from SAP.Bio.PDB import PDBParser
if len(sys.argv) != 4:
print("Expects three arguments,")
print(" - FASTA alignment filename (expect two sequences)")
print(" - PDB file one")
print(" - PDB file two")
sys.exit()
# The alignment
fa=AlignIO.read(open(sys.argv[1]), "fasta", generic_protein)
pdb_file1=sys.argv[2]
pdb_file2=sys.argv[3]
# The structures
p=PDBParser()
s1=p.get_structure('1', pdb_file1)
p=PDBParser()
s2=p.get_structure('2', pdb_file2)
# Get the models
m1=s1[0]
m2=s2[0]
al=StructureAlignment(fa, m1, m2)
# Print aligned pairs (r is None if gap)
for (r1, r2) in al.get_iterator():
print("%s %s" % (r1, r2))
for i in range(0, L):
residues[i].xtra["SS_PSEA"] = ss_seq[i]
#os.system("rm "+fname)
class PSEA(object):
def __init__(self, model, filename):
ss_seq = psea(filename)
ss_seq = psea2HEC(ss_seq)
annotate(model, ss_seq)
self.ss_seq = ss_seq
def get_seq(self):
"""
Return secondary structure string.
"""
return self.ss_seq
if __name__ == "__main__":
import sys
from SAP.Bio.PDB import PDBParser
# Parse PDB file
p = PDBParser()
s = p.get_structure('X', sys.argv[1])
# Annotate structure with PSEA sceondary structure info
PSEA(s[0], sys.argv[1])
for residue in residue_list:
if not is_aa(residue):
continue
rd=residue_depth(residue, surface)
ca_rd=ca_depth(residue, surface)
# Get the key
res_id=residue.get_id()
chain_id=residue.get_parent().get_id()
depth_dict[(chain_id, res_id)]=(rd, ca_rd)
depth_list.append((residue, (rd, ca_rd)))
depth_keys.append((chain_id, res_id))
# Update xtra information
residue.xtra['EXP_RD']=rd
residue.xtra['EXP_RD_CA']=ca_rd
AbstractPropertyMap.__init__(self, depth_dict, depth_keys, depth_list)
if __name__=="__main__":
import sys
from SAP.Bio.PDB import PDBParser
p=PDBParser()
s=p.get_structure("X", sys.argv[1])
model=s[0]
rd=ResidueDepth(model, sys.argv[1])
for item in rd:
print(item)
from SAP.Bio.PDB import PDBParser
if len(sys.argv) != 4:
print("Expects three arguments,")
print(" - FASTA alignment filename (expect two sequences)")
print(" - PDB file one")
print(" - PDB file two")
sys.exit()
# The alignment
fa = AlignIO.read(open(sys.argv[1]), "fasta", generic_protein)
pdb_file1 = sys.argv[2]
pdb_file2 = sys.argv[3]
# The structures
p = PDBParser()
s1 = p.get_structure('1', pdb_file1)
p = PDBParser()
s2 = p.get_structure('2', pdb_file2)
# Get the models
m1 = s1[0]
m2 = s2[0]
al = StructureAlignment(fa, m1, m2)
# Print aligned pairs (r is None if gap)
for (r1, r2) in al.get_iterator():
print("%s %s" % (r1, r2))
"""
if self.rotran is None:
raise PDBException("No transformation has been calculated yet")
rot, tran=self.rotran
rot=rot.astype('f')
tran=tran.astype('f')
for atom in atom_list:
atom.transform(rot, tran)
if __name__=="__main__":
import sys
from SAP.Bio.PDB import PDBParser, Selection
p=PDBParser()
s1=p.get_structure("FIXED", sys.argv[1])
fixed=Selection.unfold_entities(s1, "A")
s2=p.get_structure("MOVING", sys.argv[1])
moving=Selection.unfold_entities(s2, "A")
rot=numpy.identity(3).astype('f')
tran=numpy.array((1.0, 2.0, 3.0), 'f')
for atom in moving:
atom.transform(rot, tran)
sup=Superimposer()
sup.set_atoms(fixed, moving)
for i in range(0, L):
residues[i].xtra["SS_PSEA"]=ss_seq[i]
#os.system("rm "+fname)
class PSEA(object):
def __init__(self, model, filename):
ss_seq=psea(filename)
ss_seq=psea2HEC(ss_seq)
annotate(model, ss_seq)
self.ss_seq=ss_seq
def get_seq(self):
"""
Return secondary structure string.
"""
return self.ss_seq
if __name__=="__main__":
import sys
from SAP.Bio.PDB import PDBParser
# Parse PDB file
p=PDBParser()
s=p.get_structure('X', sys.argv[1])
# Annotate structure with PSEA sceondary structure info
PSEA(s[0], sys.argv[1])
def PdbAtomIterator(handle):
"""Returns SeqRecord objects for each chain in a PDB file
The sequences are derived from the 3D structure (ATOM records), not the
SEQRES lines in the PDB file header.
Unrecognised three letter amino acid codes (e.g. "CSD") from HETATM entries
are converted to "X" in the sequence.
In addition to information from the PDB header (which is the same for all
records), the following chain specific information is placed in the
annotation:
record.annotations["residues"] = List of residue ID strings
record.annotations["chain"] = Chain ID (typically A, B ,...)
record.annotations["model"] = Model ID (typically zero)
Where amino acids are missing from the structure, as indicated by residue
numbering, the sequence is filled in with 'X' characters to match the size
of the missing region, and None is included as the corresponding entry in
the list record.annotations["residues"].
This function uses the Bio.PDB module to do most of the hard work. The
annotation information could be improved but this extra parsing should be
done in parse_pdb_header, not this module.
"""
# Only import PDB when needed, to avoid/delay NumPy dependency in SeqIO
from SAP.Bio.PDB import PDBParser
from SAP.Bio.SeqUtils import seq1
def restype(residue):
"""Return a residue's type as a one-letter code.
Non-standard residues (e.g. CSD, ANP) are returned as 'X'.
"""
return seq1(residue.resname, custom_map=protein_letters_3to1)
# Deduce the PDB ID from the PDB header
# ENH: or filename?
from SAP.Bio.File import UndoHandle
undo_handle = UndoHandle(handle)
firstline = undo_handle.peekline()
if firstline.startswith("HEADER"):
pdb_id = firstline[62:66]
else:
warnings.warn("First line is not a 'HEADER'; can't determine PDB ID")
pdb_id = '????'
struct = PDBParser().get_structure(pdb_id, undo_handle)
model = struct[0]
for chn_id, chain in sorted(model.child_dict.items()):
# HETATM mod. res. policy: remove mod if in sequence, else discard
residues = [
res for res in chain.get_unpacked_list()
if seq1(res.get_resname().upper(), custom_map=protein_letters_3to1)
!= "X"
]
if not residues:
continue
# Identify missing residues in the structure
# (fill the sequence with 'X' residues in these regions)
gaps = []
rnumbers = [r.id[1] for r in residues]
for i, rnum in enumerate(rnumbers[:-1]):
if rnumbers[i + 1] != rnum + 1:
# It's a gap!
gaps.append((i + 1, rnum, rnumbers[i + 1]))
if gaps:
res_out = []
prev_idx = 0
for i, pregap, postgap in gaps:
if postgap > pregap:
gapsize = postgap - pregap - 1
res_out.extend(restype(x) for x in residues[prev_idx:i])
prev_idx = i
res_out.append('X' * gapsize)
else:
warnings.warn("Ignoring out-of-order residues after a gap",
UserWarning)
# Keep the normal part, drop the out-of-order segment
# (presumably modified or hetatm residues, e.g. 3BEG)
res_out.extend(restype(x) for x in residues[prev_idx:i])
break
else:
# Last segment
res_out.extend(restype(x) for x in residues[prev_idx:])
else:
# No gaps
res_out = [restype(x) for x in residues]
record_id = "%s:%s" % (pdb_id, chn_id)
# ENH - model number in SeqRecord id if multiple models?
# id = "Chain%s" % str(chain.id)
# if len(structure) > 1 :
# id = ("Model%s|" % str(model.id)) + id
record = SeqRecord(
Seq(''.join(res_out), generic_protein),
id=record_id,
description=record_id,
)
# The PDB header was loaded as a dictionary, so let's reuse it all
record.annotations = struct.header.copy()
# Plus some chain specifics:
record.annotations["model"] = model.id
record.annotations["chain"] = chain.id
# Start & end
record.annotations["start"] = int(rnumbers[0])
record.annotations["end"] = int(rnumbers[-1])
# ENH - add letter annotations -- per-residue info, e.g. numbers
yield record
"""
if self.rotran is None:
raise PDBException("No transformation has been calculated yet")
rot, tran = self.rotran
rot = rot.astype('f')
tran = tran.astype('f')
for atom in atom_list:
atom.transform(rot, tran)
if __name__ == "__main__":
import sys
from SAP.Bio.PDB import PDBParser, Selection
p = PDBParser()
s1 = p.get_structure("FIXED", sys.argv[1])
fixed = Selection.unfold_entities(s1, "A")
s2 = p.get_structure("MOVING", sys.argv[1])
moving = Selection.unfold_entities(s2, "A")
rot = numpy.identity(3).astype('f')
tran = numpy.array((1.0, 2.0, 3.0), 'f')
for atom in moving:
atom.transform(rot, tran)
sup = Superimposer()
sup.set_atoms(fixed, moving)
