def dcd_fit(filename_dcd, filename_dcd_out, natom_total, serials,
filename_rmsd):
f_out = open(filename_rmsd, 'w')
# Coord1
pdb = PdbFile('16SCD.cg.pdb')
pdb.open_to_read()
ref_chains = pdb.read_all()
pdb.close()
#num_atom = 0
#for chain in ref_chains :
# for residue in chain.residues :
# num_atom += len(residue.atoms)
ref = zeros((natom_total, 3), dtype=float64, order='C')
i = 0
for chain in ref_chains:
for residue in chain.residues:
for atom in residue.atoms:
(ref[i][0], ref[i][1], ref[i][2]) = atom.xyz.get_as_tuple()
i += 1
mask = []
for i in range(natom_total):
# the serial ID starts from 1, thus i+1 is the serial ID
if i + 1 in serials:
mask.append(1)
else:
mask.append(0)
dcd = DcdFile(filename_dcd)
dcd.open_to_read()
dcd.read_header()
out_dcd = DcdFile(filename_dcd_out)
out_dcd.open_to_write()
out_dcd.set_header(dcd.get_header())
out_dcd.write_header()
#dcd.show_header()
k = 0
while dcd.has_more_data():
k += 1
coords_dcd = dcd.read_onestep_np()
rmsd = superimpose(ref.T, coords_dcd.T, mask)
f_out.write('{:8d} {:6.2f}\n'.format(k, rmsd))
out_dcd.write_onestep(coords_dcd)
dcd.close()
out_dcd.close()
chains_cg.append(c_cg)
return chains_cg
if __name__ == '__main__':
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) not in (3, 4):
print(
'Usage: SCRIPT [input aa PDB] [flag to start with P (Y/n)] [output cg PDB]'
)
sys.exit(2)
flg_start_P = False
if len(sys.argv) == 4:
if sys.argv[2] == 'Y':
flg_start_P = True
aa = PdbFile(sys.argv[1], 'r')
chains = aa.read_all()
aa.close()
chains_cg = aa2cg(chains, flg_start_P)
cg = PdbFile(sys.argv[-1], 'w')
cg.write_all(chains_cg)
cg.close()
#!/usr/bin/env python
#from Superimpose_weight import superimpose
from Superimpose_mask import superimpose
from cafysis.file_io.pdb import PdbFile
from cafysis.util_pdb import chains_to_ndarray
NATOM = 1037
chains_ref = PdbFile('../16SCD.cg.pdb', 'r').read_all_and_close()
chains_que = PdbFile('./cg.pdb', 'r').read_all_and_close()
#weight = [1.0]*NATOM
weight = [0.0] * NATOM
for i in range(14, 43):
weight[i] = 1.0
d_ref = chains_to_ndarray(chains_ref)
d_que = chains_to_ndarray(chains_que)
rmsd = superimpose(d_ref.T, d_que.T, weight)
print(rmsd)
serials.append(3*(res-1)+1) # S
elif 848 <= i <= 913:
res = i - 567
serials.append(3*(res-1)) # P
serials.append(3*(res-1)+1) # S
else:
print("Error: resid {:d} should not be there".format(i))
sys.exit(2)
for cM in cMs:
filename_dcd = 'cM{:s}.fit{:s}.dcd'.format(cM,name)
filename_dx = 'cM{:s}.fit{:s}.dx'.format(cM,name)
nMg = 0
c = PdbFile('../make_ninfo/16SCD.cM{:s}.cg.ion.pdb'.format(cM),'r').read_all_and_close()[0]
for r in c.residues:
if r.atoms[0].name.strip() == 'MG':
nMg += 1
dcd = DcdFile(filename_dcd)
dcd.open_to_read()
dcd.read_header()
data = []
mm = minmax()
''' Create target volume '''
mm_target = minmax()
c = PdbFile('./16SCD.cg.pdb','r').read_all_and_close()[0]
ID_DOM_INI = int(sys.argv[3]) - 1 # 重心を求める際に必要
ID_DOM_END = int(sys.argv[4]) - 1
ID_DOM_INI_FIT = int(sys.argv[5]) - 1 # 重心を求める際に必要
ID_DOM_END_FIT = int(sys.argv[6]) - 1
BOXSIZE = float(sys.argv[7])
BOXMAX = 0.5 * BOXSIZE
BOXMIN = -0.5 * BOXSIZE
### Files
dcd = DcdFile(sys.argv[1])
dcd.open_to_read()
pdb = PdbFile(sys.argv[2])
pdb.open_to_read()
dcd_out = DcdFile(sys.argv[-1])
dcd_out.open_to_write()
### Read the reference pdb
ref_chains = pdb.read_all()
num_atom = 0
for chain in ref_chains :
num_atom += chain.num_atom()
ref = zeros((3, num_atom), dtype=float64, order='F')
i = 0
def apply_rot(chains, rot):
for c in chains:
for r in c.residues:
for a in r.atoms:
coords = a.xyz.get_as_list()
coords = dot(rot, coords + [
1.0,
])[0:3]
a.xyz.x = coords[0]
a.xyz.y = coords[1]
a.xyz.z = coords[2]
if __name__ == '__main__':
import sys
if len(sys.argv) != 3:
print("Usage: SCRIPT [input reference PDB] [input query PDB]")
sys.exit(2)
chains_ref = PdbFile(sys.argv[1], 'r').read_all_and_close()
chains_que = PdbFile(sys.argv[2], 'r').read_all_and_close()
rmsd, rot = fit(chains_ref, chains_que)
print(rmsd)
print(rot)
# print(' % SCRIPT [input DCD] [beginning (0)] [end] [stride] [reference PDB] [output movie]')
# sys.exit(2)
#if args.flg_fit:
# from Superimpose import superimpose
if args.frame_begin < 0:
print('Error: Beginning frame must be > 0')
sys.exit(2)
if args.frame_stride <= 0:
print('Error: Frame stride must be > 0')
sys.exit(2)
# Read the reference PDB
pdb = PdbFile(args.pdb)
pdb.open_to_read()
chains = pdb.read_all()
pdb.close()
# Output PDB
movie = PdbFile(args.out)
movie.open_to_write()
# Open DCD and read the header
dcd = DcdFile(args.dcd)
dcd.open_to_read()
dcd.read_header()
num_dcd_frames = dcd.count_frame()
nt = nt12 - 11
mp_domA.append(3 * (nt - 1)) # Use phosphate
mp_domA_0 = 3 * (110 - 11)
mp_domA_1 = 3 * (72 - 11)
mp_domB = []
for nt12 in list(range(42, 47 + 1)) + list(range(174, 178 + 1)) + list(
range(130, 166 + 1)):
nt = nt12 - 11
mp_domB.append(3 * (nt - 1)) # Use phosphate
mp_domB_0 = 3 * (155 - 11)
mp_domB_1 = 3 * (130 - 11)
pdb = PdbFile(pdbfilepath)
pdb.open_to_read()
chains = pdb.read_all()
c = chains[0]
pdb.close()
'''
Domain A
'''
xyzs = []
for imp in mp_domA:
xyzs.append(c.get_atom(imp - 1).xyz.get_as_list())
xyzs = np.array(xyzs)
com = np.sum(xyzs, axis=0) / float(xyzs.shape[0])
#print com
xyzs = xyzs - com
if len(sys.argv) < 5:
print(('Usage: % SCRIPT [PDB filename] [DCD filename]'
+'[serial ID begin] [serial ID end]'))
sys.exit(2)
filename_pdb = sys.argv[1]
filename_dcd = sys.argv[2]
id_begin = []
id_end = []
for iarg in range(3, len(sys.argv)-1, 2) :
id_begin.append(int(sys.argv[iarg]))
id_end.append(int(sys.argv[iarg+1]))
# Coord1
pdb = PdbFile(filename_pdb)
pdb.open_to_read()
ref_chains = pdb.read_all()
pdb.close()
num_atom = 0
for chain in ref_chains :
for residue in chain.residues :
num_atom += len(residue.atoms)
ref = zeros((3, num_atom), dtype=float64, order='F')
i = 0
for chain in ref_chains :
for residue in chain.residues:
for atom in residue.atoms :
from cafysis.file_io.dcd import DcdFile
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 5:
print(
'Usage: % SCRIPT [PDB filename] [DCD filename] [out PDB filename] [out bfactor file]'
)
sys.exit(2)
filename_pdb = sys.argv[1]
filename_dcd = sys.argv[2]
filename_outpdb = sys.argv[3]
filename_out = sys.argv[4]
# Coord1 fron input PDB
pdb = PdbFile(filename_pdb)
pdb.open_to_read()
chains = pdb.read_all()
pdb.close()
num_atom = 0
for chain in chains:
num_atom += chain.num_atom()
#i = 0
#for chain in ref_chains :
# for residue in chain.residues:
# for atom in residue.atoms :
# (ref[0][i], ref[1][i], ref[2][i]) = atom.xyz.get_as_tuple()
# i += 1
#
print('Usage: SCRIPT [PDB]')
print('')
print('Returns: %5i %6.3f %6.3f %6.3f % (N, Rg, D, S)')
print(' N = number of particles (atoms)')
print(' Rg = radius of gyration')
print(' D = Sphericity (0 <= D <= 1)')
print(' D = 0 --> perfect sphere')
print(' D > 0 --> anisotropic')
print(' S = Spheroidal shape (-1/4 <= S <= 2)')
print(' S < 0 --> oblate')
print(' S > 0 --> prolate')
sys.exit(2)
# Read PDB coordinates
pdb = PdbFile(sys.argv[1])
pdb.open_to_read()
chains = pdb.read_all()
xyzs = []
for c in chains:
for r in c.residues:
for a in r.atoms:
xyzs.append(a.xyz.get_as_list())
'''
xyzs for N-atom PDB
[ [ 1x, 1y, 1z],
[ 2x, 2y, 2z],
[ 3x, 3y, 3z],
[ 4x, .
.
(ignore Hydrogen atom)
'''
import sys
from cafysis.file_io.pdb import PdbFile
from cafysis.elements.coord import Coord
from cafysis.elements.pdb import Chain, Residue, Atom
element2mass = {'P': 30.973761, 'O': 15.9994, 'C': 12.0107, 'N': 14.0067}
if __name__ == '__main__':
if len(sys.argv) != 3:
print('Usage: %SCRIPT [input PDB file] [output PDB]')
sys.exit(2)
pdb_in = PdbFile(sys.argv[1])
pdb_in.open_to_read()
chains = pdb_in.read_all()
pdb_in.close()
pdb_out = PdbFile(sys.argv[2])
pdb_out.open_to_write()
pdb_out.write_remark('Generated using cafysis/pdb_rna_nucleotide_com.py')
import time
import datetime
pdb_out.write_remark('At %s' % (datetime.datetime.fromtimestamp(
time.time()).strftime('%Y%m%d %H:%M%S'), ))
chains_com = []
from . import elements
#!/usr/bin/env python
'''
@author: Naoto Hori
'''
import sys
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 5:
print('\n Usage: SCRIPT [list file] [input PDB1] [input PDB2] [output]\n')
sys.exit(2)
f_list = open(sys.argv[1], 'r')
f_pdb = PdbFile(sys.argv[2])
f_pdb.open_to_read()
chains1 = f_pdb.read_all()
f_pdb.close
f_pdb = PdbFile(sys.argv[3])
f_pdb.open_to_read()
chains2 = f_pdb.read_all()
f_pdb.close
f_out = open(sys.argv[4], 'w')
if len(chains1) != len(chains2):
print(("Error: len(chains1)(=%i) != len(chains2)(=%i)" %
(len(chains1), len(chains2))))
sys.exit(2)
# !!! current version is for only single chain !!!
if len(chains1) != 1 or len(chains2) != 1:
import sys
import math
from cafysis.file_io.pdb import PdbFile
from cafysis.elements.coord import Coord
if len(sys.argv) not in (2, 3):
print('Usage: SCRIPT [PDB] (score cutoff = 0.5)')
print(' or : SCRIPT [PDB] [score cutoff]')
sys.exit(2)
SCORE_CUT = 0.5
if len(sys.argv) > 2:
SCORE_CUT = float(sys.argv[2])
pf = PdbFile(sys.argv[1])
pf.open_to_read()
chains = pf.read_all()
pf.close()
coms = []
normals = []
locations = []
## Suppose all residues have a base
nres = 0
for ic, c in enumerate(chains):
for ir, r in enumerate(c.residues):
nres += 1
## If residues in the original PDB are
# DT5, DA, DC ...., then
SEQ_POSITION = 1
# T5, A, C ...., then
#SEQ_POSITION = 0
ATOMS_P = ('P', 'OP1', 'OP2', "O5'") # "O3'" from the previous nucleotide
ATOMS_P_AMBER = ("P", "O1P", "O2P", "O5*")
ATOMS_S = ("C5'", "C4'", "C3'", "C2'", "C1'", "O4'")
ATOMS_S_AMBER = ("C5*", "C4*", "C3*", "C2*", "C1*", "O4*")
ATOMS_A = ("N9", "C8", "N7", "C5", "C6", "N6", "N1", "C2", "N3", "C4")
ATOMS_G = ("N9", "C8", "N7", "C5", "C6", "O6", "N1", "C2", "N2", "N3", "C4")
ATOMS_C = ("N1", "C2", "O2", "N3", "C4", "N4", "C5", "C6")
ATOMS_T = ("N1", "C2", "O2", "N3", "C4", "O4", "C5", "C7", "C6")
aa = PdbFile(sys.argv[1])
aa.open_to_read()
chains = aa.read_all()
cg_chains = []
atom_id = 0
for c in chains:
c_cg = Chain()
xyz_O3 = None
res_id = 0
for ir, r in enumerate(c.residues):
xyz_P = Coord()
nP = 0
#!/usr/bin/env python
import sys
import math
from cafysis.file_io.pdb import PdbFile
from cafysis.file_io.ninfo import NinfoFile
from cafysis.para.rnaAform import ARNA
from cafysis.para.rnaDT13 import DT13
from cafysis.elements.ninfo import NinfoSet, BondLength, BondAngle, BaseStackDT, HBondDT
if len(sys.argv) != 4:
print('Usage: SCRIPT [cg pdb] [hb list file] [output ninfo]')
sys.exit(2)
f_in = PdbFile(sys.argv[1])
f_in.open_to_read()
chains = f_in.read_all()
f_in.close()
if len(chains) > 1:
print('%i chains' % len(chains))
n_nt = []
for ic, c in enumerate(chains):
n_nt.append(c.num_res())
print('#nt (chain %i): ', ic + 1, n_nt)
seq = []
for ic, c in enumerate(chains):
s = []
assembly_units.append(mtx_id)
if row == 3:
row_pre = 0
else:
row_pre = row
#TEST
#for mtx_id in assembly_units:
# print (mtx_id)
# matrices[mtx_id].show()
#sys.exit(1)
filename_pdb = sys.argv[1]
''' Read inpout PDB '''
pdb = PdbFile(filename_pdb)
pdb.open_to_read()
chains = pdb.read_all()
pdb.close()
_, ext = os.path.splitext(filename_pdb)
filename_base = os.path.basename(filename_pdb)[:-len(ext)]
''' Rotate and output each assembly unit '''
for mtx_id in assembly_units:
newchains = copy.deepcopy(chains)
for c in newchains:
for r in c.residues:
for a in r.atoms:
#print ('###')
atoms_AU = 'N6 O4 N1 N3 TER'
atoms_GC = 'N1 N3 N2 O2 O6 N4 TER'
atoms_GU = 'N1 O2 O6 N3 TER'
if len(sys.argv) != 4:
print(
"Usage: SCRIPT [input cg.pdb (for seq)] [input hb.native.dat] [output hbond.dat]"
)
sys.exit(2)
filepath_pdb = sys.argv[1]
filepath_hb = sys.argv[2]
filepath_out = sys.argv[3]
pdb = PdbFile(filepath_pdb)
pdb.open_to_read()
chains = pdb.read_all()
if len(chains) != 1:
print("Error: len(chains) != 1, not supported")
sys.exit(2)
seq = ''
for r in chains[0].residues:
seq += r.atoms[0].res_name.strip()[-1]
nseq = len(seq)
print(seq)
print('length = %i' % nseq)
'''
Created on 2013/08/06
@author: Naoto Hori
'''
import sys
from cafysis.file_io.dcd import DcdFile
from cafysis.file_io.ts import TsFile
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 5:
print('Usage: % SCRIPT [input DCD] [ts file] [reference PDB] [output movie]')
sys.exit(2)
# Read the reference PDB
pdb = PdbFile(sys.argv[-2])
pdb.open_to_read()
chains = pdb.read_all()
pdb.close()
# Output PDB
pdb = PdbFile(sys.argv[-1])
pdb.open_to_write()
# Open DCD and read the header
dcd_filename = sys.argv[1]
dcd = DcdFile(dcd_filename)
dcd.open_to_read()
dcd.read_header()
# Open TS and read the header
'''
RN20:107
Ste7のPDBについて、位置と配向を揃える
'''
from cafysis.elements.coord import Coord
from cafysis.mtx_coord_transform import mtx_crd_transform
from cafysis.file_io.pdb import PdbFile
import sys
from math import hypot, atan2
if len(sys.argv) != 2:
print('Usage: SCRIPT [file]')
sys.exit(2)
pdb = PdbFile(sys.argv[1])
pdb.open_to_read()
chains = pdb.read_all()
#DEBUG from math import sqrt
#DEBUG Q = Coord(-2,-2*sqrt(3.0), - 4*sqrt(3.0))
# QにSte7のQ189:CAの座標を代入
Q = Coord()
for atom in chains[1].residues[188].atoms:
if atom.name.find("CA") != -1:
#(Q.x,Q.y,Q.z) = atom.xyz.get_as_tuple()
Q = atom.xyz
N = Coord()
for atom in chains[1].residues[200].atoms:
if atom.name.find("CA") != -1:
N = atom.xyz
SEP_B_B = 3 # residue (i) and residue (i+3)
SEP_B_S = 2 # residue (i) and residue (i+2)
SEP_S_S = 2 # residue (i) and residue (i+2)
import sys
from cafysis.file_io.pdb import PdbFile
from cafysis.file_io.ninfo import NinfoFile
from cafysis.elements.ninfo import NinfoSet, Fene, LJ
from cafysis.para.BetancourtThirumalai import BTmatrix
if len(sys.argv) != 3:
print('Usage: SCRIPT [input PDB] [output ninfo]')
sys.exit(2)
p = PdbFile(sys.argv[1])
p.open_to_read()
chains = p.read_all()
ns = NinfoSet()
a_BB_pre = None
for ic, c in enumerate(chains):
for r in c.residues:
num_a = len(r.atoms)
a_BB = None
a_SC = None
import sys
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) < 5:
print(
'Usage: % SCRIPT [average file] [input pdb] [ev file] [,ev file ....] [output PC file]'
)
sys.exit(2)
data_ave = []
for line in open(sys.argv[1], 'r'):
data_ave.append(float(line.strip()))
print(("#Dimension: %s" % len(data_ave)))
f_pdb = PdbFile(sys.argv[2])
f_pdb.open_to_read()
f_out = open(sys.argv[-1], 'w')
# Read eigen values
num_ev = len(sys.argv) - 4
ev = []
for i in range(num_ev):
f_ev = open(sys.argv[i + 3], 'r')
ev_tmp = []
for line in f_ev:
if line.find('#') != -1: continue
ev_tmp.append(float(line.strip()))
ev.append(ev_tmp)
f_ev.close()
from cafysis.file_io.dcd import DcdFile
from cafysis.file_io.pdb import PdbFile
from Superimpose_mask import superimpose
from numpy import zeros, asarray, float64
import sys
id_begin = []
id_end = []
for iarg in range(4, len(sys.argv)-1, 2) :
id_begin.append(int(sys.argv[iarg]))
id_end.append(int(sys.argv[iarg+1]))
NATOM_TOTAL = 5594
# Coord1
pdb = PdbFile('16SCD.cg.pdb')
pdb.open_to_read()
ref_chains = pdb.read_all()
pdb.close()
num_atom = 0
for chain in ref_chains :
for residue in chain.residues :
num_atom += len(residue.atoms)
#ref = zeros((3, NATOM_TOTAL), dtype=float64, order='F')
ref = zeros((NATOM_TOTAL, 3), dtype=float64, order='C')
i = 0
for chain in ref_chains :
for residue in chain.residues:
'''
@author: Naoto Hori
'''
import sys
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 5:
print('')
print(
' Usage: SCRIPT [input PDB] [The residue number of the first a.a.] [output PDB] [log file]'
)
print('')
sys.exit(2)
pdb_in = PdbFile(sys.argv[1])
pdb_in.open_to_read()
chains = pdb_in.read_all()
pdb_in.close()
res_id = int(sys.argv[2])
f_log = open(sys.argv[4], 'w')
f_log.write('#original -> new\n')
for c in chains:
print(sys.argv[1], '#residues', len(c.residues))
for r in c.residues:
f_log.write('%i %s -> %i\n' %
(r.atoms[0].res_seq, r.atoms[0].ins_code, res_id))
for a in r.atoms:
a.res_seq = res_id
a.ins_code = ' '
from cafysis.elements.ninfo import NinfoSet
from cafysis.file_io.ninfo import NinfoFile
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 4:
print ("Usage: SCRIPT [ninfo file] [pdb file] [output file]")
sys.exit(2)
file_ninfo = NinfoFile(sys.argv[1])
file_ninfo.open_to_read()
ns = NinfoSet()
file_ninfo.read_all(ns)
ns.update_info()
file_ninfo.close()
file_pdb = PdbFile(sys.argv[2])
file_pdb.open_to_read()
chains = file_pdb.read_all()
xyz = []
for c in chains:
for i in range(c.num_atom()):
xyz.append(c.get_atom(i).xyz)
print(("## Confirmation: number of atoms = %i" % len(xyz)))
f_out = open(sys.argv[-1],'w')
f_out.write('#Contacts\n')
for con in ns.contacts:
conid = con.id
#!/usr/bin/env python
# -*- coding: utf-8 -*-
'''
@author: Naoto Hori
'''
import sys
from cafysis.file_io.pdb import PdbFile
if len(sys.argv) != 6:
print(
'\n Usage: SCRIPT [bfactor file] [PDB file] [scale] [Upper] [output PDB file]\n'
)
sys.exit(2)
f_bf_in = open(sys.argv[1], 'r')
f_pdb = PdbFile(sys.argv[2])
f_pdb.open_to_read()
chains = f_pdb.read_all()
f_pdb.close()
f_pdb_out = PdbFile(sys.argv[-1])
f_pdb_out.open_to_write()
f_pdb_out._file.write('RECORD # SCRIPT: bfactor_write_to_pdb.py\n')
f_pdb_out._file.write('RECORD # argv[1]: ' + sys.argv[1] + '\n')
f_pdb_out._file.write('RECORD # argv[2]: ' + sys.argv[2] + '\n')
f_pdb_out._file.write('RECORD # argv[3]: ' + sys.argv[3] + '\n')
f_pdb_out._file.write('RECORD # argv[4]: ' + sys.argv[4] + '\n')
f_pdb_out._file.write('RECORD # argv[5]: ' + sys.argv[5] + '\n')
scale = float(sys.argv[3])
upper = float(sys.argv[4])
#!/usr/bin/env python
from cafysis.elements.pdb import Chain, Residue
from cafysis.file_io.pdb import PdbFile
from cafysis.pdb_aa2cg import aa2cg
from cafysis.bestfit_pdb_chains import fit, apply_rot
# Reference structure
chains_1j5e_cg = PdbFile('../16SCD.cg.pdb', 'r').read_all_and_close()
'''
4y4o-pdb-bundle1.pdb
4y4o-pdb-bundle2.pdb <=== A 562-913 = 16SCD
4y4o-pdb-bundle3.pdb
4y4o-pdb-bundle4.pdb <=== A 562-913 = 16SCD
'''
DISTANCE_MG = 6.0
def check_distance(chain_ref, atom_query):
for r in chain_ref.residues:
for a in r.atoms:
if atom_query.xyz.distance(a.xyz) <= DISTANCE_MG:
return True
return False
for ibundle_16SCD, ibundles_Mg, modelname in ((2, (1, 2), '1a'), (4, (3, 4),
'2a')):
# Read 16SCD (Turn on HETATM to read Mg)
