def make_oligomer(input_file,
largest_oligo_complexes,
report,
args,
residue_index_mapping=None):
global workdir
global input_name
global verbosity
global g_input_file
global g_args
global best_oligo_template_code
global renamed_chains_file
g_input_file = input_file
g_args = args
verbosity = args.verbosity
workdir = os.getcwd()
symmetry = args.symmetry
# Subsection 2[a] #######################################################################
if args.sequence_mode is False:
input_name = os.path.basename(input_file).split(".pdb")[0].replace(
'.', '_')
candidate_qscores = {}
# Select structurally best oligomeric template using GESAMT
pctools.print_section(2, 'OLIGOMER ASSEMBLING')
pctools.print_subsection('2[a]', 'Structural template selection')
if args.multiprocess is True:
p = Pool()
for hitchain, average_qscore, output in p.map_async(
analyse_largest_complexes,
largest_oligo_complexes.items()).get():
candidate_qscores[hitchain] = average_qscore
report['hits'][hitchain]['qscore'] = round(average_qscore, 3)
print(output)
p.close()
p.join()
else:
for item in largest_oligo_complexes.items():
hitchain, average_qscore, output = analyse_largest_complexes(
item)
candidate_qscores[hitchain] = average_qscore
report['hits'][hitchain]['qscore'] = round(average_qscore, 3)
print(output)
best_oligo_template = max(candidate_qscores.keys(),
key=(lambda x: candidate_qscores[x]))
if candidate_qscores[best_oligo_template] >= args.qscore_cutoff:
print('Structurally, the best template is: ' + clrs['y'] +
best_oligo_template + clrs['n'] + '. Using that!\n')
report['best_template'] = best_oligo_template.split(':')[0]
report['best_id'] = report['hits'][best_oligo_template]['id']
report['best_cov'] = report['hits'][best_oligo_template][
'coverage']
report['best_qscore'] = report['hits'][best_oligo_template][
'qscore']
report['best_nchains'] = report['hits'][best_oligo_template][
'final_homo_chains']
else:
print('No template had an average Q-score above cut-off of ' +
clrs['c'] + str(args.qscore_cutoff) + clrs['n'] +
'\nTry lowering the cutoff or running in sequence mode.\n')
report['exit'] = '4'
return None, None, report
report['topology_figure'] = './' + best_oligo_template.replace(
':', '_') + '_CHOIR_Topology.png'
template_chains = largest_oligo_complexes[best_oligo_template]
best_oligo_template_code = best_oligo_template.split(':')[0]
clean_template_file = make_local_template(best_oligo_template_code)
elif args.sequence_mode is True:
if input_file.endswith('.pdb'):
input_name = os.path.basename(input_file).split(".pdb")[0].replace(
'.', '_')
input_file = os.path.join(
workdir, input_name + '_CHOIR_MonomerSequence.fasta')
g_input_file = input_file
elif input_file.endswith('_CHOIR_MonomerSequence.fasta'):
input_name = os.path.basename(input_file).split(
"_CHOIR_MonomerSequence.fasta")[0]
pctools.print_section(2, 'OLIGOMER ASSEMBLING - SEQUENCE MODE')
print(clrs['y'] +
"Skipping section 2[a] - Structural template selection" +
clrs['n'] + "\n")
attempt = 0
while attempt < len(largest_oligo_complexes):
try:
best_oligo_template = list(largest_oligo_complexes)[attempt]
report['best_template'] = best_oligo_template.split(':')[0]
report['best_id'] = report['hits'][best_oligo_template]['id']
report['best_cov'] = report['hits'][best_oligo_template][
'coverage']
report['best_qscore'] = 'NA'
report['best_nchains'] = report['hits'][best_oligo_template][
'final_homo_chains']
report['topology_figure'] = './' + best_oligo_template.replace(
':', '_') + '_CHOIR_Topology.png'
template_chains = largest_oligo_complexes[best_oligo_template]
best_oligo_template_code = best_oligo_template.split(':')[0]
clean_template_file = make_local_template(
best_oligo_template_code)
break
except:
attempt += 1
if attempt < len(largest_oligo_complexes):
print('Attempt ' + str(attempt) +
' failed, trying a differente template candidate.')
if attempt == len(largest_oligo_complexes):
print('Failed to find templates in local databases.')
report['exit'] = '5'
return None, None, report
relevant_chains_file = extract_relevant_chains(clean_template_file,
template_chains)
if args.generate_report is True:
report['template_figure'], pymol_output = pctools.pymol_screenshot(
relevant_chains_file, args)
print(pymol_output)
renamed_chains_file, chains_dict = rename_relevant_chains(
relevant_chains_file)
relevant_chains = [
chains_dict[template_chain] for template_chain in template_chains
]
# Subsection 2[b] #######################################################################
pctools.print_subsection('2[b]', 'Generating alignment')
# Generate per chain alignment files
alignment_files = []
if args.sequence_mode is False:
if args.multiprocess is True:
p = Pool()
for qscore, rmsd, fasta_out, gesamt_output in p.map_async(
run_gesamt_parallel, chains_dict.values()).get():
alignment_files.append(fasta_out)
print(gesamt_output)
p.close()
p.join()
else:
for chain in chains_dict.values():
qscore, rmsd, fasta_out, gesamt_output = run_gesamt_parallel(
chain)
alignment_files.append(fasta_out)
print(gesamt_output)
elif args.sequence_mode is True:
if args.multiprocess is True:
p = Pool()
for fasta_out, output in p.map_async(alignment_from_sequence,
chains_dict.values()).get():
alignment_files.append(fasta_out)
print(output)
else:
for current_chain in chains_dict.values():
fasta_out, output = alignment_from_sequence(current_chain)
alignment_files.append(fasta_out)
print(output)
print('Alignment files:\n' + clrs['g'] +
('\n').join([os.path.basename(i)
for i in alignment_files]) + clrs['n'])
# Generate final alignment which will be the input for Modeller
final_alignment, full_residue_mapping = generate_ali(
alignment_files, best_oligo_template_code, residue_index_mapping, args)
# Score said alignment and enforce treshold
report[
'relative_alignment_score'], relative_wscores, nchains = score_alignment(
final_alignment)
print('\nFinal average relative score for alignment: ' +
str(round(report['relative_alignment_score'], 2)) + '%')
bad_streches = 0
for wscore in relative_wscores:
if wscore < args.similarity_cutoff:
bad_streches += 1
if bad_streches >= args.bad_streches * nchains:
if args.sequence_mode is True:
print(
'\nThe alignment score was unacceptable for ' + clrs['r'] +
str(bad_streches) + clrs['n'] +
' 30-res segments of the protein complex.\nTry running the default (structure) mode.\n'
)
else:
print(
'\nThe alignment score was unacceptable for ' + clrs['r'] +
str(bad_streches) + clrs['n'] +
' 30-res segments of the protein complex.\nTry increasing the number of candidate templates or tweaking the similarity cut-offs.\n'
)
report['exit'] = '6'
return None, None, report
# Subsection 2[c] #######################################################################
pctools.print_subsection('2[c]', 'Generating models')
genmodel_file, expected_models = create_genmodel(final_alignment,
best_oligo_template_code,
relevant_chains, args)
run_modeller(genmodel_file)
# Record list of oligomers built
nmodels = 0
built_oligomers = []
for model in expected_models:
built_oligomers.append(
restore_chain_identifiers(model, chains_dict,
full_residue_mapping))
nmodels += 1
print(clrs['b'] + 'ProtCHOIR' + clrs['n'] + ' built ' + clrs['c'] +
str(nmodels) + clrs['n'] + ' model oligomers:')
for model in built_oligomers:
print(clrs['g'] + model + clrs['n'])
return best_oligo_template, built_oligomers, report
def analyse_model(oligomer):
output = []
model_report = g_report.copy()
model_report['model_filename'] = oligomer
model_oligomer_name = os.path.basename(oligomer).split(
"_CHOIR_")[0].replace('.', '_')
output.append(pctools.subsection('3', model_oligomer_name))
output.append('Analysing oligomer file: ' + clrs['y'] + oligomer +
clrs['n'] + '\n')
model_report['model_oligomer_name'] = model_oligomer_name
if g_args.generate_report is True:
model_report['model_figures'], pymol_output = pctools.pymol_screenshot(
oligomer, g_args, putty=True)
output.append(pymol_output)
pdb_name, structure, nchains = pctools.parse_any_structure(oligomer)
nchains, seqs, chain_ids = pctools.extract_seqs(structure, 0)
relevant_chains = []
for seq in seqs:
relevant_chains.append(seq[0])
pisa_output, pisa_error, protomer_data = pctools.run_pisa(
oligomer,
'',
g_args.verbosity,
gen_monomer_data=True,
gen_oligomer_data=True)
protomer_surface_residues = pctools.get_areas(protomer_data)
model_report['assemblied_protomer_plot'], model_report[
'assemblied_protomer_exposed_area'], model_report[
'assemblied_protomer_hydrophobic_area'], model_report[
'assemblied_protomer_conserved_area'], minx, maxx, analysis_output = pctools.plot_analysis(
pdb_name,
protomer_surface_residues,
g_entropies,
g_z_entropies,
g_tmdata,
g_args,
minx=g_minx,
maxx=g_maxx)
output.append(analysis_output)
if 'I' in g_args.assessment and not g_args.allow_monomers:
output.append(
pctools.subsection('3' + '[I]', 'Interfaces Comparison: ' +
model_oligomer_name))
if g_args.sequence_mode is False and g_args.skip_conservation is False:
model_report['exposed_area_reduction'] = int(
100 *
(float(model_report['assemblied_protomer_exposed_area']) -
float(model_report['protomer_exposed_area'])) /
float(model_report['protomer_exposed_area']))
model_report['hydrophobic_area_reduction'] = int(
100 *
(float(model_report['assemblied_protomer_hydrophobic_area']) -
float(model_report['protomer_hydrophobic_area'])) /
float(model_report['protomer_hydrophobic_area']))
model_report['conserved_area_reduction'] = int(
100 *
(float(model_report['assemblied_protomer_conserved_area']) -
float(model_report['protomer_conserved_area'])) /
float(model_report['protomer_conserved_area']))
if model_report['exposed_area_reduction'] < -5:
if model_report['hydrophobic_area_reduction'] < 0:
hydophobic_surface_score = 10 * (
model_report['hydrophobic_area_reduction'] /
model_report['exposed_area_reduction']) / 3
else:
hydophobic_surface_score = 0
if hydophobic_surface_score > 10:
hydophobic_surface_score = 10
output.append('Hydrophobic surface score: ' +
str(hydophobic_surface_score))
if model_report['conserved_area_reduction'] < 0:
conserved_surface_score = 10 * (
model_report['conserved_area_reduction'] /
model_report['exposed_area_reduction']) / 3
else:
conserved_surface_score = 0
if conserved_surface_score > 10:
conserved_surface_score = 10
output.append('Conserved surface score: ' +
str(conserved_surface_score))
model_report['surface_score'] = round(
(hydophobic_surface_score + conserved_surface_score) / 2,
2)
else:
output.append(clrs['r'] + 'Exposed area reduction too small.' +
clrs['n'])
model_report['surface_score'] = 0
output.append('Final surface score: ' +
str(model_report['surface_score']))
else:
model_report['surface_score'] = 'NA'
model_oligomer = oligomer.split('_CHOIR_CorrectedChains')[0]
xml_out = model_oligomer + '_CHOIR_PisaInterfaces.xml'
model_interfaces_list, interfaces_output = pctools.parse_interfaces(
xml_out, relevant_chains, g_args.verbosity)
template_interfaces_list = g_interfaces_dict[g_template_hitchain]
if model_interfaces_list and template_interfaces_list:
if g_args.verbosity > 0:
output.append(clrs['y'] + 'MODEL INTERFACES' + clrs['n'])
for model_interface in model_interfaces_list:
output.append(clrs['y'] +
' <> '.join(model_interface['chains']) +
clrs['n'])
output.append(clrs['y'] + 'Interface Area: ' + clrs['n'] +
str(model_interface['interface area']) +
' A^2')
output.append(
clrs['y'] + 'Interface Solvation Energy: ' +
clrs['n'] +
str(model_interface['interface solvation energy']) +
' kcal/mol')
output.append(clrs['y'] + 'Hydrogen Bonds: ' + clrs['n'] +
str(model_interface['hydrogen bonds']))
output.append(clrs['y'] + 'Salt Bridges: ' + clrs['n'] +
str(model_interface['salt bridges']))
output.append(clrs['y'] + 'Disulphide Bridges: ' +
clrs['n'] +
str(model_interface['disulphide bridges']) +
"\n\n")
interfaces_comparison = {}
for template_interface in template_interfaces_list:
for model_interface in model_interfaces_list:
if set(model_interface['chains']) == set(
template_interface['chains']):
comparison_data = {}
denominator = 12
delta_area = round(
model_interface['interface area'] -
template_interface['interface area'], 2)
comparison_data['model area'] = model_interface[
'interface area']
comparison_data['template area'] = template_interface[
'interface area']
comparison_data['delta area'] = delta_area
delta_energy = round(
model_interface['interface solvation energy'] -
template_interface['interface solvation energy'],
2)
comparison_data['model energy'] = model_interface[
'interface solvation energy']
comparison_data[
'template energy'] = template_interface[
'interface solvation energy']
comparison_data['delta energy'] = delta_energy
delta_hb = round(
model_interface['hydrogen bonds'] -
template_interface['hydrogen bonds'], 2)
comparison_data['model hb'] = model_interface[
'hydrogen bonds']
comparison_data['template hb'] = template_interface[
'hydrogen bonds']
comparison_data['delta hb'] = delta_hb
delta_sb = round(
model_interface['salt bridges'] -
template_interface['salt bridges'], 2)
comparison_data['model sb'] = model_interface[
'salt bridges']
comparison_data['template sb'] = template_interface[
'salt bridges']
comparison_data['delta sb'] = delta_sb
delta_ss = round(
model_interface['disulphide bridges'] -
template_interface['disulphide bridges'], 2)
comparison_data['model ss'] = model_interface[
'disulphide bridges']
comparison_data['template ss'] = template_interface[
'disulphide bridges']
comparison_data['delta ss'] = delta_ss
output.append(clrs['y'] + 'INTERFACES COMPARISON' +
clrs['n'])
output.append(' <> '.join(model_interface['chains']))
if delta_area >= 0:
emphasis_color = clrs['g']
relative_area = 100
else:
emphasis_color = clrs['r']
relative_area = round(
model_interface['interface area'] * 100 /
template_interface['interface area'], 2)
output.append('Delta Interface Area: ' +
emphasis_color + str(delta_area) +
clrs['n'] + ' A^2 (' +
str(relative_area) + '%)')
if delta_energy <= 0:
emphasis_color = clrs['g']
relative_energy = 100
else:
emphasis_color = clrs['r']
if model_interface[
'interface solvation energy'] < 0 and template_interface[
'interface solvation energy'] < 0:
relative_energy = round(
model_interface[
'interface solvation energy'] * 100 /
template_interface[
'interface solvation energy'], 2)
elif model_interface[
'interface solvation energy'] > 0 and template_interface[
'interface solvation energy'] < 0:
relative_energy = 0
elif model_interface[
'interface solvation energy'] < 0 and template_interface[
'interface solvation energy'] > 0:
relative_energy = 100
elif model_interface[
'interface solvation energy'] > 0 and template_interface[
'interface solvation energy'] > 0:
relative_energy = 0
output.append('Delta Interface Solvation Energy: ' +
emphasis_color + str(delta_energy) +
clrs['n'] + ' kcal/mol (' +
str(relative_energy) + '%)')
if model_interface[
'hydrogen bonds'] == template_interface[
'hydrogen bonds'] == 0:
relative_hb = 0
emphasis_color = clrs['r']
denominator -= 2
elif delta_hb >= 0:
relative_hb = 100
emphasis_color = clrs['g']
else:
emphasis_color = clrs['r']
relative_hb = round(
model_interface['hydrogen bonds'] * 100 /
template_interface['hydrogen bonds'], 2)
output.append('Delta Hydrogen Bonds: ' +
emphasis_color + str(delta_hb) +
clrs['n'] + ' (' + str(relative_hb) +
'%)')
if model_interface[
'salt bridges'] == template_interface[
'salt bridges'] == 0:
relative_sb = 0
emphasis_color = clrs['r']
denominator -= 3
elif delta_sb >= 0:
relative_sb = 100
emphasis_color = clrs['g']
else:
relative_sb = round(
model_interface['salt bridges'] * 100 /
template_interface['salt bridges'], 2)
emphasis_color = clrs['r']
output.append('Delta Salt Bridges: ' + emphasis_color +
str(delta_sb) + clrs['n'] + ' (' +
str(relative_sb) + '%)')
if model_interface[
'disulphide bridges'] == template_interface[
'disulphide bridges'] == 0:
relative_ss = 0
emphasis_color = clrs['r']
denominator -= 4
elif delta_ss >= 0:
relative_ss = 100
emphasis_color = clrs['g']
else:
relative_ss = round(
model_interface['disulphide bridges'] * 100 /
template_interface['disulphide bridges'], 2)
emphasis_color = clrs['r']
output.append('Delta Disulphide Bridges: ' +
emphasis_color + str(delta_ss) +
clrs['n'] + ' (' + str(relative_ss) +
'%)\n')
if denominator == 0:
comparison_data['score'] = 0
else:
comparison_data['score'] = round(
(relative_area + 2 * relative_energy +
2 * relative_hb + 3 * relative_sb +
4 * relative_ss) / denominator, 2)
output.append('Interface score: ' +
str(comparison_data['score']))
interfaces_comparison[''.join(
sorted(
model_interface['chains']))] = comparison_data
comparison_plots, interfaces_output = plot_deltas(
model_oligomer_name, template, interfaces_comparison, g_args)
model_report['comparison_plots'] = os.path.basename(
comparison_plots)
output.append(interfaces_output)
summed_score = 0
for interface, data in interfaces_comparison.items():
summed_score += data['score']
model_report['interfaces_score'] = round(
summed_score / (10 * len(interfaces_comparison)), 2)
output.append('Final interfaces score: ' +
str(model_report['interfaces_score']))
else:
if 'surface_score' not in model_report:
model_report['surface_score'] = 0
model_report['interfaces_score'] = 0
else:
model_report['surface_score'] = 'NA'
model_report['interfaces_score'] = 'NA'
model_report['comparison_plots'] = 'NA'
model_report['assemblied_protomer_exposed_area'] = 'NA'
model_report['assemblied_protomer_hydrophobic_area'] = 'NA'
model_report['assemblied_protomer_conserved_area'] = 'NA'
if 'G' in g_args.assessment:
output.append(pctools.subsection('3' + '[G]', 'GESAMT Comparison'))
qscore, rmsd, fasta_out, gesamt_output = pctools.run_gesamt(
template, template_file, model_oligomer_name, oligomer, None,
g_args)
output.append(gesamt_output)
model_report['gesamt_qscore'] = str(qscore)
model_report['gesamt_rmsd'] = str(rmsd)
else:
model_report['gesamt_qscore'] = 'NA'
model_report['gesamt_rmsd'] = 'NA'
if 'M' in g_args.assessment:
output.append(pctools.subsection('3' + '[M]', 'Molprobity Comparison'))
model_molprobity, molprobity_output = pctools.run_molprobity(
oligomer, g_args)
output.append(molprobity_output)
model_report['model_clashscore'] = str(model_molprobity['clashscore'])
model_report['model_molprobity'] = str(
model_molprobity['molprobity_score'])
output.append(clrs['y'] + 'MOLPROBITY COMPARISON' + clrs['n'])
output.append('Criterion\tTempl.\tModel')
output.append('Rama. Fav.\t' + str(template_molprobity['rama_fav']) +
'\t' + str(model_molprobity['rama_fav']))
output.append('Rama. Out.\t' + str(template_molprobity['rama_out']) +
'\t' + str(model_molprobity['rama_out']))
output.append('Rot. Out.\t' + str(template_molprobity['rot_out']) +
'\t' + str(model_molprobity['rot_out']))
output.append('CBeta Dev.\t' + str(template_molprobity['cb_dev']) +
'\t' + str(model_molprobity['cb_dev']))
output.append('Clashscore\t' + str(template_molprobity['clashscore']) +
'\t' + str(model_molprobity['clashscore']))
output.append('Molprob. Score\t' +
str(template_molprobity['molprobity_score']) + '\t' +
str(model_molprobity['molprobity_score']))
molprobity_radar, radar_output = plot_molprobity(
model_oligomer_name, model_molprobity, template,
template_molprobity)
output.append(radar_output)
model_report['molprobity_radar'] = molprobity_radar
delta_clashscore = (model_molprobity['clashscore'] -
template_molprobity['clashscore']) / 10
output.append('Delta clashscore: ' + str(delta_clashscore))
if delta_clashscore >= 1:
model_report['quality_score'] = round(
10 - math.log(delta_clashscore**5, 10), 2)
else:
model_report['quality_score'] = 10
output.append('Final quality score: ' +
str(model_report['quality_score']))
else:
model_report['model_clashscore'] = 'NA'
model_report['model_molprobity'] = 'NA'
model_report['quality_score'] = 'NA'
if 'M' in g_args.assessment and 'I' in g_args.assessment and not g_args.allow_monomers:
if g_args.sequence_mode is False and g_args.skip_conservation is False:
model_report['protchoir_score'] = round(
sum([
model_report['interfaces_score'],
model_report['surface_score'],
model_report['quality_score']
]) / 3, 2)
else:
model_report['protchoir_score'] = round(
sum([
model_report['interfaces_score'],
model_report['quality_score']
]) / 2, 2)
elif 'M' in g_args.assessment:
model_report['protchoir_score'] = model_report['quality_score']
elif 'I' in g_args.assessment:
if g_args.sequence_mode is False and g_args.skip_conservation is False:
model_report['protchoir_score'] = round(
sum([
model_report['interfaces_score'],
model_report['surface_score']
]) / 2, 2)
else:
model_report['protchoir_score'] = model_report['interfaces_score']
else:
model_report['protchoir_score'] = 'NA'
if str(model_report['protchoir_score']) == 'NA':
model_report['score_color'] = 'grey'
elif model_report['protchoir_score'] <= 5:
model_report['score_color'] = 'red'
elif 5 < model_report['protchoir_score'] <= 7:
model_report['score_color'] = 'orange'
elif model_report['protchoir_score'] > 7:
model_report['score_color'] = 'green'
pickle.dump(model_report,
open(model_oligomer_name + '_CHOIR_model_report.pickle', 'wb'))
return model_report, '\n'.join(output)