Mercurial > repos > trinity_ctat > ctat_fusion_inspector
changeset 0:1a7ec343001c draft default tip
Upload ctat tools.
| author | trinity_ctat |
|---|---|
| date | Tue, 17 Jul 2018 11:51:18 -0400 |
| parents | |
| children | |
| files | 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 |
| diffstat | 8 files changed, 280 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ctat_fusion_inspector.xml Tue Jul 17 11:51:18 2018 -0400 @@ -0,0 +1,181 @@ +<tool id="ctat_fusion_inspector" name="ctat_fusion_inspector" version="1.0.0" profile="17.05"> + <description>In silico Validation of Fusion Transcript Predictions</description> + <requirements> + <requirement type="package" version="1.2.0">fusion-inspector</requirement> + </requirements> + <command detect_errors="default"> + <![CDATA[ + FusionInspector + --fusions $fusion_candidates_list + --genome_lib "${genome_resource_lib.fields.path}" + --left_fq $left_input + --right $right_input + --out_dir "subdir" + --out_prefix "finspector" + --prep_for_IGV + #if $trinity_status.trinity=="true" + --include_Trinity + #end if + ]]> + </command> + <stdio> + <exit_code range="1:" level="fatal" description="Error returned from pipeline" /> + </stdio> + <regex match="Must investigate error above." + source="stderr" + level="fatal" + description="Unknown error encountered" /> + <inputs> + <param format="tabular" name="fusion_candidates_list" type="data" multiple="True" label="Choose candidate list:" help="Fusion predictions"/> + <param format="fastq" name="left_input" type="data" label="Left/Forward strand reads" help=""/> + <param format="fastq" name="right_input" type="data" label="Right/Reverse strand reads" help=""/> + <!-- The HISAT and GSNAP methods are not supported and are being removed, leaving only STAR. + <param name="method" type="select" label="Choose method:"> + <option value="HISAT">HISAT</option> + <option value="STAR">STAR</option> + <option value="GSNAP">GSNAP</option> + </param> + --> + <conditional name="trinity_status"> + <param name="trinity" type="select" label="Use Trinity:"> + <option value="true">True</option> + <option value="false">False</option> + </param> + </conditional> + <param name="genome_resource_lib" type="select" label="Select a reference genome"> + <options from_data_table="ctat_genome_resource_libs"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No indexes are available" /> + </options> + </param> + </inputs> + <outputs> + <data format="txt" name="finspector_idx" label="fidx" from_work_dir="subdir/finspector.fa.fai"/> + <data format="txt" name="cytoBand" label="cytoBand" from_work_dir="subdir/cytoBand.txt"/> + <data format="fasta" name="finspector_fa" label="finspector_fasta" from_work_dir="subdir/finspector.fa"/> + <data format="bed" name="finspector_bed" label="finspector_bed" from_work_dir="subdir/finspector.bed"/> + <data format="tabular" name="FusionJuncSpan" label="FusionJuncSpan" from_work_dir="subdir/finspector.igv.FusionJuncSpan"/> + <data format="bed" name="junction_bed" label="junction_bed" from_work_dir="subdir/finspector.junction_reads.bam.bed"/> + <data format="bam" name="junction_bam" label="junction_bam" from_work_dir="subdir/finspector.junction_reads.bam"/> + <data format="bam" name="spanning_bam" label="spanning_bam" from_work_dir="subdir/finspector.spanning_reads.bam"/> + <data format="bed" name="spanning_bed" label="spanning_bed" from_work_dir="subdir/finspector.spanning_reads.bam.bed"/> + <data format="bed" name="trinity_bed" label="trinity_bed" from_work_dir="subdir/finspector.gmap_trinity_GG.fusions.gff3.bed.sorted.bed"> + <filter>trinity_status['trinity'] == "true"</filter> + </data> + <data format="txt" name="fusionPredictions" label="fusion_predictions.final" from_work_dir="subdir/finspector.fusion_predictions.final"/> + <data format="txt" name="fusionPredictionsAbridged" label="fusion_predictions_abridged" from_work_dir="subdir/finspector.fusion_predictions.final.abridged"/> + <data format="json" name="fusion_json" label="fusion_json" from_work_dir="subdir/finspector.fusion_inspector_web.json"/> + </outputs> + <tests> + <test> + <param name="fusion_candidates_list" value="FusionInspector/fusion_targets.A.txt,FusionInspector/fusion_targets.B.txt,FusionInspector/fusion_targets.C.txt" /> + <param name="left_input" value="FusionInspector/test.reads_1.fastq.gz" /> + <param name="right_input" value="FusionInspector/test.reads_2.fastq.gz" /> + <!-- The HISAT and GSNAP methods are not supported and are being removed, leaving only STAR. + <param name="method" value="STAR" /> + --> + <param name="trinity" value="false" /> + <!-- FIX - now that we added the CTAT resource lib path as a parameter, how do we find it for testing? + <param name="genome_resource_lib.fields.path" value="?????" /> + --> + <output name="finspector_idx" file="FusionInspector/test.reads_1_2.fa.fai" /> + <output name="cytoBand" file="FusionInspector/test.reads_1_2.cytoBand.tail.txt" compare="contains" /> + <output name="finspector_fa" file="FusionInspector/test.reads_1_2.fa" /> + <output name="finspector_bed" file="FusionInspector/test.reads_1_2.bed.sorted" sort="true" /> + <output name="FusionJuncSpan" > + <assert_contents> + <has_line_matching expression=".+" /> + <has_line line="#scaffold	fusion_break_name	break_left	break_right	num_junction_reads	num_spanning_frags	spanning_frag_coords" /> + </assert_contents> + </output> + <!-- sorted output sometimes matches, but simetimes not, so now I just test for similar size. --> + <output name="junction_bed" file="FusionInspector/test.reads_1_2.junction_reads.bam.bed.sorted" sort="true" compare="sim_size" > + <assert_contents> + <has_line_matching expression=".+" /> + <has_n_columns n="12" /> + </assert_contents> + </output> + <output name="junction_bam" > + <assert_contents> + <has_line_matching expression=".+" /> + <!-- The following checks for the magic number at the start of the bam file --> + <has_text_matching expression="\x1F\x8B" /> + </assert_contents> + </output> + <output name="spanning_bam" > + <assert_contents> + <has_line_matching expression=".+" /> + <!-- The following checks for the magic number at the start of the bam file --> + <has_text_matching expression="\x1F\x8B" /> + </assert_contents> + </output> + <output name="spanning_bed" file="FusionInspector/test.reads_1_2.spanning_reads.bam.bed.sorted" sort="true" /> + <!-- + Since trinity is false in this test, trinity_bed does not exist. + <output name="trinity_bed" /> + <assert_contents> + <has_line_matching expression=".+" /> + </assert_contents> + </output> + --> + <output name="fusionPredictions" > + <assert_contents> + <has_line_matching expression=".+" /> + <has_line line="#fusion_name	JunctionReads	SpanningFrags	Splice_type	LeftGene	LeftBreakpoint	RightGene	RightBreakpoint	JunctionReads	SpanningFrags	Annotations	TrinityGG" /> + </assert_contents> + </output> + <output name="fusionPredictionsAbridged" > + <assert_contents> + <has_line_matching expression=".+" /> + <has_line line="#fusion_name	JunctionReads	SpanningFrags	Splice_type	LeftGene	LeftBreakpoint	RightGene	RightBreakpoint	Annotations	TrinityGG" /> + </assert_contents> + </output> + <!-- So far in my testing of the fusion_json, I have had up to 18 different lines + (9 positions values switched between two entries)- 64 gives some padding. --> + <output name="fusion_json" file="FusionInspector/test.reads_1_2.web.json" lines_diff="64" /> + + </test> + </tests> + <help> +.. class:: infomark + +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_. + +.. _here: https://github.com/FusionInspector/FusionInspector/wiki + +**To Visualize Output** + +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. + +**There are several output files for the CTAT Fusion Inspector Pipeline. Files of interest include:** + +1. **fidx**: Finspector_fasta index file (required for visualization). + +2. **cytoBand**: Cytogenetic information for hg19. + +3. **finspector_fasta**: The candidate fusion-gene contigs. + +4. **finspector_bed**: The reference gene structure annotations for fusion partners. + +5. **FusionJuncSpan**: Tabular details on junction reads and spanning reads. + +6. **junction_bed**: Alignments of the breakpoint-junction supporting reads. + +7. **junction_bam**: Alignments of the breakpoint-junction supporting reads. + +8. **spanning_bam**: Alignments of the breakpoint-spanning paired-end reads. + +9. **spanning_bed**: Alignments of the breakpoint-spanning paired-end reads. + +10. **trinity_bed**: Fusion-guided Trinity assembly. + +11. **fusion_predictions.final**: All fusion evidence described. + +12. **fusion_predictions_abridged**: encompasses all information in fusion_predictions.final excluding the names of the reads. + +13. **fusion_json**: A logistical file that enables the visualization. + + </help> + <cite> + </cite> +</tool>
--- /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 @@ -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
--- /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 @@ -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
--- /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 @@ -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
--- /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 @@ -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 +#
--- /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 @@ -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>