Commit message:
Upload ctat tools. |
added:
ctat_fusion_inspector.xml test-data/FusionInspector/fusion_targets.A.txt test-data/FusionInspector/fusion_targets.B.txt test-data/FusionInspector/fusion_targets.C.txt test-data/FusionInspector/test.reads_1.fastq.gz test-data/FusionInspector/test.reads_2.fastq.gz tool-data/ctat_genome_resource_libs.loc.sample tool_data_table_conf.xml.sample |
b |
diff -r 000000000000 -r 1a7ec343001c ctat_fusion_inspector.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ctat_fusion_inspector.xml Tue Jul 17 11:51:18 2018 -0400 |
[ |
b'@@ -0,0 +1,181 @@\n+<tool id="ctat_fusion_inspector" name="ctat_fusion_inspector" version="1.0.0" profile="17.05">\n+ <description>In silico Validation of Fusion Transcript Predictions</description>\n+ <requirements>\n+ <requirement type="package" version="1.2.0">fusion-inspector</requirement>\n+ </requirements>\n+ <command detect_errors="default">\n+ <![CDATA[\n+ FusionInspector \n+ --fusions $fusion_candidates_list\n+ --genome_lib "${genome_resource_lib.fields.path}"\n+ --left_fq $left_input\n+ --right $right_input\n+ --out_dir "subdir"\n+ --out_prefix "finspector" \n+ --prep_for_IGV \n+ #if $trinity_status.trinity=="true"\n+ --include_Trinity\n+ #end if\n+ ]]>\n+ </command>\n+ <stdio>\n+ <exit_code range="1:" level="fatal" description="Error returned from pipeline" />\n+ </stdio>\n+ <regex match="Must investigate error above."\n+ source="stderr"\n+ level="fatal"\n+ description="Unknown error encountered" />\n+ <inputs>\n+ <param format="tabular" name="fusion_candidates_list" type="data" multiple="True" label="Choose candidate list:" help="Fusion predictions"/>\n+ <param format="fastq" name="left_input" type="data" label="Left/Forward strand reads" help=""/>\n+ <param format="fastq" name="right_input" type="data" label="Right/Reverse strand reads" help=""/>\n+ <!-- The HISAT and GSNAP methods are not supported and are being removed, leaving only STAR.\n+ <param name="method" type="select" label="Choose method:">\n+ <option value="HISAT">HISAT</option>\n+ <option value="STAR">STAR</option>\n+ <option value="GSNAP">GSNAP</option>\n+ </param>\n+ -->\n+ <conditional name="trinity_status">\n+ <param name="trinity" type="select" label="Use Trinity:">\n+ <option value="true">True</option>\n+ <option value="false">False</option>\n+ </param>\n+ </conditional>\n+ <param name="genome_resource_lib" type="select" label="Select a reference genome">\n+ <options from_data_table="ctat_genome_resource_libs">\n+ <filter type="sort_by" column="2" />\n+ <validator type="no_options" message="No indexes are available" />\n+ </options>\n+ </param>\n+ </inputs>\n+ <outputs>\n+ <data format="txt" name="finspector_idx" label="fidx" from_work_dir="subdir/finspector.fa.fai"/>\n+ <data format="txt" name="cytoBand" label="cytoBand" from_work_dir="subdir/cytoBand.txt"/>\n+ <data format="fasta" name="finspector_fa" label="finspector_fasta" from_work_dir="subdir/finspector.fa"/>\n+ <data format="bed" name="finspector_bed" label="finspector_bed" from_work_dir="subdir/finspector.bed"/>\n+ <data format="tabular" name="FusionJuncSpan" label="FusionJuncSpan" from_work_dir="subdir/finspector.igv.FusionJuncSpan"/>\n+ <data format="bed" name="junction_bed" label="junction_bed" from_work_dir="subdir/finspector.junction_reads.bam.bed"/>\n+ <data format="bam" name="junction_bam" label="junction_bam" from_work_dir="subdir/finspector.junction_reads.bam"/>\n+ <data format="bam" name="spanning_bam" label="spanning_bam" from_work_dir="subdir/finspector.spanning_reads.bam"/>\n+ <data format="bed" name="spanning_bed" label="spanning_bed" from_work_dir="subdir/finspector.spanning_reads.bam.bed"/>\n+ <data format="bed" name="trinity_bed" label="trinity_bed" from_work_dir="subdir/finspector.gmap_trinity_GG.fusions.gff3.bed.sorted.bed">\n+ <filter>trinity_status[\'trinity\'] == "true"</filter>\n+ </data>\n+ <data format="txt" name="fusionPredictions" label="fusion_predictions.final" from_work_dir="subdir/finspector.fusion_predictions.final"/>\n+ <data format="txt" name="fusionPredictionsAbridged" label="fusion_predictions_abridged" from_work_dir="subdir/finspector.fusion_predictions.final.abridged"/>\n+ <data format="json" name="fusion_json" label="fusion_json" f'..b'has_line_matching expression=".+" />\n+ <!-- The following checks for the magic number at the start of the bam file -->\n+ <has_text_matching expression="\\x1F\\x8B" />\n+ </assert_contents>\n+ </output>\n+ <output name="spanning_bam" >\n+ <assert_contents>\n+ <has_line_matching expression=".+" />\n+ <!-- The following checks for the magic number at the start of the bam file -->\n+ <has_text_matching expression="\\x1F\\x8B" />\n+ </assert_contents>\n+ </output>\n+ <output name="spanning_bed" file="FusionInspector/test.reads_1_2.spanning_reads.bam.bed.sorted" sort="true" />\n+ <!--\n+ Since trinity is false in this test, trinity_bed does not exist.\n+ <output name="trinity_bed" />\n+ <assert_contents>\n+ <has_line_matching expression=".+" />\n+ </assert_contents>\n+ </output>\n+ -->\n+ <output name="fusionPredictions" >\n+ <assert_contents>\n+ <has_line_matching expression=".+" />\n+ <has_line line="#fusion_name	JunctionReads	SpanningFrags	Splice_type	LeftGene	LeftBreakpoint	RightGene	RightBreakpoint	JunctionReads	SpanningFrags	Annotations	TrinityGG" />\n+ </assert_contents>\n+ </output>\n+ <output name="fusionPredictionsAbridged" >\n+ <assert_contents>\n+ <has_line_matching expression=".+" />\n+ <has_line line="#fusion_name	JunctionReads	SpanningFrags	Splice_type	LeftGene	LeftBreakpoint	RightGene	RightBreakpoint	Annotations	TrinityGG" />\n+ </assert_contents>\n+ </output>\n+ <!-- So far in my testing of the fusion_json, I have had up to 18 different lines \n+ (9 positions values switched between two entries)- 64 gives some padding. -->\n+ <output name="fusion_json" file="FusionInspector/test.reads_1_2.web.json" lines_diff="64" />\n+\n+ </test>\n+ </tests>\n+ <help>\n+.. class:: infomark\n+\n+FusionInspector is a component of the Trinity Cancer Transcriptome Analysis Toolkit (CTAT). FusionInspector assists in fusion transcript discovery by performing a supervised analysis of fusion predictions, attempting to recover and re-score evidence for such predictions. Please read more here_.\n+\n+.. _here: https://github.com/FusionInspector/FusionInspector/wiki\n+\n+**To Visualize Output**\n+\n+After completion, results can be visualized in galaxy. Click on the output json file name in the history (on the right). A more detailed view of that file will be shown. Click on the button in the middle that looks like a bar chart. The visualization should now open for you to explore results.\n+\n+**There are several output files for the CTAT Fusion Inspector Pipeline. Files of interest include:**\n+\n+1. **fidx**: Finspector_fasta index file (required for visualization).\n+\n+2. **cytoBand**: Cytogenetic information for hg19.\n+\n+3. **finspector_fasta**: The candidate fusion-gene contigs.\n+\n+4. **finspector_bed**: The reference gene structure annotations for fusion partners.\n+\n+5. **FusionJuncSpan**: Tabular details on junction reads and spanning reads.\n+\n+6. **junction_bed**: Alignments of the breakpoint-junction supporting reads.\n+\n+7. **junction_bam**: Alignments of the breakpoint-junction supporting reads.\n+\n+8. **spanning_bam**: Alignments of the breakpoint-spanning paired-end reads.\n+\n+9. **spanning_bed**: Alignments of the breakpoint-spanning paired-end reads.\n+\n+10. **trinity_bed**: Fusion-guided Trinity assembly.\n+\n+11. **fusion_predictions.final**: All fusion evidence described.\n+\n+12. **fusion_predictions_abridged**: encompasses all information in fusion_predictions.final excluding the names of the reads.\n+\n+13. **fusion_json**: A logistical file that enables the visualization.\n+\n+ </help>\n+ <cite>\n+ </cite>\n+</tool>\n' |
b |
diff -r 000000000000 -r 1a7ec343001c test-data/FusionInspector/fusion_targets.A.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/FusionInspector/fusion_targets.A.txt Tue Jul 17 11:51:18 2018 -0400 |
b |
@@ -0,0 +1,24 @@ +ACACA--STAC2 +AHCTF1--NAAA +CTD-2328D6.1--MT-CO1 +DIDO1--TTI1 +FITM2--UQCC1 +GLB1--CMTM7 +LAMP1--MCF2L +MED1--ACSF2 +MED1--STXBP4 +MT-ND5--MT-RNR2 +PIP4K2B--RAD51C +RAB22A--MYO9B +RP11-96H19.1--RP11-446N19.1 +RPS6KB1--SNF8 +STARD3--DOK5 +STX16--RAE1 +STX16-NPEPL1--RAE1 +THRA--AC090627.1 +TOB1--SYNRG +TRIM37--MYO19 +TRPC4AP--MRPL45 +TULP4--RP11-732M18.3 +VAPB--IKZF3 +ZMYND8--CEP250 |
b |
diff -r 000000000000 -r 1a7ec343001c test-data/FusionInspector/fusion_targets.B.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/FusionInspector/fusion_targets.B.txt Tue Jul 17 11:51:18 2018 -0400 |
b |
@@ -0,0 +1,22 @@ +ACACA--STAC2 +AHCTF1--NAAA +ASTN2--RP11-281A20.1 +CPNE1--PI3 +CTD-2319I12.2--HEATR6 +CTD-2328D6.1--MT-CO1 +DIDO1--TTI1 +FITM2--UQCC1 +GLB1--CMTM7 +RAB22A--MYO9B +RP11-96H19.1--RP11-446N19.1 +RPS6KB1--SNF8 +STARD3--DOK5 +STX16--RAE1 +STX16-NPEPL1--RAE1 +THRA--AC090627.1 +TOB1--SYNRG +TRIM37--MYO19 +TRPC4AP--MRPL45 +TULP4--RP11-732M18.3 +VAPB--IKZF3 +ZMYND8--CEP250 |
b |
diff -r 000000000000 -r 1a7ec343001c test-data/FusionInspector/fusion_targets.C.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/FusionInspector/fusion_targets.C.txt Tue Jul 17 11:51:18 2018 -0400 |
b |
@@ -0,0 +1,24 @@ +ACACA--STAC2 +AHCTF1--NAAA +ASTN2--RP11-281A20.1 +CPNE1--PI3 +CTD-2319I12.2--HEATR6 +CTD-2328D6.1--MT-CO1 +DIDO1--TTI1 +FITM2--UQCC1 +GLB1--CMTM7 +LAMP1--MCF2L +MED1--ACSF2 +MED1--STXBP4 +MT-ND5--MT-RNR2 +PIP4K2B--RAD51C +RAB22A--MYO9B +RP11-96H19.1--RP11-446N19.1 +RPS6KB1--SNF8 +STARD3--DOK5 +STX16--RAE1 +STX16-NPEPL1--RAE1 +THRA--AC090627.1 +TOB1--SYNRG +TRIM37--MYO19 +ZMYND8--CEP250 |
b |
diff -r 000000000000 -r 1a7ec343001c test-data/FusionInspector/test.reads_1.fastq.gz |
b |
Binary file test-data/FusionInspector/test.reads_1.fastq.gz has changed |
b |
diff -r 000000000000 -r 1a7ec343001c test-data/FusionInspector/test.reads_2.fastq.gz |
b |
Binary file test-data/FusionInspector/test.reads_2.fastq.gz has changed |
b |
diff -r 000000000000 -r 1a7ec343001c tool-data/ctat_genome_resource_libs.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/ctat_genome_resource_libs.loc.sample Tue Jul 17 11:51:18 2018 -0400 |
b |
@@ -0,0 +1,15 @@ +# This file lists the locations of CTAT Genome Resource Libraries +# Usually there will only be one library, but it is concievable +# that there could be multiple libraries. +# This file format is as follows +# (white space characters are TAB characters): +# +#<value> <name> <path> +# value is a unique id +# name is the display name +# path is the directory where the genome resource lib files are stored +# +#ctat_genome_resource_libs.loc could look like: +# +#GRCh38_v27_CTAT_lib_Feb092018 CTAT_GenomeResourceLib_GRCh38_v27_CTAT_lib_Feb092018 /path/to/ctat/genome/resource/lib/directory +# |
b |
diff -r 000000000000 -r 1a7ec343001c tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Jul 17 11:51:18 2018 -0400 |
b |
@@ -0,0 +1,14 @@ +<tables> + <table name="ctat_genome_resource_libs" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/ctat_genome_resource_libs.loc" /> + </table> + <table name="ctat_centrifuge_indexes" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/ctat_centrifuge_indexes.loc" /> + </table> + <table name="ctat_lncrna_annotations" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/ctat_lncrna_annotations.loc" /> + </table> +</tables> |