Source Code for Module Bio.Motif.Applications._XXmotif

  1  # -*- coding: utf-8 -*- 
  2  # Copyright 2012 by Christian Brueffer.  All rights reserved. 
  3  # 
  4  # This code is part of the Biopython distribution and governed by its 
  5  # license.  Please see the LICENSE file that should have been included 
  6  # as part of this package. 
  7  """Command line wrapper for the motif finding program XXmotif.""" 
  8   
  9  import os 
 10  from Bio.Application import AbstractCommandline, _Option, _Switch, _Argument 
 11   
 12   
 13 -class XXmotifCommandline(AbstractCommandline): 
 14      """Command line wrapper for XXmotif. 
 15   
 16      http://xxmotif.genzentrum.lmu.de/ 
 17   
 18      Example: 
 19   
 20      >>> from Bio.Motif.Applications import XXmotifCommandline 
 21      >>> out_dir = "results" 
 22      >>> in_file = "sequences.fasta" 
 23      >>> xxmotif_cline = XXmotifCommandline(outdir=out_dir, seqfile=in_file, revcomp=True) 
 24      >>> print xxmotif_cline 
 25      XXmotif results sequences.fasta --revcomp 
 26   
 27      You would typically run the command line with xxmotif_cline() or via 
 28      the Python subprocess module, as described in the Biopython tutorial. 
 29   
 30      Citations: 
 31   
 32      Luehr S, Hartmann H, and Söding J. The XXmotif web server for eXhaustive, 
 33      weight matriX-based motif discovery in nucleotide sequences, 
 34      Nucleic Acids Res. 40: W104-W109 (2012). 
 35   
 36      Hartmann H, Guthoehrlein EW, Siebert M., Luehr S, and Söding J. P-value 
 37      based regulatory motif discovery using positional weight matrices 
 38      (to be published) 
 39   
 40      Last checked against version: 1.3 
 41      """ 
 42   
 43 -    def __init__(self, cmd="XXmotif", **kwargs): 
 44          # order of parameters is the same as in XXmotif --help 
 45          _valid_alphabet = set("ACGTNX") 
 46   
 47          self.parameters = \ 
 48            [ 
 49            _Argument(["outdir", "OUTDIR"], 
 50                     "output directory for all results", 
 51                     filename = True, 
 52                     is_required = True, 
 53                     # XXmotif currently does not accept spaces in the outdir name 
 54                     checker_function = lambda x: " " not in x), 
 55            _Argument(["seqfile", "SEQFILE"], 
 56                     "file name with sequences from positive set in FASTA format", 
 57                     filename = True, 
 58                     is_required = True, 
 59                     # XXmotif currently only accepts a pure filename 
 60                     checker_function = lambda x: os.path.split(x)[0] == ""), 
 61   
 62            # Options 
 63            _Option(["--negSet", "negSet", "negset", "NEGSET"], 
 64                     "sequence set which has to be used as a reference set", 
 65                     filename = True, 
 66                     equate = False), 
 67            _Switch(["--zoops", "zoops", "ZOOPS"], 
 68                     "use zero-or-one occurrence per sequence model (DEFAULT)"), 
 69            _Switch(["--mops", "mops", "MOPS"], 
 70                     "use multiple occurrence per sequence model"), 
 71            _Switch(["--oops", "oops", "OOPS"], 
 72                     "use one occurrence per sequence model"), 
 73            _Switch(["--revcomp", "revcomp", "REVCOMP"], 
 74                     "search in reverse complement of sequences as well (DEFAULT: NO)"), 
 75            _Option(["--background-model-order", "background-model-order", "BACKGROUND-MODEL-ORDER"], 
 76                     "order of background distribution (DEFAULT: 2, 8(--negset) )", 
 77                     checker_function = lambda x: isinstance(x, int), 
 78                     equate = False), 
 79            _Option(["--pseudo", "pseudo", "PSEUDO"], 
 80                     "percentage of pseudocounts used (DEFAULT: 10)", 
 81                     checker_function = lambda x: isinstance(x, int), 
 82                     equate = False), 
 83            _Option(["-g", "--gaps", "gaps", "GAPS"], 
 84                     "maximum number of gaps used for start seeds [0-3] (DEFAULT: 0)", 
 85                     checker_function = lambda x: x in [0-3], 
 86                     equate = False), 
 87            _Option(["--type", "type", "TYPE"], 
 88                     "defines what kind of start seeds are used (DEFAULT: ALL)" 
 89                     "possible types: ALL, FIVEMERS, PALINDROME, TANDEM, NOPALINDROME, NOTANDEM", 
 90                     checker_function = lambda x: x in ["ALL", "all", 
 91                                                        "FIVEMERS", "fivemers", 
 92                                                        "PALINDROME", "palindrome", 
 93                                                        "TANDEM", "tandem", 
 94                                                        "NOPALINDROME", "nopalindrome", 
 95                                                        "NOTANDEM", "notandem"], 
 96                     equate = False), 
 97            _Option(["--merge-motif-threshold", "merge-motif-threshold", "MERGE-MOTIF-THRESHOLD"], 
 98                     "defines the similarity threshold for merging motifs (DEFAULT: HIGH)" 
 99                     "possible modes: LOW, MEDIUM, HIGH", 
100                     checker_function = lambda x: x in ["LOW", "low", 
101                                                        "MEDIUM", "medium", 
102                                                        "HIGH", "high"], 
103                     equate = False), 
104            _Switch(["--no-pwm-length-optimization", "no-pwm-length-optimization", "NO-PWM-LENGTH-OPTIMIZATION"], 
105                     "do not optimize length during iterations (runtime advantages)"), 
106            _Option(["--max-match-positions", "max-match-positions", "MAX-MATCH-POSITIONS"], 
107                     "max number of positions per motif (DEFAULT: 17, higher values will lead to very long runtimes)", 
108                     checker_function = lambda x: isinstance(x, int), 
109                     equate = False), 
110            _Switch(["--batch", "batch", "BATCH"], 
111                     "suppress progress bars (reduce output size for batch jobs)"), 
112            _Option(["--maxPosSetSize", "maxPosSetSize", "maxpossetsize", "MAXPOSSETSIZE"], 
113                     "maximum number of sequences from the positive set used [DEFAULT: all]", 
114                     checker_function = lambda x: isinstance(x, int), 
115                     equate = False), 
116            # does not make sense in biopython 
117            #_Switch(["--help", "help", "HELP"], 
118            #         "print this help page"), 
119            _Option(["--trackedMotif", "trackedMotif", "trackedmotif", "TRACKEDMOTIF"], 
120                     "inspect extensions and refinement of a given seed (DEFAULT: not used)", 
121                     checker_function = lambda x: any((c in _valid_alphabet) for c in x), 
122                     equate = False), 
123   
124            # Using conservation information 
125            _Option(["--format", "format", "FORMAT"], 
126                     "defines what kind of format the input sequences have (DEFAULT: FASTA)", 
127                     checker_function = lambda x: x in ["FASTA", "fasta", 
128                                                        "MFASTA", "mfasta"], 
129                     equate = False), 
130            _Option(["--maxMultipleSequences", "maxMultipleSequences", "maxmultiplesequences", "MAXMULTIPLESEQUENCES"], 
131                     "maximum number of sequences used in an alignment [DEFAULT: all]", 
132                     checker_function = lambda x: isinstance(x, int), 
133                     equate = False), 
134   
135            # Using localization information 
136            _Switch(["--localization", "localization", "LOCALIZATION"], 
137                     "use localization information to calculate combined P-values" 
138                     "(sequences should have all the same length)"), 
139            _Option(["--downstream", "downstream", "DOWNSTREAM"], 
140                     "number of residues in positive set downstream of anchor point (DEFAULT: 0)", 
141                     checker_function = lambda x: isinstance(x, int), 
142                     equate = False), 
143   
144            # Start with self defined motif 
145            _Option(["-m", "--startMotif", "startMotif", "startmotif", "STARTMOTIF"], 
146                     "Start motif (IUPAC characters)", 
147                     checker_function = lambda x: any((c in _valid_alphabet) for c in x), 
148                     equate = False), 
149            _Option(["-p", "--profileFile", "profileFile", "profilefile", "PROFILEFILE"], 
150                     "profile file", 
151                     filename = True, 
152                     equate = False), 
153            _Option(["--startRegion", "startRegion", "startregion", "STARTREGION"], 
154                     "expected start position for motif occurrences relative to anchor point (--localization)", 
155                     checker_function = lambda x: isinstance(x, int), 
156                     equate = False), 
157            _Option(["--endRegion", "endRegion", "endregion", "ENDREGION"], 
158                     "expected end position for motif occurrences relative to anchor point (--localization)", 
159                     checker_function = lambda x: isinstance(x, int), 
160                     equate = False), 
161            ] 
162          AbstractCommandline.__init__(self, cmd, **kwargs) 
163   
164   
165 -def _test(): 
166      """Run the module's doctests (PRIVATE).""" 
167      print "Running XXmotif doctests..." 
168      import doctest 
169      doctest.testmod() 
170      print "Done" 
171   
172   
173  if __name__ == "__main__": 
174      _test() 
175