def human_go_annotations():
go = get_gene_ontology()
annots = {}
df = pd.read_pickle('data/cafa3/swissprot_exp.pkl')
for i, row in df.iterrows():
acc = row['accessions']
gos = set()
for go_id in row['annots']:
go_id = go_id.split('|')
if go_id[1] in EXP_CODES and go_id[0] in go:
gos.add(go_id[0])
if len(gos) > 0:
annots[acc] = gos
id_df = pd.read_pickle('data/idmapping.9606.pkl')
st_ids = dict()
for i, row in id_df.iterrows():
if isinstance(row['string'], str):
st_ids[row['accessions']] = row['string']
with open('data/human_annotations.tab', 'w') as f:
for acc, gos in annots.iteritems():
if acc in st_ids:
f.write(st_ids[acc])
for go_id in gos:
f.write('\t' + go_id)
f.write('\n')
def table():
bp = get_data('bp.res')
mf = get_data('mf.res')
cc = get_data('cc.res')
bp_seq = get_data('bp-seq.res')
mf_seq = get_data('mf-seq.res')
cc_seq = get_data('cc-seq.res')
go = get_gene_ontology('go.obo')
gos = go[BIOLOGICAL_PROCESS]['children']
res = list()
for go_id in gos:
if go_id in bp:
res.append((go_id, go[go_id]['name'], bp[go_id][0], bp[go_id][1],
bp_seq[go_id][0], bp_seq[go_id][1]))
for row in sorted(res, key=lambda x: x[2], reverse=True):
print('%s & %s & %f & %f & %f & %f \\\\' % row)
gos = go[MOLECULAR_FUNCTION]['children']
print()
res = list()
for go_id in gos:
if go_id in mf:
res.append((go_id, go[go_id]['name'], mf[go_id][0], mf[go_id][1],
mf_seq[go_id][0], mf_seq[go_id][1]))
for row in sorted(res, key=lambda x: x[2], reverse=True):
print('%s & %s & %f & %f & %f & %f \\\\' % row)
gos = go[CELLULAR_COMPONENT]['children']
print()
res = list()
for go_id in gos:
if go_id in cc:
res.append((go_id, go[go_id]['name'], cc[go_id][0], cc[go_id][1],
cc_seq[go_id][0], cc_seq[go_id][1]))
for row in sorted(res, key=lambda x: x[2], reverse=True):
print('%s & %s & %f & %f & %f & %f \\\\' % row)
def main(function, device, org, train):
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
logging.info('Functions: %s %d' % (FUNCTION, len(functions)))
if ORG is not None:
logging.info('Organism %s' % ORG)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
global node_names
node_names = set()
with tf.device('/' + device):
model(is_train=train)
def main(split):
global SPLIT
SPLIT = split
global GO_IDS
GO_IDS = list(FUNC_DICT.values())
global go
go = get_gene_ontology('go.obo')
func_df = pd.read_pickle(DATA_ROOT + 'bp.pkl')
global functions
functions = func_df['functions'].values
func_df = pd.read_pickle(DATA_ROOT + 'mf.pkl')
functions = np.concatenate((functions, func_df['functions'].values))
func_df = pd.read_pickle(DATA_ROOT + 'cc.pkl')
functions = np.concatenate((functions, func_df['functions'].values))
global func_set
func_set = (
get_go_set(go, GO_IDS[0])
| get_go_set(go, GO_IDS[1])
| get_go_set(go, GO_IDS[2]))
print(len(functions))
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
run()
def get_annotations():
gene_ontology = get_gene_ontology()
annots = dict()
gene_name = dict()
with open(DATA_ROOT + 'gene_association.sgd', 'r') as f:
for line in f:
if line[0] == '!':
continue
items = line.strip().split('\t')
if items[3] == 'NOT' or items[6] == 'ND':
continue
gene_id = items[1]
gene_name[gene_id] = items[2]
go = items[4]
if gene_id not in annots:
annots[gene_id] = set()
if go in gene_ontology:
annots[gene_id].add(go)
groups = dict()
for gene_id, gos in annots.iteritems():
l = len(gos)
if l not in groups:
groups[l] = list()
groups[l].append((list(gos), gene_id))
with open(DATA_ROOT + 'sgd_annotations_genes2.txt', 'w') as f:
for group in sorted(groups.keys()):
gos_list = groups[group]
print group
for gos, gene_id in gos_list:
f.write(gene_name[gene_id] + '\t')
f.write(gos[0])
for go in gos[1:]:
f.write('\t' + go)
f.write('\n')
def main(function, device, org, train, param, embeddingmethod, shuffleseed,
buildmethod, evomodel, cached):
global CACHED
CACHED = cached
global BUILDMETHOD
BUILDMETHOD = buildmethod
global EVOMODEL
EVOMODEL = evomodel
global EMBEDDINGMETHOD
EMBEDDINGMETHOD = embeddingmethod
global SEED
SEED = shuffleseed
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
global experiment_id
experiment_id = str(function) + '-' + str(embeddingmethod) + '-' + str(
shuffleseed) + '-' + str(buildmethod) + '-' + str(evomodel)
logging.info('Functions: %s %d' % (FUNCTION, len(functions)))
a = experiment_id
global resdir
resdir = "results/" + experiment_id
if not os.path.isdir(resdir):
os.mkdir(resdir)
if ORG is not None:
logging.info('Organism %s' % ORG)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
global node_names
node_names = set()
with tf.device('/' + device):
params = {
'fc_output': 1024,
'learning_rate': 0.001,
'embedding_dims': 128,
'embedding_dropout': 0.2,
'nb_conv': 3,
'nb_dense': 2,
'filter_length': 128,
'nb_filter': 32,
'pool_length': 64,
'stride': 32
}
# model(params, is_train=train)
model(params, is_train=True)
def compute_performance(func):
go = get_gene_ontology()
train_df = pd.read_pickle('data/swissexp/train-' + func + '.pkl')
test_df = pd.read_pickle('data/swissexp/test-' + func + '.pkl')
train_labels = {}
test_labels = {}
for i, row in train_df.iterrows():
go_set = set()
for go_id in row['gos']:
if go_id in go:
go_set |= get_anchestors(go, go_id)
train_labels[row['proteins']] = row['labels']
for i, row in test_df.iterrows():
go_set = set()
for go_id in row['gos']:
if go_id in go:
go_set |= get_anchestors(go, go_id)
test_labels[row['proteins']] = row['labels']
preds = list()
test = list()
with open('data/swissexp/blast-' + func + '.res') as f:
for line in f:
it = line.strip().split('\t')
preds.append(train_labels[it[1]])
test.append(test_labels[it[0]])
total = 0
p = 0.0
r = 0.0
f = 0.0
p_total = 0
for label, pred in zip(test, preds):
tp = np.sum(label * pred)
fp = np.sum(pred) - tp
fn = np.sum(label) - tp
# tp = len(label.intersection(pred))
# fp = len(pred) - tp
# fn = len(label) - tp
if tp == 0 and fp == 0 and fn == 0:
continue
total += 1
if tp != 0:
p_total += 1
precision = tp / (1.0 * (tp + fp))
recall = tp / (1.0 * (tp + fn))
p += precision
r += recall
p /= p_total
r /= total
f = 2 * p * r / (p + r)
return f, p, r
def main(function, device, org, train, param):
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
logging.info('Functions: %s %d' % (FUNCTION, len(functions)))
if ORG is not None:
logging.info('Organism %s' % ORG)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
global node_names
node_names = set()
with tf.device('/' + device):
params = {
'fc_output': 1024,
'learning_rate': 0.001,
'embedding_dims': 128,
'embedding_dropout': 0.2,
'nb_conv': 3,
'nb_dense': 2,
'filter_length': 128,
'nb_filter': 32,
'pool_length': 64,
'stride': 32
}
model(params, is_train=train)
dims = [64, 128, 256, 512]
nb_filters = [16, 32, 64, 128]
nb_convs = [1, 2, 3, 4]
nb_dense = [1, 2, 3, 4]
for i in range(param * 32, param * 32 + 32):
dim = i % 4
i = i / 4
nb_fil = i % 4
i /= 4
conv = i % 4
i /= 4
den = i
params['embedding_dims'] = dims[dim]
params['nb_filter'] = nb_filters[nb_fil]
params['nb_conv'] = nb_convs[conv]
params['nb_dense'] = nb_dense[den]
def get_real_annotations():
go = get_gene_ontology()
df = pd.read_pickle('data/cafa3/swissprot_exp.pkl')
annots = {}
for i, row in df.iterrows():
go_set = set()
for go_id in row['annots']:
go_id = go_id.split('|')
if go_id[0] in go and go_id[1] in EXP_CODES:
go_set |= get_anchestors(go, go_id[0])
annots[row['proteins']] = go_set
return annots
def main(function, test_df, device):
org = None
param = 0
filename = 'ResultSequenceStructPPI.txt'
train = False
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
logging.info('Functions: %s %d' % (FUNCTION, len(functions)))
global go_indexes
go_indexes = dict()
#will be used for my prediction list
indexes_for_prediction = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
indexes_for_prediction[ind] = go_id
global node_names
global FILENAME
FILENAME = filename
global PARAMS
node_names = set()
global prediction_list
with tf.device('/' + device):
params = {
'fc_output': 1024,
'learning_rate': 0.001,
'embedding_dims': 128,
'embedding_dropout': 0.2,
'nb_conv': 1,
'nb_dense': 1,
'filter_length': 128,
'nb_filter': 32,
'pool_length': 64,
'stride': 32
}
PARAMS = params
prediction_list = model(params, test_df, is_train=train)
return prediction_list
def main(data_root, go_filename, go_domain, split):
global DATA_ROOT
DATA_ROOT = data_root
global go
go = get_gene_ontology()
global FUNCTION
FUNCTION = go_domain
df = pd.read_pickle(DATA_ROOT + go_domain + '.pkl')
global functions
functions = list(df['functions'])
global func_set
func_set = set(functions)
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
dataset = load_data(split=split)
train_model(dataset)
def specific_predictions():
root = 'data/cafa3/'
go = get_gene_ontology()
fw = open(root + 'test_predictions_specific.tab', 'w')
with open(root + 'test_predictions.tab', 'r') as f:
for line in f:
items = line.strip().split('\t')
go_set = set(items[1:])
gos = go_set.copy()
for go_id in gos:
anchestors = get_anchestors(go, go_id)
anchestors.remove(go_id)
go_set -= anchestors
fw.write(items[0])
for go_id in go_set:
fw.write('\t' + go_id)
fw.write('\n')
fw.close()
def main(function, device, org, train, param, filename):
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
logging.info('Functions: %s %d' % (FUNCTION, len(functions)))
if ORG is not None:
logging.info('Organism %s' % ORG)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
global node_names
global FILENAME
FILENAME = filename
global PARAMS
node_names = set()
with tf.device('/' + device):
params = {
'fc_output': 1024,
'learning_rate': 0.001,
'embedding_dims': 128,
'embedding_dropout': 0.2,
'nb_conv': 1,
'nb_dense': 1,
'filter_length': 128,
'nb_filter': 32,
'pool_length': 64,
'stride': 32
}
PARAMS = params
model(params, is_train=train)
def main(device, org, train):
global GO_IDS
GO_IDS = FUNC_DICT.values()
global go
go = get_gene_ontology('go.obo')
global ORG
ORG = org
func_df = pd.read_pickle(DATA_ROOT + 'bp.pkl')
global functions
functions = func_df['functions'].values
func_df = pd.read_pickle(DATA_ROOT + 'mf.pkl')
functions = np.concatenate((functions, func_df['functions'].values))
func_df = pd.read_pickle(DATA_ROOT + 'cc.pkl')
functions = np.concatenate((functions, func_df['functions'].values))
global func_set
func_set = set(functions)
global all_functions
all_functions = (
get_go_set(go, GO_IDS[0])
| get_go_set(go, GO_IDS[1])
| get_go_set(go, GO_IDS[2]))
logging.info('Functions: %d' % (len(functions), ))
if ORG is not None:
logging.info('Organism %s' % ORG)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
global node_names
node_names = set()
with tf.device('/' + device):
params = {
'fc_output': 1024,
'learning_rate': 0.001,
'embedding_dims': 128,
'embedding_dropout': 0.2,
'filter_length': 128,
'nb_filter': 32,
'pool_length': 64,
'stride': 32
}
model(params, is_train=train)
def main(function, split):
global SPLIT
SPLIT = split
global GO_ID
GO_ID = FUNC_DICT[function]
global go
go = get_gene_ontology('go.obo')
global FUNCTION
FUNCTION = function
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = get_go_set(go, GO_ID)
print len(functions)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
run()
def main(function, device, model_name):
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
func_df = pd.read_pickle(DATA_ROOT + FUNCTION + '.pkl')
global functions
functions = func_df['functions'].values
global func_set
func_set = set(functions)
global all_functions
all_functions = get_go_set(go, GO_ID)
logging.info(len(functions))
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
with tf.device('/' + device):
model(model_name)
def main(function, annot_num):
global FUNCTION
FUNCTION = function
global GO_ID
GO_ID = FUNC_DICT[FUNCTION]
global go
go = get_gene_ontology('go.obo')
global functions
functions = deque()
dfs(GO_ID)
functions.remove(GO_ID)
functions = list(functions)
print((len(functions)))
global func_set
func_set = set(functions)
global go_indexes
go_indexes = dict()
for ind, go_id in enumerate(functions):
go_indexes[go_id] = ind
get_functions(annot_num)
def compute_performance():
root = 'data/cafa3/'
preds = {}
annots = {}
go = get_gene_ontology()
with open(root + 'test_predictions.tab', 'r') as f:
for line in f:
items = line.strip().split('\t')
preds[items[0]] = set(items[1:])
with open(root + 'test_annotations.tab', 'r') as f:
for line in f:
items = line.strip().split('\t')
annots[items[0]] = set()
for go_id in items[1:]:
if go_id in go:
annots[items[0]] |= get_anchestors(go, go_id)
total = 0
p = 0.0
r = 0.0
f = 0.0
for prot, pred_annots in preds.iteritems():
real_annots = annots[prot]
if len(real_annots) == 0:
continue
tp = len(real_annots.intersection(pred_annots))
fp = len(pred_annots - real_annots)
fn = len(real_annots - pred_annots)
if tp == 0 and fp == 0 and fn == 0:
continue
total += 1
if tp != 0:
precision = tp / (1.0 * (tp + fp))
recall = tp / (1.0 * (tp + fn))
p += precision
r += recall
f += 2 * precision * recall / (precision + recall)
print(f / total, p / total, r / total)
Dense, Dropout, Activation, Flatten)
from keras.layers.convolutional import Convolution1D, MaxPooling1D
from keras.layers.embeddings import Embedding
from keras.optimizers import SGD
from sklearn.metrics import classification_report
from keras.utils import np_utils
from utils import (
shuffle, train_val_test_split, get_gene_ontology)
import sys
import os
from collections import deque
LAMBDA = 24
DATA_ROOT = 'data/molecular_functions/paac/'
go = get_gene_ontology()
go_model = dict()
def load_data(go_id):
pass
def get_model(
go_id,
max_features=10000,
embedding_dims=100,
nb_filters=250,
hidden_dims=250,
pool_length=2,
filter_length=3):
import pandas as pd
from keras.models import Sequential, Model
from keras.layers import (Dense, Dropout, Activation, Input, Flatten, merge)
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import (Convolution1D, MaxPooling1D)
from sklearn.metrics import classification_report
from utils import (shuffle, get_gene_ontology)
from keras.callbacks import ModelCheckpoint, EarlyStopping
import sys
from aaindex import (AAINDEX)
from collections import deque
import pdb
DATA_ROOT = 'yeast/'
MAXLEN = 500
go = get_gene_ontology('goslim_yeast.obo')
def get_go_set(go_id):
go_set = set()
q = deque()
q.append(go_id)
while len(q) > 0:
g_id = q.popleft()
go_set.add(g_id)
for ch_id in go[g_id]['children']:
q.append(ch_id)
return go_set
functions = get_go_set('GO:0003674')
def main(function):
global go
go = get_gene_ontology()
func_df = pd.read_pickle(DATA_ROOT + function + '.pkl')
global functions
functions = func_df['functions'].values
func_index = dict()
for i, go_id in enumerate(functions):
func_index[go_id] = i
global func_set
func_set = set(func_index)
global GO_ID
GO_ID = FUNC_DICT[function]
global all_functions
all_functions = get_go_set(go, GO_ID)
pred_df = pd.read_pickle(DATA_ROOT + 'model_preds_' + function + '.pkl')
# FFPred preds
preds_dict = {}
# files = os.listdir('data/ffpred/')
# for fl in files:
# with open('data/gofdr/predictions.tab') as f:
# for line in f:
# it = line.strip().split('\t')
# target_id = it[0]
# if function[1].upper() != it[2]:
# continue
# if target_id not in preds_dict:
# preds_dict[target_id] = list()
# preds_dict[target_id].append((it[1], float(it[3])))
# print(len(preds_dict))
target_ids = list()
predictions = list()
for key, val in preds_dict.items():
target_ids.append(key)
predictions.append(val)
# pred_df = pd.DataFrame({'targets': target_ids, 'predictions': predictions})
targets = dict()
with open('data/cafa3/CAFA3_benchmark20170605/groundtruth/leafonly_' +
function.upper() + 'O_unique.txt') as f:
for line in f:
it = line.strip().split('\t')
target = it[0]
go_id = it[1]
if target not in targets:
targets[target] = list()
targets[target].append(go_id)
target_ids = list()
labels = list()
go_ids = list()
for target, gos in targets.items():
go_set = set()
for go_id in gos:
if go_id in all_functions:
go_set |= get_anchestors(go, go_id)
label = np.zeros((len(functions), ), dtype=np.int32)
for go_id in go_set:
if go_id in func_index:
label[func_index[go_id]] = 1
target_ids.append(target)
go_ids.append(go_set)
labels.append(label)
df = pd.DataFrame({'targets': target_ids, 'gos': go_ids, 'labels': labels})
df = pd.merge(df, pred_df, on='targets', how='inner')
df.to_pickle(DATA_ROOT + 'model_preds_filtered_' + function + '.pkl')
def reshape(values):
values = np.hstack(values).reshape(len(values), len(values[0]))
return values
preds = reshape(df['predictions'].values)
labels = reshape(df['labels'].values)
# preds = df['predictions'].values
gos = df['gos'].values
f, p, r, t, preds_max = compute_performance(preds, labels, gos)
print(f, p, r)
# labels = list()
# scores = list()
# for i in range(len(preds)):
# all_gos = set()
# for go_id in gos[i]:
# if go_id in all_functions:
# all_gos |= get_anchestors(go, go_id)
# all_gos.discard(GO_ID)
# scores_dict = {}
# for val in preds[i]:
# go_id, score = val
# if go_id in all_functions:
# go_set = get_anchestors(go, go_id)
# for g_id in go_set:
# if g_id not in scores_dict or scores_dict[g_id] < score:
# scores_dict[g_id] = score
# all_preds = set(scores_dict) # | all_gos
# all_preds.discard(GO_ID)
# for go_id in all_preds:
# if go_id in scores_dict:
# scores.append(scores_dict[go_id])
# else:
# scores.append(0)
# if go_id in all_gos:
# labels.append(1)
# else:
# labels.append(0)
# scores = np.array(scores)
# labels = np.array(labels)
roc_auc = compute_roc(preds, labels)
print(roc_auc)
# preds_max = (scores > t).astype(np.int32)
mcc = compute_mcc(preds_max, labels)
print(mcc)
from keras.layers.convolutional import (
Convolution1D, MaxPooling1D)
from sklearn.metrics import classification_report
from utils import (
shuffle,
get_gene_ontology)
from keras.callbacks import ModelCheckpoint, EarlyStopping
import sys
from aaindex import (
AAINDEX)
from collections import deque
import pdb
DATA_ROOT = 'yeast/'
MAXLEN = 500
go = get_gene_ontology('goslim_yeast.obo')
def get_go_set(go_id):
go_set = set()
q = deque()
q.append(go_id)
while len(q) > 0:
g_id = q.popleft()
go_set.add(g_id)
for ch_id in go[g_id]['children']:
q.append(ch_id)
return go_set
functions = get_go_set('GO:0003674')
functions.remove('GO:0003674')
get_gene_ontology
)
import os
import sys
import pdb
from keras.optimizers import Adam
import shutil
from collections import deque
import pandas as pd
LAMBDA = 24
DATA_ROOT = 'data/fofe/'
CUR_LEVEL = 'level_1/'
NEXT_LEVEL = 'level_2/'
go = get_gene_ontology()
go_model = dict()
MAXLEN = 500
def get_gos_by_prot_id():
data = dict()
with open(DATA_ROOT + 'train.txt', 'r') as f:
prot_id = 0
for line in f:
line = line.strip().split('\t')
gos = line[2].split('; ')
go_set = set()
for go_id in gos:
go_set.add(go_id)
#!/usr/bin/env python
import sys
import numpy as np
import pandas as pd
from keras.utils import np_utils
from utils import get_gene_ontology
from collections import deque
DATA_ROOT = 'data/fofe/'
FILENAME = 'train.txt'
go = get_gene_ontology('go.obo')
def get_go_set(go_id):
go_set = set()
q = deque()
q.append(go_id)
while len(q) > 0:
g_id = q.popleft()
go_set.add(g_id)
for ch_id in go[g_id]['children']:
q.append(ch_id)
return go_set
functions = get_go_set('GO:0003674')
def get_anchestors(go_id):
go_set = set()
#!/usr/bin/env python
import sys
import numpy as np
import pandas as pd
from keras.utils import np_utils
from utils import get_gene_ontology
from collections import deque
DATA_ROOT = "data/fofe/"
FILENAME = "train.txt"
go = get_gene_ontology("go.obo")
def get_go_set(go_id):
go_set = set()
q = deque()
q.append(go_id)
while len(q) > 0:
g_id = q.popleft()
go_set.add(g_id)
for ch_id in go[g_id]["children"]:
q.append(ch_id)
return go_set
functions = get_go_set("GO:0003674")
def get_predictions():
root = 'data/cafa3/'
annots = {}
preds = {}
go = get_gene_ontology()
mf = pd.read_pickle(root + 'mf.pkl')
mf_df = pd.read_pickle(root + 'test-mf-preds.pkl')
functions = mf['functions']
for i, row in mf_df.iterrows():
prot_id = row['proteins']
if prot_id not in preds:
preds[prot_id] = set()
for i in xrange(len(functions)):
if row['predictions'][i] == 1:
preds[prot_id].add(functions[i])
if prot_id not in annots:
annots[prot_id] = row['gos']
cc = pd.read_pickle(root + 'cc.pkl')
cc_df = pd.read_pickle(root + 'test-cc-preds.pkl')
functions = cc['functions']
for i, row in cc_df.iterrows():
prot_id = row['proteins']
if prot_id not in preds:
preds[prot_id] = set()
for i in xrange(len(functions)):
if row['predictions'][i] == 1:
preds[prot_id].add(functions[i])
if prot_id not in annots:
annots[prot_id] = row['gos']
bp = pd.read_pickle(root + 'bp.pkl')
bp_df = pd.read_pickle(root + 'test-bp-preds.pkl')
functions = bp['functions']
for i, row in bp_df.iterrows():
prot_id = row['proteins']
if prot_id not in preds:
preds[prot_id] = set()
for i in xrange(len(functions)):
if row['predictions'][i] == 1:
preds[prot_id].add(functions[i])
if prot_id not in annots:
annots[prot_id] = row['gos']
# Removing parent classes
for prot_id in preds:
go_set = preds[prot_id]
gos = go_set.copy()
for go_id in gos:
anchestors = get_anchestors(go, go_id)
anchestors.remove(go_id)
go_set -= anchestors
proteins = sorted(annots.keys(),
key=lambda x: (x.split('_')[1], x.split('_')[0]))
with open(root + 'test_predictions.tab', 'w') as f:
for prot_id in proteins:
f.write(prot_id)
for go_id in preds[prot_id]:
f.write('\t' + go_id)
f.write('\n')
with open(root + 'test_annotations.tab', 'w') as f:
for prot_id in proteins:
f.write(prot_id)
for go_id in annots[prot_id]:
if go_id in go:
f.write('\t' + go_id)
f.write('\n')
