def run_single_block(input_list):
baseName,model,out_dir,rst,window,keep_temp,threshold,penality,DB_file,input_file,chromosome,strand,fa_file,depth,start,end = input_list
print("Generating blocks ...%s %d %s"%(baseName,start,end))
####Generate sliding windlows
gw_start_time = datetime.datetime.now()
block = split_chr_bedGraph2(out_dir,input_file,chromosome,strand,window,fa_file,depth,start,end)
#ww = open(baseName,'w')
#for a,b,c in block:
# ww.write('%s\t%s\t%s\n'%(a,b,c))
#ww.close()
gw_end_time = datetime.datetime.now()
print("Generate blocks used time: {}".format(gw_end_time - gw_start_time))
print("Evaluating blocks ...%s %d %s"%(baseName,start,end))
gw_start_time = datetime.datetime.now()
Evaluate(baseName,block,model,out_dir,rst,window,keep_temp)
gw_end_time = datetime.datetime.now()
print("Evaluated blocks used time: {}".format(gw_end_time - gw_start_time))
Scan_Forward(baseName,threshold,penality,out_dir)
Scan_Backward(baseName,threshold,penality,out_dir)
if(keep_temp != 'yes'):
predict_file = out_dir+'/predict/'+baseName+'.txt'
os.system('rm %s'%predict_file)
Postprocess(DB_file,baseName,threshold,penality,out_dir)
if(keep_temp != 'yes'):
forward_file=out_dir+"/maxSum/%s.forward.%d.%d.txt"%(baseName,threshold,penality)
backward_file=out_dir+"/maxSum/%s.backward.%d.%d.txt"%(baseName,threshold,penality)
os.system('rm %s %s'%(forward_file,backward_file))
print('Finished postprocessing...\n')
def run_single_block(input_list):
data = input_list[0]
model = input_list[1]
out_dir = input_list[2]
rst = input_list[3]
window = input_list[4]
keep_temp = input_list[5]
threshold = input_list[6]
penality = input_list[7]
DB_file = input_list[8]
if 'wig' not in data:
baseName = data.split('/')[-1]
Evaluate(model, out_dir, rst, window, baseName, keep_temp)
Scan_Forward(baseName, threshold, penality, out_dir)
Scan_Backward(baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
predict_file = out_dir + '/predict/' + baseName + '.txt'
os.system('rm %s' % predict_file)
Postprocess(DB_file, baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
forward_file = out_dir + "/maxSum/%s.forward.%d.%d.txt" % (
baseName, threshold, penality)
backward_file = out_dir + "/maxSum/%s.backward.%d.%d.txt" % (
baseName, threshold, penality)
os.system('rm %s %s' % (forward_file, backward_file))
print('Finished postprocessing...\n')
def run_single_block(input_list):
#global ref
#print(ref.keys())
baseName, model, out_dir, rst, window, keep_temp, threshold, penality, DB_file, input_file, fa_file, chromosome, strand, depth, start, end = input_list
#log_dir = out_dir+'/log'
#if not os.path.exists(log_dir):
# os.makedirs(log_dir)
#log.basicConfig(filename='%s/%s.log'%(log_dir,baseName), level=log.INFO)
print("Generating blocks ...%s %d %s" % (baseName, start, end))
####Generate sliding windlows
gw_start_time = datetime.datetime.now()
block = split_chr_bedGraph2(out_dir, input_file, chromosome, strand,
window, fa_file, depth, start, end)
#ww = open(baseName,'w')
#for a,b,c in block:
# ww.write('%s\t%s\t%s\n'%(a,b,c))
#ww.close()
gw_end_time = datetime.datetime.now()
print("Generate blocks used time: {}\n".format(gw_end_time -
gw_start_time))
print("Evaluating blocks ...%s %d %s" % (baseName, start, end))
ev_start_time = datetime.datetime.now()
Evaluate(baseName, block, model, out_dir, rst, window, keep_temp)
del block #destroyed the block reference
gc.collect() #manually run garbage collection process
ev_end_time = datetime.datetime.now()
print("Evaluated blocks used time: {}\n".format(ev_end_time -
ev_start_time))
print("Postprocessing blocks ...%s %d %s" % (baseName, start, end))
ps_start_time = datetime.datetime.now()
Scan_Forward(baseName, threshold, penality, out_dir)
Scan_Backward(baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
predict_file = out_dir + '/predict/' + baseName + '.txt'
os.system('rm %s' % predict_file)
Postprocess(DB_file, baseName, threshold, penality, out_dir)
ps_end_time = datetime.datetime.now()
print("Postprocessed blocks used time: {}\n".format(ps_end_time -
ps_start_time))
if (keep_temp != 'yes'):
forward_file = out_dir + "/maxSum/%s.forward.%d.%d.txt" % (
baseName, threshold, penality)
backward_file = out_dir + "/maxSum/%s.backward.%d.%d.txt" % (
baseName, threshold, penality)
os.system('rm %s %s' % (forward_file, backward_file))
#print('Finished postprocessing...%s\n'%baseName)
return [
gw_end_time - gw_start_time, ev_end_time - ev_start_time,
ps_end_time - ps_start_time
]
def run_single_block(input_list):
baseName, model, out_dir, rst, window, keep_temp, threshold, penality, DB_file, input_file, strand, depth, block_pos = input_list
chromosome = block_pos[3]
start = block_pos[4]
end = block_pos[5]
print("Generating blocks ...%s %d %s" %
(baseName, block_pos[4], block_pos[5]))
####Generate sliding windlows
gw_start_time = datetime.datetime.now()
blocks = Bedgraph_to_blocks(input_file, fa_file, window, depth, block_pos)
#ww = open(baseName,'w')
#for a,b,c in blocks:
# ww.write('%s\t%s\t%s\n'%(a,b,c))
#ww.close()
gw_end_time = datetime.datetime.now()
print("Generate blocks used time: {}\n".format(gw_end_time -
gw_start_time))
print("Evaluating blocks ...%s %d %s" % (baseName, start, end))
ev_start_time = datetime.datetime.now()
Evaluate(baseName, blocks, model, out_dir, rst, window, keep_temp)
del blocks #destroyed the block reference
gc.collect() #manually run garbage collection process
ev_end_time = datetime.datetime.now()
print("Evaluated blocks used time: {}\n".format(ev_end_time -
ev_start_time))
print("Postprocessing blocks ...%s %d %s" % (baseName, start, end))
ps_start_time = datetime.datetime.now()
Scan_Forward(baseName, threshold, penality, out_dir)
Scan_Backward(baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
predict_file = out_dir + '/predict/' + baseName + '.txt'
os.system('rm %s' % predict_file)
Postprocess(DB_file, baseName, threshold, penality, out_dir)
ps_end_time = datetime.datetime.now()
print("Postprocessed blocks used time: {}\n".format(ps_end_time -
ps_start_time))
if (keep_temp != 'yes'):
forward_file = out_dir + "/maxSum/%s.forward.%d.%d.txt" % (
baseName, threshold, penality)
backward_file = out_dir + "/maxSum/%s.backward.%d.%d.txt" % (
baseName, threshold, penality)
os.system('rm %s %s' % (forward_file, backward_file))
#print('Finished postprocessing...%s\n'%baseName)
return [
gw_end_time - gw_start_time, ev_end_time - ev_start_time,
ps_end_time - ps_start_time
]
def main(out_dir, input_file, input_plus, input_minus, fa_file, keep_temp,
window, name, model, rst, threshold, penality, DB_file):
if not os.path.exists(out_dir):
os.makedirs(out_dir)
out_dir = out_dir + '/' + name
####Generate sliding windlows
Generate_windows(out_dir, input_file, input_plus, input_minus, fa_file,
keep_temp, window, name)
data_dir = out_dir + '/data'
data_files = glob.glob(data_dir + "/*")
for data in data_files:
if 'wig' in data:
continue
baseName = data.split('/')[-1]
Evaluate(model, out_dir, rst, window, baseName, keep_temp)
Scan_Forward(baseName, threshold, penality, out_dir)
Scan_Backward(baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
predict_file = out_dir + '/predict/' + baseName + '.txt'
os.system('rm %s' % predict_file)
Postprocess(DB_file, baseName, threshold, penality, out_dir)
if (keep_temp != 'yes'):
forward_file = out_dir + "/maxSum/%s.forward.%d.%d.txt" % (
baseName, threshold, penality)
backward_file = out_dir + "/maxSum/%s.backward.%d.%d.txt" % (
baseName, threshold, penality)
os.system('rm %s %s' % (forward_file, backward_file))
out_file = '%s/%s.predicted.txt' % (out_dir, name)
ww = open(out_file, 'w')
ww.write('predicted_pasid\tdb_diff\tdb_pasid\tscore\n')
ww.close()
os.system('cat %s/maxSum/*bidirection* >>%s' % (out_dir, out_file))
if (keep_temp != 'yes'):
os.system('rm -rf %s/data %s/predict %s/maxSum' %
(out_dir, out_dir, out_dir))
print("Job Done!")
####Generate sliding windlows
<<<<<<< HEAD
Generate_windows(out_dir,input_file,input_plus,input_minus,fa_file,keep_temp,window,name)
=======
Generate_windows(out_dir,input_file,input_plus,input_minus,fa_file,keep_temp,window,name,depth)
>>>>>>> e6e9d5b305368adbd0eec6e055e70e82e740a154
data_dir = out_dir+'/data'
data_files = glob.glob(data_dir+"/*")
for data in data_files:
if 'wig' in data:
continue
baseName = data.split('/')[-1]
Evaluate(model,out_dir,rst,window,baseName,keep_temp)
Scan_Forward(baseName,threshold,penality,out_dir)
Scan_Backward(baseName,threshold,penality,out_dir)
if(keep_temp != 'yes'):
predict_file = out_dir+'/predict/'+baseName+'.txt'
os.system('rm %s'%predict_file)
Postprocess(DB_file,baseName,threshold,penality,out_dir)
if(keep_temp != 'yes'):
forward_file=out_dir+"/maxSum/%s.forward.%d.%d.txt"%(baseName,threshold,penality)
backward_file=out_dir+"/maxSum/%s.backward.%d.%d.txt"%(baseName,threshold,penality)
os.system('rm %s %s'%(forward_file,backward_file))
out_file = '%s/%s.predicted.txt' %(out_dir,name)
ww = open(out_file,'w')
<<<<<<< HEAD
ww.write('predicted_pasid\tdb_diff\tdb_pasid\tscore\n')
=======
if(DB_file is not None):