def write_reference(args): input_dir, taxid, output_dir = args foundprots, elution_datas = utils.load_data(input_dir, []) gs = utils.create_goldstandard(taxid, foundprots) out = gs.complexes.to_string() outFH = open(output_dir, "w") print >> outFH, out outFH.close()
def write_reference(args):
input_dir, taxid, output_dir = args
foundprots, elution_datas = utils.load_data(input_dir, [])
gs = utils.create_goldstandard(taxid, foundprots)
out = gs.complexes.to_string()
outFH = open(output_dir, "w")
print >> outFH, out
outFH.close()
def main():
feature_combination, input_dir, use_rf, num_cores, mode, anno_source, anno_F, target_taxid, refF, output_dir = sys.argv[1:]
#Create feature combination
if feature_combination == "00000000": sys.exit()
scores = [CS.MutualInformation(2), CS.Bayes(3), CS.Euclidiean(), CS.Wcc(), CS.Jaccard(), CS.Poisson(5), CS.Pearson(), CS.Apex()]
this_scores = []
for i, feature_selection in enumerate(feature_combination):
if feature_selection == "1": this_scores.append(scores[i])
print "\t".join([fs.name for fs in this_scores])
# Initialize CLF
use_rf = use_rf == "True"
num_cores = int(num_cores)
clf = CS.CLF_Wrapper(num_cores, use_rf)
# Load elution data
foundprots, elution_datas = utils.load_data(input_dir, this_scores)
# Generate reference data set
if refF == "":
all_gs = utils.create_goldstandard(target_taxid, foundprots)
else:
all_gs = Goldstandard_from_cluster_File(refF, foundprots)
all_gs = utils.create_goldstandard(target_taxid, foundprots)
#all_gs = Goldstandard_from_cluster_File(refF, foundprots)
# sys.exit()
scoreCalc = CS.CalculateCoElutionScores(this_scores, elution_datas, output_dir + ".scores.txt", num_cores=num_cores, cutoff= 0.5)
# scoreCalc.calculate_coelutionDatas(all_gs)
scoreCalc.readTable(output_dir + ".scores.txt", all_gs)
print "training ppis: %i" % len(set(scoreCalc.ppiToIndex.keys()))
#n_fold cross validation to test the stability of preicted PPIs
utils.stability_evaluation(10, all_gs, scoreCalc, clf, output_dir, mode, anno_source, anno_F)
sys.exit()
#n_fold cross validation to select the best features.
n_fold_cross_validation(10, all_gs, scoreCalc, clf, output_dir, mode, anno_source, anno_F)
sys.exit()
###### actually predict the network using all data
train, eval = all_gs.split_into_holdout_training(set(scoreCalc.ppiToIndex.keys()))
print "All comp:%i" % len(all_gs.complexes.complexes)
print "Train comp:%i" % len(train.complexes.complexes)
print "Eval comp:%i" % len(eval.complexes.complexes)
print "Num valid ppis in training pos: %i" % len(train.positive)
print "Num valid ppis in training neg: %i" % len(train.negative)
print "Num valid ppis in eval pos: %i" % len(eval.positive)
print "Num valid ppis in eval neg: %i" % len(eval.negative)
# Evaluate classifier
utils.bench_clf(scoreCalc, train, eval, clf, output_dir, verbose=True)
functionalData = ""
if mode != "exp":
functionalData = utils.get_FA_data(anno_source, anno_F)
print functionalData.scores.shape
# Predict protein interaction
network = utils.make_predictions(scoreCalc, mode, clf, all_gs, functionalData)
outFH = open("%s.%s.pred.txt" % (output_dir, mode + anno_source), "w")
print >> outFH, "\n".join(network)
outFH.close()
# Predicting clusters
utils.predict_clusters("%s.%s.pred.txt" % (output_dir, mode + anno_source), "%s.%s.clust.txt" % (output_dir, mode + anno_source))
# Evaluating predicted clusters
pred_clusters = GS.Clusters(False)
pred_clusters.read_file("%s.%s.clust.txt" % (output_dir, mode + anno_source))
# utils.clustering_evaluation(train.complexes, pred_clusters, "Train", True)
clusterEvaluationScores = utils.clustering_evaluation(eval.complexes, pred_clusters, "", True)
outFH = open("%s.%s.evaluation.txt" % (output_dir, mode + anno_source), "w")
head = clusterEvaluationScores[1]
cluster_scores = clusterEvaluationScores[0]
tmp_head = head.split("\t")
tmp_scores = cluster_scores.split("\t")
for i in range(len(tmp_head)):
outFH.write("%s\t%s" % (tmp_head[i], tmp_scores[i]))
outFH.write("\n")
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()