def trans_topface():
topface = lt.pickle_load(t_f)
basic = ['K', 'R', 'H']
acid = ['D', 'E']
aromatic = ['F', 'W', 'Y']
polar = ['S', 'T', 'C', 'P', 'N', 'Q']
nonpolar = ['G', 'V', 'L', 'I', 'M', 'A']
res_hash = {'K':'b','R':'b','H':'b','D':'a','E':'a','S':'p','T':'p','C':'p','P':'p',\
'N':'p','Q':'p','G':'n','V':'n','L':'n','I':'n','M':'n','A':'n','*':'*'}
transed_topface = {}
for p, h in topface:
h_new = [res_hash[i] for bla in h for i in bla]
h_new = [''.join(h_new[i:i + 3]) for i in range(0, len(h_new), 3)]
transed_topface[p] = h_new
def read_pickle():
for f in lt.files_in_dir(sys.argv[-1]):
if 'hbplus' in f:
hbplus_neighbors = lt.pickle_load(f)
if 'salt' in f:
salt_neighbors = lt.pickle_load(f)
hbplus_neighbors_dic = OrderedDict()
for pdb_id, res, neighbors in hbplus_neighbors:
hbplus_neighbors_dic[(pdb_id, res)] = neighbors
salt_neighbors_dic = {}
for pdb_id, res, neighbors in salt_neighbors:
salt_neighbors_dic[(pdb_id, res)] = neighbors
combine_neighbors = []
for k, v in hbplus_neighbors_dic.iteritems():
if k in salt_neighbors_dic.keys():
v.extend(salt_neighbors_dic[k])
v = set(v)
combine_neighbors.append((k[0], k[1], v))
else:
combine_neighbors.append((k[0], k[1], v))
return combine_neighbors
def hotsta_classify():
seq = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
hot = lt.pickle_load(sys.argv[-1])
basic = ['K', 'R', 'H']
acid = ['D', 'E']
aromatic = ['F', 'W', 'Y']
polar = ['S', 'T', 'C', 'P', 'N', 'Q']
nonpolar = ['G', 'V', 'L', 'I', 'M', 'A']
r1 = {'basic': 0, 'acid': 0, 'aromatic': 0, 'polar': 0, 'nonpolar': 0}
r2 = {'basic': 0, 'acid': 0, 'aromatic': 0, 'polar': 0, 'nonpolar': 0}
d1 = {'basic': 0, 'acid': 0, 'aromatic': 0, 'polar': 0, 'nonpolar': 0}
sta = {'basic': 0, 'acid': 0, 'aromatic': 0, 'polar': 0, 'nonpolar': 0}
for pro_name, pro_hot in hot.iteritems():
for h in pro_hot:
if h[0] in basic:
r1['basic'] += 1
sta['basic'] += 1
elif h[0] in acid:
r1['acid'] += 1
sta['acid'] += 1
elif h[0] in aromatic:
r1['aromatic'] += 1
sta['aromatic'] += 1
elif h[0] in polar:
r1['polar'] += 1
sta['polar'] += 1
elif h[0] in nonpolar:
r1['nonpolar'] += 1
sta['nonpolar'] += 1
if h[1] in basic:
r2['basic'] += 1
sta['basic'] += 1
elif h[1] in acid:
r2['acid'] += 1
sta['acid'] += 1
elif h[1] in aromatic:
r2['aromatic'] += 1
sta['aromatic'] += 1
elif h[1] in polar:
r2['polar'] += 1
sta['polar'] += 1
elif h[1] in nonpolar:
r2['nonpolar'] += 1
sta['nonpolar'] += 1
if h[2] in basic:
d1['basic'] += 1
sta['basic'] += 1
elif h[2] in acid:
d1['acid'] += 1
sta['acid'] += 1
elif h[2] in aromatic:
d1['aromatic'] += 1
sta['aromatic'] += 1
elif h[2] in polar:
d1['polar'] += 1
sta['polar'] += 1
elif h[2] in nonpolar:
d1['nonpolar'] += 1
sta['nonpolar'] += 1
fname = lt.fname(sys.argv[-1])
lt.write_sta_dict(r1, fname + 'R1_hot_rc_sta')
lt.write_sta_dict(r2, fname + 'R1_2_hot_rc_sta')
lt.write_sta_dict(d1, fname + 'D_1_hot_rc_sta')
lt.write_sta_dict(sta, fname + 'R1_R1_2_D_1_hot_rc_sta')
def hotsta():
hot = lt.pickle_load(sys.argv[-1])
r1 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
r2 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
d1 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
r1_r2 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
r1_d1 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
r2_d1 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
r1_r2_d1 = {
'A': 0,
'R': 0,
'N': 0,
'D': 0,
'C': 0,
'Q': 0,
'E': 0,
'G': 0,
'H': 0,
'I': 0,
'L': 0,
'K': 0,
'M': 0,
'F': 0,
'P': 0,
'S': 0,
'T': 0,
'W': 0,
'Y': 0,
'V': 0
}
for pro_name, pro_hot in hot.iteritems():
for h in pro_hot:
if h[0] in r1.keys():
r1[h[0]] += 1
if h[1] in r2.keys():
r2[h[1]] += 1
if h[2] in d1.keys():
d1[h[2]] += 1
for k, v in r1.items():
r1_r2[k] = r1[k] + r2[k]
r2_d1[k] = r2[k] + d1[k]
r1_d1[k] = r1[k] + d1[k]
r1_r2_d1[k] = r1[k] + r2[k] + d1[k]
fname = lt.fname(sys.argv[-1])
lt.write_sta_dict(r1, fname + 'R1_hotsta')
lt.write_sta_dict(r2, fname + 'R1_2_hotsta')
lt.write_sta_dict(d1, fname + 'D_1_hotsta')
lt.write_sta_dict(r1_d1, fname + 'R1_D_1_hotsta')
lt.write_sta_dict(r2_d1, fname + 'R1_2_D_1_hotsta')
lt.write_sta_dict(r1_r2, fname + 'R1_R1_2_hotsta')
lt.write_sta_dict(r1_r2_d1, fname + 'R1_R1_2_D_1_hotsta')
def main():
res_neighbors = lt.pickle_load(sys.argv[-1])
#delete water
res_neighbors_dw = [(pdb,res,[n for n in neighbors if not 'HOH' in n]) for pdb,res,neighbors in res_neighbors]
res_neighbors_dw = [(pdb,res,neighbors) for pdb,res,neighbors in res_neighbors_dw if len(neighbors) > 0]
write_result(res_neighbors_dw,'1_delete_water')
#filter entry containing hetero residues
res_neighbors_fh = [(pdb,res,[n for n in neighbors if n.split('_')[-1] != 'H']) for pdb,res,neighbors in res_neighbors_dw]
res_neighbors_fh = [(pdb,res,neighbors) for pdb,res,neighbors in res_neighbors_fh if len(neighbors) > 0]
write_result(res_neighbors_fh,'2_dw_filter_hetero')
#special case: phos_res neighboring residues involving main-chain interaction is not considered
res_neighbors_pm = []
for pdb,res,neighbors in res_neighbors_fh:
res_id,res_chain = res.split('_')[1:3]
new_neighbors = []
for n in neighbors:
words=n.split('_')
if words[3] == 'M' and words[2] == res_chain and words[1] == res_id:
pass
else:
new_neighbors.append(n)
res_neighbors_pm.append((pdb,res,new_neighbors))
write_result(res_neighbors_pm,'3_dw_fh_pm')
#filter_entry containing only same-chain neighbors
res_neighbors_fs = []
for pdb,res,neighbors in res_neighbors_pm:
res_chain = [res.split("_")[2]]
neighbors_chain = [n.split("_")[2] for n in neighbors]
if set(res_chain)== set(neighbors_chain):
pass
else:
res_neighbors_fs.append((pdb,res,neighbors))
write_result(res_neighbors_fs,'4_dw_fh_pm_fs')
#change main-chain interaction residue as 'GLY'
res_neighbors_cm = []
for pdb,res,neighbors in res_neighbors_fs:
new_neighbors = []
for n in neighbors:
words = n.split('_')
if words[3] == 'M':
words = ['GLY'] + words[1:3]
else:
words = words[0:3]
new_neighbors.append('_'.join(words))
res_neighbors_cm.append((pdb,res,new_neighbors))
write_result(res_neighbors_cm,'4.0_dw_fh_fs_cm')
write_sta_result(res_neighbors_cm,'4.0_dw_fh_pm_cm')
#filter entry involves main-chain interaction
res_neighbors_fm = []
for pdb,res,neighbors in res_neighbors_fs:
interaction_type = [n.split('_')[3] for n in neighbors]
if 'M' in interaction_type:
pass
else:
res_neighbors_fm.append((pdb,res,neighbors))
write_result(res_neighbors_fm,'5_dw_fh_pm_fs_fm')
write_sta_result(res_neighbors_fm,'5_dw_fh_pm_fs_fm')
lt.pickle_dump(res_neighbors_dw,'hbplus_salt_combine_1_dw')
lt.pickle_dump(res_neighbors_fh,'hbplus_salt_combine_2_dw_fh')
lt.pickle_dump(res_neighbors_pm,'hbplus_salt_combine_3_dw_fh_pm')
lt.pickle_dump(res_neighbors_fs,'hbplus_salt_combine_4_dw_fh_pm_fs')
lt.pickle_dump(res_neighbors_cm,'hbplus_salt_combine_4.0_dw_fh_fs_cm')
lt.pickle_dump(res_neighbors_fm,'hbplus_salt_combine_5_dw_fh_pm_fs_fm')