Source Code for Module Bio.Align.Applications._Prank

  1  # Copyright 2009 by Cymon J. Cox.  All rights reserved. 
  2  # This code is part of the Biopython distribution and governed by its 
  3  # license.  Please see the LICENSE file that should have been included 
  4  # as part of this package. 
  5  """Command line wrapper for the multiple alignment program PRANK. 
  6  """ 
  7   
  8  __docformat__ = "epytext en"  # Don't just use plain text in epydoc API pages! 
  9   
 10  from Bio.Application import _Option, _Switch, AbstractCommandline 
 11   
 12   
 13 -class PrankCommandline(AbstractCommandline): 
 14      """Command line wrapper for the multiple alignment program PRANK. 
 15   
 16      http://www.ebi.ac.uk/goldman-srv/prank/prank/ 
 17   
 18      Example: 
 19   
 20      To align a FASTA file (unaligned.fasta) with the output in aligned 
 21      FASTA format with the output filename starting with "aligned" (you 
 22      can't pick the filename explicitly), no tree output and no XML output, 
 23      use: 
 24   
 25      >>> from Bio.Align.Applications import PrankCommandline 
 26      >>> prank_cline = PrankCommandline(d="unaligned.fasta", 
 27      ...                                o="aligned", #prefix only! 
 28      ...                                f=8, #FASTA output 
 29      ...                                notree=True, noxml=True) 
 30      >>> print prank_cline 
 31      prank -d=unaligned.fasta -o=aligned -f=8 -noxml -notree 
 32   
 33      You would typically run the command line with prank_cline() or via 
 34      the Python subprocess module, as described in the Biopython tutorial. 
 35   
 36      Citations: 
 37   
 38      Loytynoja, A. and Goldman, N. 2005. An algorithm for progressive 
 39      multiple alignment of sequences with insertions. Proceedings of 
 40      the National Academy of Sciences, 102: 10557--10562. 
 41   
 42      Loytynoja, A. and Goldman, N. 2008. Phylogeny-aware gap placement 
 43      prevents errors in sequence alignment and evolutionary analysis. 
 44      Science, 320: 1632. 
 45   
 46      Last checked against version: 081202 
 47      """ 
 48 -    def __init__(self, cmd="prank", **kwargs): 
 49          OUTPUT_FORMAT_VALUES = list(range(1,18)) 
 50          self.parameters = [ 
 51              ################## input/output parameters: ################## 
 52              #-d=sequence_file 
 53              _Option(["-d", "d"], 
 54                      "Input filename", 
 55                      filename=True, 
 56                      is_required=True), 
 57              #-t=tree_file [default: no tree, generate approximate NJ tree] 
 58              _Option(["-t", "t"],"Input guide tree filename", 
 59                      filename=True), 
 60              #-tree="tree_string" [tree in newick format; in double quotes] 
 61              _Option(["-tree", "tree"], 
 62                      "Input guide tree as Newick string"), 
 63              #-m=model_file [default: HKY2/WAG] 
 64              _Option(["-m", "m"], 
 65                      "User-defined alignment model filename. Default: " 
 66                      "HKY2/WAG"), 
 67              #-o=output_file [default: 'output'] 
 68              _Option(["-o", "o"], 
 69                      "Output filenames prefix. Default: 'output'\n " 
 70                      "Will write: output.?.fas (depending on requested " 
 71                      "format), output.?.xml and output.?.dnd", 
 72                      filename=True), 
 73              #-f=output_format [default: 8] 
 74              _Option(["-f", "f"], 
 75                      "Output alignment format. Default: 8 FASTA\n" 
 76                      "Option are:\n" 
 77                      "1. IG/Stanford     8. Pearson/Fasta\n" 
 78                      "2. GenBank/GB      11. Phylip3.2\n" 
 79                      "3. NBRF            12. Phylip\n" 
 80                      "4. EMBL            14. PIR/CODATA\n" 
 81                      "6. DNAStrider      15. MSF\n" 
 82                      "7. Fitch           17. PAUP/NEXUS", 
 83                      checker_function=lambda x: x in OUTPUT_FORMAT_VALUES), 
 84              _Switch(["-noxml", "noxml"], 
 85                      "Do not output XML files"), 
 86              _Switch(["-notree", "notree"], 
 87                      "Do not output dnd tree files"), 
 88              _Switch(["-shortnames", "shortnames"], 
 89                      "Truncate names at first space"), 
 90              _Switch(["-quiet", "quiet"], 
 91                      "Reduce verbosity"), 
 92              ####################### model parameters: ###################### 
 93              #+F [force insertions to be always skipped] 
 94              #-F [equivalent] 
 95              _Switch(["-F", "+F", "F"], 
 96                      "Force insertions to be always skipped: same as +F"), 
 97              #-dots [show insertion gaps as dots] 
 98              _Switch(["-dots", "dots"], 
 99                      "Show insertion gaps as dots"), 
100              #-gaprate=# [gap opening rate; default: dna 0.025 / prot 0.0025] 
101              _Option(["-gaprate", "gaprate"], 
102                      "Gap opening rate. Default: dna 0.025 prot 0.0025", 
103                      checker_function=lambda x: isinstance(x, float)), 
104              #-gapext=# [gap extension probability; default: dna 0.5 / prot 0.5] 
105              _Option(["-gapext", "gapext"], 
106                      "Gap extension probability. Default: dna 0.5 " 
107                      "/ prot 0.5", 
108                      checker_function=lambda x: isinstance(x, float)), 
109              #-dnafreqs=#,#,#,# [ACGT; default: empirical] 
110              _Option(["-dnafreqs", "dnafreqs"], 
111                      "DNA frequencies - 'A,C,G,T'. eg '25,25,25,25' as a quote " 
112                      "surrounded string value. Default: empirical", 
113                      checker_function=lambda x: isinstance(x, bytes)), 
114              #-kappa=# [ts/tv rate ratio; default:2] 
115              _Option(["-kappa", "kappa"], 
116                      "Transition/transversion ratio. Default: 2", 
117                      checker_function=lambda x: isinstance(x, int)), 
118              #-rho=# [pur/pyr rate ratio; default:1] 
119              _Option(["-rho", "rho"], 
120                      "Purine/pyrimidine ratio. Default: 1", 
121                      checker_function=lambda x: isinstance(x, int)), 
122              #-codon [for DNA: use empirical codon model] 
123              #Assuming this is an input file as in -m 
124              _Option(["-codon", "codon"], 
125                      "Codon model filename. Default: empirical codon model"), 
126              #-termgap [penalise terminal gaps normally] 
127              _Switch(["-termgap", "termgap"], 
128                      "Penalise terminal gaps normally"), 
129              ################ other parameters: ################################ 
130              #-nopost [do not compute posterior support; default: compute] 
131              _Switch(["-nopost", "nopost"], 
132                      "Do not compute posterior support. Default: compute"), 
133              #-pwdist=# [expected pairwise distance for computing guidetree; 
134              #default: dna 0.25 / prot 0.5] 
135              _Option(["-pwdist", "pwdist"], 
136                      "Expected pairwise distance for computing guidetree. " 
137                      "Default: dna 0.25 / prot 0.5", 
138                      checker_function=lambda x: isinstance(x, float)), 
139              _Switch(["-once", "once"], 
140                      "Run only once. Default: twice if no guidetree given"), 
141              _Switch(["-twice", "twice"], 
142                      "Always run twice"), 
143              _Switch(["-skipins", "skipins"], 
144                      "Skip insertions in posterior support"), 
145              _Switch(["-uselogs", "uselogs"], 
146                      "Slower but should work for a greater number of sequences"), 
147              _Switch(["-writeanc", "writeanc"], 
148                      "Output ancestral sequences"), 
149              _Switch(["-printnodes", "printnodes"], 
150                      "Output each node; mostly for debugging"), 
151              #-matresize=# [matrix resizing multiplier] 
152              # Doesnt specify type but Float and Int work 
153              _Option(["-matresize", "matresize"], 
154                      "Matrix resizing multiplier", 
155                      checker_function=lambda x: isinstance(x, float) or 
156                                                 isinstance(x, int)), 
157              #-matinitsize=# [matrix initial size multiplier] 
158              # Doesnt specify type but Float and Int work 
159              _Option(["-matinitsize", "matinitsize"], 
160                      "Matrix initial size multiplier", 
161                      checker_function=lambda x: isinstance(x, float) or 
162                                                 isinstance(x, int)), 
163              _Switch(["-longseq", "longseq"], 
164                      "Save space in pairwise alignments"), 
165              _Switch(["-pwgenomic", "pwgenomic"], 
166                      "Do pairwise alignment, no guidetree"), 
167              #-pwgenomicdist=# [distance for pairwise alignment; default: 0.3] 
168              _Option(["-pwgenomicdist", "pwgenomicdist"], 
169                      "Distance for pairwise alignment. Default: 0.3", 
170                      checker_function=lambda x: isinstance(x, float)), 
171              #-scalebranches=# [scale branch lengths; default: dna 1 / prot 2] 
172              _Option(["-scalebranches", "scalebranches"], 
173                      "Scale branch lengths. Default: dna 1 / prot 2", 
174                      checker_function=lambda x: isinstance(x, int)), 
175              #-fixedbranches=# [use fixed branch lengths] 
176              #Assume looking for a float 
177              _Option(["-fixedbranches", "fixedbranches"], 
178                      "Use fixed branch lengths of input value", 
179                      checker_function=lambda x: isinstance(x, float)), 
180              #-maxbranches=# [set maximum branch length] 
181              #Assume looking for a float 
182              _Option(["-maxbranches", "maxbranches"], 
183                      "Use maximum branch lengths of input value", 
184                      checker_function=lambda x: isinstance(x, float)), 
185              #-realbranches [disable branch length truncation] 
186              _Switch(["-realbranches", "realbranches"], 
187                      "Disable branch length truncation"), 
188              _Switch(["-translate", "translate"], 
189                      "Translate to protein"), 
190              _Switch(["-mttranslate", "mttranslate"], 
191                      "Translate to protein using mt table"), 
192              ###################### other: #################### 
193              _Switch(["-convert", "convert"], 
194                      "Convert input alignment to new format. Do " 
195                      "not perform alignment") 
196              ] 
197          AbstractCommandline.__init__(self, cmd, **kwargs) 
198   
199   
200 -def _test(): 
201      """Run the module's doctests (PRIVATE).""" 
202      print "Running modules doctests..." 
203      import doctest 
204      doctest.testmod() 
205      print "Done" 
206   
207  if __name__ == "__main__": 
208      _test() 
209