[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[modeller_usage] modeling a chimeric protein



Dear all,
I have to model a chimeric protein of two known sequnces. I have gone through the previous archives and have come across the emails of people who have done it. 
however, I am confused with how to start the first alignment to get the following alignment file

>P1;proteinA
structureX:proteinA
aaaaaaaaaaaaaaaaaaaaaaaaaaaa----------------------------------*
>P1;proteinB
structureX:proteinB
----------------------------bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb*
>P1;chimera
sequence:chimera
aaaaaaaaaaaaaaaaaaaaaaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb*
is this the .ali file to give for alignment. Which script should I use. 
Kindly help with which is the correct script to use.
Thank you
Regards
Ayesha Fatima
QIUP, Ipoh, Perak
from modeller import *

log.verbose()
env = environ()

env.libs.topology.read(file='$(LIB)/top_heav.lib')

# Read aligned structure(s):
aln = alignment(env)
aln.append(file='fip.ali', align_codes='all')
aln_block = len(aln)

# Read aligned sequence(s):
aln.append(file='fip.ali', align_codes='fip')

# Structure sensitive variable gap penalty sequence-sequence alignment:
aln.salign(output='', max_gap_length=20,
           gap_function=True,   # to use structure-dependent gap penalty
           alignment_type='PAIRWISE', align_block=aln_block,
           feature_weights=(1., 0., 0., 0., 0., 0.), overhang=0,
           gap_penalties_1d=(-450, 0),
           gap_penalties_2d=(0.35, 1.2, 0.9, 1.2, 0.6, 8.6, 1.2, 0., 0.),
           similarity_flag=True)

aln.write(file='fip-mult.ali', alignment_format='PIR')
aln.write(file='fip-mult.pap', alignment_format='PAP')
# Illustrates the SALIGN multiple structure/sequence alignment

from modeller import *

log.verbose()
env = environ()
env.io.atom_files_directory = './:../atom_files/'

aln = alignment(env)
for (code, chain) in (('1osy', 'A'), ('3ob4', 'A')):
    mdl = model(env, file=code, model_segment=('FIRST:'+chain, 'LAST:'+chain))
    aln.append_model(mdl, atom_files=code, align_codes=code+chain)

for (weights, write_fit, whole) in (((1., 0., 0., 0., 1., 0.), False, True),
                                    ((1., 0.5, 1., 1., 1., 0.), False, True),
                                    ((1., 1., 1., 1., 1., 0.), True, False)):
    aln.salign(rms_cutoff=3.5, normalize_pp_scores=False,
               rr_file='$(LIB)/as1.sim.mat', overhang=30,
               gap_penalties_1d=(-450, -50),
               gap_penalties_3d=(0, 3), gap_gap_score=0, gap_residue_score=0,
               dendrogram_file='fm00495.tree',
               alignment_type='tree', # If 'progresive', the tree is not
                                      # computed and all structues will be
                                      # aligned sequentially to the first
               feature_weights=weights, # For a multiple sequence alignment only
                                        # the first feature needs to be non-zero
               improve_alignment=True, fit=True, write_fit=write_fit,
               write_whole_pdb=whole, output='ALIGNMENT QUALITY')

aln.write(file='fip-arah.pap', alignment_format='PAP')
aln.write(file='fip-arah.ali', alignment_format='PIR')

aln.salign(rms_cutoff=1.0, normalize_pp_scores=False,
           rr_file='$(LIB)/as1.sim.mat', overhang=30,
           gap_penalties_1d=(-450, -50), gap_penalties_3d=(0, 3),
           gap_gap_score=0, gap_residue_score=0, dendrogram_file='fa.tree',
           alignment_type='progressive', feature_weights=[0]*6,
           improve_alignment=False, fit=False, write_fit=True,
           write_whole_pdb=False, output='QUALITY')