def test_dp():
"""
Run on two small tableaux to test.
"""
ta = get_tableaux('/local/charikar/astivala/pdb/d1ubia_.ent', 'dssp',
'none',True,True,use_numeric=True)[1][0]
tb = get_tableaux('/local/charikar/ASTRAL/pdbstyle-1.73/xd/d1xd3b_.ent',
'dssp',
'none',True,True, use_numeric=True)[1][0]
score = tabmatch_dp(ta, tb, use_numeric=True,
disallow_type_mismatch = False)
print 'score = ',score
def build_db(
input_root,
secstruct_program="dssp",
domain_program="none",
include_310_helices=True,
include_pi_helices=True,
min_sse_len=None,
use_numeric=False,
use_hk=False,
build_dist_matrices=False,
):
"""
Build the tableaux db in memory.
Parameters:
input_root - root of PDB or ASTRAL pdbstyle divided hierarchy
secstruct_program - secondary structure definition program
('stride' or 'dssp' or 'pdb') to use.
domain_progam - domain decompositino method ('ddomain','cath', etc.)
include_310_helices - if True, include 3_10 helices in the graph
include_pi_helices - if True, include pi helices in the graph
min_sse_len - if not None, minimum SSE length
use_numeric - if True build database of Numeric array (Omega matrix)
rather than PTTableauPacked
use_hk - If True build database with HH and KK codes for strands in
same sheet.
build_dist_matrices - If True build database of SSE axis midpoint
distance matrices rather than tableaux.
Return value:
dict of { pdbid : [PTTableauPacked list] } for use_numeric=False OR
{ pdbid : [Numeric.array list ]} for use_numeric=True OR
{ pdbid : [Numeric.array list ]} for build_dist_matrices=True
pdbid is e.g. 1QLP when built from PDB or
e.g. 1qlp1a when built from ASTRAL pdbstyle
"""
tableau_db = {} # dict of { pdbid : [PTTableauPacked list] }, OR
# { pdbid : [Numeric.array list ]} for use_numeric=True
# or build_dist_matrices=True
# pdbid is e.g. 1QLP when built from PDB or
# e.g. 1qlp1a when built from ASTRAL pdbstyle
key_count = 0
tableaux_count = 0
keyerror_count = 0
file_count = 0
for root, dirs, files in os.walk(input_root):
for pdb_filename in [
filename
for filename in files
if (
os.path.splitext(filename)[1] == ".ent"
or os.path.splitext(filename)[1] == ".pdb"
or os.path.splitext(filename)[1] == ".gz"
)
]:
sys.stderr.write("processing " + pdb_filename + "\n")
file_count += 1
(pdbid, tableaux_list, sse_string_list) = get_tableaux(
os.path.join(root, pdb_filename),
secstruct_program,
domain_program,
include_310_helices,
include_pi_helices,
None, # sse_id_list
min_sse_len,
use_numeric,
use_hk,
build_dist_matrices,
)
if not (use_numeric or build_dist_matrices):
tableaux_list = [PTTableauPacked(tableau) for tableau in tableaux_list]
if tableau_db.has_key(pdbid):
sys.stderr.write("ERROR: duplicate key " + pdbid + "\n")
keyerror_count += 1
else:
tableau_db[pdbid] = tableaux_list
key_count += 1
tableaux_count += len(tableaux_list)
sys.stdout.write("processed %d files\n" % file_count)
sys.stdout.write("resulting in %d db entries\n" % key_count)
if build_dist_matrices:
sys.stdout.write(" %d SSE distance matrices\n" % tableaux_count)
else:
sys.stdout.write(" %d tableaux\n" % tableaux_count)
sys.stdout.write("with %d duplicate key errors\n" % keyerror_count)
return tableau_db
