def calc_merit( pos_strings, neg_strings, mapping ):
# Apply mapping to strings
pos_strings = [ mapping.translate( s ) for s in pos_strings ]
neg_strings = [ mapping.translate( s ) for s in neg_strings ]
# Cross validate using those strings
radix = mapping.get_out_size()
order = max_order( radix )
model_factory = lambda d0, d1: model.train( order, radix, d0, d1 )
cv_engine = cv.CV( model_factory, pos_strings, neg_strings, fold=fold, passes=passes )
cv_engine.run()
# Merit is TP + TN
return cv_engine.cls1.pos + cv_engine.cls2.neg
def calc_merit(self, mapping):
# Apply mapping to strings
pos_strings = [mapping.translate(s) for s in self.pos_strings]
neg_strings = [mapping.translate(s) for s in self.neg_strings]
# Cross validate using those strings
radix = mapping.get_out_size()
## model_factory = lambda d0, d1: ProductModel( radix, d0, d1 )
model_factory = lambda d0, d1: rp.models.complex_periodic.train(5, 1, 4, radix, d0, d1)
cv_engine = rp.cv.CV(
model_factory,
zip(self.pos_genome_seqs, pos_strings),
zip(self.neg_genome_seqs, neg_strings),
fold=fold,
passes=passes,
)
cv_engine.run()
# Merit is TP + TN
## print "Pos:", cv_engine.cls1
## print "Neg:", cv_engine.cls2
return (cv_engine.cls1.pos / (len(pos_strings) * passes) + cv_engine.cls2.neg / (len(neg_strings) * passes)) / 2
def run( pos_file, neg_file, format, mapping, order, modname ):
pos_blocks = list( bx.align.maf.Reader( pos_file ) )
neg_blocks = list( bx.align.maf.Reader( neg_file ) )
# Read integer sequences
pos_strings = list( [ mapping.translate( rp.mapping.DNA.translate_list( [ c.text for c in block.components ] ) ) for block in pos_blocks ] )
neg_strings = list( [ mapping.translate( rp.mapping.DNA.translate_list( [ c.text for c in block.components ] ) ) for block in neg_blocks ] )
# Determine radix
radix = max( map( max, pos_strings ) + map( max, neg_strings ) ) + 1
# Build model
model = rp.models.train( modname, order, radix, pos_strings, neg_strings )
# Find all words in the training data
words = words_from_blocks( itertools.chain( pos_blocks, neg_blocks ), order )
for word, count in words:
ints = rp.mapping.DNA.translate_list( word )
ints = mapping.translate( ints )
assert len( ints ) == order + 1
scores = array( [ float("nan") ] * len( ints ), typecode="f" )
model.score_positions( ints, scores )
print "%s\t%d\t%0.6f" % ( "|".join( word ), count, scores[-1] )
def run( data_file, modname, model_file, out_file, mapping, window, shift, low, high, reorder ):
# Read model
model = rp.models.get( modname ).from_file( model_file )
radix = model.get_radix()
# Open maf file
mafs = bx.align.maf.Reader( data_file )
# Score each alignment
for i, maf in enumerate( mafs ):
if reorder: components = [ maf.components[ i ] for i in reorder ]
else: components = maf.components
ints = rp.mapping.DNA.translate_list( [ c.text for c in components ] )
if mapping: ints = mapping.translate( ints )
# print i
score_windows( maf, ints, model, out_file, window, shift, low, high )
def calc_merit( training_sets, mapping, modname, modorder ):
# Apply mapping to strings
training_sets = [ [ mapping.translate( s ) for s in strings ] for strings in training_sets ]
# Cross validate using those strings
radix = mapping.get_out_size()
if len( training_sets ) == 2:
pos_strings, neg_strings = training_sets
model_factory = lambda d0, d1: rp.models.train( modname, modorder, radix, d0, d1 )
cv_engine = rp.cv.CV( model_factory, pos_strings, neg_strings, fold=fold, passes=passes )
cv_engine.run()
# Merit is TP + TN
return ( cv_engine.cls1.pos / ( len( pos_strings ) * passes ) + cv_engine.cls2.neg / ( len( neg_strings ) * passes ) ) / 2
elif len( training_sets ) > 2:
model_factory = lambda d: rp.models.prob_train( modname, modorder, radix, d )
cv_engine = rp.cv.MultiCV( model_factory, training_sets, fold=fold, passes=passes )
cv_engine.run()
## print >> sys.stderr, cv_engine.get_summary()
## print >> sys.stderr, cv_engine.get_success_rate()
return cv_engine.get_success_rate()
else:
raise Exception( "No support for '%d' training sets" % len( training_sets ) )
#!/usr/bin/env python
import bx.align.maf
import rp.mapping
import sys
mapping = rp.mapping.alignment_mapping_from_file( file( sys.argv[1] ) )
for maf in align.maf.Reader( sys.stdin ):
ints = rp.mapping.DNA.translate_list( [ c.text for c in maf.components ] )
ints = mapping.translate( ints )
print ' '.join( map( str, ints ) )
