annotation/new/generatereport.py

   1 import numpy as np
   2 import scipy as scipy
   3 import pandas as pd
   4 import io
   5
   6 pd.set_option("display.max_colwidth", 10000)
   7
   8 filename = "reportdata.txt"
   9 samplename = "hu34D5B9_var-GS000015891-ASM"
  10 headfile = "head.html"
  11 tailfile = "tail.html"
  12
  13 headerlist = ["Variant ID", "Chromosome", "Position", "Ref","Alt","Allele ID", "Clinical Significance","Disease Name","Frequency GO-ESP", "Frequency EXAC", "Frequency 1000 Genomes Project","GT"]
  14 reportdata = pd.read_csv(filename,header=0,names=headerlist,sep='\t')
  15 reportdata['Zygosity']="."
  16
  17 idxHOM1 = reportdata.GT=='1|1'
  18 idxHOM2 = reportdata.GT=='1/1'
  19 idxHET1 = reportdata.GT=='1|0'
  20 idxHET2 = reportdata.GT=='1/0'
  21 idxHET3 = reportdata.GT=='0|1'
  22 idxHET4 = reportdata.GT=='0/1'
  23 idxHOM = idxHOM1 | idxHOM2
  24 idxHET = idxHET1 | idxHET2 | idxHET3 | idxHET4
  25 reportdata.Zygosity[idxHOM]='HOM'
  26 reportdata.Zygosity[idxHET]='HET'
  27
  28 #reportdata['URL'] =reportdata['Variant ID'].apply(lambda x: '<a href="www.ncbi.nlm.nih.gov/clinvar/variation/'+str(x)+'> Link </a>')
  29 reportdata['URL'] = '<a href="http://www.mywebsite.com/about.html">About</a>'
  30 reportdata.to_json('test.json',orient='records')
  31 str_io = io.StringIO()
  32
  33 reportdatasub = reportdata[["Variant ID", "Allele ID", "Clinical Significance","Disease Name", "Frequency EXAC", "Frequency 1000 Genomes Project","Zygosity","URL"]]
  34
  35 reportdatasub.to_html(buf=str_io, classes='table table-bordered',index_names=False,index=False)
  36 html_str = str_io.getvalue()
  37 html_str_encoded = unicode(html_str).encode('utf8')
  38
  39 html_str_encoded = html_str_encoded.replace('&lt;','<')
  40 html_str_encoded = html_str_encoded.replace('&gt;','>')
  41 html_str_encoded = html_str_encoded.replace('|','<br/>')
  42
  43 html_file = open(headfile, 'r')
  44 source_code_head = html_file.read()
  45 html_file.close()
  46
  47 html_file = open(tailfile, 'r')
  48 source_code_tail = html_file.read()
  49 html_file.close()
  50
  51
  52 total_html = source_code_head + html_str_encoded + source_code_tail
  53
  54 f = open(samplename+'.html','wb')
  55
  56 f.write(total_html)
  57 f.close()