def simulate_heterodimer_grammar(motif1, motif2, seq_length, min_spacing,
max_spacing, num_pos, num_neg, GC_fraction):
"""
Simulates two classes of sequences with motif1 and motif2:
- Positive class sequences with motif1 and motif2 positioned
min_spacing and max_spacing
- Negative class sequences with independent motif1 and motif2 positioned
anywhere in the sequence, not as a heterodimer grammar
Parameters
----------
seq_length : int, length of sequence
GC_fraction : float, GC fraction in background sequence
num_pos : int, number of positive class sequences
num_neg : int, number of negatice class sequences
motif1 : str, encode motif name
motif2 : str, encode motif name
min_spacing : int, minimum inter motif spacing
max_spacing : int, maximum inter motif spacing
Returns
-------
sequence_arr : 1darray
Array with sequence strings.
y : 1darray
Array with positive/negative class labels.
embedding_arr: list
List of embedding objects.
"""
import simdna
from simdna import synthetic
loaded_motifs = synthetic.LoadedEncodeMotifs(
simdna.ENCODE_MOTIFS_PATH, pseudocountProb=0.001)
motif1_generator = synthetic.ReverseComplementWrapper(
synthetic.PwmSamplerFromLoadedMotifs(loaded_motifs, motif1))
motif2_generator = synthetic.ReverseComplementWrapper(
synthetic.PwmSamplerFromLoadedMotifs(loaded_motifs, motif2))
separation_generator = synthetic.UniformIntegerGenerator(
min_spacing, max_spacing)
embedder = synthetic.EmbeddableEmbedder(
synthetic.PairEmbeddableGenerator(motif1_generator, motif2_generator,
separation_generator))
embed_in_background = synthetic.EmbedInABackground(
synthetic.ZeroOrderBackgroundGenerator(
seq_length, discreteDistribution=get_distribution(GC_fraction)),
[embedder])
generated_sequences = tuple(
synthetic.GenerateSequenceNTimes(embed_in_background,
num_pos).generateSequences())
grammar_sequence_arr = np.array(
[generated_seq.seq for generated_seq in generated_sequences])
positive_embedding_arr = [
generated_seq.embeddings for generated_seq in generated_sequences
]
nongrammar_sequence_arr, _, negative_embedding_arr = simulate_multi_motif_embedding(
[motif1, motif2], seq_length, 2, 2, num_neg, GC_fraction)
sequence_arr = np.concatenate((grammar_sequence_arr, nongrammar_sequence_arr))
y = np.array([[True]] * num_pos + [[False]] * num_neg)
embedding_arr = positive_embedding_arr + negative_embedding_arr
return sequence_arr, y, embedding_arr
def test_simple_motif_grammar(self):
seq_len = 100
min_sep = 2
max_sep = 6
random.seed(1234)
np.random.seed(1234)
num_sequences = 4000
loaded_motifs = sn.LoadedEncodeMotifs(
simdna.ENCODE_MOTIFS_PATH,
pseudocountProb=0.001)
motif1_generator = sn.PwmSamplerFromLoadedMotifs(
loaded_motifs, "SIX5_known5")
motif2_generator = sn.PwmSamplerFromLoadedMotifs(
loaded_motifs, "ZNF143_known2")
separation_generator = sn.UniformIntegerGenerator(min_sep,max_sep)
embedder = sn.EmbeddableEmbedder(
sn.PairEmbeddableGenerator(
motif1_generator, motif2_generator, separation_generator))
embed_in_background = sn.EmbedInABackground(
sn.ZeroOrderBackgroundGenerator(seq_len),
[embedder])
generated_sequences = sn.GenerateSequenceNTimes(
embed_in_background, num_sequences).generateSequences()
generated_seqs = [seq for seq in generated_sequences]
separations = defaultdict(lambda: 0)
for seq in generated_seqs:
assert len(seq.seq) == seq_len
embedding1 = seq.embeddings[0]
embedding2 = seq.embeddings[1]
embedding3 = seq.embeddings[2]
assert len(embedding1.what) == len(embedding1.what.string)
assert len(embedding2.what) == len(embedding2.what.string)
assert len(embedding3.what) == (len(embedding1.what)+
len(embedding2.what)+
embedding3.what.separation)
#testing that the string of the first motif is placed correctly
assert (seq.seq[
embedding1.startPos:embedding1.startPos+len(embedding1.what)]
== embedding1.what.string)
#testing that the string of the second motif is placed correctly
assert (seq.seq[
embedding2.startPos:embedding2.startPos+len(embedding2.what)]
== embedding2.what.string)
#testing that the motifs are placed correctly
assert ((embedding2.startPos - (embedding1.startPos
+ len(embedding1.what.string)))
== embedding3.what.separation)
#test separation is within the right limits
assert embedding3.what.separation >= min_sep
assert embedding3.what.separation <= max_sep
#log the separation; will later test distribution
separations[embedding3.what.separation] += 1
for possible_sep in range(min_sep, max_sep+1):
np.testing.assert_almost_equal(
separations[possible_sep]/float(num_sequences),
1.0/(max_sep-min_sep+1),2)
def variableSpacingGrammar(options):
pc = 0.001
pathToMotifs = options.pathToMotifs
loadedMotifs = synthetic.LoadedEncodeMotifs(pathToMotifs, pseudocountProb=pc)
motifName1 = options.motifName1
motifName2 = options.motifName2
seqLength = options.seqLength
numSeq = options.numSeq
outputFileName = ("variableSpacingGrammarSimulation_"
+"prefix-"+options.prefix
+"_motif1-"+motifName1+"_motif2-"+motifName2
+"_seqLength"+str(seqLength)+"_numSeq"
+str(numSeq)+".simdata")
kwargs={'loadedMotifs':loadedMotifs}
theClass=synthetic.PwmSamplerFromLoadedMotifs
motif1Generator=theClass(motifName=motifName1,**kwargs)
motif2Generator=theClass(motifName=motifName2,**kwargs)
motif1Embedder=synthetic.SubstringEmbedder(substringGenerator=motif1Generator)
motif2Embedder=synthetic.SubstringEmbedder(substringGenerator=motif2Generator)
embedders = []
separationGenerator=synthetic.MinMaxWrapper(
synthetic.PoissonQuantityGenerator(options.meanSpacing),
theMin=options.minSpacing,
theMax=options.maxSpacing)
embedders.append(synthetic.EmbeddableEmbedder(
embeddableGenerator=synthetic.PairEmbeddableGenerator(
embeddableGenerator1=motif1Generator
,embeddableGenerator2=motif2Generator
,separationGenerator=separationGenerator
)
))
embedInBackground = synthetic.EmbedInABackground(
backgroundGenerator=synthetic.ZeroOrderBackgroundGenerator(seqLength)
, embedders=embedders
)
sequenceSet = synthetic.GenerateSequenceNTimes(embedInBackground, numSeq)
synthetic.printSequences(outputFileName, sequenceSet,
includeFasta=True, includeEmbeddings=True,
prefix=options.prefix)
def motifGrammarSimulation(options):
pc = 0.001
bestHit = options.bestHit
pathToMotifs = options.pathToMotifs
loadedMotifs = synthetic.LoadedEncodeMotifs(pathToMotifs,
pseudocountProb=pc)
motifName1 = options.motifName1
motifName2 = options.motifName2
seqLength = options.seqLength
numSeq = options.numSeq
generationSetting = options.generationSetting
outputFileName = "motifGrammarSimulation_" + generationSetting + (
"_bestHit" if bestHit else "")
if (generationSetting is not generationSettings.singleMotif2):
outputFileName += "_motif1-" + motifName1
if (generationSetting is not generationSettings.singleMotif1):
outputFileName += "_motif2-" + motifName2
outputFileName += "_seqLength" + str(seqLength) + "_numSeq" + str(
numSeq) + ".simdata"
kwargs = {'loadedMotifs': loadedMotifs}
if (bestHit):
theClass = synthetic.BestHitPwmFromLoadedMotifs
else:
theClass = synthetic.PwmSamplerFromLoadedMotifs
motif1Generator = theClass(motifName=motifName1, **kwargs)
motif2Generator = theClass(motifName=motifName2, **kwargs)
motif1Embedder = synthetic.SubstringEmbedder(
substringGenerator=motif1Generator)
motif2Embedder = synthetic.SubstringEmbedder(
substringGenerator=motif2Generator)
embedders = []
if (generationSetting == generationSettings.allBackground
or generationSetting == generationSettings.twoMotifs):
namePrefix = "synthNeg"
else:
namePrefix = "synthPos"
if (generationSetting == generationSettings.allBackground):
pass
elif (generationSetting in [
generationSettings.singleMotif1, generationSettings.twoMotifs,
generationSettings.singleMotif2
]):
if (generationSetting == generationSettings.singleMotif1):
embedders.append(motif1Embedder)
elif (generationSetting == generationSettings.singleMotif2):
embedders.append(motif2Embedder)
elif (generationSetting == generationSettings.twoMotifs):
embedders.append(motif1Embedder)
embedders.append(motif2Embedder)
else:
raise RuntimeError("Unsupported generation setting: " +
generationSetting)
elif (generationSetting in [
generationSettings.twoMotifsFixedSpacing,
generationSettings.twoMotifsVariableSpacing
]):
if (generationSetting == generationSettings.twoMotifsFixedSpacing):
separationGenerator = synthetic.FixedQuantityGenerator(
options.fixedSpacingOrMinSpacing)
elif (generationSetting == generationSettings.twoMotifsVariableSpacing
):
separationGenerator = synthetic.UniformIntegerGenerator(
minVal=options.fixedSpacingOrMinSpacing,
maxVal=options.maxSpacing)
else:
raise RuntimeError("unsupported generationSetting:" +
generationSetting)
embedders.append(
synthetic.EmbeddableEmbedder(
embeddableGenerator=synthetic.PairEmbeddableGenerator(
embeddableGenerator1=motif1Generator,
embeddableGenerator2=motif2Generator,
separationGenerator=separationGenerator)))
else:
raise RuntimeError("unsupported generationSetting:" +
generationSetting)
embedInBackground = synthetic.EmbedInABackground(
backgroundGenerator=synthetic.ZeroOrderBackgroundGenerator(seqLength),
embedders=embedders,
namePrefix=namePrefix)
sequenceSet = synthetic.GenerateSequenceNTimes(embedInBackground, numSeq)
synthetic.printSequences(outputFileName,
sequenceSet,
includeFasta=True,
includeEmbeddings=True)