def swithces_from_diagonal(args, run_filters, coh_seq_dict, doc_seq_dict):
"""
:param args: run arguments
:param run_filters: run filters
:param coh_seq_dict: {name: AASeq()} of cohesins
:param doc_seq_dict: {name: AASeq()} of dockerins
:return: {switch_name: {design_name: #purples}
"""
# positions_dict = {'1anu': [32, 36, 62, 65, 69, 82, 115, 126],
# '1aoh': [33, 37, 63, 66, 70, 83, 119, 130],
# '1ohz': [33, 35, 37, 39, 63, 66, 68, 70, 73, 75, 77, 79, 81, 83, 121, 125, 127],
# '2ccl': [33, 37, 63, 66, 70, 83, 116, 127]}
# type_dict = {'D': 'n', 'E': 'n', 'K': 'p', 'R': 'p'}
results = {}
sc_files = [a for a in os.listdir(args['score_dir']) if a[-6:] == '.score']
bins = {}
for sc_file in sc_files:
score_dict = score2dict(sc_file)
passed, failed = all_who_pass_run_filters(args, score_dict,
run_filters)
# results[sc_file] = len(list(passed.keys()))
if len(list(passed.keys())) <= args['purples_threshold']:
continue
### these kick out the date from the score names, and the makes it into the proper names:
if '_11.10' in sc_file:
coh_seq = coh_seq_dict[''.join(
str(sc_file[4:-6] + '_0001.pdb.A').split('_11.10'))]
doc_seq = doc_seq_dict[''.join(
str(sc_file[4:-6] + '_0001.pdb.B').split('_11.10'))]
elif '_12.10' in sc_file:
coh_seq = coh_seq_dict[''.join(
str(sc_file[4:-6] + '_0001.pdb.A').split('_12.10'))]
doc_seq = doc_seq_dict[''.join(
str(sc_file[4:-6] + '_0001.pdb.B').split('_12.10'))]
result = Result(sc_file[4:-6], coh_seq, doc_seq,
len(list(passed.keys())))
# pos_str = coh_seq.get_positions(positions_dict['1ohz'])
# switch_str = ''.join([type_dict[a] if a in type_dict.keys() else 'c' for a in pos_str])
#
# doc_str = doc_seq.get_positions(list(doc_symm_poses.keys()))
# doc_switch = ''.join([type_dict[a] if a in type_dict.keys() else 'c' for a in doc_str])
# if switch_str not in bins.keys():
# bins[switch_str] = {}
# if doc_switch not in bins[switch_str].keys():
# bins[switch_str][doc_switch] = {}
# bins[switch_str][doc_switch][''.join(str(sc_file[4:-6]+'_0001.pdb.A').split('_11.10'))] \
# = {'doc_seq': doc_seq, 'purples': len(list(passed.keys()))}
results[sc_file[4:-6]] = result
# return bins
return results
def post_pred_cliques(args):
run_filters = generate_run_filters(args={'ddg': 25.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3})
if not os.path.isfile('./all_data.obj'):
sc_files = [a for a in os.listdir('./') if '.score' in a]
cohs_seqs = read_multi_fastas('/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/recliques_4Nov/all_cohs.fasta')
docs_seqs = read_multi_fastas('/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/recliques_4Nov/all_docs.fasta')
results = []
for sc_file in sc_files:
seq_name = '_'.join(sc_file.split('_')[1:8])
coh_name = seq_name+'.pdb.gz.A'
doc_name = seq_name+'.pdb.gz.B'
sc_dict = score2dict(sc_file)
ynum = re.search('y[0-9]{3}', sc_file).group(0)
passed, failed = all_who_pass_run_filters(args, sc_dict, run_filters)
if len(passed) >= args['purples_threshold']:
r = Result(seq_name, cohs_seqs[coh_name], docs_seqs[doc_name], len(passed))
results.append(r)
with open('./all_data.obj', 'wb') as fout:
pickle.dump(results, fout)
else:
with open('./all_data.obj', 'rb') as fin:
results = pickle.load(fin)
if not os.path.isfile('./graph.obj'):
result_dict = {i+1: r for i, r in enumerate(results)}
G = nx.Graph()
[G.add_node(a) for a in result_dict.keys()]
for n1 in G.nodes_iter():
for n2 in G.nodes_iter():
if n1 != n2:
coh_sw_1, coh_sw_2 = result_dict[n1].coh_switch, result_dict[n2].coh_switch
doc_sw_1, doc_sw_2 = result_dict[n1].doc_switch, result_dict[n2].doc_switch
doc_wt_1, doc_wt_2 = result_dict[n1].doc_wt, result_dict[n2].doc_wt
doc_diff = 1 if are_docs_from_diff_clusters(doc_wt_1, doc_wt_2) else 0
symm_switch = switch_symm_changer(doc_sw_2)
if switches_differ({'diff_by': args['diff_by']}, coh_sw_1, coh_sw_2) >= args['diff_by'] and \
switches_differ({'diff_by': args['doc_diff_by']}, doc_sw_1, doc_sw_2) + doc_diff >= args['doc_diff_by'] and \
switches_differ({'diff_by': args['doc_diff_by']}, doc_sw_1, symm_switch) + doc_diff >= args['doc_diff_by']:
G.add_edge(n1, n2)
print('adding edge\n', result_dict[n1], '\n', result_dict[n2])
else:
print('NOT\n', result_dict[n1], '\n', result_dict[n2])
cliques = [a for a in nx.find_cliques(G)]
max_len = max([len(a) for a in cliques])
max_cliques = [a for a in cliques if len(a) == max_len]
for clq in max_cliques:
print(clq, '\n', '\n'.join([str(result_dict[a]) for a in clq]))
def swithces_from_diagonal(args, run_filters, coh_seq_dict, doc_seq_dict):
"""
:param args: run arguments
:param run_filters: run filters
:param coh_seq_dict: {name: AASeq()} of cohesins
:param doc_seq_dict: {name: AASeq()} of dockerins
:return: {switch_name: {design_name: #purples}
"""
# positions_dict = {'1anu': [32, 36, 62, 65, 69, 82, 115, 126],
# '1aoh': [33, 37, 63, 66, 70, 83, 119, 130],
# '1ohz': [33, 35, 37, 39, 63, 66, 68, 70, 73, 75, 77, 79, 81, 83, 121, 125, 127],
# '2ccl': [33, 37, 63, 66, 70, 83, 116, 127]}
# type_dict = {'D': 'n', 'E': 'n', 'K': 'p', 'R': 'p'}
results = {}
sc_files = [a for a in os.listdir(args['score_dir']) if a[-6:] == '.score']
bins = {}
for sc_file in sc_files:
score_dict = score2dict(sc_file)
passed, failed = all_who_pass_run_filters(args, score_dict, run_filters)
# results[sc_file] = len(list(passed.keys()))
if len(list(passed.keys())) <= args['purples_threshold']:
continue
### these kick out the date from the score names, and the makes it into the proper names:
if '_11.10' in sc_file:
coh_seq = coh_seq_dict[''.join(str(sc_file[4:-6]+'_0001.pdb.A').split('_11.10'))]
doc_seq = doc_seq_dict[''.join(str(sc_file[4:-6]+'_0001.pdb.B').split('_11.10'))]
elif '_12.10' in sc_file:
coh_seq = coh_seq_dict[''.join(str(sc_file[4:-6]+'_0001.pdb.A').split('_12.10'))]
doc_seq = doc_seq_dict[''.join(str(sc_file[4:-6]+'_0001.pdb.B').split('_12.10'))]
result = Result(sc_file[4:-6], coh_seq, doc_seq, len(list(passed.keys())))
# pos_str = coh_seq.get_positions(positions_dict['1ohz'])
# switch_str = ''.join([type_dict[a] if a in type_dict.keys() else 'c' for a in pos_str])
#
# doc_str = doc_seq.get_positions(list(doc_symm_poses.keys()))
# doc_switch = ''.join([type_dict[a] if a in type_dict.keys() else 'c' for a in doc_str])
# if switch_str not in bins.keys():
# bins[switch_str] = {}
# if doc_switch not in bins[switch_str].keys():
# bins[switch_str][doc_switch] = {}
# bins[switch_str][doc_switch][''.join(str(sc_file[4:-6]+'_0001.pdb.A').split('_11.10'))] \
# = {'doc_seq': doc_seq, 'purples': len(list(passed.keys()))}
results[sc_file[4:-6]] = result
# return bins
return results
def main():
global log
original_pwd = os.getcwd()
running = get_running_folders()
pending = get_pending_folders()
run_filters = generate_run_filters(args={'ddg': 25.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3})
for runner in running:
os.chdir(runner)
if is_folder_finished(runner):
print('processing %s' % runner)
log += 'folder is finished, processing %s\n' % runner.split('/')[-2]
process_folder({'folder': runner, 'force_process': False, 'remove_pdbs': False})
move_to_processed(runner, running, 0)
else:
score_dict = folder_scores(runner)
passed, failed = all_who_pass_run_filters({}, score_dict, run_filters)
log += 'passed %i, failed %i' % (len(passed), len(failed))
if len(passed) >= 50:
print('found enough passed, stopping folder %s' % runner.split('/')[-1])
log += 'found enough passed, stopping folder\n'
bkill_folder(runner)
process_folder({'folder': runner, 'force_process': True, 'remove_pdbs': False})
move_to_processed(runner, running, len(passed))
else:
print('not enough finished, letting him be %s, found %i passed and %i failed' %
(runner.split('/')[-2], len(passed), len(failed)))
log += 'not enough finished, letting him be %s, found %i passed and %i failed\n' % \
(runner.split('/')[-2], len(passed), len(failed))
os.chdir(original_pwd)
# for pender in pending:
# os.chdir(pender)
# lsf_status, pends = how_many_queue()
# if lsf_status['fleishman'] < 12000:
# print('found %i jobs in fleishman, submitting %s' % (lsf_status['fleishman'], pender))
# log += 'found %i jobs in fleishman, submitting %s\n' % (lsf_status['fleishman'], pender)
# submit_folder(pender)
# move_pender_to_runner(pending, pender)
# os.chdir(original_pwd)
# lsf_status, pends = how_many_queue()
# if lsf_status['new-all.q'] <= 2000:
# bswitch_pends(pends, 2000-lsf_status['new-all.q'])
os.chdir(original_pwd)
def creat_coh_doc_purples():
results_path = '/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/reclique_18Nov/cliques_prediction/results/'
sc_files = [a for a in os.listdir(results_path) if '.score' in a]
run_filters = generate_run_filters(args={'ddg': 24.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3,
'hbonds': -10.})
if not os.path.isfile(results_path+'analysed.obj'):
coh_doc_purples = {}
for sc_file in sc_files:
sc_dict = score2dict(results_path+sc_file)
passed, failed = all_who_pass_run_filters({}, sc_dict, run_filters)
coh_name = what_coh(sc_file, args={'naming': 'coh_on_doc'})
doc_name = what_doc(sc_file, args={'naming': 'coh_on_doc'})
if coh_name not in coh_doc_purples.keys():
coh_doc_purples[coh_name] = {}
coh_doc_purples[coh_name][doc_name] = len(passed)
pickle.dump(coh_doc_purples, open(results_path+'analysed.obj', 'wb'))
else:
print("reading coh_doc_purples")
coh_doc_purples = pickle.load(open(results_path+'analysed.obj', 'rb'))
return coh_doc_purples
topath = '/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/recliques_4Nov/clique_6_pdbs/mini_diagonal_11Nov/'
run_filters = generate_run_filters(args={'ddg': 24.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3,
'hbonds': 10})
all_docs = [a for a in os.listdir(topath) if 'doc_' in a]
fout = open(topath+'minidiagonal_full_names.txt', 'w')
for doc in all_docs:
all_dirs = os.listdir(topath+doc)
for dir in all_dirs:
try:
sc_file = [a for a in os.listdir(topath+doc+'/'+dir) if a[-3:] == '.sc']
if sc_file:
sc_dict = score2dict(topath+doc+'/'+dir+'/'+sc_file[0])
passed, failed = all_who_pass_run_filters({}, sc_dict, run_filters)
if len(passed) > 5:
fout.write('%s\t%i\n' % (dir, len(passed)))
shutil.copy(topath+doc+'/'+dir+'/'+list(sc_dict.keys())[0]+'.pdb.gz', topath+'minidiagonal_pdbs')
except:
print('no folder', dir)
fout.close()
# def analyse_minidiagonal(args):
# with open('../minidiagonal.txt', 'w') as fout:
# run_filters = generate_run_filters(args={'ddg': 24.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3,
# 'hbonds': 10})
# counter = 0
# score_files = [a for a in os.listdir('./') if a[-3:] == '.sc']
# for sc in score_files:
# score_dict = score2dict(sc)
})
all_docs = [a for a in os.listdir(topath) if 'doc_' in a]
fout = open(topath + 'minidiagonal_full_names.txt', 'w')
for doc in all_docs:
all_dirs = os.listdir(topath + doc)
for dir in all_dirs:
try:
sc_file = [
a for a in os.listdir(topath + doc + '/' + dir)
if a[-3:] == '.sc'
]
if sc_file:
sc_dict = score2dict(topath + doc + '/' + dir + '/' +
sc_file[0])
passed, failed = all_who_pass_run_filters({}, sc_dict,
run_filters)
if len(passed) > 5:
fout.write('%s\t%i\n' % (dir, len(passed)))
shutil.copy(
topath + doc + '/' + dir + '/' +
list(sc_dict.keys())[0] + '.pdb.gz',
topath + 'minidiagonal_pdbs')
except:
print('no folder', dir)
fout.close()
# def analyse_minidiagonal(args):
# with open('../minidiagonal.txt', 'w') as fout:
# run_filters = generate_run_filters(args={'ddg': 24.0, 'sasa': 1400, 'shape': 0.6, 'packstat': 0.6, 'buried_2': 3,
# 'hbonds': 10})
# counter = 0
def post_pred_cliques(args):
run_filters = generate_run_filters(args={
'ddg': 25.0,
'sasa': 1400,
'shape': 0.6,
'packstat': 0.6,
'buried_2': 3
})
if not os.path.isfile('./all_data.obj'):
sc_files = [a for a in os.listdir('./') if '.score' in a]
cohs_seqs = read_multi_fastas(
'/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/recliques_4Nov/all_cohs.fasta'
)
docs_seqs = read_multi_fastas(
'/home/labs/fleishman/jonathaw/no_backup/designs/multi_docs_15Oct/recliques_4Nov/all_docs.fasta'
)
results = []
for sc_file in sc_files:
seq_name = '_'.join(sc_file.split('_')[1:8])
coh_name = seq_name + '.pdb.gz.A'
doc_name = seq_name + '.pdb.gz.B'
sc_dict = score2dict(sc_file)
ynum = re.search('y[0-9]{3}', sc_file).group(0)
passed, failed = all_who_pass_run_filters(args, sc_dict,
run_filters)
if len(passed) >= args['purples_threshold']:
r = Result(seq_name, cohs_seqs[coh_name], docs_seqs[doc_name],
len(passed))
results.append(r)
with open('./all_data.obj', 'wb') as fout:
pickle.dump(results, fout)
else:
with open('./all_data.obj', 'rb') as fin:
results = pickle.load(fin)
if not os.path.isfile('./graph.obj'):
result_dict = {i + 1: r for i, r in enumerate(results)}
G = nx.Graph()
[G.add_node(a) for a in result_dict.keys()]
for n1 in G.nodes_iter():
for n2 in G.nodes_iter():
if n1 != n2:
coh_sw_1, coh_sw_2 = result_dict[
n1].coh_switch, result_dict[n2].coh_switch
doc_sw_1, doc_sw_2 = result_dict[
n1].doc_switch, result_dict[n2].doc_switch
doc_wt_1, doc_wt_2 = result_dict[n1].doc_wt, result_dict[
n2].doc_wt
doc_diff = 1 if are_docs_from_diff_clusters(
doc_wt_1, doc_wt_2) else 0
symm_switch = switch_symm_changer(doc_sw_2)
if switches_differ({'diff_by': args['diff_by']}, coh_sw_1, coh_sw_2) >= args['diff_by'] and \
switches_differ({'diff_by': args['doc_diff_by']}, doc_sw_1, doc_sw_2) + doc_diff >= args['doc_diff_by'] and \
switches_differ({'diff_by': args['doc_diff_by']}, doc_sw_1, symm_switch) + doc_diff >= args['doc_diff_by']:
G.add_edge(n1, n2)
print('adding edge\n', result_dict[n1], '\n',
result_dict[n2])
else:
print('NOT\n', result_dict[n1], '\n', result_dict[n2])
cliques = [a for a in nx.find_cliques(G)]
max_len = max([len(a) for a in cliques])
max_cliques = [a for a in cliques if len(a) == max_len]
for clq in max_cliques:
print(clq, '\n', '\n'.join([str(result_dict[a]) for a in clq]))
def main():
global log
original_pwd = os.getcwd()
running = get_running_folders()
pending = get_pending_folders()
run_filters = generate_run_filters(args={
'ddg': 25.0,
'sasa': 1400,
'shape': 0.6,
'packstat': 0.6,
'buried_2': 3
})
for runner in running:
os.chdir(runner)
if is_folder_finished(runner):
print('processing %s' % runner)
log += 'folder is finished, processing %s\n' % runner.split(
'/')[-2]
process_folder({
'folder': runner,
'force_process': False,
'remove_pdbs': False
})
move_to_processed(runner, running, 0)
else:
score_dict = folder_scores(runner)
passed, failed = all_who_pass_run_filters({}, score_dict,
run_filters)
log += 'passed %i, failed %i' % (len(passed), len(failed))
if len(passed) >= 50:
print('found enough passed, stopping folder %s' %
runner.split('/')[-1])
log += 'found enough passed, stopping folder\n'
bkill_folder(runner)
process_folder({
'folder': runner,
'force_process': True,
'remove_pdbs': False
})
move_to_processed(runner, running, len(passed))
else:
print(
'not enough finished, letting him be %s, found %i passed and %i failed'
% (runner.split('/')[-2], len(passed), len(failed)))
log += 'not enough finished, letting him be %s, found %i passed and %i failed\n' % \
(runner.split('/')[-2], len(passed), len(failed))
os.chdir(original_pwd)
# for pender in pending:
# os.chdir(pender)
# lsf_status, pends = how_many_queue()
# if lsf_status['fleishman'] < 12000:
# print('found %i jobs in fleishman, submitting %s' % (lsf_status['fleishman'], pender))
# log += 'found %i jobs in fleishman, submitting %s\n' % (lsf_status['fleishman'], pender)
# submit_folder(pender)
# move_pender_to_runner(pending, pender)
# os.chdir(original_pwd)
# lsf_status, pends = how_many_queue()
# if lsf_status['new-all.q'] <= 2000:
# bswitch_pends(pends, 2000-lsf_status['new-all.q'])
os.chdir(original_pwd)
