Supplementary Materials

g:Profiler Gene List

Code

#Motif Filter - Finds Sequence and SRR number of the motif match in large chip4-seqdata

SRR_motif_mismatch = []

SRR_number_only = []

with open("MYC_motif.txt","r") as f:

   adding_array = []

   for line in f:

       line = line.split()

       if 'Sequence:' in line:

           adding_array.append(line[1])

           adding_array.append(line[2])

           SRR_number_only.append(line[2])

       if len(line) > 1 and 'pattern' in line[1]:

           if (len(adding_array)!=0):

               adding_array.append(line[2])

               SRR_motif_mismatch.append(adding_array)

               adding_array = []

fasta_file = "SRR11978411.fasta"

# Assuming SRR_number_only is a list of strings defined earlier

with open(fasta_file, "r") as f:

   for line in f:

       for srr in SRR_number_only:

           # Check if line is a header and contains the specific SRR

           if line.startswith(">") and srr in line:

               # Use f-string to print SRR followed by the sequence line

               # next(f) gets the very next line (the sequence)

               print(f"{srr}: {next(f).strip()}")