def calc_feature_combination(args):
feature_combination, se, input_dir, use_rf, num_folds, overlap, local, cutoff, num_cores, scoreF, mode, anno, faF, ref_complexes, output_dir = args
#Create feature combination
cutoff = float(cutoff) / 100
num_folds = int(num_folds)
if feature_combination == "00000000": sys.exit()
this_scores = get_fs_comb(feature_combination)
num_cores = int(num_cores)
use_rf = use_rf == "True"
overlap = overlap == "True"
local = local == "True"
clf_name = "SVM"
if use_rf: clf_name = "RF"
clf = CS.CLF_Wrapper(num_cores, use_rf)
ref_gs = Goldstandard_from_cluster_File(ref_complexes)
scoreCalc = CS.CalculateCoElutionScores(this_scores,
"",
scoreF,
num_cores=num_cores,
cutoff=cutoff)
scoreCalc.readTable(scoreF, ref_gs)
feature_comb = feature_selector([fs.name for fs in this_scores], scoreCalc)
print feature_comb.scoreCalc.scores.shape
print scoreCalc.scores.shape
if mode == "comb":
fa = utils.get_FA_data(anno, faF)
feature_comb.add_fun_anno(fa)
elif mode == "fa":
feature_comb = utils.get_FA_data(anno, faF)
print type(feature_comb)
elif mode != "exp":
print "not support this mode"
sys.exit()
scores, head = n_fold_cross_validation(num_folds, ref_gs, feature_comb,
clf, output_dir, overlap, local)
outFH = open(output_dir + ".eval.txt", "w")
print "FS\tSE\tCLF\t" + head
print "%s\t%s\t%s\t" % (feature_combination, se, clf_name) + scores
print >> outFH, "FS\tSE\tCLF\t" + head
print >> outFH, "%s\t%s\t%s\t" % (feature_combination, se,
clf_name) + scores
outFH.close()
def ppi_fs(args):
fsc, scoreF, use_rf, se, num_cores, refComplexesF, output_dir = args
num_cores = int(num_cores)
use_rf = use_rf == "True"
clf_name = "SVM"
if use_rf: clf_name = "RF"
clf = CS.CLF_Wrapper(num_cores, use_rf)
this_fs = get_fs_comb(fsc)
all_gs = Goldstandard_from_cluster_File(refComplexesF)
valprots = all_gs.get_proteins()
scoreCalc = CS.CalculateCoElutionScores(this_fs,
"",
scoreF,
num_cores=num_cores,
cutoff=-1)
scoreCalc.readTable(scoreF, all_gs)
print scoreCalc.scores.shape
test_scoreCalc = feature_selector([fs.name for fs in this_fs], scoreCalc)
print("The size of chopped matrix for selected features")
print np.shape(test_scoreCalc.get_scoreCalc().get_all_scores())
print "training ppis: %i" % len(set(test_scoreCalc.ppiToIndex.keys()))
train_gold_complexes = all_gs.return_gold_standard_complexes(
set(test_scoreCalc.ppiToIndex.keys()))
print "Train_gold comp:%i" % len(train_gold_complexes.complexes.complexes)
print "Num valid ppis in pos: %i" % len(train_gold_complexes.positive)
print "Num valid ppis in neg: %i" % len(train_gold_complexes.negative)
# Evaluate classifier
evaluation_results = utils.bench_by_PPI_clf(10, test_scoreCalc,
train_gold_complexes, clf)
print evaluation_results
outFH = open("%s.ppi_eva.txt" % (output_dir), "w")
print >> outFH, "FS\tSE\tCLF\tFM\tauPR\tauROC\n%s\t%s\t%s\t%s" % (
fsc, se, clf_name, "\t".join(map(str, evaluation_results)))
outFH.close()
def cut(args):
fc, scoreF, outF = args
if fc == "00000000": sys.exit()
this_scores = get_fs_comb(fc)
scoreCalc = CS.CalculateCoElutionScores("", "", "", "", cutoff=0.5)
empty_gs = GS.Goldstandard_from_Complexes()
empty_gs.positive = set([])
empty_gs.negative = set([])
scoreCalc.readTable(scoreF, empty_gs)
print scoreCalc.to_predict
feature_comb = feature_selector([fs.name for fs in this_scores], scoreCalc)
feature_comb.open()
outFH = open(outF, "w")
print >> outFH, "\t".join(feature_comb.scoreCalc.header)
for i in range(feature_comb.to_predict):
edge, edge_scores = feature_comb.get_next()
if edge == "" or edge_scores == []: continue
print >> outFH, "%s\t%s" % (edge, "\t".join(map(str, edge_scores)))
outFH.close()
feature_comb.close()
def calc_scores(args):
topred = []
if args[0] == "-ref":
_, refF, fs, numcores, cutoff, e_dir, outF = args
gs = Goldstandard_from_cluster_File(refF)
topred = list(gs.positive | gs.negative)
print len(topred)
else:
fs, numcores, cutoff, e_dir, outF = args
numcores = int(numcores)
cutoff = float(cutoff)
this_fs = get_fs_comb(fs)
prots, edatas = utils.load_data(e_dir, this_fs)
scoreCalc = CS.CalculateCoElutionScores(this_fs,
edatas,
outF,
num_cores=numcores,
cutoff=cutoff)
if topred == []: topred = scoreCalc.getAllPairs()
scoreCalc.calculateScores(topred)
def filter_scoreCalc(self, scoreCalc):
filtered_sc = CS.CalculateCoElutionScores("", "", "", 1)
filtered_sc.scoreF = scoreCalc.scoreF
filtered_sc.header = list(
np.array(scoreCalc.header)[self.to_keep_header])
filtered_sc.scores = np.zeros(
(len(scoreCalc.ppiToIndex.keys()), len(self.to_keep_score)))
ppi_index = 0
for i in range(scoreCalc.scores.shape[0]):
ppi = scoreCalc.IndexToPpi[i]
protA, protB = ppi.split("\t")
if (protA not in self.valprots
or protB not in self.valprots) and self.valprots != []:
continue
ppi_scores = self.filter_score(scoreCalc.scores[i, :])
if ppi_scores == []: continue
filtered_sc.ppiToIndex[ppi] = ppi_index
filtered_sc.IndexToPpi[ppi_index] = ppi
filtered_sc.scores[ppi_index, :] = ppi_scores
ppi_index += 1
filtered_sc.scores = filtered_sc.scores[0:ppi_index, :]
return filtered_sc
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"-s",
"--feature_selection",
type=str,
help=
"Select which features to use. This is an 8 position long array of 0 and 1, where each position determines which co-elution feature to use. Features sorted by position are: MI, Bayes, Euclidean, WCC, Jaccard, PCCN, PCC, and Apex. Each default=11101001",
default="11101001")
parser.add_argument(
"input_dir",
type=str,
help="Directory containing the elution files for each experiment")
parser.add_argument(
"-t",
"--taxid",
type=str,
help="TAXID to automatically download reference from GO,CORUM,INtACT",
default="")
parser.add_argument(
"-c",
"--cluster",
type=str,
help="Path to file containing protein clsuter reference",
default="")
parser.add_argument("-p",
"--ppi",
type=str,
help="path to ppi File",
default="")
parser.add_argument("output_dir",
type=str,
help="Directory containing the output files")
parser.add_argument("-o",
"--output_prefix",
type=str,
help="Prefix name for all output Files",
default="Out")
parser.add_argument(
"-M",
"--classifier",
type=str,
help="Select which classifier to use. Values: RF SVM, default RF",
default="RF")
parser.add_argument("-n",
"--num_cores",
type=int,
help="Number of cores to be used, default 1",
default=1)
parser.add_argument(
"-m",
"--mode",
type=str,
help=
"Run EPIC with experimental, functional, or both evidences. Values: EXP, FA, COMB, default: EXP ",
default="EXP")
parser.add_argument(
"-f",
"--fun_anno_source",
type=str,
help=
"Where to get functional annotaiton from. Values: STRING or GM or FILE, default= GM",
default="GM")
parser.add_argument(
"-F",
"--fun_anno_file",
type=str,
help=
"Path to File containing functional annotation. This flag needs to be set when using FILE as fun_anno_source.",
)
parser.add_argument("-r",
"--co_elution_cutoff",
type=float,
help="Co-elution score cutoff. default 0.5",
default=0.5)
parser.add_argument(
"-R",
"--classifier_cutoff",
type=float,
help="Classifier confidence valye cutoff. default = 0.5",
default=0.5)
parser.add_argument(
"-e",
"--elution_max_count",
type=int,
help=
"Removies protein that have a maximal peptide count less than the given value. default = 1",
default=1)
parser.add_argument(
"-E",
"--frac_count",
type=int,
help=
"Number of fracrions a protein needs to be measured in. default = 2",
default=2)
parser.add_argument(
"-P",
"--precalcualted_score_file",
type=str,
help=
"Path to precalulated scorefile to read scores from for faster rerunning of EPIC. default = None",
default="NONE")
args = parser.parse_args()
args.mode = args.mode.upper()
args.fun_anno_source = args.fun_anno_source.upper()
#Create feature combination
if args.feature_selection == "00000000":
print "Select at least one feature"
sys.exit()
this_scores = utils.get_fs_comb(args.feature_selection)
print "\t".join([fs.name for fs in this_scores])
# Initialize CLF
use_rf = args.classifier == "RF"
clf = CS.CLF_Wrapper(args.num_cores, use_rf)
# Load elution data
foundprots, elution_datas = utils.load_data(args.input_dir,
this_scores,
fc=args.frac_count,
mfc=args.elution_max_count)
# Generate reference data set
gs = ""
if ((args.taxid != "" and args.ppi != "")
or (args.cluster != "" and args.ppi != "")):
print "Refernce from cluster and PPI are nor compatiple. Please supply ppi or complex reference, not both!"
sys.exit()
if args.taxid == "" and args.ppi == "" and args.cluster == "":
print "Please supply a reference by setting taxid, cluster, or ppi tag"
sys.exit()
gs_clusters = []
if (args.taxid != "" and args.cluster == "" and args.ppi == ""):
print "Loading clusters from GO, CORUM, and Intact"
gs_clusters.extend(utils.get_reference_from_net(args.taxid))
if args.cluster != "":
print "Loading complexes from file"
if args.mode == "FA":
gs_clusters.append(GS.FileClusters(args.cluster, "all"))
else:
gs_clusters.append(GS.FileClusters(args.cluster, foundprots))
if args.ppi != "":
print "Reading PPI file from %s" % args.reference
gs = Goldstandard_from_PPI_File(args.ppi, foundprots)
print gs_clusters
if len(gs_clusters) > 0:
gs = utils.create_goldstandard(gs_clusters, args.taxid, foundprots)
output_dir = args.output_dir + os.sep + args.output_prefix
refFH = open(output_dir + ".ref_complexes.txt", "w")
for comp in gs.complexes.complexes:
print >> refFH, "%s\t%s" % (",".join(comp), ",".join(
gs.complexes.complexes[comp]))
refFH.close()
scoreCalc = CS.CalculateCoElutionScores(this_scores,
elution_datas,
output_dir + ".scores.txt",
num_cores=args.num_cores,
cutoff=args.co_elution_cutoff)
if args.precalcualted_score_file == "NONE":
scoreCalc.calculate_coelutionDatas(gs)
else:
scoreCalc.readTable(args.precalcualted_score_file, gs)
print scoreCalc.scores.shape
functionalData = ""
gs.positive = set(gs.positive & set(scoreCalc.ppiToIndex.keys()))
gs.negative = set(gs.negative & set(scoreCalc.ppiToIndex.keys()))
gs.rebalance()
print len(gs.positive)
print len(gs.negative)
if args.mode != "EXP":
print "Loading functional data"
functionalData = utils.get_FA_data(args.fun_anno_source, args.taxid,
args.fun_anno_file)
print "Dimension of fun anno " + str(functionalData.scores.shape)
print "Start benchmarking"
if args.mode == "EXP":
utils.cv_bench_clf(scoreCalc,
clf,
gs,
output_dir,
format="pdf",
verbose=True,
folds=5)
if args.mode == "COMB":
tmp_sc = copy.deepcopy(scoreCalc)
tmp_sc.add_fun_anno(functionalData)
utils.cv_bench_clf(tmp_sc,
clf,
gs,
output_dir,
format="pdf",
verbose=True,
folds=5)
if args.mode == "FA":
utils.cv_bench_clf(functionalData,
clf,
gs,
output_dir,
format="pdf",
verbose=True,
folds=5)
# PPI evaluation
print utils.cv_bench_clf(scoreCalc,
clf,
gs,
args.output_dir,
verbose=False,
format="pdf",
folds=5)
#print "I am here"
network = utils.make_predictions(scoreCalc,
args.mode,
clf,
gs,
fun_anno=functionalData)
# Predict protein interaction
outFH = open("%s.pred.txt" % (output_dir), "w")
final_network = []
for PPI in network:
items = PPI.split("\t")
if float(items[2]) >= args.classifier_cutoff:
final_network.append(PPI)
print >> outFH, "\n".join(final_network)
outFH.close()
# Predicting clusters
utils.predict_clusters("%s.pred.txt" % (output_dir),
"%s.clust.txt" % (output_dir))
# Evaluating predicted clusters
pred_clusters = GS.Clusters(False)
pred_clusters.read_file("%s.clust.txt" % (output_dir))
overlapped_complexes_with_reference = gs.get_complexes(
).get_overlapped_complexes_set(pred_clusters)
print "# of complexes in reference dataset: " + str(
len(overlapped_complexes_with_reference))
#clust_scores, header = utils.clustering_evaluation(gs.complexes, pred_clusters, "", False)
clust_scores, header, composite_score = utils.clustering_evaluation(
gs.complexes, pred_clusters, "", False)
outFH = open("%s.eval.txt" % (output_dir), "w")
header = header.split("\t")
clust_scores = clust_scores.split("\t")
for i, head in enumerate(header):
print "%s\t%s" % (head, clust_scores[i])
print >> outFH, "%s\t%s" % (head, clust_scores[i])
outFH.close()
def exp_comb(args):
FS, i, j, num_iter, input_dir, num_cores, ref_complexes, scoreF, mode, fun_anno_F, ppi, output_dir = args
i, j, num_iter, num_cores = map(int, [i, j, num_iter, num_cores])
ppi == "True"
search_engine = input_dir.split(os.path.sep)[-2]
def get_eData_comb(data_dir, num_iex, num_beads):
all_exp = map(str, glob.glob(data_dir + "*.txt"))
iex_exp = [
f for f in all_exp if (f.split(os.sep)[-1].startswith("all"))
]
beads_exp = [
f for f in all_exp if (not f.split(os.sep)[-1].startswith("all"))
]
if (i > len(iex_exp)):
print "i is to large"
sys.exit()
if (j > len(beads_exp)):
print "j is to large"
sys.exit()
sel_iex = rnd.sample(iex_exp, num_iex)
sel_beads = rnd.sample(beads_exp, num_beads)
return sel_iex + sel_beads
# EPIC paramters
if FS == "00000000": sys.exit()
this_scores = get_fs_comb(FS)
clf = CS.CLF_Wrapper(num_cores, True)
ref_gs = Goldstandard_from_cluster_File(ref_complexes)
scoreCalc = CS.CalculateCoElutionScores(this_scores,
"",
scoreF,
num_cores=num_cores,
cutoff=0.5)
scoreCalc.readTable(scoreF, ref_gs)
# the supplied functional evidence data needs to have the correct header row...
functionalData = ""
if mode == "comb":
functionalData = utils.get_FA_data("FILE", fun_anno_F)
if i == 0 and j == 0: sys.exit()
out_head = ""
all_scores = []
for iter in range(num_iter):
rnd.seed()
this_eprofiles = get_eData_comb(input_dir, i, j)
this_eprofiles_fnames = [
f.rsplit(os.sep, 1)[1] for f in this_eprofiles
]
rnd.seed(1)
print this_eprofiles_fnames
this_foundprots, _ = utils.load_data(this_eprofiles, [])
print len(this_foundprots)
feature_comb = feature_selector(
[fs.name for fs in this_scores],
scoreCalc,
valprots=this_foundprots,
elution_file_names=this_eprofiles_fnames)
if mode == "comb":
feature_comb.add_fun_anno(functionalData)
scores = ""
head = ""
if ppi:
print "Running PPI cross fold"
ppi_ref = ref_gs.return_gold_standard_complexes(
set(feature_comb.scoreCalc.ppiToIndex.keys()))
fmeasure, auc_pr, auc_roc = utils.bench_by_PPI_clf(
10, feature_comb, ppi_ref, clf)
scores = "\t".join(map(str, [fmeasure, auc_pr, auc_roc]))
head = "\tFM\taucPR\taucROC"
else:
print "Running Cluster cross fold"
scores, head = n_fold_cross_validation(2,
ref_gs,
feature_comb,
clf,
"%s_%i_%i" %
(output_dir, i, j),
overlap=True,
local=False)
# head, scores = run_epic_with_feature_combinations(this_scores, ref_gs, scoreCalc, clf, output_dir, valprots=this_foundprots)
out_head = head
all_scores.append(
"%s\t%s\t%i\t%i\t%s\t%i\t%s" %
(FS, mode, i, j, search_engine, len(this_foundprots), scores))
print head
print scores
outFH = open(output_dir + ".%i_%i.all.eval.txt" % (i, j), "w")
print >> outFH, "FS\tNum_iex\tNum_beads\tSearch_engine\tNum_Prots\t%s" % out_head
for score in all_scores:
print >> outFH, "%s" % (score)
outFH.close()
