if len(SCORE_RESULTS[clf]) >= i + 1:
outline += str(SCORE_RESULTS[clf][i])
outline += ','
outfile.write(outline + '\n')
print('Done.')
def draw_graphs():
print('Making histograms...')
for clf in CLASSIFICATIONS:
plt.hist(SCORE_RESULTS[clf], bins=100)
plt.title('Molprobity ' + clf)
ax = plt.gca()
ax.set_ylabel('Count')
ax.set_xlabel('Clipper Score')
ax.set_yscale('log')
plt.savefig(os.path.join(TESTING_OUTPUT_DIR,
'rama_hist_' + clf.lower() + '.png'),
dpi=600)
plt.close()
if __name__ == '__main__':
setup()
PDB_IDS = get_available_pdb_ids()
PDB_REPORT_DATA = load_pdb_report_data()
ramalyze_all()
export_results()
draw_graphs()
cleanup_all_pdb_redo_dirs()
shortlists[0].append(pdb_id)
elif status == 200:
if [ os.path.exists(os.path.join(PDB_REDO_DATA_DIR, pdb_id, pdb_id + suffix + '.gz')) for suffix in PDB_REDO_SUFFIXES ].count(True) < 4:
shortlists[1].append(pdb_id)
elif retry_failed_ids:
shortlists[2].append(pdb_id)
print('Unchecked IDs:', len(shortlists[0]))
print('Successes to retry:', len(shortlists[1]))
print('Failures to retry:', len(shortlists[2]))
compiled_shortlist = [ pdb_id for shortlist in shortlists for pdb_id in shortlist ]
shortlist_length = len(compiled_shortlist)
# For each PDB ID in the shortlist, check if it exists in PDB-REDO, and if so, add it to the download queue
for i, pdb_id in enumerate(compiled_shortlist):
response = requests.get(PDB_REDO_URL + pdb_id)
PDB_REDO_RECORD[pdb_id] = response.status_code
print(pdb_id + ' ' + str(response.status_code) + ' ::: ' + str(i) + ' / ' + str(shortlist_length))
if response.status_code == 200:
queue.put(pdb_id)
# Every 10 codes, write out the record file
if i % 10 == 0 or i == shortlist_length-1:
with open(PDB_REDO_RECORD_PATH, 'w') as outfile:
for pdb_id in pdb_ids:
outfile.write(pdb_id + ',' + str(PDB_REDO_RECORD[pdb_id]) + '\n')
if __name__ == '__main__':
setup()
PDB_REPORT_VALUES = load_pdb_report_data()
scrape_pdb_redo()
print('Done.')