def create_amylpred_data(n):
if os.path.exists("data/temp/amylpred" + str(n) + "set.txt"):
print "Using existing data."
return
if not os.path.exists("data/temp/amino_acid_index.txt"):
create_aaindex()
create_amylpred_npeptide_data(n)
fp = open("data/temp/amylpred" + str(n) + "peptides.txt")
fn = open("data/temp/neg-" + str(n) + "peptides.txt")
data = [line.rstrip() + " 1" for line in fp.readlines()] # Positive data
neg = [line.rstrip() + " 0" for line in fn.readlines()] # Negative data
data.extend(neg)
# Shuffle the data randomly so that we can do cross-validation
random.shuffle(data)
# Creating a dataset with all features
temp_amylprednset = open("data/temp/temp_amylpred" + str(n) + "set.txt",
"w")
# Compute the features for each sequence and append them to the data
for i in xrange(len(data)):
seq_features = " ".join(
str(e) for e in compute_features(data[i].split()[0]))
temp_amylprednset.write(data[i] + " " + seq_features + "\n")
temp_amylprednset.close()
if not os.path.exists("data/temp/amylpred_feature_dataframe.csv"):
import optimal_feature_selection as ofs
ofs.select_optimal_features(n, "amylpred")
feature_dataframe = pd.read_csv("data/temp/amylpred_feature_dataframe.csv",
index_col=0,
header=0)
feature_ids = [x for x in feature_dataframe["id"]]
feature_ids.extend(range(len(feature_ids), len(feature_ids) + n))
# Compute the features for each sequence and append them to the data
amylprednset = open("data/temp/amylpred" + str(n) + "set.txt", "w")
for i in xrange(len(data)):
seq_features = " ".join(
str(e) for e in compute_features(data[i].split()[0], feature_ids))
amylprednset.write(data[i] + " " + seq_features + "\n")
print "The amylprednset.txt has been created."
def create_zipper_data(n):
if os.path.exists("data/temp/zipper_hexpepset.txt"):
print "Using existing data."
return
if not os.path.exists("data/temp/amino_acid_index.txt"):
create_aaindex()
f = open("data/test/zipper_dataset.txt")
data = []
for line in f:
if line.strip()[0] == "+":
data.append(line.split()[1] + " 1") # Positive data
else:
data.append(line.split()[1] + " 0") # Negative data
# Shuffle the data randomly so that we can do cross-validation
random.shuffle(data)
# Creating a dataset with all features
temp_zipper_hexpepset = open("data/temp/temp_zipper_hexpepset.txt", "w")
# Compute the features for each sequence and append them to the data
for i in xrange(len(data)):
seq_features = " ".join(
str(e) for e in compute_features(data[i].split()[0]))
temp_zipper_hexpepset.write(data[i] + " " + seq_features + "\n")
temp_zipper_hexpepset.close()
if not os.path.exists("data/temp/zipper_feature_dataframe.csv"):
import optimal_feature_selection as ofs
ofs.select_optimal_features(6, "zipper")
feature_dataframe = pd.read_csv("data/temp/zipper_feature_dataframe.csv",
index_col=0,
header=0)
feature_ids = [x for x in feature_dataframe["id"]]
feature_ids.extend(range(len(feature_ids), len(feature_ids) + n))
# Compute the features for each sequence and append them to the data
zipper_hexpepset = open("data/temp/zipper_hexpepset.txt", "w")
for i in xrange(len(data)):
seq_features = " ".join(
str(e) for e in compute_features(data[i].split()[0], feature_ids))
zipper_hexpepset.write(data[i] + " " + seq_features + "\n")
print "The zipper_hexpepset.txt has been created."
def create_amylpred_data(n):
if os.path.exists("data/temp/amylpred_hexpepset.txt"):
print "Using existing data."
return
if not os.path.exists("data/temp/amino_acid_index.txt"):
create_aaindex()
f = open("data/test/amylpred_dataset.txt")
data = []
for line in f:
if line.strip()[0]=="+":
data.append(line.split()[1] + " 1") # Positive data
else:
data.append(line.split()[1] + " 0") # Negative data
# Shuffle the data randomly so that we can do cross-validation
random.shuffle(data)
# Creating a dataset with all features
temp_amylpred_hexpepset = open("data/temp/temp_amylpred_hexpepset.txt", "w")
# Compute the features for each sequence and append them to the data
for i in xrange(len(data)):
seq_features = " ".join(str(e) for e in compute_features(data[i].split()[0]))
temp_amylpred_hexpepset.write(data[i] + " " + seq_features + "\n")
temp_amylpred_hexpepset.close()
if not os.path.exists("data/temp/amylpred_feature_dataframe.csv"):
import optimal_feature_selection as ofs
ofs.select_optimal_features(6, "amylpred")
feature_dataframe = pd.read_csv("data/temp/amylpred_feature_dataframe.csv",
index_col=0, header=0)
feature_ids = [x for x in feature_dataframe["id"]]
feature_ids.extend(range(len(feature_ids), len(feature_ids)+n))
# Compute the features for each sequence and append them to the data
amylpred_hexpepset = open("data/temp/amylpred_hexpepset.txt", "w")
for i in xrange(len(data)):
seq_features = " ".join(str(e) for e in compute_features(data[i].split()[0],
feature_ids))
amylpred_hexpepset.write(data[i] + " " + seq_features + "\n")
print "The amylpred_hexpepset.txt has been created."
def create_amylnset(n):
if os.path.exists("data/temp/amyl"+str(n)+"set.txt"):
return
if not os.path.exists("data/temp/amino_acid_index.txt"):
create_aaindex()
create_npeptide_data(n)
fp = open("data/temp/"+str(n)+"peptides.txt")
fn = open("data/temp/neg-"+str(n)+"peptides.txt")
data = [line.rstrip() + " 1" for line in fp.readlines()] # Positive data
neg = [line.rstrip() + " 0" for line in fn.readlines()] # Negative data
data.extend(neg)
# Shuffle the data randomly so that we can do cross-validation
random.shuffle(data)
# Creating dataset with all features.
temp_amylnset = open("data/temp/temp_amyl"+str(n)+"set.txt", "w")
# Compute the features for each sequence and append them to the data
for i in xrange(len(data)):
seq_features = " ".join(str(e) for e in compute_features(data[i].split()[0]))
temp_amylnset.write(data[i] + " " + seq_features + "\n")
temp_amylnset.close()
# Create the .csv file of the sorted scores of features if it does not exist
if not os.path.exists("data/temp/amylnset_feature_dataframe.csv"):
import optimal_feature_selection as ofs
ofs.select_optimal_features(6, "amylnset")
# Creating dataset with optimal features.
amylnset = open("data/temp/amyl"+str(n)+"set.txt", "w")
feature_dataframe = pd.read_csv("data/temp/amylnset_feature_dataframe.csv",
index_col=0, header=0)
feature_ids = [x for x in feature_dataframe["id"]]
feature_ids.extend(range(len(feature_ids), len(feature_ids)+n))
# Compute the features for each sequence and append them to the data
for i in xrange(len(data)):
seq_features = " ".join(str(e) for e in compute_features(data[i].split()[0],
feature_ids))
amylnset.write(data[i] + " " + seq_features + "\n")
