10/03

projet_steyeart.py

@@ -4,31 +4,37 @@ Created on Tue Jan 22 15:39:51 2019
 
 @author: Amaury Leroy
 """
+
+######################## PROJET JEAN-MARC STEYAERT ############################
 import numpy as np
 import re
+import os
 from Bio.ExPASy import Prosite
-#help(Prosite)
+
+print("1. Détection de signatures sur un génome complet")
+print("1.1 Identification du motif")
+
 import urllib.request
 urllib.request.urlretrieve("ftp://ftp.expasy.org/databases/prosite/prosite.dat", "prosite.dat")
-
 handle = open("prosite.dat")
 records = Prosite.parse(handle)
 
- #for record in  records:
+
 for record in (r for r in records if "P-loop" in r.description):
-     print(record.accession)
-     print(record.pattern)
+     print("Le code d'accès Prosite du motif est: ", record.accession)
+     print("Son motif structural est: ",record.pattern)
 
 handle.close()
     
-#Questions 3/4/5
+print("1.2 Lecture du format")
 import subprocess
 import Bio.SeqIO
 
 def download_orf_code():
     urllib.request.urlretrieve("http://downloads.yeastgenome.org/sequence/S288C_reference/orf_dna/orf_coding_all.fasta.gz", "orf.fasta.gz")
     subprocess.call(["gunzip", "-k", "orf.fasta.gz"])
-    return "orf.fasta.gz"
+    print("La taille du fichier fasta est: ",os.stat("orf.fasta").st_size," bytes")
+    return "orf.fasta"
 
 def read_fasta(filename):
     file = open(filename, "r")
@@ -37,7 +43,6 @@ def read_fasta(filename):
     file.close()
 
 filename = download_orf_code()
-filename = "orf.fasta"
 read_fasta(filename)
 
 
@@ -176,7 +181,7 @@ for i in ploop_indices:
     if no_site:
         unrestricted.append((rec.id, no_site))
 
-import os
+
 #os.mkdir("cartes_restrictions")
 
 for sequence in sequences: