# Tokens
ADENINE_TKN  = 'A'
CYTOSINE_TKN = 'C'
URACIL_TKN   = 'U'
GUANINE_TKN  = 'G'
THYMINE_TKN  = 'T'
INOSINE_TKN  = 'I'

ANY_NUCLEOTIDE_TKN = 'N'

# Tokens from https://en.wikipedia.org/wiki/FASTA_format
RNA_TOKENS = [ADENINE_TKN, CYTOSINE_TKN, GUANINE_TKN, THYMINE_TKN, INOSINE_TKN, "R", "Y", "K", "M", "S", "W", "B", "D", "H", "V", ANY_NUCLEOTIDE_TKN, "-"]

CLS_TKN  = "<cls>"
PAD_TKN  = "<pad>"
BOS_TKN  = "<bos>"
EOS_TKN  = "<eos>"
UNK_TKN  = "<unk>"
MASK_TKN = "<mask>"

CODON_DICT = {
    'ATA':'I', 'ATC':'I', 'ATT':'I', 'ATG':'M',
    'ACA':'T', 'ACC':'T', 'ACG':'T', 'ACT':'T',
    'AAC':'N', 'AAT':'N', 'AAA':'K', 'AAG':'K',
    'AGC':'S', 'AGT':'S', 'AGA':'R', 'AGG':'R',
    'CTA':'L', 'CTC':'L', 'CTG':'L', 'CTT':'L',
    'CCA':'P', 'CCC':'P', 'CCG':'P', 'CCT':'P',
    'CAC':'H', 'CAT':'H', 'CAA':'Q', 'CAG':'Q',
    'CGA':'R', 'CGC':'R', 'CGG':'R', 'CGT':'R',
    'GTA':'V', 'GTC':'V', 'GTG':'V', 'GTT':'V',
    'GCA':'A', 'GCC':'A', 'GCG':'A', 'GCT':'A',
    'GAC':'D', 'GAT':'D', 'GAA':'E', 'GAG':'E',
    'GGA':'G', 'GGC':'G', 'GGG':'G', 'GGT':'G',
    'TCA':'S', 'TCC':'S', 'TCG':'S', 'TCT':'S',
    'TTC':'F', 'TTT':'F', 'TTA':'L', 'TTG':'L',
    'TAC':'Y', 'TAT':'Y', 'TAA':'*', 'TAG':'*',
    'TGC':'C', 'TGT':'C', 'TGA':'*', 'TGG':'W'
}

CODON_TOKENS = list(CODON_DICT.keys())