def test_contact_search(self):
cs = gemmi.ContactSearch(4.0)
hg = gemmi.Element('Hg')
self.assertEqual(cs.get_radius(hg), 0)
cs.setup_atomic_radii(1, 0)
cs.set_radius(hg, 1.5)
self.assertEqual(cs.get_radius(hg), 1.5)
def test_fen4(self):
path = full_path('2242624.cif')
small = gemmi.read_small_structure(path)
types = small.atom_types
self.assertEqual(len(types), 2)
self.assertEqual(types[0].symbol, 'Fe')
self.assertEqual(types[1].element, gemmi.Element('N'))
def test_pdb_element_names(self):
pdb_line = "HETATM 4154 MG MG A 341 1.384 19.340 11.968" \
" 1.00 67.64 MG"
for line in [pdb_line, pdb_line.strip(' MG'), pdb_line[:-2] + ' ']:
st = gemmi.read_pdb_string(line)
residue = st[0].sole_residue('A', gemmi.SeqId(341, ' '))
mg_atom = residue.sole_atom('MG')
self.assertEqual(mg_atom.element.name, 'Mg')
self.assertAlmostEqual(mg_atom.b_iso, 67.64, delta=1e-6)
mg_atom.element = gemmi.Element('Cu')
self.assertEqual(mg_atom.element.name, 'Cu')
def calculate_formula_weight(formula):
total = 0.
for elem_count in formula.split():
if elem_count.isalpha():
elem = elem_count
count = 1
else:
n = 2 if elem_count[1].isalpha() else 1
elem = elem_count[:n]
count = int(elem_count[n:])
total += count * gemmi.Element(elem).weight
return total
def test_pdb_element_names_from_amber(self):
st = gemmi.read_pdb_string(AMBER_FRAGMENT)
residue = st[0][''][0]
self.assertEqual(residue.sole_atom('CB').element, gemmi.Element('C'))
self.assertEqual(residue.sole_atom('HB').element, gemmi.Element('H'))
self.assertEqual(residue.sole_atom('CG1').element, gemmi.Element('C'))
self.assertEqual(residue.sole_atom('HG11').element, gemmi.Element('H'))
chain = gemmi.read_pdb_string(FRAGMENT_WITH_HG)[0]['P']
self.assertEqual(chain[0].sole_atom('HG').element, gemmi.Element('Hg'))
self.assertEqual(chain[1].sole_atom('HG1').element, gemmi.Element('Hg'))
def test_pdb_element_names_from_amber(self):
st = gemmi.read_pdb_string(AMBER_FRAGMENT)
residue = st[0][''][0]
self.assertEqual(residue.sole_atom('CB').element, gemmi.Element('C'))
self.assertEqual(residue.sole_atom('HB').element, gemmi.Element('H'))
self.assertEqual(residue.sole_atom('CG1').element, gemmi.Element('C'))
self.assertEqual(residue.sole_atom('HG11').element, gemmi.Element('H'))
lines = AMBER_FRAGMENT.splitlines()
for n, atom in enumerate(residue):
self.assertEqual(atom.padded_name(), lines[n][12:16].rstrip())
chain = gemmi.read_pdb_string(FRAGMENT_WITH_HG)[0]['P']
self.assertEqual(chain[0].sole_atom('HG').element, gemmi.Element('Hg'))
self.assertEqual(chain[1].sole_atom('HG1').element,
gemmi.Element('Hg'))
def main():
# stage 1: reading PDB data
pdb_data = []
for arg in sys.argv[1:]:
for path in sorted_search(arg):
try:
item = get_file_stats(path)
except RuntimeError as e:
sys.stderr.write('Failed to read %s: %s\n' % (path, e))
continue
pdb_data.append(item)
if PLAIN_TEXT:
print('%s %5.0f %3.1g %s' % item)
# stage 2: gathering per-component statistics
stats = defaultdict(lambda: {
'cat': None,
'files': 0,
'poly': 0,
'nonpoly': 0,
'pdb': (None, 0)
})
for item in pdb_data:
pdb_id, volume, resolution, rest = item
if volume < 10 or volume != volume:
volume = 1e12
score_mult = 1.0 / volume / resolution
for item in rest.split():
comp, poly, nonpoly = item.split(':')
d = stats[comp]
d['files'] += 1
d['poly'] += int(poly)
d['nonpoly'] += int(nonpoly)
score = (int(poly) + int(nonpoly)) * score_mult
if score > d['pdb'][1]:
d['pdb'] = (pdb_id, score)
# stage 2a: add category from components.cif; also, count metal atoms
ccd_category = {}
metal_count = {}
ccd = gemmi.cif.read(CCD_PATH)
for block in ccd:
comp_id = block.find_value('_chem_comp.id')
ccd_category[comp_id] = block.find_value('_chem_comp.type')
symbols = block.find_values('_chem_comp_atom.type_symbol')
metal_count[comp_id] = sum(gemmi.Element(s).is_metal for s in symbols)
# stage 2b: add category from the Refmac monomer library
monlist = gemmi.cif.read(MON_LIB_LIST)['comp_list']
refmac_category = {
cc[0]: cc[1]
for cc in monlist.find('_chem_comp.', ['id', 'group'])
}
# stage 3: output
total_files = len(pdb_data)
if not PLAIN_TEXT:
print('{\n"file_count": %d,\n"data": [' % total_files, end='')
sep = ''
for key in sorted(stats.keys(), key=lambda k: -stats[k]['files']):
cat = ccd_category.get(key, '?').strip('"\'').lower()
cat = cat.replace('beta', '\u03B2')
cat = cat.replace('gamma', '\u03B3')
cat = cat.replace('delta', '\u03B4')
if 'terminus' in cat:
cat = cat.replace('NH3 amino terminus', 'N-terminus')
cat = cat.replace('cooh carboxy terminus', 'C-terminus')
cat = cat.replace('oh 3 prime terminus', "3'-terminus")
cat = cat.replace('oh 5 prime terminus', "5'-terminus")
rcat = refmac_category.get(key, 'n/a').lower().strip('"')
d = stats[key]
total = d['poly'] + d['nonpoly']
poly_percent = 100.0 * d['poly'] / total
example = d['pdb'][0]
if PLAIN_TEXT:
print('%3s %2d %7d %5d %7.3f %s' %
(key, metal_count[key], d['files'], total, poly_percent,
example))
else:
print('%s\n["%s",%d,"%s","%s",%d,%d,%.3f,"%s"]' %
(sep, key, metal_count[key], cat, rcat, d['files'], total,
poly_percent, example),
end='')
sep = ','
if not PLAIN_TEXT:
print('\n]\n}')