# optional arguments
do_append = False
if options.do_append: do_append = options.do_append
simil_metric = 'Dice'
if options.simil: simil_metric = options.simil
outpath = path
outpath_set = False
if options.outpath:
outpath_set = True
outpath = path+options.outpath
# check for sensible input
fp_names = scor.checkFPFile(fp_file)
if not fp_names: raise ValueError('No fingerprints given in', fp_file)
if outpath_set: scor.checkPath(outpath, 'output')
scor.checkSimil(simil_metric)
scor.checkQueryMols(num_query_mols, conf.list_num_query_mols)
# loop over data-set sources
for dataset in conf.set_data.keys():
print dataset
# loop over targets
for target in conf.set_data[dataset]['ids']:
print target
# read in actives and calculate fps
actives = []
for line in gzip.open(inpath_cmp+dataset+'/cmp_list_'+dataset+'_'+str(target)+'_actives.dat.gz', 'r'):
if line[0] != '#':
# structure of line: [external ID, internal ID, SMILES]]
do_append = options.do_append
simil_metric = "Dice"
if options.simil:
simil_metric = options.simil
outpath = path
outpath_set = False
if options.outpath:
outpath_set = True
# outpath = path + options.outpath
# changed to absolute , by @Matt
outpath = options.outpath
os.system("mkdir -p {}".format(outpath))
# check for sensible input
if outpath_set:
scor.checkPath(outpath, "output")
scor.checkSimil(simil_metric)
scor.checkQueryMols(num_query_mols, conf.list_num_query_mols)
# default machine-learning method variables
ml_dict = dict(
criterion="gini",
max_features="auto",
n_jobs=1,
max_depth=10,
min_samples_split=2,
min_samples_leaf=1,
num_estimators=100,
)
if options.ml:
ml_dict = ml_func.readMLFile(ml_dict, read_dict, path + options.ml)
# optional arguments
do_append = False
if options.do_append: do_append = options.do_append
simil_metric = 'Dice'
if options.simil: simil_metric = options.simil
outpath = path
outpath_set = False
if options.outpath:
outpath_set = True
outpath = path + options.outpath
# check for sensible input
fp_names = scor.checkFPFile(fp_file)
if not fp_names: raise ValueError('No fingerprints given in', fp_file)
if outpath_set: scor.checkPath(outpath, 'output')
scor.checkSimil(simil_metric)
scor.checkQueryMols(num_query_mols, conf.list_num_query_mols)
# loop over data-set sources
for dataset in conf.set_data.keys():
print dataset
# loop over targets
for target in conf.set_data[dataset]['ids']:
print target
# read in actives and calculate fps
actives = []
for line in gzip.open(
inpath_cmp + dataset + '/cmp_list_' + dataset + '_' +
str(target) + '_actives.dat.gz', 'r'):
dest="do_append",
action="store_true",
help="append to the output file (default: False)",
)
######################## MAIN PART ###########################
if __name__ == "__main__":
# read in command line options
(options, args) = parser.parse_args()
# required arguments
if options.inpath:
inpath = [path + i for i in options.inpath]
for inp in inpath:
scor.checkPath(inp, "input")
else:
raise RuntimeError(
"one or more of the required options was not given!"
)
# optional arguments
method = "max"
if options.method:
if options.method not in ["max", "ave"]:
raise ValueError(
"method is unkown. supported methods are: max and ave"
)
else:
method = options.method
remove_fps = []
parser.add_option("-a",
"--append",
dest="do_append",
action="store_true",
help="append to the output file (default: False)")
######################## MAIN PART ###########################
if __name__ == '__main__':
# read in command line options
(options, args) = parser.parse_args()
# required arguments
if options.inpath:
inpath = [path + i for i in options.inpath]
for inp in inpath:
scor.checkPath(inp, 'input')
else:
raise RuntimeError(
'one or more of the required options was not given!')
# optional arguments
method = 'max'
if options.method:
if options.method not in ['max', 'ave']:
raise ValueError(
'method is unkown. supported methods are: max and ave')
else:
method = options.method
remove_fps = []
if options.rm_file:
remove_fps = scor.readFPs(path + options.rm_file)
do_append = options.do_append
simil_metric = "Dice"
if options.simil:
simil_metric = options.simil
outpath = path
outpath_set = False
if options.outpath:
outpath_set = True
outpath = path + options.outpath
# check for sensible input
fp_names = scor.checkFPFile(fp_file)
if not fp_names:
raise ValueError("No fingerprints given in", fp_file)
if outpath_set:
scor.checkPath(outpath, "output")
scor.checkSimil(simil_metric)
# loop over targets
for target in conf.set_data:
print target
# read in training actives and calculate fps
actives = cPickle.load(open(inpath_cmp + "ChEMBL_II/Target_no_" + str(target) + ".pkl", "r"))
for k in actives.keys():
for i, m in enumerate(actives[k]):
fp_dict = scor.getFPDict(fp_names, m[1])
actives[k][i] = [str(target) + "_" + str(k) + "_A_" + str(i + 1), fp_dict]
# read in test actives and calculate fps
div_actives = []
method = options.method
MODE = "SIM"
else:
raise RuntimeError("the method option was not recognized")
else:
method = "Tanimoto"
MODE = "SIM"
DEFAULT_OUTDIR = os.path.join(os.getcwd(), "benchmark_results/")
if options.outdir:
outdir = options.outdir
else:
outdir = DEFAULT_OUTDIR
if not os.path.exists(outdir):
os.system("mkdir {path}".format(path=outdir))
scor.checkPath(outdir, "outdir")
### run the required benchmark scripts ###
# first score
os.chdir(scoring_path)
print("cwd: ", os.getcwd())
if MODE == "ML":
# need to change dir
os.system(
"python calculate_scored_lists_{ml_method}.py -n {ml_num} -f {ml_fp} -s {ml_sim} -o {ml_outpath}".format(
ml_method=method,
ml_num=num_query_mols,
ml_fp=fp,
ml_sim="Tanimoto",
ml_outpath=os.path.join(
parser.add_option("-m", "--method", dest="method", help="method for data fusion (max or ave, default: max)")
parser.add_option("-r", "--remove", dest="rm_file", metavar="FILE", help="FILE containing the fingerprints to be left out (default: all fingerprints are read)")
parser.add_option("-o", "--outpath", dest="outpath", metavar="PATH", help="relative output PATH (default: pwd)")
parser.add_option("-a", "--append", dest="do_append", action="store_true", help="append to the output file (default: False)")
######################## MAIN PART ###########################
if __name__=='__main__':
# read in command line options
(options, args) = parser.parse_args()
# required arguments
if options.inpath:
inpath = [path+i for i in options.inpath]
for inp in inpath:
scor.checkPath(inp, 'input')
else:
raise RuntimeError('one or more of the required options was not given!')
# optional arguments
method = 'max'
if options.method:
if options.method not in ['max', 'ave']:
raise ValueError('method is unkown. supported methods are: max and ave')
else:
method = options.method
remove_fps = []
if options.rm_file:
remove_fps = scor.readFPs(path+options.rm_file)
outpath = path
if options.outpath: