#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
La description complète et les caractéristiques d'une protéine particulière peuvent être obtenues via l'ID "uniprot_id" de la "UniProt database", en insérant la référence dans ce lien : 
http://www.uniprot.org/uniprot/uniprot_id

On peut aussi obtenir la séquence peptidique au format FASTA via le lien :
http://www.uniprot.org/uniprot/uniprot_id.fasta
"""

from Bio import SeqIO
from Bio import ExPASy
from Bio import SeqIO

dic = {"UUU":"F", "UUC":"F", "UUA":"L", "UUG":"L",
    "UCU":"S", "UCC":"S", "UCA":"S", "UCG":"S",
    "UAU":"Y", "UAC":"Y", "UAA":"STOP", "UAG":"STOP",
    "UGU":"C", "UGC":"C", "UGA":"STOP", "UGG":"W",
    "CUU":"L", "CUC":"L", "CUA":"L", "CUG":"L",
    "CCU":"P", "CCC":"P", "CCA":"P", "CCG":"P",
    "CAU":"H", "CAC":"H", "CAA":"Q", "CAG":"Q",
    "CGU":"R", "CGC":"R", "CGA":"R", "CGG":"R",
    "AUU":"I", "AUC":"I", "AUA":"I", "AUG":"M",
    "ACU":"T", "ACC":"T", "ACA":"T", "ACG":"T",
    "AAU":"N", "AAC":"N", "AAA":"K", "AAG":"K",
    "AGU":"S", "AGC":"S", "AGA":"R", "AGG":"R",
    "GUU":"V", "GUC":"V", "GUA":"V", "GUG":"V",
    "GCU":"A", "GCC":"A", "GCA":"A", "GCG":"A",
    "GAU":"D", "GAC":"D", "GAA":"E", "GAG":"E",
    "GGU":"G", "GGC":"G", "GGA":"G", "GGG":"G",}

aminoacids = ''.join(sorted(list(set([v for k,v in dic.items() if v != "STOP"]))))
print(aminoacids)

# UniProt Protein Database access IDs
proteins = ['A2Z669', 'B5ZC00', 'P07204_TRBM_HUMAN', 'P20840_SAG1_YEAST'] 

handle = ExPASy.get_sprot_raw(proteins[0])
seq_record = SeqIO.read(handle, "swiss")
handle.close()
print()
print(seq_record)