
"INFO\tKill any other PathwayTools instance running on the machine and try again"
)
if errorlogger:
errorlogger.write(
"ERROR\tFailed to run extract pathways for %s : " %
(options.sample_name))
errorlogger.write(
"INFO\tKill any other PathwayTools instance running on the machine and try again\n"
)
StopPathwayTools()
if not path.exists(options.table_out):
ExtractPathway_WTD(options)
def ExtractPathway_WTD(options):
# Extract pathways and WTD
# place to store list of expected taxonomic range(s)
printf('\n')
printf('INFO\tEntering the WTD calculations!\n')
serialized_metacyc_taxa_ranges = "/tmp/metacyc_pwy_taxa_range.pk"
try:
#print options.wtd, not path.isfile(serialized_metacyc_taxa_ranges), serialized_metacyc_taxa_ranges
if options.wtd and not path.isfile(serialized_metacyc_taxa_ranges):
# get MetaCyc's expected taxonomic range(s) and serialize for later use in /tmp
# try:
printf('INFO\tGetting MetaCyc Expected Taxonomic Range(s)\n')
pythonCyc = startPathwayTools('meta', options.ptoolsExec, True)
pwys = pythonCyc.getAllPathways()
pwy_taxa_range = {} # hash from pwy to expected taxonomic range(s)
pwy_taxa_range_pk = open(serialized_metacyc_taxa_ranges ,"w")
# get expected taxonomic ranges for each pathway
for pwy in pwys:
printf(" " + pwy)
my_expected_taxonomic_range = pythonCyc.getExpectedTaxonomicRange(pwy)
pwy_taxa_range[pwy] = my_expected_taxonomic_range
# printf(" " + pwy)
# write the pathway
pickle.dump(pwy_taxa_range, pwy_taxa_range_pk)
pwy_taxa_range_pk.close()
StopPathwayTools()
# read expected taxonomic range from serialized file
exepected_taxa_in = open(serialized_metacyc_taxa_ranges ,"r")
pwy_taxa_range = pickle.load(exepected_taxa_in)
# create mapping of preferred NCBI to MEGAN taxonomy
megan_map = {}
if options.ncbi_megan_map:
with open(options.ncbi_megan_map) as megan_map_file:
for line in megan_map_file:
fields = line.split("\t")
fields = map(str.strip, fields)
megan_map[ fields[0] ] = fields[1]
# get ORF to taxa map from annotation_table
printf("INFO\tGetting ORF to Taxa Map from AnnotationTable\n")
orf_lca = {}
with open(options.annotation_table) as f:
for line in f:
fields = line.split("\t")
orf_lca[fields[0].strip()] = fields[8].strip()
# get pathway ORFs and Rxns
pwy_to_orfs = {}
pwy_to_long = {}
pwy_to_rxns = {}
try:
pythonCyc = startPathwayTools(options.sample_name.lower(), options.ptoolsExec, True)
pwys = pythonCyc.getAllPathways()
for pwy in pwys:
printf(" " + pwy)
genes = pythonCyc.getPathwayORFs(pwy)
rxns = pythonCyc.getPathwayReactionInfo(pwy)
pwy_to_orfs[pwy] = genes
pwy_to_long[pwy] = cleanup(pythonCyc.get_slot_value(pwy, "common-name"))
pwy_to_rxns[pwy] = rxns
# printf("\n")
StopPathwayTools()
except:
insert_error(9)
print """
Problem connecting to Pathway Tools. Check the /tmp/ptools-socket file.
"""
except:
print """
Problem calculating WTD via Pathway Tools. Check the /tmp/ptools-socket file.
"""
insert_error(9)
# get LCA per pathway
pwy_lca = {}
# load NCBI taxonomy map
printf("\nINFO\tLoading NCBI Taxonomy Map\n")
lca = LCAComputation([ options.ncbi_tree ], )
for pwy in pwy_to_orfs:
orfs = pwy_to_orfs[pwy]
taxa_ids = []
for orf in orfs:
if orf in orf_lca:
# could strip out id here
res = re.search("(.+?)\(([0-9]+?)\)", orf_lca[orf] )
if res:
taxa_annotation = res.group(1)
id = res.group(2)
else:
id = lca.get_a_Valid_ID([ orf_lca[orf] ])
taxa_ids.append(id)
pwy_lca_id = lca.get_lca(taxa_ids, True)
# print "In run_pathologic"
# print pwy_lca_id
# print pwy_lca_id
lca.clear_cells(taxa_ids)
pwy_lca[pwy] = [pwy_lca_id, lca.translateIdToName(pwy_lca_id)]
# calculate weighted taxonomic distance
pwy_to_wtd = {}
printf("INFO\tCalculating WTD\n")
for pwy in pwy_lca:
C = [] # list of distances
C_taxa = [] # list of parallel observed-expected taxa pairs
C_pos = [] # list of non-negative distances
C_pos_taxa = [] # list of parallel observed-expected taxa pairs
C_neg = [] # list of negative distances
C_neg_taxa = [] # list of parallel observed-expected taxa pairs
if pwy in pwy_taxa_range and len(pwy_taxa_range[pwy]) :
for expected in pwy_taxa_range[pwy]:
dist = lca.wtd(expected[0], pwy_lca[pwy][0])
if dist or dist == 0:
# valid distance
# add distance respective lists
C.append(dist) # add distance
C_taxa.append([ expected[0], pwy_lca[pwy][0] ])
if dist >= 0:
C_pos.append(dist) # add to non-negative list
C_pos_taxa.append([ expected[0], pwy_lca[pwy][0] ])
else:
C_neg.append(dist) # add to negative list
C_neg_taxa.append([ expected[0], pwy_lca[pwy][0] ])
else:
print "Not a valid distance"
continue
else:
# no expected taxonomy, set to root
min_taxa = "1"
dist = lca.wtd(min_taxa, pwy_lca[pwy][0])
# add distance respective lists
C.append(dist) # add distance
C_taxa.append([ min_taxa, pwy_lca[pwy][0] ])
if dist >= 0:
C_pos.append(dist) # add to non-negative list
C_pos_taxa.append([ min_taxa, pwy_lca[pwy][0] ])
else:
C_neg.append(dist) # add to negative list
C_neg_taxa.append([ min_taxa, pwy_lca[pwy][0] ])
# find index with max distance (closest to expected taxonomy)
max_index, max_dist = max(enumerate(C), key=operator.itemgetter(1))
max_taxa = C_taxa[max_index]
# remap to preferred names
observed = get_preferred_taxa_name(max_taxa[1], megan_map, lca.id_to_name)
expected = get_preferred_taxa_name(max_taxa[0], megan_map, lca.id_to_name)
pwy_to_wtd[pwy] = [ max_dist, observed, expected ]
# write out pathway table
table_out_tmp = options.table_out + ".tmp"
try:
out = open(table_out_tmp, "w")
except:
print "Had problems opening file: " + options.table_out
insert_error(9)
# write appropreate header
if options.wtd:
header = "SAMPLE\tPWY_NAME\tPWY_COMMON_NAME\tNUM_REACTIONS\tNUM_COVERED_REACTIONS\tORF_COUNT\tWTD\tOBSERVED\tEXPECTED\tORFS\n"
else:
header = "SAMPLE\tPWY_NAME\tPWY_COMMON_NAME\tNUM_REACTIONS\tNUM_COVERED_REACTIONS\tORF_COUNT\tORFS\n"
out.write(header)
sample = options.sample_name # sample name
for pwy in pwy_to_orfs:
# generate output line
line = []
line.append(sample) # sample name
line.append(pwy) # pathway name
line.append(pwy_to_long[pwy]) # pathway longname
line.append(pwy_to_rxns[pwy][0]) # pathway num reactions
line.append(pwy_to_rxns[pwy][1]) # pathway covered reactions
line.append(len(pwy_to_orfs[pwy])) # num orfs
if options.wtd:
line.append(pwy_to_wtd[pwy][0]) # wtd
line.append(pwy_to_wtd[pwy][1]) # wtd observed taxa
line.append(pwy_to_wtd[pwy][2]) # wtd expected taxa
line.append("[" + ",".join(pwy_to_orfs[pwy]) + "]") # list of ORFs
line = map(str, line) # cast all to string
out.write("\t".join(line) + "\n") # write out line
try:
out.close() # close file
rename(table_out_tmp, options.table_out)
except:
print "Had problems closing file: " + options.table_out
insert_error(9)
def main(argv, errorlogger = None, runcommand = None, runstatslogger = None):
global parser
options, args = parser.parse_args(argv)
if options.inputfolder ==None:
parser.error('ERROR\tInput folder for Pathologic not found')
else:
# required files to be able to build ePGDB
files = [
#options.inputfolder + PATHDELIM + '0.pf',
# options.inputfolder + PATHDELIM + '0.fasta',
options.inputfolder + PATHDELIM + 'genetic-elements.dat',
options.inputfolder + PATHDELIM + 'organism-params.dat'
]
if files_exist( files , errorlogger = errorlogger):
exit_process("ERROR\tCannot find all inputs for Pathologic in folder %s : " %(options.inputfolder) )
# is there a pathwaytools executable installed
if not path.exists(options.ptoolsExec):
eprintf("ERROR\tPathwayTools executable %s not found!\n", options.ptoolsExec)
if errorlogger:
errorlogger.printf("ERROR\tPathwayTools executable %s not found!\n", options.ptoolsExec)
exit_process("ERROR\tPathwayTools executable %s not found!\n" %(options.ptoolsExec))
# command to build the ePGDB
command = "%s -patho %s" %(options.ptoolsExec, options.inputfolder)
if options.no_taxonomic_pruning:
command += " -no-taxonomic-pruning "
if options.no_web_cel_overview:
command += " -no-web-cel-overview"
command += " -tip"
command += " -api"
status =0
fix_pgdb_input_files(options.pgdbdir, pgdbs = [])
if not path.exists(options.pgdbdir):
status = runPathologicCommand(runcommand = command)
fix_pgdb_input_files(options.pgdbdir, pgdbs = [])
if status!=0:
eprintf("ERROR\tFailed to run Pathologic on input %s : \n" %(options.inputfolder))
eprintf("INFO\tKill any other PathwayTools instance running on the machine and try again\n")
if errorlogger:
errorlogger.write("ERROR\tFailed to run Pathologic on input %s : " %(options.inputfolder))
errorlogger.write("INFO\tKill any other PathwayTools instance running on the machine and try again")
errorlogger.write(" : " + command)
insert_error(9)
sys.exit(0)
#exit_process("ERROR\tFailed to run Pathologic on input %s : " %(options.inputfolder) )
if not path.exists(options.reactions_list):
try:
pythonCyc = startPathwayTools(options.sample_name.lower(), options.ptoolsExec, True)
pythonCyc.setDebug() # disable pathway debug statements
printf("INFO\tExtracting the reaction list from ePGDB " + options.sample_name + "\n")
resultLines = pythonCyc.getReactionListLines()
#pythonCyc.stopPathwayTools()
reaction_list_file = open(options.reactions_list + ".tmp", 'w')
for line in resultLines:
fprintf(reaction_list_file,"%s\n",line.strip())
reaction_list_file.close()
rename(options.reactions_list + ".tmp", options.reactions_list)
StopPathwayTools()
except:
print traceback.print_exc(10)
eprintf("ERROR\tFailed to run extract pathways for %s : \n" %(options.sample_name))
eprintf("INFO\tKill any other PathwayTools instance running on the machine and try again")
if errorlogger:
errorlogger.write("ERROR\tFailed to run extract pathways for %s : " %(options.sample_name))
errorlogger.write("INFO\tKill any other PathwayTools instance running on the machine and try again\n")
insert_error(9)
StopPathwayTools()
if not path.exists(options.table_out):
ExtractPathway_WTD(options)
