Mercurial > repos > vipints > fml_mergeloci

diff fml_gff_groomer/galaxy/gff_loci_merge.xml @ 0:79726c328621 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 1.0.0 from old tool shed archive to new tool shed repository
author vipints
date Tue, 07 Jun 2011 17:29:24 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/fml_gff_groomer/galaxy/gff_loci_merge.xml	Tue Jun 07 17:29:24 2011 -0400
@@ -0,0 +1,114 @@
+<tool id="fml_mergeloci" name="MergeLoci" version="1.0.0">
+  <description>Merge feature annotation from same loci</description>
+  <command interpreter="python"> 
+        gff_loci_merge.py
+		$gff_input
+		$gff_result
+		> $logfile
+    </command>
+  <inputs>
+    <param format="gff3" name="gff_input" type="data" label="Genome annotation in GFF3 format" help="Genome annotation in GFF3 format describing the known gene structures for the provided genome."/>
+  </inputs>
+  <outputs>
+    <data format="txt" name="logfile" label="Log file for MergeLoci" />
+    <data format="gff3" name="gff_result" />
+  </outputs>
+		<tests>
+    		<test>
+            	<param name="gff_input" value="ucsc_splitted_genes.gff3" />
+            	<output name="logfile" file="ucsc_merged_genes_log.txt" />
+            	<output name="gff_result" file="ucsc_merged_genes.gff3" />
+            </test>
+		</tests>
+  <help>
+
+**What it does** 
+
+This tool merge the feature annotation of same loci. MergeLoci will be able to merge several transcripts from single loci to a main feature instead of several features. For example, in UCSC genome annotation files the alternative splice model of the transcript are represented as individual gene models. 
+
+--------
+
+**Example**
+
+- data in GFF3 format::
+
+	##gff-version 3
+	chr19   hg19_knownGene  gene    44764033        44779468        .       +       .       ID=Gene:uc002oyy.1;Name=Gene:uc002oyy.1
+	chr19   hg19_knownGene  mRNA    44764033        44779468        .       +       .       ID=Transcript:uc002oyy.1;Parent=Gene:uc002oyy.1
+	chr19   hg19_knownGene  protein 44777369        44778826        .       +       .       ID=Protein:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44764033        44764091        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44768467        44768528        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS     44777369        44778826        .       +       0       Name=CDS:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  three_prime_UTR 44778827        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44764033        44764091        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44768467        44768528        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777052        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  gene    44770351        44779468        .       +       .       ID=Gene:uc002oyy.1;Name=Gene:uc002oyy.1
+	chr19   hg19_knownGene  mRNA    44770351        44779468        .       +       .       ID=Transcript:uc002oyy.1;Parent=Gene:uc002oyy.1
+	chr19   hg19_knownGene  protein 44777052        44778826        .       +       .       ID=Protein:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS	44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS	44777489        44778826        .       +       0       Name=CDS:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  three_prime_UTR 44778827        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777489        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+
+- Will be merged as::
+
+	##gff-version 3
+	chr19   hg19_knownGene  gene    44764033        44779468        .       +       .       ID=Gene_hg19_chr19_00001;Name=Gene_hg19_chr19_0001
+	chr19   hg19_knownGene  mRNA    44764033        44779468        .       +       .       ID=Transcript:uc002oyy.1;Parent=Gene_hg19_chr19_0001
+	chr19   hg19_knownGene  protein 44777369        44778826        .       +       .       ID=Protein:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44764033        44764091        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44768467        44768528        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS     44777369        44778826        .       +       0       Name=CDS:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  three_prime_UTR 44778827        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44764033        44764091        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44768467        44768528        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777052        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  mRNA    44770351        44779468        .       +       .       ID=Transcript:uc002oyy.1;Gene_hg19_chr19_0001
+	chr19   hg19_knownGene  protein 44777052        44778826        .       +       .       ID=Protein:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  five_prime_UTR  44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS	44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  CDS	44777489        44778826        .       +       0       Name=CDS:uc002oyy.1;Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  three_prime_UTR 44778827        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44770351        44770477        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44771019        44771297        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777052        44777368        .       +       .       Parent=Transcript:uc002oyy.1
+	chr19   hg19_knownGene  exon    44777489        44779468        .       +       .       Parent=Transcript:uc002oyy.1
+
+--------
+
+**About formats**
+
+**GFF3 format** General Feature Format is a format for describing genes and other features associated with DNA, RNA and Protein sequences. GFF3 lines have nine tab-separated fields:
+
+    1. seqid - Must be a chromosome or scaffold.
+    2. source - The program that generated this feature.
+    3. type - The name of this type of feature. Some examples of standard feature types are "gene", "CDS", "protein", "mRNA", and "exon". 
+    4. start - The starting position of the feature in the sequence. The first base is numbered 1.
+    5. stop - The ending position of the feature (inclusive).
+    6. score - A score between 0 and 1000. If there is no score value, enter ".".
+    7. strand - Valid entries include '+', '-', or '.' (for don't know/care).
+    8. phase - If the feature is a coding exon, frame should be a number between 0-2 that represents the reading frame of the first base. If the feature is not a coding exon, the value should be '.'.
+    9. attributes - All lines with the same group are linked together into a single item.
+
+--------
+
+This tool is a part of the **MLB Group at Friedrich Miescher Laboratory of the Max Planck Society**. Copyright (C) 2010 Vipin T. Sreedharan (vipin.ts@tuebingen.mpg.de)
+</help>
+</tool>