changeset 8:b0f9aca4a34f draft

Uploaded

--- a/cmsearch.xml	Sat Aug 31 15:22:49 2013 -0400
+++ b/cmsearch.xml	Sat Aug 31 17:32:40 2013 -0400
@@ -6,7 +6,7 @@
         <requirement type="package" version="8.21">gnu_coreutils</requirement>
     </requirements>
     <command>
-        temp_tabular_output=$(mktemp);
+        temp_tabular_output=\$(mktemp);
 
         cmsearch 
             --cpu 12
@@ -19,8 +19,8 @@
             $max
             $nohmm
             $mid
-            $bitscore_thresholds
-            --tblout $temp_tabular_output
+            ##$bitscore_thresholds
+            --tblout \$temp_tabular_output
             $g
             #if $A:
                 $A $multiple_alignment_output
@@ -48,7 +48,9 @@
             2>&#38;1
             ;
 
-            sed -e 's/#.*$//' -e '/^$/d' -e 's/ /\t/g' -e 's/\t/ /18g' $temp_tabular_output > $outfile
+            ## 1. replace all lines starting # (comment lines)
+            ## 2. replace the first 18 spaces with tabs, 18th field is a free text field (can contain spaces)
+            sed -e 's/#.*$//' -e '/^$/d' -e 's/ /\t/g' -e 's/\t/ /18g' \$temp_tabular_output > $outfile
 
     </command>
         <inputs>
@@ -103,14 +105,14 @@
 
 
             <!-- Options for model-specific score thresholding -->
-
+            <!--
             <param name="bitscore_thresholds" type="select" label="Bit score thresholds" help="Curated CM databases may define specific bit score thresholds for each CM, superseding any thresholding based on statistical significance alone.">
                 <option value="" selected="true">None</option>
-                <option value="--cut_ga">GA (gathering) bit scores</option>
-                <option value="--cut_nc">NC (noise cutoff) bit score</option>
-                <option value="--cut_tc">TC (trusted cutoff) bit score</option>
+                <option value=" - -cut_ga">GA (gathering) bit scores</option>
+                <option value=" - -cut_nc">NC (noise cutoff) bit score</option>
+                <option value=" - -cut_tc">TC (trusted cutoff) bit score</option>
             </param>
-
+            -->
             <!-- Options for inclusion thresholds -->
 
 
@@ -191,16 +193,18 @@
 
 **What it does**
 
-Options for model-specific score thresholding
----------------------------------------------
-
+Infernal is used to search sequence databases for homologs of structural RNA sequences, and to make
+sequence- and structure-based RNA sequence alignments. Infernal needs a profile from a structurally
+annotated multiple sequence alignment of an RNA family with a position-specific scoring system for substitutions, 
+insertions, and deletions. Positions in the profile that are basepaired in the consensus secondary
+structure of the alignment are modeled as dependent on one another, allowing Infernal’s scoring system to
+consider the secondary structure, in addition to the primary sequence, of the family being modeled. Infernal
+profiles are probabilistic models called “covariance models”, a specialized type of stochastic context-free
+grammar (SCFG) (Lari and Young, 1990).
 
-  - GA thresholds are generally considered to be the reliable curated thresholds defining family membership; for example, in Rfam, these thresholds define what gets included in Rfam Full alignments based on searches with Rfam Seed models.
-  - NC thresholds are generally considered to be the score of the highest-scoring known false positive.
-  - TC thresholds are generally considered to be the score of the lowest-scoring known true positive that is above all known false positives.
-
-
--g Turn on the glocal alignment algorithm, global with respect to the query model and local with respect to the target database. By default, the local alignment algorithm is used which is local with respect to both the target sequence and the model. In local mode, the alignment to span two or more subsequences if necessary (e.g. if the structures of the query model and target sequence are only partially shared), allowing certain large insertions and deletions in the structure to be penalized differently than normal indels. Local mode performs better on empirical benchmarks and is significantly more sensitive for remote homology detection. Empirically, glocal searches return many fewer hits than local searches, so glocal may be desired for some applications. With -g, all models must be calibrated, even those with zero basepairs.
+Compared to other alignment and database search tools based only on sequence comparison, Infernal
+aims to be significantly more accurate and more able to detect remote homologs because it models sequence 
+and structure.
 
 
 Output format
@@ -226,8 +230,22 @@
 (18) description of target: The remainder of the line is the target’s description line, as free text.
 
 
+For further questions please refere to the Infernal Userguide_.
+
+.. _Userguide: http://selab.janelia.org/software/infernal/Userguide.pdf
 
 
+How do I cite Infernal?
+-----------------------
+
+The Infernal 1.0 paper (Nawrocki et al., 2009) is the best paper to reference. 
+If you’re writing for an enlightened (url-friendly) journal, you may want to cite the webpage
+http://infernal.janelia.org/ because it is kept up-to-date. We hope to publish a paper related to
+Infernal version 1.1 soon.
+
+**Galaxy Wrapper Author**::
+
+    *  Bjoern Gruening, University of Freiburg
 
     </help>
 </tool>