Last active
July 26, 2018 12:40
-
-
Save daniel-dona/40991c5530ac04e9347d004239572537 to your computer and use it in GitHub Desktop.
Lectura de un fichero en formato FASTA, conversión de bases a codones y de codones a aminoácidos
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
''' | |
Descargado de https://www.ncbi.nlm.nih.gov/nuccore/NM_001143854.1?report=fasta | |
''' | |
file = open('sample_rna.txt', 'r') | |
stringfile = file.read() | |
''' | |
A Alanina | |
B Ácido aspártico o Asparagina | |
C Cisteína | |
D Ácido aspártico | |
E Ácido glutámico | |
F Fenilalanina | |
G Glicina | |
H Histidina | |
I Isoleucina | |
K Lisina | |
L Leucina | |
M Metionina | |
N Asparagina | |
O Pirrolisina | |
P Prolina | |
Q Glutamina | |
R Arginina | |
S Serina | |
T Treonina | |
U Selenocisteína | |
V Valina | |
W Triptófano | |
Y Tirosina | |
''' | |
def procesar_fasta(fichero): | |
secuencias = fichero.split(">")[1:] | |
resultado = [] | |
for secuencia in secuencias: | |
descripcion = secuencia.split("\n")[0] | |
bases = secuencia.split("\n")[1:] | |
bases = ''.join(bases).replace("T", "U") | |
objeto = {'descripcion': descripcion, 'bases': bases} | |
resultado.append(objeto) | |
return resultado | |
def secuencia_a_codones(secuencia): | |
codones = [] | |
for i in range(0, len(secuencia)-(3+len(secuencia)%3), 3): | |
codones.append(secuencia[i:i+3]) | |
return codones | |
def codon_a_aminoacido(codon): | |
rna_codon = {"UUU" : "F", "CUU" : "L", "AUU" : "I", "GUU" : "V", | |
"UUC" : "F", "CUC" : "L", "AUC" : "I", "GUC" : "V", | |
"UUA" : "L", "CUA" : "L", "AUA" : "I", "GUA" : "V", | |
"UUG" : "L", "CUG" : "L", "AUG" : "M", "GUG" : "V", | |
"UCU" : "S", "CCU" : "P", "ACU" : "T", "GCU" : "A", | |
"UCC" : "S", "CCC" : "P", "ACC" : "T", "GCC" : "A", | |
"UCA" : "S", "CCA" : "P", "ACA" : "T", "GCA" : "A", | |
"UCG" : "S", "CCG" : "P", "ACG" : "T", "GCG" : "A", | |
"UAU" : "Y", "CAU" : "H", "AAU" : "N", "GAU" : "D", | |
"UAC" : "Y", "CAC" : "H", "AAC" : "N", "GAC" : "D", | |
"UAA" : "STOP", "CAA" : "Q", "AAA" : "K", "GAA" : "E", | |
"UAG" : "STOP", "CAG" : "Q", "AAG" : "K", "GAG" : "E", | |
"UGU" : "C", "CGU" : "R", "AGU" : "S", "GGU" : "G", | |
"UGC" : "C", "CGC" : "R", "AGC" : "S", "GGC" : "G", | |
"UGA" : "STOP", "CGA" : "R", "AGA" : "R", "GGA" : "G", | |
"UGG" : "W", "CGG" : "R", "AGG" : "R", "GGG" : "G" | |
} | |
return rna_codon[codon] | |
def secuencia_a_aminoacidos(secuencia): | |
codones = secuencia_a_codones(secuencia) | |
aminoacidos = [] | |
for codon in codones: | |
aminoacido = codon_a_aminoacido(codon) | |
aminoacidos.append(aminoacido) | |
return aminoacidos | |
# 1º Pocesamos un fichero en formato FASTA para extraer las secuencias que contiene, nos quedamos con la primera [0] | |
secuencia1 = procesar_fasta(stringfile)[0] | |
# 2º Convertimos la secuencia a aminoacidos | |
print(secuencia_a_aminoacidos(secuencia1['bases'])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment