|
0
|
1 <tool id="patser-v3e" name="patser" description="finds putative transcription factor binding sites" version="0.1.2">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="package" version="v3e">patser</requirement>
|
|
|
4 </requirements>
|
|
|
5 <stdio>
|
|
|
6 <exit_code range="1:" />
|
|
|
7 </stdio>
|
|
|
8
|
|
|
9 <command><![CDATA[
|
|
|
10 ## We need to transform the fasta input file into the awkward format in that patser can work on
|
|
|
11 ## The fasta header must be followed by the nucleotide sequence encapsulated by backslashes.
|
|
|
12 ## We simply add backslashes before and after each fasta header and skip the first line,
|
|
|
13 ## and we add a final backslash at the end of the file.
|
|
|
14 awk '/>/{print "\\"}1' "$input_fasta"|awk '/>/{print;print "\\";next}1'|tail -n +2 >> special.fa;
|
|
|
15 echo "\\" >> special.fa;
|
|
|
16 patser-v3e -A a:t "$at" c:g "$gc" -m "$input_matrix" -b "$b" $c -d1 -ls "$ls" -f special.fa "$p" > "$output1"
|
|
|
17 ]]></command>
|
|
|
18 <inputs>
|
|
|
19 <param type="data" name="input_matrix" format="txt" help="Provide alignment matrix file"/>
|
|
|
20 <param type="data" name="input_fasta" format="fasta" help="Fasta file with sequence"/>
|
|
|
21 <param name="v" type="boolean" label="the matrix is a vertical matrix (default: horizontal matrix)"
|
|
|
22 truevalue="-v" falsevalue=""
|
|
|
23 help="commandline option -v" />
|
|
|
24 <param name="b" type="integer" label="Correction added to the elements of the alignment matrix"
|
|
|
25 value="1"
|
|
|
26 help="commandline option -b" />
|
|
|
27 <param name="gc" type="float" label="Enter the GC frequency"
|
|
|
28 value="0.25" min="0" max="1"
|
|
|
29 help="commandline option -A gc:(value)" />
|
|
|
30 <param name="at" type="float" label="Enter the AT frequency"
|
|
|
31 value="0.25" min="0" max="1"
|
|
|
32 help="commandline option -A at:" />
|
|
|
33 <param name="c" type="boolean" label="Also score the complementary sequences"
|
|
|
34 truevalue="-c" falsevalue="" checked="true"
|
|
|
35 help="commandline option -c: Also score the complementary sequences. The complements are determined by the program and are not explicitly stated in the sequence fasta" />
|
|
|
36 <param name="p" type="boolean" label="print the weight matrix derived from the alignment matrix"
|
|
|
37 truevalue="-p" falsevalue="" checked="true"
|
|
|
38 help="commandline option -p" />
|
|
|
39 <param name="ls" type="float" label="Lower-threshold score, inclusive"
|
|
|
40 value="7"
|
|
|
41 help="commandline option -ls" />
|
|
|
42 </inputs>
|
|
|
43 <outputs>
|
|
|
44 <data name="output1" format="txt" from_work_dir="output.txt" />
|
|
|
45 </outputs>
|
|
|
46 <tests>
|
|
|
47 <test>
|
|
|
48 <param name="input_matrix" value="PWM_training_EcR-USP.txt"/>
|
|
|
49 <param name="input_fasta" value="EcR_USP_224.fa"/>
|
|
|
50 <output name="output1" file="output.txt" lines_diff="6"/>
|
|
|
51 </test>
|
|
|
52 </tests>
|
|
|
53 <help><![CDATA[
|
|
|
54
|
|
|
55 This wrapper has been written by Marius van den Beek (m.vandenbeek at gmail.com).
|
|
|
56 Patser is available from http://stormo.wustl.edu/resources.html .
|
|
|
57
|
|
|
58 -------------------------------------------------------------------------------
|
|
|
59
|
|
|
60 The following options can be determined on the command line:
|
|
|
61
|
|
|
62 ::
|
|
|
63
|
|
|
64 0) -h: print these directions.
|
|
|
65
|
|
|
66 1) Matrix options.
|
|
|
67 -m filename: (default name is "matrix") file containing the matrix.
|
|
|
68 -w: the matrix is a weight matrix (default: alignment matrix)
|
|
|
69 -b number: a non-negative number indicating the total number of
|
|
|
70 pseudo-counts added to each alignment position (default: 1).
|
|
|
71 Before converting an alignment matrix to a weight matrix, the
|
|
|
72 total pseudo-counts multiplied by the a priori probability
|
|
|
73 (see section 3 below) of the corresponding letter is added
|
|
|
74 to each matrix element.
|
|
|
75 -v: the matrix is a vertical matrix (default: horizontal matrix).
|
|
|
76 -p: print the weight matrix derived from the alignment matrix.
|
|
|
77
|
|
|
78 2) -f filename: this file (default: read from the standard input) contains
|
|
|
79 the names of the sequences. The corresponding sequence may follow
|
|
|
80 its name if the sequence is enclosed between backslashes (\).
|
|
|
81 Otherwise, the sequence is assumed to be in a separate file having
|
|
|
82 the indicated name.
|
|
|
83
|
|
|
84 In the sequences, whitespace, slashes (/), periods, dashes (unless
|
|
|
85 part of an integer when the "-i" option is used), and comments
|
|
|
86 beginning with ';', '%', or '#' are ignored. When using letter
|
|
|
87 characters (i.e., with the "-a" or "-A" alphabet option), integers
|
|
|
88 are also ignored so that the sequence file can contain positional
|
|
|
89 information. When using integer characters (i.e., with the "-i"
|
|
|
90 alphabet option) the integers must be separated by whitespace.
|
|
|
91
|
|
|
92 A "-c" preceding the name of a sequence file indicates that the
|
|
|
93 corresponding sequence is circular.
|
|
|
94
|
|
|
95 3) Alphabet options---the three options in this section are mutually
|
|
|
96 exclusive (default: "-a alphabet"). The a priori probabilities mentioned
|
|
|
97 below are used when converting an alignment matrix to a weight matrix.
|
|
|
98 -a filename: file containing the alphabet and normalization information.
|
|
|
99
|
|
|
100 Each line contains a letter (a symbol in the alphabet) followed by an
|
|
|
101 optional normalization number (default: 1.0). The normalization is
|
|
|
102 based on the relative a priori probabilities of the letters. For
|
|
|
103 nucleic acids, this might be be the genomic frequency of the bases
|
|
|
104 or the frequencies observed in the data used to generate the alignment.
|
|
|
105 In nucleic acid alphabets, a letter and its complement appear on the
|
|
|
106 same line, separated by a colon (a letter can be its own complement,
|
|
|
107 e.g. when using a dimer alphabet). Complementary letters may use the
|
|
|
108 same normalization number. Only the standard 26 letters are
|
|
|
109 permissible; however, when the "-CS" option is used, the alphabet is
|
|
|
110 case sensitive so that a total of 52 different characters are possible.
|
|
|
111
|
|
|
112 POSSIBLE LINE FORMATS WITHOUT COMPLEMENTARY LETTERS:
|
|
|
113 letter
|
|
|
114 letter normalization
|
|
|
115
|
|
|
116 POSSIBLE LINE FORMATS WITH COMPLEMENTARY LETTERS:
|
|
|
117 letter:complement
|
|
|
118 letter:complement normalization
|
|
|
119 letter:complement normalization:complement's_normalization
|
|
|
120
|
|
|
121 -i filename: same as the "-a" option, except that the symbols of
|
|
|
122 the alphabet are represented by integers rather than by letters.
|
|
|
123 Any integer permitted by the machine is a permissible symbol.
|
|
|
124
|
|
|
125 -A alphabet_and_normalization_information: same as "-a" option, except
|
|
|
126 information appears on the command line (e.g., -A a:t 3 c:g 2).
|
|
|
127
|
|
|
128 4) Alphabet modifiers indicating whether ascii alphabets are case
|
|
|
129 sensitive---the two options in this section are mutually exclusive
|
|
|
130 with each other and with the "-i" option (default: ascii alphabets are
|
|
|
131 case insensitive).
|
|
|
132 -CS: ascii alphabets are case sensitive.
|
|
|
133 -CM: ascii alphabets are case insensitive, but mark the location
|
|
|
134 of lowercase letters by printing a line containing their locations.
|
|
|
135 This option is useful when lowercase letters indicate a functional
|
|
|
136 landmark such as a transcriptional start in a DNA sequence.
|
|
|
137
|
|
|
138 5) Options for adjusting or restricting which information
|
|
|
139 and scores are printed.
|
|
|
140 The "-ls", "-li", and "-lp" options are mutually exclusive.
|
|
|
141 -c: also score the complementary sequences. The complements are
|
|
|
142 determined by the program and are not explicitly stated in the
|
|
|
143 sequence files.
|
|
|
144 -ls number: lower threshold for printing scores, inclusive
|
|
|
145 (formerly the -l option).
|
|
|
146 -li: assume that the maximum ln(p-value) for printing scores equals
|
|
|
147 the negative of the sample-size adjusted information content;
|
|
|
148 indirectly determines the lower threshold for printing scores.
|
|
|
149 -lp number: the maximum ln(p-value) for printing scores; indirectly
|
|
|
150 determines the lower threshold for printing scores.
|
|
|
151 -u number: upper threshold for printing scores, exclusive.
|
|
|
152
|
|
|
153 -t: just print the top score for each sequence.
|
|
|
154 -t number: print the indicated number of top scores for each sequence.
|
|
|
155 -ds: if the "-t number" option is used, print the top scores for each
|
|
|
156 sequence in the order of decreasing score (default: order the
|
|
|
157 scores according to their position within the sequence).
|
|
|
158 -e number: the small difference for considering 2 scores equal
|
|
|
159 (default: 0.000001)
|
|
|
160
|
|
|
161 -s: print the sequence corresponding to each score that is printed.
|
|
|
162
|
|
|
163 6) Options indicating how unrecognized symbols are treated (default: -d1).
|
|
|
164 Symbols are letters when option "-a" or "-A" is used;
|
|
|
165 symbols are integers when option "-i" is used.
|
|
|
166 The following three options are mutually exclusive.
|
|
|
167 -d0: treat unrecognized symbols as errors and exit the program.
|
|
|
168 -d1: treat unrecognized symbols as discontinuities, but print a warning.
|
|
|
169 Treating a symbol as a discontinuity means that any L-mer
|
|
|
170 containing the unrecognized symbol will be ignored.
|
|
|
171 -d2: treat unrecognized symbols as discontinuities, and print NO warning.
|
|
|
172
|
|
|
173 7) Options for adjusting the estimation of p-value.
|
|
|
174 If the -R option is set to zero, the p-value is not estimated.
|
|
|
175 -R number: the range for approximating a column of the weight matrix with
|
|
|
176 integers (default: 10000). This number is the difference
|
|
|
177 between the largest and smallest integers used to estimate
|
|
|
178 the scores. Higher values increase precision, but will take
|
|
|
179 longer to calculate the table of p-values.
|
|
|
180 -M number: the minimum score for approximating p-values (default: 0).
|
|
|
181 Higher values will increase precision,
|
|
|
182 but may miss interesting scores.
|
|
|
183
|
|
|
184
|
|
|
185 ::
|
|
|
186
|
|
|
187 ----------------------------------------------------------------------
|
|
|
188
|
|
|
189 Copyright 1990, 1994, 1995, 1996, 2000, 2001, 2002 Gerald Z. Hertz
|
|
|
190 May be copied for noncommercial purposes.
|
|
|
191
|
|
|
192 Author:
|
|
|
193 Gerald Z. Hertz
|
|
|
194 gzhertz AT alum.mit.edu
|
|
|
195
|
|
|
196 PATSER (version 3e)
|
|
|
197
|
|
|
198 This program scores the L-mers (subsequences of length L) of the
|
|
|
199 indicated sequences against the indicated alignment or weight matrix.
|
|
|
200 The elements of an alignment matrix are simply the number of times
|
|
|
201 that the indicated letter is observed at the indicated position of a
|
|
|
202 sequence alignment. Such elements must be processed before the matrix
|
|
|
203 can be used to score an L-mer (e.g., Hertz and Stormo, 1999,
|
|
|
204 Bioinformatics, 15:563-577). A weight matrix is a matrix whose
|
|
|
205 elements are in a form considered appropriate for scoring an L-mer.
|
|
|
206
|
|
|
207 Each element of an alignment matrix is converted to an element of a
|
|
|
208 weight matrix by first adding pseudo-counts in proportion to the a
|
|
|
209 priori probability of the corresponding letter (see option "-b" in
|
|
|
210 section 1 below) and dividing by the total number of sequences plus
|
|
|
211 the total number of pseudo-counts. The resulting frequency is
|
|
|
212 normalized by the a priori probability for the corresponding letter.
|
|
|
213 The final quotient is converted to an element of a weight matrix by
|
|
|
214 taking its natural logarithm. The use of pseudo-counts here differs
|
|
|
215 from previous versions of this program by being proportional to the a
|
|
|
216 priori probability.
|
|
|
217
|
|
|
218 Version 3 of this program differs from previous versions by also
|
|
|
219 numerically estimating the p-value of the scores. The p-value
|
|
|
220 calculated here is the probability of observing a particular score or
|
|
|
221 higher at a particular sequence position and does NOT account for the
|
|
|
222 total amount of sequence being scored. P-values are estimated by the
|
|
|
223 method described in Staden, 1989, CABIOS, p. 89--96. The relative
|
|
|
224 value for each element of the weight matrix is approximated by
|
|
|
225 integers in a range determined by the "-R" and "-M" options (section 6
|
|
|
226 below). The p-value is calculated for each possible integer score and
|
|
|
227 the values are stored. The actual scores for the sequences are
|
|
|
228 determined from the true weight matrix. The true scores are converted
|
|
|
229 to their corresponding integer values and their p-values are looked up.
|
|
|
230
|
|
|
231 Matrices can be either horizontal or vertical. In a horizontal
|
|
|
232 matrix, the columns correspond to the positions within the pattern,
|
|
|
233 and the rows correspond to the letters. Each row begins with the
|
|
|
234 corresponding letter (or integer, if the "-i" option is used). In a
|
|
|
235 vertical matrix, the rows correspond to the positions within the
|
|
|
236 pattern, and the columns correspond to the letters. The first row
|
|
|
237 contains the letters (or integers, if the "-i" option is used)
|
|
|
238 corresponding to each column. In both types of matrices, spaces,
|
|
|
239 tabs, and vertical bars (|) are ignored. The output of the "consensus"
|
|
|
240 and "wconsensus" programs consists of horizontal alignment matrices.
|
|
|
241
|
|
|
242 The input files can contain comments according to the following
|
|
|
243 convention. The portion of a line following a ';', '%', or '#' is
|
|
|
244 considered a comment and is ignored. Comments can begin anywhere in a
|
|
|
245 line and always end at the end of the line. The output of this
|
|
|
246 program is sent to the standard output.
|
|
|
247
|
|
|
248
|
|
|
249 ]]></help>
|
|
|
250 <citations>
|
|
|
251 <citation type="doi">10.1093/bioinformatics/15.7.563</citation>
|
|
|
252 </citations>
|
|
|
253 </tool>
|
