###################################################################################
#                                                                                 #
#                     Estimate Expected Motif Frequencies                         #
#               -----------------------------------------------                   #
#                                                                                 #
#  This protocol will generate 50 random DNA sequences with specified length      #
#  based on a chosen background model and then perform motif scanning in these    #
#  sequences and calculate the occurrence frequency of each motif.                #
#  These frequencies can be used as "expected frequencies" to calculate p-values  #
#  for overrepresentation with the "count motif occurrences" analysis.            #
#  Note that the same scanning method and settings should be used when scanning   #
#  for motifs in these artificial control sequences that you used when analysing  #
#  the actual target sequences.                                                   #
#                                                                                 #
###################################################################################

length = new Numeric Variable(100000)
prompt for length "Please select a length for the 50 sequences that will be generated"
background = new Background Model(Model:Uniform)
prompt for background "Please select a background model for DNA sequence generation"
Sequence01 = new Sequence(length)
Sequence02 = new Sequence(length)
Sequence03 = new Sequence(length)
Sequence04 = new Sequence(length)
Sequence05 = new Sequence(length)
Sequence06 = new Sequence(length)
Sequence07 = new Sequence(length)
Sequence08 = new Sequence(length)
Sequence09 = new Sequence(length)
Sequence10 = new Sequence(length)
Sequence11 = new Sequence(length)
Sequence12 = new Sequence(length)
Sequence13 = new Sequence(length)
Sequence14 = new Sequence(length)
Sequence15 = new Sequence(length)
Sequence16 = new Sequence(length)
Sequence17 = new Sequence(length)
Sequence18 = new Sequence(length)
Sequence19 = new Sequence(length)
Sequence20 = new Sequence(length)
Sequence21 = new Sequence(length)
Sequence22 = new Sequence(length)
Sequence23 = new Sequence(length)
Sequence24 = new Sequence(length)
Sequence25 = new Sequence(length)
Sequence26 = new Sequence(length)
Sequence27 = new Sequence(length)
Sequence28 = new Sequence(length)
Sequence29 = new Sequence(length)
Sequence30 = new Sequence(length)
Sequence31 = new Sequence(length)
Sequence32 = new Sequence(length)
Sequence33 = new Sequence(length)
Sequence34 = new Sequence(length)
Sequence35 = new Sequence(length)
Sequence36 = new Sequence(length)
Sequence37 = new Sequence(length)
Sequence38 = new Sequence(length)
Sequence39 = new Sequence(length)
Sequence40 = new Sequence(length)
Sequence41 = new Sequence(length)
Sequence42 = new Sequence(length)
Sequence43 = new Sequence(length)
Sequence44 = new Sequence(length)
Sequence45 = new Sequence(length)
Sequence46 = new Sequence(length)
Sequence47 = new Sequence(length)
Sequence48 = new Sequence(length)
Sequence49 = new Sequence(length)
Sequence50 = new Sequence(length)
DNA = new DNA Sequence Dataset(background)

Motifs = new Motif Collection()
prompt for Motifs "Please select motifs to calculate expected frequencies"

cutoff = new Numeric Variable(95)
prompt for cutoff "Please specify a cutoff threshold [0-100] for motif scanning"

# Perform motif scanning. Note that you should use the same scanning method and settings
# when scanning for motifs in these artificial control sequences that you used when scanning
# for motifs in the actual target sequences
BindingSites = motifScanning on DNA with SimpleScanner {Motif Collection=Motifs,Threshold type="Percentage",Threshold=cutoff,Score="Absolute"}

# Derive the frequency of each motif and store the results in a Motif Numeric Map
ExpectedFrequencies = new Motif Numeric Map(Track:BindingSites,property=Frequency)

$display(ExpectedFrequencies)