Skip to content

Commit

Permalink
output separate files
Browse files Browse the repository at this point in the history
  • Loading branch information
@rcannood
rcannood committed Jul 29, 2024
1 parent b39b2b8 commit 732ac4d
Show file tree
Hide file tree
Showing 3 changed files with 431 additions and 90 deletions.
347 changes: 336 additions & 11 deletions src/bd_rhapsody/bd_rhapsody_sequence_analysis/config.vsh.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -116,20 +116,317 @@ argument_groups:
info:
config_key: Supplemental_Reference
- name: Outputs
description: Outputs for all pipeline runs
# based on https://bd-rhapsody-bioinfo-docs.genomics.bd.com/outputs/top_outputs.html
arguments:
# TODO: split up into different outputs
# - ${run_name}_Bioproduct_Stats.csv
# - ${run_name}_Metrics_Summary.csv
# - ${run_name}_RSEC_MolsPerCell_Unfiltered_MEX.zip
# - ${run_name}_Logs/
# TODO: determine additional outputs for ABC, ATAC, VDJ, SMK
- name: "--output"
- name: "--output_dir"
type: file
direction: output
alternatives: [-o]
description: "Output folder. Output still needs to be processed further."
description: "The unprocessed output directory containing all the outputs from the pipeline."
required: true
example: output_dir/
- name: "--output_seurat"
type: file
direction: output
description: "Single-cell analysis tool inputs. Seurat (.rds) input file containing RSEC molecules data table and all cell annotation metadata."
example: output_seurat.rds
required: false
info:
template: "[sample_name]_Seurat.rds"
- name: "--output_mudata"
type: file
direction: output
description: "Single-cell analysis tool inputs. Scanpy / Muon input file containing RSEC molecules data table and all cell annotation metadata."
example: output_mudata.h5mu
required: false
info:
template: "[sample_name].h5mu"
- name: "--metrics_summary"
type: file
direction: output
description: "Metrics Summary. Report containing sequencing, molecules, and cell metrics."
example: metrics_summary.csv
required: false
info:
template: "[sample_name]_Metrics_Summary.csv"
- name: "--pipeline_report"
type: file
direction: output
description: "Pipeline Report. Summary report containing the results from the sequencing analysis pipeline run."
example: pipeline_report.html
required: false
info:
template: "[sample_name]_Pipeline_Report.html"
- name: "--rsec_mols_per_cell"
type: file
direction: output
description: "Molecules per bioproduct per cell bassed on RSEC"
example: RSEC_MolsPerCell_MEX.zip
required: false
info:
template: "[sample_name]_RSEC_MolsPerCell_MEX.zip"
- name: "--dbec_mols_per_cell"
type: file
direction: output
description: "Molecules per bioproduct per cell bassed on DBEC. DBEC data table is only output if the experiment includes targeted mRNA or AbSeq bioproducts."
example: DBEC_MolsPerCell_MEX.zip
required: false
info:
template: "[sample_name]_DBEC_MolsPerCell_MEX.zip"
- name: "--rsec_mols_per_cell_unfiltered"
type: file
direction: output
description: "Unfiltered tables containing all cell labels with ≥10 reads."
example: RSEC_MolsPerCell_Unfiltered_MEX.zip
required: false
info:
template: "[sample_name]_RSEC_MolsPerCell_Unfiltered_MEX.zip"
- name: "--bam"
type: file
direction: output
description: "Alignment file of R2 with associated R1 annotations for Bioproduct."
example: BioProduct.bam
required: false
info:
template: "[sample_name]_Bioproduct.bam"
- name: "--bam_inddex"
type: file
direction: output
description: "Index file for the alignment file."
example: BioProduct.bam.bai
required: false
info:
template: "[sample_name]_Bioproduct.bam.bai"
- name: "--bioproduct_stats"
type: file
direction: output
description: "Bioproduct Stats. Metrics from RSEC and DBEC Unique Molecular Identifier adjustment algorithms on a per-bioproduct basis."
example: Bioproduct_Stats.csv
required: false
info:
template: "[sample_name]_Bioproduct_Stats.csv"
- name: "--dimred_tsne"
type: file
direction: output
description: "t-SNE dimensionality reduction coordinates per cell index"
example: tSNE_coordinates.csv
required: false
info:
template: "[sample_name]_(assay)_tSNE_coordinates.csv"
- name: "--dimred_umap"
type: file
direction: output
description: "UMAP dimensionality reduction coordinates per cell index"
example: UMAP_coordinates.csv
required: false
info:
template: "[sample_name]_(assay)_UMAP_coordinates.csv"
- name: "--immune_cell_classification"
type: file
direction: output
description: "Immune Cell Classification. Cell type classification based on the expression of immune cell markers."
example: Immune_Cell_Classification.csv
required: false
info:
template: "[sample_name]_(assay)_cell_type_experimental.csv"
- name: Multiplex outputs
description: Outputs when multiplex option is selected
arguments:
- name: "--sample_tag_metrics"
type: file
direction: output
description: "Sample Tag Metrics. Metrics from the sample determination algorithm."
example: Sample_Tag_Metrics.csv
required: false
info:
template: "[sample_name]_Sample_Tag_Metrics.csv"
- name: "--sample_tag_calls"
type: file
direction: output
description: "Sample Tag Calls. Assigned Sample Tag for each putative cell"
example: Sample_Tag_Calls.csv
required: false
info:
template: "[sample_name]_Sample_Tag_Calls.csv"
- name: "--sample_tag_counts"
type: file
direction: output
description: "Sample Tag Counts. Separate data tables and metric summary for cells assigned to each sample tag. Note: For putative cells that could not be assigned a specific Sample Tag, a Multiplet_and_Undetermined.zip file is also output."
example: Sample_Tag1.zip
required: false
multiple: true
info:
template: "[sample_name]_Sample_Tag[number].zip"
- name: "--sample_tag_counts_unassigned"
type: file
direction: output
description: "Sample Tag Counts Unassigned. Data table and metric summary for cells that could not be assigned a specific Sample Tag."
example: Multiplet_and_Undetermined.zip
required: false
info:
template: "[sample_name]_Multiplet_and_Undetermined.zip"
- name: VDJ Outputs
description: Outputs when VDJ option selected
arguments:
- name: "--vdj_metrics"
type: file
direction: output
description: "VDJ Metrics. Overall metrics from the VDJ analysis."
example: VDJ_Metrics.csv
required: false
info:
template: "[sample_name]_VDJ_Metrics.csv"
- name: "--vdj_per_cell"
type: file
direction: output
description: "VDJ Per Cell. Cell specific read and molecule counts, VDJ gene segments, CDR3 sequences, paired chains, and cell type."
example: VDJ_perCell.csv
required: false
info:
template: "[sample_name]_VDJ_perCell.csv"
- name: "--vdj_per_cell_uncorrected"
type: file
direction: output
description: "VDJ Per Cell Uncorrected. Cell specific read and molecule counts, VDJ gene segments, CDR3 sequences, paired chains, and cell type."
example: VDJ_perCell_uncorrected.csv
required: false
info:
template: "[sample_name]_VDJ_perCell_uncorrected.csv"
- name: "--vdj_dominant_contigs"
type: file
direction: output
description: "VDJ Dominant Contigs. Dominant contig for each cell label chain type combination (putative cells only)."
example: VDJ_Dominant_Contigs_AIRR.csv
required: false
info:
template: "[sample_name]_VDJ_Dominant_Contigs_AIRR.csv"
- name: "--vdj_unfiltered_contigs"
type: file
direction: output
description: "VDJ Unfiltered Contigs. All contigs that were assembled and annotated successfully (all cells)."
example: VDJ_Unfiltered_Contigs_AIRR.csv
required: false
info:
template: "[sample_name]_VDJ_Unfiltered_Contigs_AIRR.csv"
- name: "ATAC-Seq outputs"
description: Outputs when ATAC-Seq option selected
arguments:
- name: "--atac_metrics"
type: file
direction: output
description: "ATAC Metrics. Overall metrics from the ATAC-Seq analysis."
example: ATAC_Metrics.csv
required: false
info:
template: "[sample_name]_ATAC_Metrics.csv"
- name: "--atac_metrics_json"
type: file
direction: output
description: "ATAC Metrics JSON. Overall metrics from the ATAC-Seq analysis in JSON format."
example: ATAC_Metrics.json
required: false
info:
template: "[sample_name]_ATAC_Metrics.json"
- name: "--atac_fragments"
type: file
direction: output
description: "ATAC Fragments. Chromosomal location, cell index, and read support for each fragment detected"
example: ATAC_Fragments.bed.gz
required: false
info:
template: "[sample_name]_ATAC_Fragments.bed.gz"
- name: "--atac_fragments_index"
type: file
direction: output
description: "Index of ATAC Fragments."
example: ATAC_Fragments.bed.gz.tbi
required: false
info:
template: "[sample_name]_ATAC_Fragments.bed.gz.tbi"
- name: "--atac_transposase_sites"
type: file
direction: output
description: "ATAC Transposase Sites. Chromosomal location, cell index, and read support for each transposase site detected"
example: ATAC_Transposase_Sites.bed.gz
required: false
info:
template: "[sample_name]_ATAC_Transposase_Sites.bed.gz"
- name: "--atac_transposase_sites_index"
type: file
direction: output
description: "Index of ATAC Transposase Sites."
example: ATAC_Transposase_Sites.bed.gz.tbi
required: false
info:
template: "[sample_name]_ATAC_Transposase_Sites.bed.gz.tbi"
- name: "--atac_peaks"
type: file
direction: output
description: "ATAC Peaks. Peak regions of transposase activity"
example: ATAC_Peaks.bed.gz
required: false
info:
template: "[sample_name]_ATAC_Peaks.bed.gz"
- name: "--atac_peaks_index"
type: file
direction: output
description: "Index of ATAC Peaks."
example: ATAC_Peaks.bed.gz.tbi
required: false
info:
template: "[sample_name]_ATAC_Peaks.bed.gz.tbi"
- name: "--atac_peak_annotation"
type: file
direction: output
description: "ATAC Peak Annotation. Estimated annotation of peak-to-gene connections"
example: peak_annotation.tsv.gz
required: false
info:
template: "[sample_name]_peak_annotation.tsv.gz"
- name: "--atac_cell_by_peak"
type: file
direction: output
description: "ATAC Cell by Peak. Peak regions of transposase activity per cell"
example: ATAC_Cell_by_Peak_MEX.zip
required: false
info:
template: "[sample_name]_ATAC_Cell_by_Peak_MEX.zip"
- name: "--atac_cell_by_peak_unfiltered"
type: file
direction: output
description: "ATAC Cell by Peak Unfiltered. Unfiltered file containing all cell labels with >=1 transposase sites in peaks."
example: ATAC_Cell_by_Peak_Unfiltered_MEX.zip
required: false
info:
template: "[sample_name]_ATAC_Cell_by_Peak_Unfiltered_MEX.zip"
- name: "--atac_bam"
type: file
direction: output
description: "ATAC BAM. Alignment file for R1 and R2 with associated I2 annotations for ATAC-Seq. Only output if the BAM generation flag is set to true."
example: ATAC.bam
required: false
info:
template: "[sample_name]_ATAC.bam"
- name: "--atac_bam_index"
type: file
direction: output
description: "Index of ATAC BAM."
example: ATAC.bam.bai
required: false
info:
template: "[sample_name]_ATAC.bam.bai"
- name: AbSeq Cell Calling outputs
description: Outputs when Cell Calling Abseq is selected
arguments:
- name: "--protein_aggregates_experimental"
type: file
direction: output
description: "Protein Aggregates Experimental"
example: Protein_Aggregates_Experimental.csv
required: false
info:
template: "[sample_name]_Protein_Aggregates_Experimental.csv"
- name: Putative Cell Calling Settings
arguments:
- name: "--cell_calling_data"
Expand Down Expand Up @@ -298,9 +595,37 @@ argument_groups:
- name: "--timestamps"
type: boolean_true
description: "Add timestamps to the errors, warnings, and notifications."
- name: "--dryrun"
type: boolean_true
description: "If true, the output directory will only contain the CWL input files, but the pipeline itself will not be executed."
- name: Undocumented arguments
arguments:
- name: --abseq_umi
type: integer
multiple: false
info:
config_key: AbSeq_UMI
- name: --target_analysis
type: boolean
multiple: false
info:
config_key: Target_analysis
- name: --vdj_jgene_evalue
type: double
description: |
e-value threshold for J gene. The e-value threshold for J gene call by IgBlast/PyIR, default is set as 0.001
multiple: false
info:
config_key: VDJ_JGene_Evalue
- name: --vdj_vgene_evalue
type: double
description: |
e-value threshold for V gene. The e-value threshold for V gene call by IgBlast/PyIR, default is set as 0.001
multiple: false
info:
config_key: VDJ_VGene_Evalue
- name: --write_filtered_reads
type: boolean
multiple: false
info:
config_key: Write_Filtered_Reads
resources:
- type: python_script
path: script.py
Expand Down
Loading

0 comments on commit 732ac4d

Please sign in to comment.