def run_jobs( args ):
if exists( args.lockfile ):
stderr.write("%s has already existed\n" % args.lockfile )
return 0
else:
if not args.dry_run:
filesystem_util.touch( args.lockfile )
rsn = int( basename( getcwd() ) )
'''
if args.prepack:
silent_fn = "pos_%s_silent.out" % rsn
else:
#silent_fn = "pos_%s_silent_packed_c3.out" % rsn
#silent_fn = "pos_%s_silent.out.packed.out" % rsn
#silent_fn = glob("pos_%s_silent*packed*.out" % rsn )[0]
#silent_fn = glob("pos_%s_silent_packed_v2_minbb.out" % rsn )[0]
'''
#silent_fn = glob("pos_%s_silent%s.out" % args.silentfn_pattern )[0]
if args.silentfn_pattern:
#silent_fn = glob("pos_%s_silent_%s.out" %( rsn, args.silentfn_pattern ))
#assert len(silent_fn)==1, silent_fn
#silent_fn = silent_fn[0]
silent_fn = "pos_%s_silent_%s.out" %( rsn, args.silentfn_pattern )
else:
silent_fn = "pos_%s_silent.out" % rsn
print silent_fn
assert exists( silent_fn )
extract_out = extract_cmd( silent_fn )
clustering_out = clustering_cmd( extract_out )
parse_results( extract_out, clustering_out )
def run_jobs( args ):
if exists("run.lock"):
stderr.write("job has already existed\n")
return 0
else:
filesystem_util.touch("run.lock")
rsn = int( basename( getcwd() ) )
assert isdir( args.input_dir ), args.input_dir
ref_fragfiles = " ".join( glob("%s/after_rotation_frags.%s.%s.*pdb" %( args.input_dir, args.mers, rsn ) ) )
fragfiles_list = []
# saner
j_rsds = range( 1, args.n_total_positions+1 )[rsn:]
for pdb in glob("%s/after_rotation_frags.%s.*pdb" %( args.input_dir, args.mers )):
frag_rsn = int( basename(pdb).split(".")[2] )
# to prevent silly bug
assert frag_rsn < args.n_total_positions, "ERROR: please reset the n_total_positions!\n"
if frag_rsn in j_rsds:
fragfiles_list.append( pdb )
fragfiles = " ".join( fragfiles_list )
#flags += "-mapfile %s\n" % args.mapfile
flags = "-ref_fragfiles %s\n" % ref_fragfiles
flags += "-fragfiles %s\n" % fragfiles
flags += "-out:score pos_%s_score.sc\n" % rsn
flags += "-clash_dist_threshold %s\n" % args.clash_dist
flags += "-database /work/wangyr/xtal_rosetta_database\n"
if args.native:
flags += "-native %s\n" % args.native
fast_flags = "-chemical:exclude_patches LowerDNA UpperDNA Cterm_amidation SpecialRotamer protein_cutpoint_upper protein_cutpoint_lower VirtualBB ShoveBB VirtualDNAPhosphate VirtualNTerm CTermConnect sc_orbitals pro_hydroxylated_case1 pro_hydroxylated_case2 ser_phosphorylated thr_phosphorylated tyr_phosphorylated tyr_sulfated lys_dimethylated lys_monomethylated lys_trimethylated lys_acetylated glu_carboxylated cys_acetylated tyr_diiodinated N_acetylated C_methylamidated MethylatedProteinCterm\n"
arguments = fast_flags + flags
if args.noloophash:
arguments += "-bound\n"
arguments += "-bound_stringent\n"
else:
arguments += "-lh:db_path /work/kenjung/for/possu/3to25mer\n"
if args.soften_clash_score:
arguments += "-soften_clash_score\n"
flags_fn = open("flags", "w")
flags_fn.write( arguments + "-mute all\n" )
flags_fn.close()
#print "writing down args"
system( "%s @flags" % args.exe )
def run_jobs( args ):
if exists("running.lock"):
stderr.write("job has already existed\n")
return 0
else:
filesystem_util.touch("running.lock")
if not exists( args.flags_fn ):
stderr.write("flags has not already existed\n")
return 0
flags = " " + " ".join( [ line.strip() for line in open( args.flags_fn, "r" ).readlines() ] )
currdir = basename( getcwd() )
extra_flags = " -pos %s -out:file:scorefile pos_%s_score.sc -out:file:silent pos_%s_silent.out " %( currdir, currdir, currdir )
system( args.exe + flags + extra_flags + "-mute all" )
def run_jobs( args ):
if exists("run.lock"):
stderr.write("job has already existed\n")
return 0
else:
filesystem_util.touch("run.lock")
rsn = int( basename( getcwd() ) )
assert isdir( args.input_dir ), args.input_dir
ref_fragfiles = " ".join( glob("%s/after_rotation_frags.%s.%s.*pdb" %( args.input_dir, args.mers, rsn ) ) )
fragfiles_list = []
for pdb in glob("%s/after_rotation_frags.%s.*pdb" %( args.input_dir, args.mers )):
this_rsn = int( basename(pdb).split(".")[2] )
if this_rsn != rsn:
fragfiles_list.append( pdb )
fragfiles = " ".join( fragfiles_list )
flags = " -native %s -mapfile %s -ref_fragfiles %s -fragfiles %s -out:score pos_%s_score.sc -clash_dist_threshold %s -database /work/wangyr/xtal_rosetta_database " %(
args.native, args.mapfile, ref_fragfiles, fragfiles, rsn, args.clash_dist )
fast_flags = " -chemical:exclude_patches LowerDNA UpperDNA Cterm_amidation SpecialRotamer protein_cutpoint_upper protein_cutpoint_lower VirtualBB ShoveBB VirtualDNAPhosphate VirtualNTerm CTermConnect sc_orbitals pro_hydroxylated_case1 pro_hydroxylated_case2 ser_phosphorylated thr_phosphorylated tyr_phosphorylated tyr_sulfated lys_dimethylated lys_monomethylated lys_trimethylated lys_acetylated glu_carboxylated cys_acetylated tyr_diiodinated N_acetylated C_methylamidated MethylatedProteinCterm "
arguments = fast_flags + flags
if args.noloophash:
arguments += " -bound "
else:
arguments += " -lh:db_path /work/kenjung/for/possu/3to25mer "
if args.soften_clash_score:
arguments += " -soften_clash_score "
if args.go_ahead:
flags_fn = open("flags", "w")
flags_fn.write( args.exe + arguments + " -mute all " )
flags_fn.close()
system( "sh flags" )
else:
flags_fn = open("flags", "w")
flags_fn.write( arguments + " -mute all " )
flags_fn.close()
print "writing down args"
def run_jobs(args):
filesystem_util.touch("extract.lock")
rsn = int(basename(getcwd()))
tags = " ".join(
[
line.split()[-1].split(".pdb")[0]
for line in open(args.clustered_results, "r").readlines()
if float(line.split()[0]) == rsn
]
)
if not tags:
stderr.write("ERROR: no tags available for this target\n")
exit()
# silent_fn = "pos_%s_silent_packed_c3_80percent_cut.out" % rsn
# silent_fn = "pos_%s_silent_packed_c3_100percent_cut.out" % rsn
matched_files = glob("pos_%s_%s*" % (rsn, args.silent_fn_pattern))
assert len(matched_files) == 1, matched_files
silent_fn = matched_files[0]
fast_flags = " -chemical:exclude_patches LowerDNA UpperDNA Cterm_amidation SpecialRotamer protein_cutpoint_upper protein_cutpoint_lower VirtualBB ShoveBB VirtualDNAPhosphate VirtualNTerm CTermConnect sc_orbitals pro_hydroxylated_case1 pro_hydroxylated_case2 ser_phosphorylated thr_phosphorylated tyr_phosphorylated tyr_sulfated lys_dimethylated lys_monomethylated lys_trimethylated lys_acetylated glu_carboxylated cys_acetylated tyr_diiodinated N_acetylated C_methylamidated MethylatedProteinCterm "
# arguments = fast_flags + "-mute all -out:file:residue_type_set centroid -in:file:silent %s -in:file:silent_struct_type binary -in:file:tags %s" %( silent_fn, tags )
arguments = fast_flags + "-mute all -in:file:silent %s -in:file:silent_struct_type binary -in:file:tags %s" % (
silent_fn,
tags,
)
if args.go_ahead:
system(args.exe + arguments)
assert len(glob("after_rotation_frags.*.*.*.*.????.pdb")) != 0
# shutil.move("after_rotation_frags*pdb", args.outfrags_dir )
system("mv after_rotation_frags*pdb %s" % args.outfrags_dir)
else:
print(args.exe + arguments)
parser.add_argument("-a", "--fastaA", required=True )
parser.add_argument("-r", "--closabscore_gapsize", default=15, type=int )
parser.add_argument("-m", "--mer", default=9 )
parser.add_argument("--lockfile", default="junction_closabscore_cleaner.lock" )
args = parser.parse_args()
#assert not exists( args.lockfile ), args.lockfile
if exists( args.lockfile ): exit()
scorefile = "pos_%s_score.sc" % basename( getcwd() )
assert exists( scorefile ), scorefile
assert exists( args.fastaA ), args.fastaA
filesystem_util.touch( args.lockfile )
rsds_to_clean = is_within_junction( args, scorefile )
if not rsds_to_clean:
exit()
print scorefile, rsds_to_clean
# if not
outlines = cleaner( scorefile, rsds_to_clean )
clean_outfile = scorefile + ".clean"
out = open( clean_outfile, "w" )
out.write( outlines )
out.close()
