def translate(**kwargs):
# Another way to do this is like:
# source = 'en'
# try:
# source = kwargs['source']
# except KeyError:
# pass
source = "en" if "source" not in kwargs else kwargs["source"]
dest = "es" if "dest" not in kwargs else kwargs["dest"]
file = None if "file" not in kwargs else kwargs["file"]
text = None if "text" not in kwargs else kwargs["text"]
if not text and not file:
source = input("Enter the source language: ")
dest = input("Enter the destination language: ")
text = input("Enter a text to translate: ")
elif file:
if isinstance(file, str) and not Path(file).is_file():
raise TranslateException("Please provide a valid path to a file")
if isinstance(file, str) and Path(file).suffix != ".txt":
raise TranslateException("Only .txt files are allowed")
text = read_file(file)
translated_text = ""
try:
translated_text = Translator().translate(text,
dest=dest,
source=source).text
except ValueError as verror:
raise TranslateException(
"The source or destination language is invalid.") from verror
except Exception as ex:
raise ApiException(
"An error ocurred while connecting with the API") from ex
else:
if file:
output_file = ("data/output.txt"
if "output" not in kwargs else kwargs["output"])
write_file(translated_text, output_file)
return translated_text
j = j - 1
#Revertendo a String
alignedseq1 = alignedseq1[::-1]
alignedseq2 = alignedseq2[::-1]
return alignedseq1, alignedseq2
if __name__ == '__main__':
#Definicoes dos parametros
par = Parameters(gapopen=-10, gap=-0.5, matrix='BLOSUM62', stype='protein')
#Sequencias
seq1 = io.read_fasta(io.read_file("../inputs/default1.fasta"))
seq2 = io.read_fasta(io.read_file("../inputs/default2.fasta"))
#Matriz de apontadores
M, Ix, Iy = global_align(seq1, seq2, par)
#Sequencias alinhadas
leftalignedseq1, leftalignedseq2 = traceback_left(M, Ix, Iy, seq1, seq2,
par)
upalignedseq1, upalignedseq2 = traceback_up(M, Ix, Iy, seq1, seq2, par)
result = Alignment(leftalignedseq1, leftalignedseq2, "LEFT")
result.calculate_mat_mis_gaps()
io.write_file("../outputs/locally_global_affine_output.txt", str(result))
result = Alignment(upalignedseq1, upalignedseq2, "UP")
#EBI URLS
EBI_RUN_URL = "http://www.ebi.ac.uk/Tools/services/rest/emboss_water/run/"
EBI_RESULT_URL = "http://www.ebi.ac.uk/Tools/services/rest/emboss_water/result/"
REGEX = "(?<=\d )[AGVLYETDFQHICSMKPRNW\-]{1,50}"
#EXAMPLE OF REQUEST
data = {"email":"*****@*****.**",
"matrix":"EBLOSUM62",
"gapopen":"10.0",
"gapext":"0.5",
"endweight":"false",
"endopen":"10.0",
"endextend":"0.5",
"format":"pair",
"stype":"protein",
"asequence":io.read_file("../inputs/default1.fasta"),
"bsequence":io.read_file("../inputs/default2.fasta")
}
def get_alignment(string):
"""
summary: This fuctions receives a string returned by EBI and parses it
to get just the two sequences aligned.
return: An alignment object
"""
string = re.sub(re.compile("#.*?\n" ) ,"" ,string) ##removing all comments
p = re.compile(REGEX) #getting the REGEX variable
m = p.findall(string) #returns all list of strings that match with that regex
string1 = m[0::2] #gets all the even itens on the list (i.e the first sequence)