######################################################################
##### READ IN FASTA FILE AND STORE CONTENTS IN *SEQUENCE* ############
######################################################################

file = open("protein.txt")

# Read in first line of file and check for FASTA format
headerLine = file.readline()
if (headerLine[0] == '>'):  # First character is '>'
    print "The file is in FASTA format."
else:
    print "The file is not in FASTA format."

# Read in the rest of the file (i.e., the sequence)
sequence = file.read()

# Remove all carriage returns from the sequence
sequence = sequence.replace("\n", "")



######################################################################
##### PRINT OUT ALL NON-NUCLEOTIDE CHARACTERS IN *SEQUENCE* ##########
######################################################################

# Search for ambiguous characters in nucleotide sequence
indexOfCurrentNucleotide = 0
while (indexOfCurrentNucleotide < len(sequence)):
    if (sequence[indexOfCurrentNucleotide] not in "ACGT"):
        print "I don't recognize the character: ", sequence[indexOfCurrentNucleotide]
    indexOfCurrentNucleotide = indexOfCurrentNucleotide + 1