/var/lib/mobyle/programs/imogene.xml is in mobyle-programs 5.1.2-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | <?xml version="1.0" encoding="ISO-8859-1"?>
<!-- This file has been adapted for the needs of imogene by -->
<!-- Hervé Rouault <rouault@lps.ens.fr> -->
<!-- -->
<!-- -->
<!-- XML Authors: Corinne Maufrais -->
<!-- 'Biological Software and Databases' Group, Institut Pasteur, Paris. -->
<!-- Distributed under LGPLv2 License. Please refer to the COPYING.LIB document. -->
<program>
<head xmlns:xi="http://www.w3.org/2001/XInclude">
<name>imogene</name>
<version>1.0-253</version>
<doc>
<title>imogene</title>
<description>
<text lang="en">Genome-wide identification of cis-regulatory
motifs and modules</text>
</description>
<authors>H. Rouault, M. Santolini</authors>
<reference> H. Rouault, M. Santolini, F. Schweisguth and V. Hakim
(2013), Imogene: identification of motifs and cis regulatory
modules underlying gene co-regulation, submitted. </reference>
<reference> H. Rouault, K. Mazouni, L. Couturier, V. Hakim and F.
Schweisguth (2010), Genome-wide identification of
cis-regulatory motifs and modules underlying gene coregulation
using statistics and phylogeny. Proc. Natl. Acad. Sci. U.S.A.,
107:14615-14620. </reference>
<doclink>https://github.com/hrouault/Imogene</doclink>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p><em>Imogene</em> has two main purposes:
<ul><li>it detects statistically overrepresented motifs,
considering closely related genomes, in a set of training
sequences. These sequences are generally selected for their
biological relationships, ie cis-regulatory role.</li>
<li>it predicts novel cis-regulatory sequences based
on user-selected motifs at the whole genome scale.</li>
</ul>
</p>
<p>Currently, <em>Imogene</em> supports two genome sets: mammals and
drosophilae, but we are open to integrating other sets if you
feel interested.</p>
<p>The source code of Imogene is available on <em>github</em>:
<a href="https://github.com/hrouault/Imogene">https://github.com/hrouault/Imogene</a>.
It contains the main source code, as well as a documentation and
local installation instructions. An online manual can also be
found <a href="http://hrouault.github.com/Imogene">here</a>. Any
trouble concerning its installation or bugs should be addressed on
<em>github</em>.</p> <p>Please, feel free to contact us for any
question concerning <em>Imogene</em>: Herve Rouault
<a href="mailto:herve.rouault@pasteur.fr">herve.rouault@pasteur.fr</a>,
Marc Santolini <a href="mailto:marc.santolini@lps.ens.fr">marc.santolini@lps.ens.fr</a>.</p>
</div>
</comment>
</doc>
<category>sequence:nucleic:regulation</category>
<xi:include href="../../../Local/Services/Programs/Env/imogene_env.xml" xpointer="xpointer(//env)">
<xi:fallback/>
</xi:include>
</head>
<parameters>
<parameter ismandatory="1" issimple="1">
<name>model</name>
<prompt lang="en">Execution mode</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>null</value>
</vdef>
<vlist>
<velem undef="1">
<value>null</value>
<label>Choice</label>
</velem>
<velem>
<value>genmot</value>
<label>genmot: Generate motifs from a training set</label>
</velem>
<velem>
<value>scangen</value>
<label>scangen: Find instances of a list of motifs in the
genome</label>
</velem>
</vlist>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml"><em>Imogene</em> has two
different modes of execution that should be performed sequentially:
<ul><li><strong>genmot</strong>: generates motifs from a
set of functionally related CRMs</li>
<li><strong>scangen</strong>: predicts enhancers given
the set of motifs generated using the <em>genmot</em> mode.</li>
</ul>
</div>
</comment>
</parameter>
<paragraph>
<name>general</name>
<prompt lang="en">General options</prompt>
<argpos>1</argpos>
<parameters>
<parameter ismandatory="1" issimple="1">
<name>species</name>
<prompt lang="en">Family of species to consider</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>null</value>
</vdef>
<vlist>
<velem undef="1">
<value>null</value>
<label>Choice</label>
</velem>
<velem>
<value>droso</value>
<label>Drosophilae</label>
</velem>
<velem>
<value>eutherian</value>
<label>Eutherians</label>
</velem>
</vlist>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
Two families of genomes are currently supported by
<em>Imogene</em>:
<ul><li><strong>Drosophilae</strong>: genomes are taken from the
12 genomes project (A. G. Clark, <em>et al</em>. Evolution of
genes and genomes on the Drosophila phylogeny.
<em>Nature</em>, 450(7167):203-218, Nov 2007.)</li>
<li><strong>Eutherian</strong>: genomes are taken from the
ensembl project (<a href="http://www.ensembl.org/">http://www.ensembl.org/</a>,
folder epo_12_eutherian)</li>
</ul>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>width</name>
<prompt lang="en">Width of the motifs</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>10</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml"> Motifs represent
the affinity of transcription factors for binding sites (BS).
Please indicate here the <em>width</em> of BSs in number of
nucleotides (nts). Typical values range between 8 and 12 nts.
Note that motifs of larger width can model motifs with a specific
core of lower width and flanking nts with background frequencies
(non-specific non-coding sequences). However, large motifs are
more difficult to infer when containing many degenerate bases.
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>extent</name>
<prompt lang="en">Allowed shift of a binding site position in
orthologous species</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>20</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>In order to be robust to mistakes in the alignments,
<em>Imogene</em> allows for local shifts of the binding sites
in orthologous sequences.</p>
<p>Considering the first base of a binding site in the reference
species, an alignment will make it correspond to a position
<em>p</em> in an orthologous genome. The algorithm will then
search for binding sites in this orthologous species at
positions <em>(p-s,p+w+s)</em>, where <em>s</em> is the shift
indicated here and <em>w</em> is the width of the motif.</p>
</div>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>genmot</name>
<prompt lang="en">Genmot options</prompt>
<precond>
<code proglang="perl">$model == 'genmot'</code>
<code proglang="python">model == 'genmot'</code>
</precond>
<argpos>2</argpos>
<parameters>
<parameter ismandatory="1">
<name>evolutionary</name>
<prompt lang="en">Evolutionary model used for motif generation</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>1</value>
</vdef>
<vlist>
<velem>
<value>1</value>
<label>Felsenstein model</label>
</velem>
<velem>
<value>2</value>
<label>Halpern-Bruno model</label>
</velem>
</vlist>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p><em>Imogene</em> makes use of the evolution of binding sites
to infer motifs. In order to function, <em>Imogene</em>
consider the mutation rate of bases under selection thanks
to an evolutionary model.</p>
<p>Two models are currently supported by <em>Imogene</em> (see
refs at the end of the page for a detailed description):
<ul><li>Felsentein: this model is simple and runs faster</li>
<li>Halpern-Bruno: this model has a deeper theoretical
ground and better predicts the speed of evolution of
the motifs but takes more time to run.</li>
</ul></p>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>Sg</name>
<prompt lang="en">Threshold used for motif generation</prompt>
<type>
<datatype>
<class>Float</class>
</datatype>
</type>
<vdef>
<value>11.0</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>The <em>threshold</em>, expressed in bits, corresponds to the
level of specificity of a motif. As an order of magnitude,
a threshold equal to 10 corresponds approximatively to one
binding site every 1000 bases on average in the whole genome.
Since we use conservation to define motifs instances, this
number is actually an upper bound. Common values, that give
reasonable results are comprised between 10 and 13 bits.</p>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>Ss1</name>
<prompt lang="en">Threshold used to scan training set sequences for
display</prompt>
<type>
<datatype>
<class>Float</class>
</datatype>
</type>
<vdef>
<value>8.0</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>Note that this scanning threshold is only used for the final
display and does not interviene in motifs generation. In
particular, a lower threshold is useful to check for cryptic
sites in the sequences. </p>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>gennbmots</name>
<prompt lang="en">Number of motifs to display at maximum (between 1
and 10)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>5</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>The algorithm output consists of many motifs on general.
Although, they are all present in the text file output, they
cannot all be displayed and shown on the input sequences. It is
usually fine to consider between 5 et 10 motifs. </p>
</div>
</comment>
</parameter>
<parameter ismandatory="1" issimple="1">
<name>coord_file</name>
<prompt lang="en">Training set sequences coordinates</prompt>
<type>
<datatype>
<class>Coordinates</class>
<superclass>AbstractText</superclass>
</datatype>
</type>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p> List of sequence coordinates in the BED4 format:
<pre>chrN start stop seq_name </pre>
Below we give example training sets than can be copy/pasted in
the following form. </p>
<!--<example>-->
<ul>
<li> Mouse example training set (mm9 assembly, enhancers
specific of the neural tube):</li>
<pre>
chr8 91462919 91464123 CYLD-SALL1
chr4 99040833 99042291 APG4C-FOXD3
chr14 118834760 118836087 SOX21-ABCC4
chr18 69658816 69660452 TCF4(intragenic)
chr6 138199417 138201368 MGST1-LMO3
chr12 51291542 51292872 FOXG1B-PRKD1
chr4 73149468 73150526 FLJ46321-RASEF
chrX 57972482 57973750 LOC347487-SOX3
chr5 42914188 42915270 FAM44A-CPEB2
chr9 91261697 91263041 ZIC4-ZIC1
chr18 82027407 82028703 GALR1-SALL3
chr13 73170587 73173631 IRX4-IRX2</pre>
<li> Drosophila example training set (release 5 assembly, enhancers expressed in mesoderm and somatic muscle):</li>
<pre>
chr3R 10415381 10415780 seq2300
chr3R 17228198 17228402 seq2821
chr2R 18937351 18937843 seq1357
chr2L 21853080 21853669 seq6531
chr3R 17392100 17392639 seq2837
chr2R 19526211 19526451 seq1396
chr2R 19526657 19527033 seq1397
chr3R 17227574 17227958 seq2820
chr2R 5025930 5026695 seq257</pre>
</ul>
<!--</example> -->
</div>
</comment>
</parameter>
<parameter ishidden="1">
<name>cmd_1</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">"imogene extract -s " + species + " -i " \
+ coord_file +" && "</code>
</format>
<argpos>1</argpos>
</parameter>
<parameter ishidden="1">
<name>cmd_2</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">" imogene genmot -s " + species + " -w " \
+ str(width) + " -t " + str(Sg) + " -x " + str(extent) + " -e " \
+ str(evolutionary) + " -a align &&" </code>
</format>
<argpos>2</argpos>
</parameter>
<parameter ishidden="1">
<name>cmd_3</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">" imogene display -t " + str(Ss1) + " -s "\
+ species + " -n " + str(gennbmots)\
+ " -m motifs.txt -a align --logos --pdf --png &&"</code>
</format>
<argpos>3</argpos>
</parameter>
<parameter ishidden="1">
<name>cmd_4</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">" imogene display -t "+ str(Ss1) +" -s " + \
species + " -n " + str(gennbmots) + " -m motifs.txt -a align --html-ref"</code>
</format>
<argpos>4</argpos>
</parameter>
<parameter isout="1">
<name>motifs</name>
<prompt>Motif file</prompt>
<type>
<datatype>
<class>ScangenMotifDefinition</class>
<superclass>AbstractText</superclass>
</datatype>
</type>
<filenames>
<code proglang="perl">"motifs.txt"</code>
<code proglang="python">"motifs.txt"</code>
</filenames>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>Predicted motifs in text file format. This file can be used as
input for the <em>scangen</em> mode</p>
</div>
</comment>
</parameter>
<parameter isout="1">
<name>genmotoutput</name>
<prompt>General output</prompt>
<type>
<datatype>
<class>GenmotReport</class>
<superclass>Report</superclass>
</datatype>
<dataFormat>HTML</dataFormat>
</type>
<filenames>
<code proglang="python">"results_genmot.html"</code>
</filenames>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>Predicted motifs in pretty printed format (xhtml). This page
contains motifs logos.</p>
</div>
</comment>
</parameter>
<parameter isout="1">
<name>motif_png_out</name>
<type>
<datatype>
<class>Logo</class>
<superclass>Binary</superclass>
</datatype>
<dataFormat>png</dataFormat>
</type>
<filenames>
<code proglang="python">"Motif*.png"</code>
</filenames>
</parameter>
<parameter isout="1">
<name>motif_pdf_out</name>
<type>
<datatype>
<class>Logo</class>
<superclass>Binary</superclass>
</datatype>
<dataFormat>pdf</dataFormat>
</type>
<filenames>
<code proglang="python">"Motif*.pdf"</code>
</filenames>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>scangen</name>
<prompt lang="en">Scangen
options</prompt>
<precond>
<code proglang="perl">$model == 'scangen'</code>
<code proglang="python">model == 'scangen'</code>
</precond>
<argpos>2</argpos>
<parameters>
<parameter ismandatory="1">
<name>Ss2</name>
<prompt lang="en">Threshold used to scan the genome </prompt>
<type>
<datatype>
<class>Float</class>
</datatype>
</type>
<vdef>
<value>8.0</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p> Usually less or equal to the generation threshold Sg. </p>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>crmwidth</name>
<prompt lang="en">Width of selected enhancers</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>1000</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>Width of the predicted enhancers in number of nucleotides.</p>
</div>
</comment>
</parameter>
<parameter ismandatory="1">
<name>nbmots</name>
<prompt lang="en">Number of motifs to consider at maximum</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>5</value>
</vdef>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>Enhancers are predicted on the basis of the presence of
binding sites corresponding to chosen motifs. You must input an
ordered list of motifs generated either by yourself (with the
appropriate syntax) or by the <em>genmot</em> mode. The number
of considered motifs will be the top <em>n</em>, where
<em>n</em> is the integer indicated here.</p>
</div>
</comment>
</parameter>
<parameter ismandatory="1" issimple="1">
<name>motifs_file</name>
<prompt lang="en">File containing a list of motif
definitions</prompt>
<type>
<datatype>
<class>ScangenMotifDefinition</class>
<superclass>AbstractText</superclass>
</datatype>
</type>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>List of motif definition in format identical to the output of
the <em>genmot</em> mode.</p>
</div>
</comment>
</parameter>
<parameter ishidden="1">
<name>cmdscangen_1</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">"imogene scangen -s " + species + " -t " \
+ str(Ss2) + " -x " + str(extent) + " -m " + motifs_file \
+ " --scanwidth=" + str(crmwidth) + "&& "</code>
</format>
<argpos>1</argpos>
</parameter>
<parameter ishidden="1">
<name>cmdscangen_2</name>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">" imogene display -e result*.dat"</code>
</format>
<argpos>2</argpos>
</parameter>
<parameter isout="1">
<name>scangenOuthtml</name>
<prompt>Scangen output</prompt>
<type>
<datatype>
<class>ScangenReport</class>
<superclass>Report</superclass>
</datatype>
<dataFormat>HTML</dataFormat>
</type>
<filenames>
<code proglang="python">"results_scangen.html"</code>
</filenames>
<comment>
<div xmlns="http://www.w3.org/1999/xhtml">
<p>List of predicted enhancers, from the most concentrated in
motifs to the less enriched.
</p>
</div>
</comment>
</parameter>
</parameters>
</paragraph>
</parameters>
</program>
|