clustalw.py

ncbi源码

#!/usr/bin/python

# $Id: clustalw.py,v 1000.0 2003/10/31 21:37:53 gouriano Exp $
#
# Author:  Josh Cherry
#
# align sequences using clustalw (from gbench)

import sys
import cgi
import os
import tempfile

# take a list of Seq-locs encoded as CGI strings,
# and write out a multi-sequence fasta file
def FastaFromCGI(locs, fname):
   s = ""
   for qs in locs:
      loc = cgi.parse_qs(qs)
      s += ">" + loc['short_title'][0] + "  " + loc['title'][0] + "\n"
      seq = loc['seq'][0]
      for pos in range(0, len(seq), 60):
         s += seq[pos:pos+60]
         s += '\n'
   f = open(fname, "w")
   f.write(s)
   f.close()

input = sys.stdin.read()
args = cgi.parse_qs(input)
action = args['action'][0]

# if a get info call ...
if action == 'info':
   print '''
   PluginInfo ::= {
      ver-major 0,
      ver-minor 0,
      ver-revision 0,
      ver-build-date "",
      class-name "clustalw.py",
      menu-item "Alignments/Multiple alignment using clustalw",
      tooltip "Multiple alignment using clustalw",
      commands algo {
        {
          command 3,
          args {
            {
              name "locs",
              desc "Locations to evaluate",
              data array {
                object {
                  docaddr "(nil)",
                  objaddr "(nil)",
                  subtype "Seq-loc"
                }
              }
            },
            {
              name "output",
              desc "Output format",
              default TRUE,
              data single string "clustal",
              constraint {
                set {
                  "clustal",
                  "phylip",
                  "gcg",
                  "gde",
                  "pir",
                  "nexus"
                }
              }
            },
            {
              name "alignment",
              desc "Alignment",
              default TRUE,
              data single string "full",
              constraint {
                set {
                  "full",
                  "fast"
                }
              }
            },
            {
              name "outorder",
              desc "Output order",
              default TRUE,
              data single string "aligned",
              constraint {
                set {
                  "aligned",
                  "input"
                }
              }
            },
            {
              name "ktuple",
              desc "ktuple (word size)",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "1",
                  "2",
                  "3",
                  "4",
                  "5"
                }
              }
            },
            {
              name "window",
              desc "Window length",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "10",
                  "9",
                  "8",
                  "7",
                  "6",
                  "5",
                  "4",
                  "3",
                  "2",
                  "1",
                  "0"
                }
              }
            },
            {
              name "topdiags",
              desc "Top diagonals",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "10",
                  "9",
                  "8",
                  "7",
                  "6",
                  "5",
                  "4",
                  "3",
                  "2",
                  "1",
                  "0"
                }
              }
            },
            {
              name "matrix",
              desc "Matrix (protein)",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "blosum",
                  "pam",
                  "gonnet",
                  "id"
                }
              }
            },
            {
              name "gapopen",
              desc "Gap open penalty",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "100",
                  "50",
                  "25",
                  "10",
                  "5",
                  "2",
                  "1"
                }
              }
            },
            {
              name "gapext",
              desc "Gap extension penalty",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "0.05",
                  "0.5",
                  "1",
                  "2.5",
                  "5",
                  "7.5",
                  "10"
                }
              }
            },
            {
              name "gapdist",
              desc "Gap separation pen. range",
              default TRUE,
              data single string "def",
              constraint {
                set {
                  "def",
                  "10",
                  "9",
                  "8",
                  "7",
                  "6",
                  "5",
                  "4",
                  "3",
                  "2",
                  "1"
                }
              }
            }
          }
        }
      }
    }
    '''
   sys.exit(0)

# otherwise, run

# write a temporary fasta file containing the sequences
infile = tempfile.mktemp('.fasta')
FastaFromCGI(args['locs'], infile)

# get the arguments
switches = []
params = {}

output = args['output'][0]
if (output != 'clustal'):
   params['output'] = output
   
if (args['alignment'][0] == 'fast'):
   switches.append('quicktree')

params['outorder'] = args['outorder'][0]

# things that could be 'def', otherwise need to be passed
# on command line
for name in ['ktuple', 'window', 'topdiags',
             'matrix', 'gapopen', 'gapext', 'gapdist']:
   value = args[name][0]
   if (value != 'def'):
      params[name] = value


params['infile'] = infile
outfile = tempfile.mktemp()  # temp file for output
params['outfile'] = outfile

# build the command line
arglist = ''
for switch in switches:
   arglist += ' -' + switch
for param in params.keys():
   arglist += ' -' + param + '=' + params[param]
cline = 'clustalw' + arglist
print cline + '\n'
sys.stdout.flush()

# run clustalw, which must be on path
os.system(cline)
os.system('cat %s' % outfile)

# then delete the temporary files
os.system('rm %s %s' % (infile, outfile))

# ===========================================================================
# $Log: clustalw.py,v $
# Revision 1000.0  2003/10/31 21:37:53  gouriano
# PRODUCTION: IMPORTED [ORIGINAL] Dev-tree R1.4
#
# Revision 1.4  2003/10/29 20:12:05  jcherry
# Reflect new spec for plugin args
#
# Revision 1.3  2003/10/07 13:47:02  dicuccio
# Renamed CPluginURL* to CPluginValue*
#
# Revision 1.2  2003/07/30 19:38:20  jcherry
# Added a bunch of parameters for the alignment
#
# Revision 1.1  2003/07/28 22:34:39  jcherry
# Initial version
#
# ===========================================================================
# 
#  ===========================================================================
#  PRODUCTION $Log: clustalw.py,v $
#  PRODUCTION Revision 1000.0  2003/10/31 21:37:53  gouriano
#  PRODUCTION PRODUCTION: IMPORTED [ORIGINAL] Dev-tree R1.4
#  PRODUCTION
#  ===========================================================================
#