def test_dssp(path):
sec_struct_codes = {
0: "I",
1: "S",
2: "H",
3: "E",
4: "G",
5: "B",
6: "T",
7: "C"
}
mmtf_file = mmtf.MMTFFile.read(path)
array = mmtf.get_structure(mmtf_file, model=1)
array = array[array.hetero == False]
first_chain_id = array.chain_id[0]
chain = array[array.chain_id == first_chain_id]
n_residues = struc.get_residue_count(chain)
# Secondary structure annotation in PDB use also DSSP
# -> compare PDB and local DSSP
sse = mmtf_file["secStructList"]
sse = sse[:n_residues]
if (sse == -1).all():
# First chain is not a polypeptide chain (presumably DNA/RNA)
# DSSP not applicable -> return
return
sse = np.array([sec_struct_codes[code] for code in sse], dtype="U1")
chain = array[array.chain_id == first_chain_id]
sse_from_app = DsspApp.annotate_sse(chain)
np.set_printoptions(threshold=10000)
# PDB uses different DSSP version -> slight differences possible
# -> only 90% must be identical
assert np.count_nonzero(sse_from_app == sse) / len(sse) > 0.9
def test_invalid_structure():
array = strucio.load_structure(join(data_dir("structure"), "5ugo.mmtf"))
# Get DNA chain -> Invalid for DSSP
chain = array[array.chain_id == "T"]
with pytest.raises(SubprocessError):
DsspApp.annotate_sse(chain)
import biotite.structure.io.xtc as xtc
from biotite.application.dssp import DsspApp
# Put here the path of the downloaded files
templ_file_path = "../../download/lysozyme_md.pdb"
traj_file_path = "../../download/lysozyme_md.xtc"
xtc_file = xtc.XTCFile.read(traj_file_path)
traj = xtc_file.get_structure(template=strucio.load_structure(templ_file_path))
time = xtc_file.get_time()
traj = traj[:, struc.filter_amino_acids(traj)]
# DSSP does not assign an SSE to the last residue -> -1
sse = np.empty((traj.shape[0], struc.get_residue_count(traj) - 1), dtype='U1')
for idx, frame in enumerate(traj):
app = DsspApp(traj[idx])
app.start()
app.join()
sse[idx] = app.get_sse()
# Matplotlib needs numbers to assign colors correctly
def sse_to_num(sse):
num = np.empty(sse.shape, dtype=int)
num[sse == 'C'] = 0
num[sse == 'E'] = 1
num[sse == 'B'] = 2
num[sse == 'S'] = 3
num[sse == 'T'] = 4
num[sse == 'H'] = 5
num[sse == 'G'] = 6