Biopipeline ouverte – Muhammad Umar Ali

def blast():
for file in os.listdir('fasta'):
filename = os.fsdecode(file)
if filename.endswith(".fasta"):
print(filename)
fasta_file.append(filename)    record = SeqIO.read('fasta/'+fasta_file[0], format="fasta")    result_handle = NCBIWWW.qblast("blastn", "nt", record.seq)    blast_result = open("results.xml", "w")
blast_result.write(result_handle.read())
blast_result.close()
result_handle.close()

def get_pathway(protein_name):
items = scrape('https://www.kegg.jp/kegg-bin/search_pathway_text?map=map&keyword='+protein_name+'&mode=1&viewImage=true','img')
url_ext = []
for i in range(len(items)):
#print(i,items[i])
url_ext.append(items[i].parent['href'])
#print(url_ext[i])images = scrape('https://www.kegg.jp'+url_ext[0],'img')urllib.request.urlretrieve('https://www.kegg.jp'+images[2]['src'], 'pathway_img/'+protein_name+"_pathway.jpg")return 'https://www.kegg.jp'+images[2]['src']

def protein_atlas_parser(xml_file):
root = ET.parse(xml_file).getroot()for i in range(len(root)):
try:
prot_name = root[i][0].text
tissue_expr = root[i][20][3][0].text
desc = root[i][7][1].get('description')
path_expr =  root[i][8][0].text        except:
print("nAn error has been thrown, please handlen")print(i,'Protein Name:', prot_name,'n  Tissue expression summary: ',tissue_expr,'n  Description: ',desc,'n  RNA Cancer Specificity:', path_expr)

>>> from blast import * 
>>> blast()

>>> from xml_parser import blast_parser
>>> blast_parser(results.xml)
'VEGFA'
>>> VEGFA = 'VEGFA'

>>> from fetch_uniprot_metadata import *
>>> gene_entry, genes = protein_entry(VEGFA)
>>> protein_function = protein_function(gene_entry) # saves function as string
>>> amino_acid_seq = protein_AASeq(gene_entry) # amino acid sequence

>>> from get_kegg_pathway import get_pathway
>>> get_pathway(VEGFA)

>>> from protein_atlas import get_atlas_xml
>>> get_atlas_xml(VEGFA)

>>> from xml_parser import protein_atlas_parser
>>> protein_atlas_parser('xml/protein_atlas/VEGFA_protein_atlas_data.xml')0 Protein Name: VEGFA
Tissue expression summary:  Most cancers showed strong cytoplasmic immunoreactivity. Lymphomas were in general moderately stained.
Description:  Antibody staining mainly consistent with RNA expression data. At least one protein variant secreted, tissue location of RNA and protein might differ and correlation is complex.  
RNA Cancer Specificity: Low cancer specificity
...