pastebin - collaborative debugging

pastebin is a collaborative debugging tool allowing you to share and modify code snippets while chatting on IRC, IM or a message board.

This site is developed to XHTML and CSS2 W3C standards. If you see this paragraph, your browser does not support those standards and you need to upgrade. Visit WaSP for a variety of options.

www private pastebin - collaborative debugging tool What's a private pastebin?


Posted by Bloguero_Connor on Wed 2 Apr 12:32 (modification of post by Bloguero_Connor view diff)
download | new post

  1. # Code by Sebastian Bassi
  2. # License: GPL 3.0 (http://www.gnu.org/licenses/gpl-3.0-standalone.html)
  3.  
  4. from Bio.Blast import NCBIXML
  5.  
  6. f_in='/mnt/hda2/bio/blast-2.2.18/bin/m3x-218.xml'
  7.  
  8. fr=NCBIXML.parse(open(f_in)).next()
  9.  
  10. print '''<HTML>
  11. <TITLE>BLAST Search Results</TITLE>
  12. <BODY BGCOLOR="#FFFFFF" LINK="#0000FF" VLINK="#660099" ALINK="#660099">
  13. <PRE>'''
  14. print '<b>%s</b>' %(fr.application+' '+fr.version+' '+fr.date)
  15. print '\n<b><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Retrieve&list_uids=9254694&dopt=Citation">Reference</a>:</b>'+\
  16.               fr.reference.replace('~',' ')
  17. for rec in NCBIXML.parse(open(f_in)):
  18.     print '<b>Query=</b> %s' %(rec.query)
  19.     print '         (%s letters)' %(rec.query_letters)
  20.     print '<b>Database:</b> %s' %(rec.database)
  21.     if fr.num_letters_in_database!=[]:
  22.         #This test is for a bug in Biopython 1.45
  23.         print '         %s sequences; %s total letters' \
  24.         %(fr.num_sequences_in_database,
  25.           fr.num_letters_in_database)
  26.     #except AttributeError:
  27.     else:
  28.         # For Biopython > 1.45
  29.         print '         %s sequences; %s total letters' \
  30.         %(fr.num_sequences_in_database,
  31.           fr._num_letters_in_database)
  32.        
  33.     print '''Searching..................................................done
  35. <PRE>
  38.                                                                  Score    E
  39. Sequences producing significant alignments:                      (bits) Value
  41. '''
  42.     for d in fr.descriptions:
  43.         k=d.accession
  44.         desc=d.title
  45.         bs=d.score
  46.         sc=d.e
  47.         if 'gi|' in k:
  48.             m=k.index('gi|')+3
  49.             gi=k[m:k[m:].index('|')+3]
  50.             print '<a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?\
  51. cmd=Retrieve&db=Nucleotide&list_uids=%s&dopt=GenBank" >\
  52. %s</a> %s <a href = #%s> %s</a>   %s' \
  53. %(gi,k.replace('gi|'+gi+'|',''),desc[:36]+'...',gi,bs,sc)
  54.         else:
  55.             print '%s <a href = #%s> %s</a>   %s' \
  56.             %(desc[:40]+'...',k,bs,sc)
  57.     print '</PRE>\n'
  58.     for alig in fr.alignments:
  59.         print '<PRE>\n'
  60.         k=alig.hit_id
  61.         desc=alig.hit_def
  62.         if 'gi|' in k:
  63.             m=k.index('gi|')+3
  64.             gi=k[m:k[m:].index('|')+3]
  65.             print '><a name=%s></a><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?\
  66. cmd=Retrieve&db=Nucleotide&list_uids=%s&dopt=GenBank" >\
  67. %s</a> %s ' \
  68. %(gi,gi,k.replace('gi|'+gi+'|',''),desc)
  69.         else:
  70.             print '><a name=%s></a>%s' %(k[k.index('|')+1:],desc)
  71.         print ' Length = %s\n' %(alig.length)
  72.         # Walk over all the hsps
  73.         for hsp in alig.hsps:
  74.             bs=hsp.bits
  75.             hsc=hsp.score
  76.             sc=hsp.expect
  77.             h_id=hsp.identities
  78.             h_pos=hsp.positives
  79.             q_frame=hsp.frame[0]
  80.             h_frame=hsp.frame[1]
  81.             q_from=str(hsp.query_start)
  82.             q_to=str(hsp.query_end)
  83.             h_from=str(hsp.sbjct_start)
  84.             h_to=str(hsp.sbjct_end)
  85.             qseq=hsp.query
  86.             hseq=hsp.sbjct
  87.             medio=hsp.match
  88.             if q_frame==1:
  89.                 qf='Plus'
  90.             else:
  91.                 qf='Minus'
  92.             if h_frame==1:
  93.                 hf='Plus'
  94.             else:
  95.                 hf='Minus'
  96.             print 'Score = %s bits (%s), Expect = %s' %(bs,hsc,sc)
  97.             print 'Identities = %s/%s (%.0f%%)' %(h_id,
  98.                                 h_pos,float(int(h_id))/int(h_pos)*100)
  99.             print 'Strand = %s/%s\n\n' %(qf,hf)
  100.             if h_frame=='1':
  101.                 mx=max(len(q_from),len(h_from))
  102.                 print 'Query: %s %s %s' %(q_from.ljust(mx),qseq,q_to)
  103.                 print '       '+' '*mx+' '+medio
  104.                 print 'Sbjct: %s %s %s\n' %(h_from.ljust(mx),hseq,h_to)
  105.             else:
  106.                 mx=max(len(q_from),len(h_to))
  107.                 print 'Query: %s %s %s' %(q_from.ljust(mx),qseq,q_to)
  108.                 print '       '+' '*mx+' '+medio
  109.                 print 'Sbjct: %s %s %s\n' %(h_to.ljust(mx),hseq,h_from)
  110.             print '</PRE>'
  111. if fr.num_letters_in_database!=[]:
  112.     print '''<PRE>
  113.   Database: %s
  114.   Number of letters in database: %s
  115.   Number of sequences in database:  %s
  117. Lambda     K      H
  118.     %.2f    %.3f     %.2f
  120. Matrix: %s matrix:%s %s
  121. Gap Penalties: Existence: %s, Extension: %s
  122. Number of Sequences: %s
  123. Length of database: %s
  124. </PRE>
  125. </BODY>
  126. </HTML>''' %(rec.database,fr.num_letters_in_database,
  127.              fr.num_sequences_in_database,
  128.              fr.ka_params[0],fr.ka_params[1],
  129.              fr.ka_params[2],fr.application,
  130.              fr.sc_match,fr.sc_mismatch,
  131.              fr.gap_penalties[0],fr.gap_penalties[1],
  132.              fr.num_sequences_in_database,
  133.              fr._num_letters_in_database)
  134. else:
  135.     # Hack for Biopython 1.45 or earlier.
  136.     print '''<PRE>
  137.   Database: %s
  138.   Number of letters in database: %s
  139.   Number of sequences in database:  %s
  141. Lambda     K      H
  142.     %.2f    %.3f     %.2f
  144. Matrix: %s matrix:%s %s
  145. Gap Penalties: Existence: %s, Extension: %s
  146. Number of Sequences: %s
  147. Length of database: %s
  148. </PRE>
  149. </BODY>
  150. </HTML>''' %(rec.database,fr._num_letters_in_database,
  151.              fr.num_sequences_in_database,
  152.              fr.ka_params[0],fr.ka_params[1],
  153.              fr.ka_params[2],fr.application,
  154.              fr.sc_match,fr.sc_mismatch,
  155.              fr.gap_penalties[0],fr.gap_penalties[1],
  156.              fr.num_sequences_in_database,
  157.              fr._num_letters_in_database)

Submit a correction or amendment below (click here to make a fresh posting)
After submitting an amendment, you'll be able to view the differences between the old and new posts easily.

Syntax highlighting:

To highlight particular lines, prefix each line with @@


Remember me