def get_kic_run_details(output_directory, pdb_id, loop_sets, test_mode = False):
'''This function returns the details required to set up the analysis for the Rosetta KIC and NGK methods.'''
details = []
c = 0
for sc_file in glob.glob(os.path.join(output_directory, '{0}*.sc'.format(pdb_id))):
# Determine the id
sc_filename = os.path.split(sc_file)[1]
assert(sc_filename.startswith('{0}_score'.format(pdb_id)))
run_id = int(sc_filename[10:-3])
# Determine the score
sc_lines = [l.strip() for l in get_file_lines(sc_file) if l.strip()]
assert(sc_lines[0] == 'SEQUENCE:')
assert(sc_lines[1].split()[:2] == ['SCORE:', 'total_score'])
assert(sc_lines[2].split()[0] == 'SCORE:')
total_score = float(sc_lines[2].split()[1])
# Determine the filepath of the predicted structure
associated_pdb_file = os.path.join(output_directory, '{0}_{0}{1}_0001.pdb'.format(pdb_id, run_id))
# Extract the PDB coordinates into a pandas dataframe (HDF5 format)
assert(os.path.exists(associated_pdb_file))
hdf5_file = os.path.splitext(associated_pdb_file)[0] + '.hdf5'
if os.path.exists(hdf5_file):
store = pandas.HDFStore(hdf5_file)
pdb_loop_residue_matrix = store['dataframe']
store.close()
else:
pdb_loop_residue_matrix = PDB.extract_xyz_matrix_from_loop_json(PDB.from_filepath(associated_pdb_file).structure_lines, loop_sets, atoms_of_interest = backbone_atoms, expected_num_residues = 12, expected_num_residue_atoms = 4)
store = pandas.HDFStore(hdf5_file)
store['dataframe'] = pdb_loop_residue_matrix
store.close()
details.append(dict(
id = run_id,
score = total_score,
predicted_structure = associated_pdb_file,
pdb_loop_residue_matrix = pdb_loop_residue_matrix,
))
if test_mode:
c += 1
if c >= 10:
break
return details
def extract_analysis_data(dataset_list_file, output_directory, data_extraction_method, expectn, top_x, prefix, test_mode = False):
'''This is the main function in this script and is where the basic analysis is compiled.
output_directory should contain the results of the prediction run.
data_extraction_method should be a function pointer to the method-specific function used to retrieve the prediction results e.g. get_kic_run_details
expectn specifies how many predictions we expect to find (useful in case some jobs failed).
top_x specifies how many of the best-scoring predictions should be used to generate the TopX metric results e.g.
the Top5 RMSD metric value measures the lowest RMSD amongst the five best-scoring structures.
prefix is used to name the output files.
'''
# Sanity check
assert(top_x <= expectn)
# Set up reference structures
structures_folder = os.path.join('..', 'input', 'structures', '12_res')
rcsb_references = os.path.join(structures_folder, 'rcsb', 'reference')
rosetta_references = os.path.join(structures_folder, 'rosetta', 'reference')
# Set up the per-case statistics dicts
best_scoring_structures = {}
median_scoring_structures = {}
worst_scoring_structures = {}
total_percent_subanstrom = {}
top_x_percent_subanstrom = {}
top_x_loop_prediction_sets = {}
# Set up the input file used to generate the graph plotting the "percentage of subangstrom models" metric over
# varying values of X used to select the TopX structures
percentage_subangstrom_over_top_X_plot_input = ['PDB\tX\tPercentage of subangstrom cases for TopX']
percent_subangrom_by_top_x = {}
# Set up the summary analysis file
csv_file = ['\t'.join(['PDB ID', 'Models', '%<1.0A', 'Top{0} %<1.0A'.format(top_x), 'Best score', 'Top{0} score'.format(top_x), 'Median score', 'Worst score', 'Closest score', 'Top1 RMSD', 'Top{0} RMSD'.format(top_x), 'Closest RMSD'])]
# Read in the benchmark input
pdb_ids = [os.path.splitext(os.path.split(s.strip())[1])[0] for s in get_file_lines(dataset_list_file) if s.strip()]
# Truncate the benchmark input for test mode
if test_mode:
pdb_ids = pdb_ids[:10]
# Analyze the performance for each case in the benchmark
for pdb_id in pdb_ids:
rcsb_reference_pdb = os.path.join(rcsb_references, pdb_id + '.pdb')
assert(os.path.exists(rcsb_reference_pdb))
rosetta_reference_pdb = os.path.join(rosetta_references, pdb_id + '.pdb')
assert(os.path.exists(rosetta_reference_pdb))
assert(len(pdb_id) == 4)
loops_file = os.path.join(structures_folder, 'rosetta', 'pruned', '{0}.loop.json'.format(pdb_id))
loop_sets = json.loads(read_file(loops_file))
assert(len(loop_sets['LoopSet']) == 1)
# Create a container for loop predictions
loop_prediction_set = LoopPredictionSet()
# Read the coordinates from the reference PDB file
rcsb_reference_matrix = PDB.extract_xyz_matrix_from_loop_json(PDB.from_filepath(rcsb_reference_pdb).structure_lines, loop_sets, atoms_of_interest = backbone_atoms, expected_num_residues = 12, expected_num_residue_atoms = 4)
rosetta_reference_matrix = PDB.extract_xyz_matrix_from_loop_json(PDB.from_filepath(rosetta_reference_pdb).structure_lines, loop_sets, atoms_of_interest = backbone_atoms, expected_num_residues = 12, expected_num_residue_atoms = 4)
colortext.wgreen('\n\nReading in the run details for {0}:'.format(pdb_id))
details = data_extraction_method(output_directory, pdb_id, loop_sets, test_mode = test_mode)
for d in details:
loop_prediction = loop_prediction_set.add(d['id'], d['score'], pdb_id = pdb_id, rmsd = None, pdb_path = d['predicted_structure'], pdb_loop_residue_matrix = d['pdb_loop_residue_matrix'])
print(' Done')
# Compute the RMSD for this case for the structure using the pandas dataframe
# It is more efficient to do this after truncation if truncating by score but in the general case users will
# probably want to consider all predictions. If not (e.g. for testing) then arbitrary subsets can be chosen
# in the loop above
colortext.wgreen('Computing RMSDs for {0}:'.format(pdb_id))
loop_prediction_set.compute_rmsds(rcsb_reference_matrix)
loop_prediction_set.check_rmsds(rosetta_reference_matrix)
print(' Done\n')
# Truncate the structures to the top expectn-scoring files
loop_prediction_set.sort_by_score()
loop_prediction_set.truncate(expectn)
if len(loop_prediction_set) != expectn:
print('Error: Expected {0} structures but only found {1}.'.format(expectn, len(loop_prediction_set)))
sys.exit(1)
# Create a new set containing the top-X-scoring structures and identify the median-scoring structure
top_x_loop_prediction_sets[pdb_id] = loop_prediction_set[:top_x]
median_scoring_structures[pdb_id] = loop_prediction_set[int(expectn / 2)]
# Determine the lowest-/best-scoring structure
best_scoring_structures[pdb_id] = loop_prediction_set[0]
best_score = best_scoring_structures[pdb_id].score
worst_scoring_structures[pdb_id] = loop_prediction_set[-1]
worst_score = worst_scoring_structures[pdb_id].score
assert(top_x_loop_prediction_sets[pdb_id][0] == best_scoring_structures[pdb_id])
# Print structures
colortext.warning('Top{0} structures'.format(top_x))
print(top_x_loop_prediction_sets[pdb_id])
colortext.warning('Top1 structure')
print(best_scoring_structures[pdb_id])
colortext.warning('Median (by score) structure')
print(median_scoring_structures[pdb_id])
colortext.warning('Lowest-scoring structures')
print(worst_scoring_structures[pdb_id])
# Create values for TopX variable plot
loop_prediction_set.sort_by_score()
for top_x_var in range(1, len(loop_prediction_set) + 1):
new_subset = loop_prediction_set[:top_x_var]
percent_subangstrom = 100 * new_subset.fraction_with_rmsd_lt(1.0)
percentage_subangstrom_over_top_X_plot_input.append('{0}\t{1}\t{2}'.format(pdb_id, top_x_var, percent_subangstrom))
percent_subangrom_by_top_x[top_x_var] = percent_subangrom_by_top_x.get(top_x_var, {})
percent_subangrom_by_top_x[top_x_var][pdb_id] = percent_subangstrom
total_percent_subanstrom[pdb_id] = 100 * loop_prediction_set.fraction_with_rmsd_lt(1.0)
top_x_percent_subanstrom[pdb_id] = 100 * top_x_loop_prediction_sets[pdb_id].fraction_with_rmsd_lt(1.0)
colortext.warning('Number of sub-angstrom cases in the full set of {0}: {1}'.format(expectn, total_percent_subanstrom[pdb_id]))
colortext.warning('Number of sub-angstrom cases in the TopX structures: {1}'.format(expectn, top_x_percent_subanstrom[pdb_id]))
loop_prediction_set.sort_by_rmsd()
closest_rmsd = loop_prediction_set[0].rmsd
closest_score = loop_prediction_set[0].score
colortext.warning('RMSD of closest model: {0}'.format(closest_rmsd))
colortext.warning('Score of closest model: {0}'.format(closest_score))
top_1_rmsd = best_scoring_structures[pdb_id].rmsd
top_x_rmsd = best_scoring_structures[pdb_id].rmsd
top_x_score = best_scoring_structures[pdb_id].score
for s in top_x_loop_prediction_sets[pdb_id]:
if (s.rmsd < top_x_rmsd) or (s.rmsd == top_x_rmsd and s.score < top_x_score):
top_x_rmsd = s.rmsd
top_x_score = s.score
assert(top_x_score <= worst_score)
assert(top_x_rmsd <= top_1_rmsd)
print('Top 1 RMSD (predicted vs Rosetta/RCSB reference structure): {0}'.format(top_1_rmsd))
print('Top {0} RMSD (predicted vs Rosetta/RCSB reference structure): {1}'.format(top_x, top_x_rmsd))
csv_file.append('\t'.join(map(str, [pdb_id, expectn, total_percent_subanstrom[pdb_id], top_x_percent_subanstrom[pdb_id], best_score, top_x_score, median_scoring_structures[pdb_id].score, worst_score, closest_score, top_1_rmsd, top_x_rmsd, closest_rmsd])))
# Add a column of median percent subangstrom values
for top_x_var, values_by_pdb in sorted(percent_subangrom_by_top_x.iteritems()):
assert(sorted(values_by_pdb.keys()) == sorted(pdb_ids))
median_value = sorted(values_by_pdb.values())[len(pdb_ids) / 2]
percentage_subangstrom_over_top_X_plot_input.append('Median\t{1}\t{2}'.format(pdb_id, top_x_var, median_value))
write_file('{0}analysis.csv'.format(prefix), '\n'.join(csv_file))
write_file('{0}analysis.tsv'.format(prefix), '\n'.join(csv_file))
write_file('{0}percentage_subangstrom_over_top_X.tsv'.format(prefix), '\n'.join(percentage_subangstrom_over_top_X_plot_input))
