def gen_input_args(g_tool, g_tool_name, outputdir, logd, directory_hierarchy,
ftest, fcdb, toa, btime, etime, dt, CONFIG_DICT):
"""
generate "input_args", which in a dictionary that holds all the varaibles
needed for your commands
"""
for inputdir, pf, seq, cdt, tmp, num in directory_hierarchy:
input_args = dict(inputdir=inputdir, pf=pf, seq=seq, cdt=cdt, num=num)
# gen paths for input files:
# (when organizing, input files could also be outputfiles)
# xtcf, grof, proxtcf, progrof, tprf, edrf, ndxf
input_args.update(gen_input_files(inputdir, pf))
# if g_tool is from organize module, no new dir needs to be created
# to compare string, is doesn't work (confirmed)
if not g_tool.__module__ == 'g_analyze.organize':
# anadir should be a subfolder under outputdir
anadir = os.path.join(outputdir, 'r_' + g_tool_name)
input_args['anadir'] = anadir
if not os.path.exists(anadir) and not ftest:
os.mkdir(anadir)
# this part will be improved later, particular when using a database
if fcdb:
import connect_db as cdb
ss = cdb.connect_db(CONFIG_DICT['database'])
query = ss.query(cdb.Cutoff_rg_alltrj).filter_by(sqid=seq)
time_for_b = query.value(cdt)
input_args['b'] = time_for_b
else:
input_args['b'] = 0 # default
# particular to make_ndx
if toa == 'g_make_ndx':
ndx_id = CONFIG_DICT['ndx_input'] # ndx_input_dict
ndx_fd = CONFIG_DICT['ndx_format'] # ndx_format_dict
# from pprint import pprint as pp
input_args['ndx_input'] = ' '.join(
[ndx_id[ndx_fd[f].format(**locals())] for f in ndx_fd]
)
if toa == 'g_select':
input_args['g_select_select'] = ("'" +
CONFIG_DICT['g_select']["seq"] +
CONFIG_DICT['g_select'][ cdt ] +
"'")
# particular to sequence_spacing, maybe later toa need also to be
# checked for other analysis, as well.
if toa == 'sequence_spacing':
from mysys import read_mysys
mysys = read_mysys.read()
# input_args['peptide_length'] = mysys[seq].len
input_args['peptide_length'] = mysys[seq].len # when analyzing ff_comparison
if toa == 'trjorder':
from mysys import read_mysys
mysys = read_mysys.read()
try:
input_args['NA'] = mysys[cdt].natom # when analyzing ff_comparison
except KeyError:
print "ASSUME NUMBER OF ATOMS PER SOLVENT MOLECULE IS THAT OF WATER: {0}".format(mysys['w'].natom)
input_args['NA'] = mysys['w'].natom
# input_args['bin'] = os.path.join(os.environ['HOME'], "exec/gromacs-4.0.5/exec/bin/")
# dirty, fix later!
input_args['bin'] = os.path.join(os.environ['HOME'], "exec/gromacs-4.5.5/exec/bin/")
if cdt in ['h', 'f']: # Heptanol
input_args['bin'] = os.path.join(os.environ['HOME'], "exec/gromacs-4.5.5/exec/bin/")
# if cdt in ['h', 'f']: # Heptanol
# os.environ['PATH'] = (os.path.join(os.environ['HOME'],
# "exec/gromacs-4.5.5/exec/bin/")
# + os.environ['PATH'])
input_args['pwd'] = os.getenv('PWD')
input_args['b'] = btime # beginning time
input_args['e'] = etime # endding time
input_args['dt'] = dt # endding time
# generate the command that is gonna be executed
cmd = g_tool(input_args)
logf = os.path.join(logd, '{0}.log'.format(pf)) if logd else None
yield (cmd, logf)
#!/usr/bin/env
from mysys import read_mysys
MYSYS = read_mysys.read()
def calc_ave_dd(seq, cdt):
dd = {
'rg_c_alpha': [1., 'rg'],
'rg_whole_length': [1., 'rg'],
'rg_backbone': [1., 'rg'],
'e2ed': [1., 'e2ed'],
} # ppty_name: [denominator, interested_col]
if seq in MYSYS:
dd.update(
{
'dssp_E': [float(MYSYS[seq].len), 'structure'],
'dssp_H': [float(MYSYS[seq].len), 'structure'],
'dssp_T': [float(MYSYS[seq].len), 'structure'],
'dssp_G': [float(MYSYS[seq].len), 'structure'],
'dssp_I': [float(MYSYS[seq].len), 'structure'],
'dssp_B': [float(MYSYS[seq].len), 'structure'],
'dssp_C': [float(MYSYS[seq].len), 'structure'],
'dssp_S': [float(MYSYS[seq].len), 'structure'],
'dssp_X': [float(MYSYS[seq].len), 'structure'],
'upup' : [float(MYSYS[seq].hbg), 'upup' ],
# g_mindist_excl1 double counts the contact, so divided by 2
'unun' : [float(MYSYS[seq].scnpg * 2),'unun'],