def main():
res_neighbors = read_pickle()
with lt.open_file(file_name='hbplus_salt_combine_initial') as w_f:
for pro, phos_res, neighbor_res in res_neighbors:
print >> w_f, '{0:<8}{1:<15}{2}'.format(pro, phos_res,
', '.join(neighbor_res))
lt.pickle_dump(res_neighbors, 'hbplus_salt_combine')
def main():
hbs = []
for hb2_f in lt.files_in_dir(sys.argv[-1]):
if hb2_f[-4:] == '.hb2':
hbs.extend(read_hb2(hb2_f))
write_initial(hbs)
hbs = [(pro, phos_res, neighbor_res)
for pro, phos_res, neighbor_res, _ in hbs]
lt.pickle_dump(hbs, 'hbplus')
def mds(scores_matrix):
seed = np.random.RandomState(seed=3)
mds = manifold.MDS(n_components=2, max_iter=3000000, eps=1e-9,
dissimilarity='precomputed', n_jobs=1)
pos = mds.fit(scores_matrix).embedding_
x = [p[0]*100 for p in pos]
y = [p[1]*100 for p in pos]
lt.pickle_dump(x,'pos_x')
lt.pickle_dump(y,'pos_y')
fig = plt.figure(1)
plt.scatter(x, y)
plt.savefig('cluster_mds.png')
plt.close()
def rcsb_uniprot():
keywords = [
'pfam', 'smart', 'supfam', 'uniprot_repeat', 'uniprot_keyword',
'prosite1', 'prosite2', 'prosite3'
]
p = Pool(8)
result = p.map(uniprot_wd40, keywords)
p.close()
wd40s = []
for k in keywords:
for r, v in result:
if r == k:
wd40s.append(v)
wdsp = get_wdsp_acc()
wd40s.append(wdsp)
keywords.append('wdsp')
total = set.union(*map(set, wd40s))
# if an entry apears in n different querys, its score is n
wd40s_score = [[] for i in range(9)]
def acc_score(acc):
i = 0
for w in wd40s:
if acc in w:
i += 1
return i
for acc in total:
num = acc_score(acc)
wd40s_score[num - 1].append(acc)
# use acc to search rcsb
resolution = 30.0
results = []
for beta in range(24):
for chain_len in range(100, 240, 10):
filename = str(beta) + '_' + str(chain_len)
uniprot_pdbids, report = rcsb_acc_customreport(
total, beta, chain_len, resolution)
pdb_scores = []
for p in report[1:]:
pdb_scores.append(p + [acc_score(p[2])])
pdb_scores = sorted(pdb_scores, key=lambda x: x[-1], reverse=True)
lt.pickle_dump(pdb_scores, filename + '_pdb_scores')
with open(filename + '_uniprot_pdb_scores.txt', 'w') as w_f:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
'acc', 'pdb', 'chain', 'entity', 'resolution', 'chain_len',
'release', 'score')
for p in pdb_scores:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
p[2], p[0], p[1], p[3], p[4], p[5], p[6], p[7])
results.append([str(beta) + '_' + str(chain_len), pdb_scores])
# plot trending barplot
keys = [r[0] for r in results]
data = map(len, [r[1] for r in results])
df = pd.DataFrame({'Parameters': keys, 'Num': data})
df = df.sort_values('Num', ascending=True)
sns.set_color_codes('pastel')
h = sns.barplot(y='Parameters', x='Num', data=wd, color='b')
h.figure.subplots_adjust(top=0.9, bottom=0.05, left=0.05, right=0.95)
ax.set(xlabel='Parameters',
ylabel='Num',
title='WD40 Structures got with Different Parameters')
plt.savefig('wd40_structures_got_by_different_parameters', dpi=300)
plt.close('all')
# get structures filtered by more strict parameters
results = sorted(results, key=lambda x: len(x[1]))
for r1, r2 in zip(results[:-1], results[1:]):
if len(r1[1]) < len(r2[1]):
added = set(r2[1]).difference(set(r1[1]))
filename = r2[0] + '_minus_' + r1[0]
with open(filename + '.txt', 'w') as w_f:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
'acc', 'pdb', 'chain', 'entity', 'resolution', 'chain_len',
'release', 'score')
for p in added:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
p[2], p[0], p[1], p[3], p[4], p[5], p[6], p[7])
def main():
beta, chain_len, resolution = 16, 160, 30.0
uniprot_pdbids, pdb_scores = rcsb_uniprot(beta, chain_len, resolution)
scop_pdbids = rcsb_scop(beta, chain_len, resolution)
pfam_pdbids = rcsb_pfam(beta, chain_len, resolution)
txt_pdbids = rcsb_pfam(beta, chain_len, resolution)
uniprot = set([u.split(':')[0] for u in uniprot_pdbids.split(',')[:-1]])
scop = set([u.split(':')[0] for u in scop_pdbids.split(',')[:-1]])
pfam = set([u.split(':')[0] for u in pfam_pdbids.split(',')[:-1]])
txt = set([u.split(':')[0] for u in txt_pdbids.split(',')[:-1]])
# plot heatmap of WD40s shared by different methods
sns.set_color_codes('pastel')
table = []
keys = ['Uniprot', 'SCOP', 'Pfam', 'Text']
total = [uniprot, scop, pfam, txt]
for w in total:
row = [len(w.intersection(wr)) * 1.0 / len(w) for wr in total]
table.append(row)
data = pd.DataFrame(table, columns=keys, index=keys)
fig = plt.figure()
ax = fig.add_subplot(111)
h = sns.heatmap(data, annot=True, fmt='.2f', cmap='Blues')
h.figure.subplots_adjust(top=0.9, bottom=0.13, left=0.13, right=0.9)
ax.set_xticklabels(keys, rotation=90)
ax.set_yticklabels(keys[::-1], rotation=0)
ax.set_title('Comaration of Different Annotation Methods')
plt.savefig('Comaration_of Different_Annotation_Methods.png', dpi=300)
plt.close('all')
sns.set_color_codes('bright')
venn2([uniprot, scop], ['UniProt', 'SCOP'])
plt.savefig('uniprot_scop.png', dpi=300)
plt.close('all')
venn2([uniprot, pfam], ['UniProt', 'Pfam'])
plt.savefig('uniprot_pfam.png', dpi=300)
plt.close('all')
venn2([uniprot, txt], ['UniProt', 'Text'])
plt.savefig('uniprot_pfam.png', dpi=300)
plt.close('all')
venn2([uniprot, set.union(*[scop, pfam, txt])],
['UniProt', 'Pfam_SCOP_Text'])
plt.savefig('uniprot_pfam_scop_txt.png', dpi=300)
plt.close('all')
venn2([pfam, txt], ['Pfam', 'Text'])
plt.savefig('pfam_txt.png', dpi=300)
plt.close('all')
venn2([pfam, scop], ['Pfam', 'SCOP'])
plt.savefig('pfam_scop.png', dpi=300)
plt.close('all')
venn3([pfam, scop, txt], ['Pfam', 'SCOP', 'Text'])
plt.savefig('pfam_scop_txt.png', dpi=300)
plt.close('all')
lt.pickle_dump([uniprot, scop, pfam, txt], 'search_method')
write_lis_lis([uniprot, scop, pfam, txt], 'rcsb_wd40_pdb',
['uniprot', 'scop', 'pfam', 'txt'])
# plot barplot
f, ax = plt.subplots()
total = set.union(*map(set, [uniprot, scop, pfam, txt]))
sns.set_color_codes('pastel')
methods = ['UniProt', 'Pfam', 'Text', 'SCOP']
wd = pd.DataFrame({
'Search Method': methods,
'Num': map(len, [total, total, total, total])
})
sns.barplot(x='Search Method', y='Num', data=wd, color='b')
sns.set_color_codes('muted')
wd = pd.DataFrame({
'Search Method': methods,
'Num': map(len, [uniprot, pfam, txt, scop])
})
sns.barplot(x='Search Method', y='Num', data=wd, color='b')
ax.set(xlabel='Search Method',
ylabel='Num',
title='WD40 Structures in RCSB')
plt.savefig('wd40_in_RCSB_pdbs', dpi=300)
plt.close('all')
def rcsb_uniprot(beta=15, chain_len=150, resolution=3.5):
keywords = [
'pfam', 'smart', 'supfam', 'uniprot_repeat', 'uniprot_keyword',
'prosite1', 'prosite2', 'prosite3'
]
p = Pool(8)
result = p.map(uniprot_wd40, keywords)
p.close()
wd40s = []
for k in keywords:
for r, v in result:
if r == k:
wd40s.append(v)
wdsp = get_wdsp_acc()
wd40s.append(wdsp)
keywords.append('wdsp')
total = set.union(*map(set, wd40s))
# if an entry apears in n different querys, its score is n
wd40s_score = [[] for i in range(9)]
def acc_score(acc):
i = 0
for w in wd40s:
if acc in w:
i += 1
return i
for acc in total:
num = acc_score(acc)
wd40s_score[num - 1].append(acc)
# use acc to search rcsb
uniprot_pdbids, report = rcsb_acc_customreport(total, beta, chain_len,
resolution)
pdb_scores = []
for p in report[1:]:
pdb_scores.append(p + [acc_score(p[2])])
pdb_scores = sorted(pdb_scores, key=lambda x: x[-1], reverse=True)
lt.pickle_dump(pdb_scores, 'pdb_scores')
with open('uniprot_pdb_scores.txt', 'w') as w_f:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
'acc', 'pdb', 'chain', 'entity', 'resolution', 'chain_len',
'release', 'score')
for p in pdb_scores:
print >> w_f, '{0:<15}{1:<10}{2:<8}{3:<8}{4:<15}{5:<8}{6:<18}{7:<8}'.format(
p[2], p[0], p[1], p[3], p[4], p[5], p[6], p[7])
# plot wd40 structures annotated by different database
total_pdb = set([p[2] for p in pdb_scores])
wd40s_pdb = [[a for a in w if a in total_pdb] for w in wd40s]
lt.pickle_dump(wd40s_pdb, 'pdb_acc_databases')
f, ax = plt.subplots()
keys = [
'Pfam', 'SMART', 'Superfamily', 'UniProt_repeat', 'UniProt_keyword',
'Prosite1', 'Prosite2', 'Prosite3', 'WDSP'
]
wd = pd.DataFrame({'Database': keys, 'Num': map(len, wd40s_pdb)})
wd = wd.sort_values('Num', ascending=False)
sns.set_color_codes('pastel')
h = sns.barplot(y='Database', x='Num', data=wd, color='b')
h.figure.subplots_adjust(top=0.9, bottom=0.05, left=0.14, right=0.95)
ax.set(xlabel='Database',
ylabel='Num',
title='WD40 Structures Annotated by Different Database')
# plt.xticks(roation=90)
plt.savefig('wd40_structures_accs_annotated_by_different_database',
dpi=300)
plt.close('all')
write_lis_lis(wd40s_pdb,
'wd40_structures_accs_annotated_by_different_database', keys)
# plot annotation score of wd40 structures
pdb_acc_scores = [[] for i in range(9)]
for p in pdb_scores:
pdb_acc_scores[p[-1] - 1].append(p[2])
pdb_acc_scores = map(set, pdb_acc_scores)
lt.pickle_dump(pdb_acc_scores, 'pdb_acc_scores')
f, ax = plt.subplots()
wd = pd.DataFrame({
'Database Score': range(1, 10),
'Num': map(len, pdb_acc_scores)
})
sns.set_color_codes('pastel')
sns.barplot(x='Database Score', y='Num', data=wd, color='b')
ax.set(xlabel='Database Score',
ylabel='Num',
title='Annotation Score of WD40 Structures')
plt.savefig('wd40_structures_annotation_score_accs', dpi=300)
plt.close('all')
write_lis_lis(pdb_acc_scores, 'wd40_structures_annotation_score_accs',
[str(i) for i in range(1, 10)])
print 'uniprot search is finished'
return uniprot_pdbids, pdb_scores
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')