def run( pos_file, neg_file, out_dir, format, align_count, mapping ):
# Open merit output
merit_out = open( os.path.join( out_dir, 'merits.txt' ), 'w' )
# Read integer sequences
pos_strings = list( io.get_reader( pos_file, format, None ) )
neg_strings = list( io.get_reader( neg_file, format, None ) )
symbol_count = mapping.get_out_size()
# Collapse
while symbol_count > stop_size:
print >> sys.stderr, "Collapsing from:", symbol_count
best_mapping = None
best_merit = 0
pb = ProgressBar( 0, symbol_count * ( symbol_count - 1 ) / 2, 78 )
count = 0
pairs = all_pairs( symbol_count )
for i, j in pairs:
collapsed = mapping.collapse( i, j )
merit = calc_merit( pos_strings, neg_strings, collapsed )
if merit > best_merit:
best_merit = merit
best_mapping = collapsed
count += 1
pb.update_and_print( count, sys.stderr )
mapping = best_mapping
symbol_count -= 1
# Append merit to merit output
print >>merit_out, symbol_count, best_merit
print >>sys.stderr, "\nBest Merit %d." % best_merit,
# Write best mapping to a file
mapping_out = open( os.path.join( out_dir, "%03d.mapping" % symbol_count ), 'w' )
for i, symbol in enumerate( mapping.get_table() ):
print >>mapping_out, str.join( '', rp.mapping.DNA.reverse_map( i, align_count ) ), symbol
mapping_out.close()
def run( pos_file, neg_file, out_dir, format, align_count, mapping ):
# Open merit output
merit_out = open( os.path.join( out_dir, 'merits.txt' ), 'w' )
# Read integer sequences
pos_strings = list( rp.io.get_reader( pos_file, format, None ) )
neg_strings = list( rp.io.get_reader( neg_file, format, None ) )
symbol_count = mapping.get_out_size()
# Collapse
while symbol_count > stop_size:
# Sync nodes on each pass, may not be required
pypar.barrier()
if node_id == 0:
print "Collapsing from:", symbol_count
pairs = all_pairs( symbol_count )
# Decide which subrange of all pairs this node will handle
lo, hi = pypar.balance( len( pairs ), nodes, node_id )
# Find best collapsed mapping in interval
best_i, best_j, best_merit = None, None, 0
for i, j in pairs[lo:hi]:
merit = calc_merit( pos_strings, neg_strings, mapping.collapse( i, j ) )
if merit > best_merit:
best_i, best_j, best_merit = i, j, merit
# Aggregate results
if node_id != 0:
# Send best i, j, merit to the master
pypar.send( ( best_i, best_j, merit ), 0 )
else:
# I am the master, get results from all other nodes and determine
# which had the best merit
for other_node_id in range( 1, nodes ):
i, j, merit = pypar.receive( other_node_id )
if merit > best_merit:
best_i, best_j, best_merit = i, j, merit
# Collapse the two symbols that resulted in the best merit
mapping = mapping.collapse( best_i, best_j )
symbol_count -= 1
# Ensure only the master writes files
if node_id == 0:
# Append merit to merit output
print >>merit_out, symbol_count, best_merit
print "\nBest Merit %d." % best_merit,
# Write best mapping to a file
mapping_out = open( os.path.join( out_dir, "%03d.mapping" % symbol_count ), 'w' )
for i, symbol in enumerate( mapping.get_table() ):
print >>mapping_out, str.join( '', rp.mapping.DNA.reverse_map( i, align_count ) ), symbol
mapping_out.close()
#!/usr/bin/env python2.3
"""
Make an identity mapping for some number of species
(each column mapped to unique symbol)
"""
import sys
import rp.mapping
align_count = int(sys.argv[1])
mapping = rp.mapping.identity_mapping(rp.mapping.DNA.get_out_size() ** align_count)
for i, symbol in enumerate(mapping.get_table()):
print str.join("", rp.mapping.DNA.reverse_map(i, align_count)), symbol