Mercurial > repos > cpt > cpt_convert_trnascan_se

changeset 0:b4134ad44443 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author cpt
date Fri, 13 May 2022 18:03:32 +0000
parents
children 7bf46fd8d62e
files cpt_trnascanse_to_gff/cpt-macros.xml cpt_trnascanse_to_gff/macros.xml cpt_trnascanse_to_gff/tRNAscan_to_gff_SE_format.py cpt_trnascanse_to_gff/tRNAscan_to_gff_SE_format.xml cpt_trnascanse_to_gff/test-data/ConvTrnaSe_In.tabular cpt_trnascanse_to_gff/test-data/ConvTrnaSe_Out.gff3
diffstat 6 files changed, 260 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/cpt-macros.xml	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,115 @@
+<?xml version="1.0"?>
+<macros>
+	<xml name="gff_requirements">
+		<requirements>
+			<requirement type="package" version="2.7">python</requirement>
+			<requirement type="package" version="1.65">biopython</requirement>
+			<requirement type="package" version="2.12.1">requests</requirement>
+			<yield/>
+		</requirements>
+		<version_command>
+		<![CDATA[
+			cd $__tool_directory__ && git rev-parse HEAD
+		]]>
+		</version_command>
+	</xml>
+	<xml name="citation/mijalisrasche">
+		<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+		<citation type="bibtex">@unpublished{galaxyTools,
+		author = {E. Mijalis, H. Rasche},
+		title = {CPT Galaxy Tools},
+		year = {2013-2017},
+		note = {https://github.com/tamu-cpt/galaxy-tools/}
+		}
+		</citation>
+	</xml>
+	<xml name="citations">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation> 
+		<yield/>
+		</citations>
+	</xml>
+    	<xml name="citations-crr">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Ross},
+				title = {CPT Galaxy Tools},
+				year = {2020-},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+		<yield/>
+		</citations>
+	</xml>
+        <xml name="citations-2020">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="citations-2020-AJC-solo">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+                        <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="citations-clm">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="sl-citations-clm">
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <yield/>
+	</xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/macros.xml	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,66 @@
+<?xml version="1.0"?>
+<macros>
+	<xml name="requirements">
+		<requirements>
+			<requirement type="package" version="3.7">python</requirement>
+			<requirement type="package" version="1.77">biopython</requirement>
+			<requirement type="package" version="1.1.3">cpt_gffparser</requirement>  
+			<yield/>
+		</requirements>
+	</xml>
+	<xml name="genome_selector">
+		<conditional name="reference_genome">
+			<param name="reference_genome_source" type="select" label="Reference Genome">
+				<option value="history" selected="True">From History</option>
+				<option value="cached">Locally Cached</option>
+			</param>
+			<when value="cached">
+				<param name="fasta_indexes" type="select" label="Source FASTA Sequence">
+					<options from_data_table="all_fasta"/>
+				</param>
+			</when>
+			<when value="history">
+				<param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/>
+			</when>
+		</conditional>
+	</xml>
+	<xml name="gff3_input">
+		<param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/>
+	</xml>
+	<xml name="input/gff3+fasta">
+		<expand macro="gff3_input" />
+		<expand macro="genome_selector" />
+	</xml>
+	<token name="@INPUT_GFF@">
+	"$gff3_data"
+	</token>
+	<token name="@INPUT_FASTA@">
+#if str($reference_genome.reference_genome_source) == 'cached':
+		"${reference_genome.fasta_indexes.fields.path}"
+#else if str($reference_genome.reference_genome_source) == 'history':
+		genomeref.fa
+#end if
+	</token>
+	<token name="@GENOME_SELECTOR_PRE@">
+#if $reference_genome.reference_genome_source == 'history':
+		ln -s $reference_genome.genome_fasta genomeref.fa;
+#end if
+	</token>
+	<token name="@GENOME_SELECTOR@">
+#if str($reference_genome.reference_genome_source) == 'cached':
+		"${reference_genome.fasta_indexes.fields.path}"
+#else if str($reference_genome.reference_genome_source) == 'history':
+		genomeref.fa
+#end if
+	</token>
+        <xml name="input/fasta">
+		<param label="Fasta file" name="sequences" type="data" format="fasta"/>
+	</xml>
+
+	<token name="@SEQUENCE@">
+		"$sequences"
+	</token>
+	<xml name="input/fasta/protein">
+		<param label="Protein fasta file" name="sequences" type="data" format="fasta"/>
+	</xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/tRNAscan_to_gff_SE_format.py	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,38 @@
+#!/usr/bin/env python
+import fileinput
+
+print ("##gff-version-3")
+# process each trna in tsv file
+metaLines = 0
+for trna in fileinput.input():
+    if metaLines < 3:
+      metaLines += 1
+      continue
+    cols_tsv = trna.split("\t")
+    if int(cols_tsv[2]) < int(cols_tsv[3]):
+      cols_gff = [
+        cols_tsv[0].strip(),
+        "tRNAscan",
+        "tRNA",
+        cols_tsv[2].strip(),
+        cols_tsv[3].strip(),
+        cols_tsv[8],
+        "+",
+        ".",
+        'ID=trna.%s;Anticodon=%s;Codon=tRNA-%s'
+        % (cols_tsv[1], cols_tsv[5].lower(), cols_tsv[4]),
+      ]
+    else:
+      cols_gff = [
+        cols_tsv[0].strip(),
+        "tRNAscan",
+        "tRNA",
+        cols_tsv[3].strip(),
+        cols_tsv[2].strip(),
+        cols_tsv[8],
+        "-",
+        ".",
+        'ID=trna.%s;Anticodon=%s;Codon=tRNA-%s'
+        % (cols_tsv[1], cols_tsv[5].lower(), cols_tsv[4]),
+      ] 
+    print ("\t".join(cols_gff))
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/tRNAscan_to_gff_SE_format.xml	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,35 @@
+<?xml version="1.0"?>
+<tool id="tRNA-SE_scan_to_gff" name="Convert tRNAscan-SE table to gff format" version="20.0.0">
+	<description></description>
+	<macros>
+		<import>macros.xml</import>
+		<import>cpt-macros.xml</import>
+	</macros>
+	<expand macro="requirements"/>
+	<command detect_errors="aggressive"><![CDATA[
+python $__tool_directory__/tRNAscan_to_gff_SE_format.py
+< $trnascan
+> $output
+]]></command>
+	<inputs>
+			<param format="tabular" type="data" name="trnascan" label="tRNAscan table" />
+	</inputs>
+	<outputs>
+		<data format="gff3" name="output">
+		</data>
+	</outputs>
+	<tests>
+		<test>
+			<param name="trnascan" value="ConvTrnaSe_In.tabular" />
+			<output name="output" file="ConvTrnaSe_Out.gff3" />
+		</test>
+	</tests>
+	<help><![CDATA[
+What it does
+============
+
+Converts tRNAscan-SE table to gff format
+
+]]></help>
+		<expand macro="citations" />
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/test-data/ConvTrnaSe_In.tabular	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,4 @@
+Sequence    		tRNA  	Bounds	tRNA	Anti	Intron Bounds	Inf	      
+Name        	tRNA #	Begin 	End   	Type	Codon	Begin	End	Score	Note
+--------    	------	----- 	------	----	-----	-----	----	------	------
+NC_028755.1 	1	49264 	49339 	Gly	TCC	0	0	77.4	
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_trnascanse_to_gff/test-data/ConvTrnaSe_Out.gff3	Fri May 13 18:03:32 2022 +0000
@@ -0,0 +1,2 @@
+##gff-version-3
+NC_028755.1	tRNAscan	tRNA	49264	49339	77.4	+	.	ID=trna.1;Anticodon=tcc;Codon=tRNA-Gly