← Files Life Sciences NGS AnalysisARCHIVED FILE
references/pipeline-registry.json
34.3 KB · Sep 30, 2026 · 22:50 UTC
{
"schema_version": "0.1.0",
"tools": {
"nextflow": {
"executables": ["nextflow"],
"kind": "workflow_runner",
"install": {"conda": "bioconda::nextflow"},
"notes": "Required for nf-core workflows."
},
"snakemake": {
"executables": ["snakemake"],
"python_modules": ["snakemake"],
"kind": "workflow_runner",
"install": {"conda": "bioconda::snakemake", "pip": "snakemake"},
"notes": "Preferred local workflow runner for file-based local or devbox execution without Docker."
},
"mamba": {
"executables": ["mamba"],
"kind": "environment_manager",
"notes": "Preferred environment manager for local conda environments when available."
},
"micromamba": {
"executables": ["micromamba"],
"kind": "environment_manager",
"notes": "Conda-compatible environment manager; useful on devboxes where system conda is absent."
},
"fastqc": {
"executables": ["fastqc"],
"kind": "qc",
"install": {"conda": "bioconda::fastqc"}
},
"multiqc": {
"executables": ["multiqc"],
"python_modules": ["multiqc"],
"kind": "reporting",
"install": {"conda": "bioconda::multiqc", "pip": "multiqc"}
},
"fastp": {
"executables": ["fastp"],
"kind": "fastq_preprocessor",
"install": {"conda": "bioconda::fastp"}
},
"cutadapt": {
"executables": ["cutadapt"],
"python_modules": ["cutadapt"],
"kind": "adapter_trimming",
"install": {"conda": "bioconda::cutadapt", "pip": "cutadapt"}
},
"seqkit": {
"executables": ["seqkit"],
"kind": "fastq_util",
"install": {"conda": "bioconda::seqkit"}
},
"samtools": {
"executables": ["samtools"],
"kind": "hts_util",
"install": {"conda": "bioconda::samtools"}
},
"bcftools": {
"executables": ["bcftools"],
"kind": "variant_util",
"install": {"conda": "bioconda::bcftools"}
},
"fgbio": {
"executables": ["fgbio"],
"kind": "umi_consensus",
"install": {"conda": "bioconda::fgbio"},
"notes": "Useful for UMI-aware targeted sequencing workflows when a lab protocol does not provide its own consensus step."
},
"bwa-mem2": {
"executables": ["bwa-mem2"],
"kind": "aligner",
"install": {"conda": "bioconda::bwa-mem2"}
},
"bowtie2": {
"executables": ["bowtie2"],
"kind": "aligner",
"install": {"conda": "bioconda::bowtie2"}
},
"bedtools": {
"executables": ["bedtools"],
"kind": "interval_util",
"install": {"conda": "bioconda::bedtools"}
},
"gatk": {
"executables": ["gatk"],
"kind": "variant_calling",
"install": {"conda": "bioconda::gatk4"},
"notes": "GATK4 is open source; best-practice resource bundles are large and should be downloaded deliberately."
},
"deepvariant": {
"executables": ["run_deepvariant"],
"kind": "variant_calling",
"container_images": ["google/deepvariant:latest"],
"notes": "Commonly run by Docker or Singularity rather than a local executable."
},
"star": {
"executables": ["STAR"],
"kind": "rna_aligner",
"install": {"conda": "bioconda::star"}
},
"salmon": {
"executables": ["salmon"],
"kind": "rna_quantification",
"install": {"conda": "bioconda::salmon"}
},
"subread": {
"executables": ["featureCounts"],
"kind": "rna_counting",
"install": {"conda": "bioconda::subread"}
},
"rscript": {
"executables": ["Rscript"],
"kind": "statistical_runtime",
"install": {"conda": "conda-forge::r-base"},
"notes": "R/Bioconductor package checks are workflow-specific; this preflight only verifies that an R runtime exists."
},
"scanpy": {
"python_modules": ["scanpy"],
"kind": "single_cell_analysis",
"install": {"conda": "conda-forge::scanpy", "pip": "scanpy"}
},
"kb-python": {
"executables": ["kb"],
"python_modules": ["kb_python"],
"kind": "single_cell_counting",
"install": {"pip": "kb-python"}
},
"macs2": {
"executables": ["macs2"],
"kind": "peak_calling",
"install": {"conda": "bioconda::macs2"}
},
"deeptools": {
"executables": ["bamCoverage", "computeMatrix", "plotProfile", "plotHeatmap"],
"kind": "signal_qc",
"install": {"conda": "bioconda::deeptools"}
},
"homer": {
"executables": ["findMotifsGenome.pl"],
"kind": "motif_enrichment",
"install": {"conda": "bioconda::homer"},
"notes": "Optional motif enrichment backend for ATAC, ChIP-seq, CUT&RUN, and CUT&Tag peak sets."
},
"qiime2": {
"executables": ["qiime"],
"kind": "amplicon_microbiome",
"notes": "QIIME2 installation is best done with its published environment file or container for the target release."
},
"dada2": {
"kind": "amplicon_denoising",
"install": {"conda": "bioconda::bioconductor-dada2"},
"notes": "R/Bioconductor DADA2 backend for ASV inference. The plugin runner checks this as an R package at execution time."
},
"kraken2": {
"executables": ["kraken2"],
"kind": "taxonomic_classification",
"install": {"conda": "bioconda::kraken2"},
"notes": "Databases are large and should be selected before download."
},
"bracken": {
"executables": ["bracken"],
"kind": "taxonomic_abundance",
"install": {"conda": "bioconda::bracken"}
},
"metaphlan": {
"executables": ["metaphlan"],
"kind": "taxonomic_profile",
"install": {"conda": "bioconda::metaphlan"}
},
"kneaddata": {
"executables": ["kneaddata"],
"kind": "host_depletion",
"install": {"conda": "bioconda::kneaddata"},
"notes": "Optional shotgun metagenomics host-depletion backend. Requires a prepared host reference database and should be treated as required when --host-reference is supplied."
},
"humann": {
"executables": ["humann"],
"kind": "functional_profile",
"install": {"conda": "bioconda::humann"}
},
"bcl-convert": {
"executables": ["bcl-convert"],
"kind": "bcl_conversion",
"license": "free_proprietary",
"notes": "Illumina BCL Convert is free for local use but proprietary and distributed as Illumina RPM installers. Do not auto-download without explicit user approval."
},
"bcl2fastq": {
"executables": ["bcl2fastq"],
"kind": "bcl_conversion",
"license": "legacy_proprietary",
"notes": "Legacy Illumina converter. Use only when BCL Convert is unavailable or the run requires legacy compatibility."
},
"cellranger": {
"executables": ["cellranger"],
"kind": "single_cell_vendor_pipeline",
"license": "eula",
"notes": "10x Cell Ranger requires EULA acceptance. Prefer public alternatives unless the user explicitly wants vendor-standard output and has accepted the license."
}
},
"profiles": {
"local_light": {
"display_name": "Local execution profile",
"runner": "snakemake_or_direct_shell",
"environment": "mamba_or_micromamba_conda_envs",
"containers": "disabled_by_default",
"required_tools": ["snakemake"],
"preferred_tools": ["fastqc", "multiqc", "fastp", "seqkit", "salmon", "samtools", "bcftools"],
"optional_tools": ["cutadapt", "bwa-mem2", "bowtie2", "bedtools", "deeptools", "subread", "scanpy", "star", "macs2", "kraken2", "bracken", "kneaddata", "humann", "bcl-convert", "bcl2fastq"],
"first_lanes": ["fastq_qc", "bulk_rnaseq_counts_qc", "bulk_rnaseq_differential_expression", "dna_variant_calling", "scrnaseq_post_count_qc", "epigenomics_peaks", "amplicon_microbiome", "shotgun_metagenomics", "bcl_to_fastq"],
"notes": "Use when Docker, Nextflow, or container registry access is unavailable or unstable. This profile runs local workflows over staged or user-provided data."
},
"production_nfcore": {
"display_name": "nf-core execution profile",
"runner": "nextflow",
"environment": "docker_singularity_conda_or_site_profile",
"required_tools": ["nextflow"],
"preferred_tools": ["multiqc"],
"first_lanes": ["bulk_rnaseq", "scrnaseq", "dna_variant_calling", "dna_germline_variants", "dna_somatic_variants", "atacseq_peaks_qc", "chip_cutrun_peaks_qc", "amplicon_microbiome", "shotgun_metagenomics"],
"adapter": "plugins/ngs-analysis/scripts/run_nfcore_pipeline.py",
"notes": "Use when the user wants pinned nf-core execution with Nextflow reports, trace, timeline, DAG, and published results captured in a standard run envelope."
}
},
"pipelines": {
"bcl_to_fastq": {
"display_name": "BCL to FASTQ conversion",
"route_when": ["bcl_run_folder", "demultiplex"],
"local_executor": "plugins/ngs-analysis/scripts/run_bcl_to_fastq.py",
"preferred_tools": ["bcl-convert"],
"optional_tools": ["bcl2fastq"],
"local_light_tools": ["bcl-convert", "bcl2fastq"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"validation/runinfo.json",
"validation/runparameters.json",
"validation/samplesheet_summary.json",
"validation/runtime_preflight.json",
"commands.sh",
"logs/bcl_conversion.log",
"qc/demux_qc_summary.json",
"artifact_index.json",
"summary.md"
],
"public_boundary": "BCL Convert is public to download and free for local use, but proprietary; do not auto-download.",
"essential_questions": [
"Where is the Illumina run folder containing RunInfo.xml?",
"Which SampleSheet.csv should be used?",
"Should lanes be split or combined?",
"Are UMI bases present in reads or index reads?",
"What output directory should receive FASTQs and reports?"
]
},
"fastq_qc": {
"display_name": "FASTQ QC and trimming",
"route_when": ["fastq", "qc", "trim"],
"local_executor": "plugins/ngs-analysis/scripts/run_fastq_qc.py",
"preferred_tools": ["fastqc", "multiqc", "fastp", "cutadapt", "seqkit"],
"local_light_tools": ["snakemake", "fastqc", "multiqc", "fastp", "seqkit"],
"essential_questions": [
"Are reads paired-end or single-end?",
"Is there a local sample sheet, or should a single sample be run from explicit R1/R2 paths?",
"Are adapters or primer sequences known?",
"Is trimming requested or QC-only?",
"Which output directory should receive the timestamped run envelope?",
"Should outputs preserve the original FASTQs?"
]
},
"dna_variant_calling": {
"display_name": "DNA variant calling with nf-core/sarek",
"route_when": ["wgs", "wes", "targeted_panel", "variant_calling"],
"preferred_workflow": "nf-core/sarek",
"preferred_tools": ["nextflow", "samtools", "bcftools"],
"optional_tools": ["bwa-mem2", "gatk", "deepvariant"],
"local_executor": "plugins/ngs-analysis/scripts/run_dna_variant_calling.py",
"local_light_workflow": "direct_samtools_bcftools_bam_to_vcf",
"local_light_tools": ["samtools", "gatk", "bcftools"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"validation/samples.normalized.tsv",
"qc/*.flagstat.txt",
"qc/*.idxstats.tsv",
"variants/*.vcf.gz",
"variants/*.bcftools_stats.txt",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/vcf_review.marimo.py",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is this WGS, WES, or targeted panel data?",
"Is the analysis germline, tumor-only, tumor-normal, or trio?",
"Which reference genome and known-sites resources should be used?",
"For WES/panel, where is the target BED file?",
"Are UMIs present?",
"Should variants be annotated with VEP or SnpEff?"
]
},
"dna_germline_variants": {
"display_name": "Germline DNA variant calling",
"route_when": ["germline", "singleton", "cohort", "trio", "family", "inherited_panel"],
"preferred_workflow": "nf-core/sarek",
"preferred_tools": ["nextflow", "samtools", "bcftools"],
"optional_tools": ["bwa-mem2", "gatk", "deepvariant"],
"local_executor": "plugins/ngs-analysis/scripts/run_dna_germline_variants.py",
"local_light_workflow": "gatk_bqsr_haplotypecaller_joint_genotyping",
"local_light_tools": ["snakemake", "bwa-mem2", "samtools", "bcftools"],
"local_outputs": [
"run_manifest.json",
"validation/samples.normalized.tsv",
"qc/*.flagstat.txt",
"qc/*.idxstats.tsv",
"recal/*.recal.table",
"recal/*.recal.bam",
"gvcf/*.g.vcf.gz",
"joint/cohort.joint.vcf.gz",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/vcf_review.marimo.py",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is this WGS, WES, or targeted inherited-panel data?",
"Is the sample model singleton, cohort, duo, trio, or family?",
"Which reference build, known-sites resources, and annotation cache should be used?",
"For WES/panel, where are the target and bait BED files?",
"Should outputs be per-sample VCFs, gVCFs, or a jointly called cohort VCF?"
]
},
"dna_somatic_variants": {
"display_name": "Somatic DNA variant calling",
"route_when": ["somatic", "tumor_normal", "tumor_only", "cancer_panel"],
"preferred_workflow": "nf-core/sarek",
"preferred_tools": ["nextflow", "gatk", "samtools", "bcftools"],
"optional_tools": ["bwa-mem2", "deepvariant"],
"local_executor": "plugins/ngs-analysis/scripts/run_dna_somatic_variants.py",
"local_light_workflow": "gatk_mutect2_tumor_normal_or_tumor_only",
"local_light_tools": ["gatk", "samtools", "bcftools"],
"local_outputs": [
"run_manifest.json",
"validation/pairs.normalized.tsv",
"workflow/somatic_command_plan.json",
"qc/somatic_qc_summary.json",
"qc/somatic_filter_reasons.tsv",
"variants/*.unfiltered.vcf.gz",
"variants/*.filtered.vcf.gz",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/vcf_review.marimo.py",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is this tumor-normal, tumor-only, relapse-baseline, or another cancer design?",
"Where is the tumor-normal pairing table?",
"Which reference build, germline resource, panel-of-normals, and annotation cache should be used?",
"For WES/panel, where is the target BED file?",
"What allele-fraction, contamination, and tumor-purity constraints should be documented?"
]
},
"dna_umi_panel_variants": {
"display_name": "UMI-aware targeted DNA panel variant calling",
"route_when": ["umi_panel", "duplex_panel", "molecular_barcode", "low_frequency_panel"],
"preferred_tools": ["fastqc", "multiqc", "samtools", "bcftools"],
"optional_tools": ["fgbio", "bwa-mem2", "gatk"],
"local_executor": "plugins/ngs-analysis/scripts/run_dna_umi_panel_variants.py",
"local_light_workflow": "fgbio_consensus_plus_bcftools_panel_calling",
"local_light_tools": ["fgbio", "samtools", "bcftools"],
"local_outputs": [
"run_manifest.json",
"validation/samples.normalized.tsv",
"workflow/umi_panel_command_plan.json",
"qc/umi_consensus_plan.json",
"qc/umi_family_size_summary.tsv",
"consensus/*.bam",
"variants/*.consensus.vcf.gz",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/vcf_review.marimo.py",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Which panel or capture kit and target BED should be used?",
"Where are the UMIs encoded: read bases, index reads, single UMI, or duplex UMI?",
"Have consensus reads already been generated?",
"What minimum allele fraction and intended sensitivity should be documented?",
"Which controls or spike-ins should be carried through QC?"
]
},
"bulk_rnaseq": {
"display_name": "Bulk RNA-seq with nf-core/rnaseq",
"route_when": ["bulk_rnaseq", "expression_counts", "differential_expression"],
"preferred_workflow": "nf-core/rnaseq",
"preferred_tools": ["nextflow", "fastqc", "multiqc"],
"optional_tools": ["star", "salmon", "subread"],
"local_executor": "plugins/ngs-analysis/scripts/run_bulk_rnaseq_counts_qc.py",
"secondary_local_executor": "plugins/ngs-analysis/scripts/run_bulk_rnaseq_de.py",
"local_light_workflow": "snakemake_salmon_quant_plus_r_de",
"local_light_tools": ["snakemake", "fastqc", "multiqc", "salmon", "rscript"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"essential_questions": [
"What organism, genome FASTA, and GTF annotation should be used?",
"Is the library stranded, reverse-stranded, unstranded, or unknown?",
"Are reads paired-end or single-end?",
"Is the goal counts only or differential expression too?",
"If differential expression is needed, what is the sample metadata and contrast design?"
]
},
"bulk_rnaseq_counts_qc": {
"display_name": "Bulk RNA-seq count generation and QC",
"route_when": ["bulk_rnaseq_counts", "fastq_to_counts", "rnaseq_qc"],
"preferred_workflow": "nf-core/rnaseq",
"preferred_tools": ["nextflow", "fastqc", "multiqc"],
"optional_tools": ["star", "salmon", "subread"],
"local_executor": "plugins/ngs-analysis/scripts/run_bulk_rnaseq_counts_qc.py",
"local_workflow": "plugins/ngs-analysis/workflows/bulk_rnaseq_counts_qc/Snakefile.smk",
"local_light_workflow": "snakemake_salmon_quant",
"local_light_tools": ["snakemake", "fastqc", "multiqc", "salmon"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"validation/input_summary.json",
"validation/validation_summary.json",
"logs/snakemake_dry_run.log",
"logs/snakemake_execute.log",
"fastqc/multiqc/multiqc_browser_helper.html",
"rnaseq_salmon/multiqc/multiqc_browser_helper.html",
"visualizations/localhost_launch_hint.txt",
"rnaseq_salmon/matrices/tpm.tsv",
"rnaseq_salmon/matrices/num_reads.tsv",
"rnaseq_salmon/matrices/effective_length.tsv",
"rnaseq_salmon/matrices/samples.tsv",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"What organism, genome FASTA, and GTF annotation should be used?",
"Is strandedness known, unknown, or should it be inferred?",
"Are reads paired-end or single-end?",
"Should quantification produce gene counts, transcript estimates, or both?",
"Where is the sample metadata table that must carry into downstream analysis?"
]
},
"bulk_rnaseq_differential_expression": {
"display_name": "Bulk RNA-seq differential expression",
"route_when": ["differential_expression", "rnaseq_de", "counts_to_de"],
"preferred_tools": ["rscript"],
"local_executor": "plugins/ngs-analysis/scripts/run_bulk_rnaseq_de.py",
"local_workflow": "plugins/ngs-analysis/workflows/bulk_rnaseq_differential_expression/run_bulk_de.R",
"local_tools": ["Rscript"],
"local_r_packages": ["DESeq2", "edgeR", "limma"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"validation/input_summary.json",
"validation/validation_summary.json",
"logs/validation_dry_run.log",
"logs/rscript_execute.log",
"manifest/contrast_status.tsv",
"results/normalized_counts.tsv",
"results/log2_expression_matrix.tsv",
"results/<contrast>.tsv",
"qc/library_sizes.png",
"qc/pca.png",
"qc/sample_distance_heatmap.png",
"plots/<contrast>_volcano.png",
"plots/<contrast>_ma.png",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/bulk_rnaseq_de_review.marimo.py",
"notebooks/marimo_server.json",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Where are the raw count matrix and sample metadata?",
"What are the biological replicates, batch variables, donor pairing, and covariates?",
"What design formula and contrasts should be run?",
"Which statistical framework should be used: DESeq2, edgeR, limma-voom, or lab standard?",
"Which plots and result tables are required?"
]
},
"scrnaseq": {
"display_name": "Single-cell RNA-seq with public alternatives",
"route_when": ["scrnaseq_fastq", "snrnaseq_fastq", "single_cell_count_generation"],
"local_executor": "plugins/ngs-analysis/scripts/run_scrnaseq_fastq_to_count.py",
"preferred_workflow": "nf-core/scrnaseq",
"preferred_tools": ["nextflow"],
"local_workflow": "plugins/ngs-analysis/workflows/scrnaseq_fastq_to_count/Snakefile.smk",
"local_tools": ["snakemake", "star"],
"optional_tools": ["kb-python", "star", "cellranger"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"manifest/lineage.tsv",
"manifest/working_samplesheet.csv",
"manifest/inputs_manifest.tsv",
"validation/input_summary.json",
"validation/validation_summary.json",
"validation/tool_preflight.json",
"versions/software_versions.json",
"counts/*/Solo.out/Gene/raw/*",
"counts/*/Solo.out/Gene/filtered/*",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is the input raw FASTQ requiring count generation, or a post-count object that should route to scrna-seq-qc?",
"Which chemistry or barcode/UMI layout was used?",
"Is this single-cell or single-nucleus?",
"What organism and reference should be used?",
"Should the output stop at a count matrix, or continue to QC, clustering, annotation, and UMAPs?"
]
},
"scrnaseq_post_count_qc": {
"display_name": "scRNA-seq post-count QC, annotation, and UMAP",
"route_when": ["h5ad", "matrix", "cellranger_output", "single_cell_qc", "single_cell_annotation", "umap"],
"preferred_skill": "scrna-seq-qc",
"local_executor": "plugins/ngs-analysis/scripts/run_scrnaseq_post_count_qc.py",
"preferred_tools": ["scanpy"],
"local_light_tools": ["scanpy"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"manifest/lineage.tsv",
"validation/input_summary.json",
"validation/tool_preflight.json",
"versions/software_versions.json",
"qc/threshold_justification.png",
"qc/cell_qc_metrics.csv",
"tables/cell_qc_summary.tsv",
"annotation/cell_labels.csv",
"embeddings/umap_coords.csv",
"plots/umap_global.png",
"plots/umap_by_coarse_label.png",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"notebooks/scrna_qc_review.marimo.py",
"notebooks/marimo_server.json",
"analysis_with_flags.h5ad",
"filtered_view.h5ad",
"provenance/analysis_status.json",
"summary.md",
"artifact_index.json"
],
"essential_questions": [
"Where is the count matrix, h5ad, h5, rds, or Cell Ranger-style output?",
"Are raw counts preserved?",
"What organism, tissue, assay type, chemistry, and sample/channel metadata are available?",
"Should the endpoint include QC only, annotation, clustering, UMAPs, or downstream differential summaries?",
"Is there a matched reference atlas or should marker-based fallback annotation be used?"
]
},
"epigenomics_peaks": {
"display_name": "Epigenomics peak calling",
"route_when": ["atacseq", "chipseq", "cutandrun", "cutandtag", "peak_calling"],
"preferred_workflows": ["nf-core/atacseq", "nf-core/chipseq", "nf-core/cutandrun"],
"preferred_tools": ["nextflow", "fastqc", "multiqc", "macs2", "bedtools"],
"local_executor": "plugins/ngs-analysis/scripts/run_fastq_assay_package.py",
"local_executor_lane": "epigenomics_peaks",
"local_light_tools": ["seqkit", "fastqc", "multiqc"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"manifest/lineage.tsv",
"validation/samples.normalized.tsv",
"qc/seqkit_stats.tsv",
"fastqc/multiqc/multiqc_browser_helper.html",
"visualizations/localhost_launch_hint.txt",
"peak_calling_readiness.json",
"qc_verdict.json after successful execution",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is this ATAC-seq, ChIP-seq, CUT&RUN, or CUT&Tag?",
"What genome and blacklist should be used?",
"Are controls available, such as input DNA or IgG?",
"Are there biological replicates?",
"Is the desired output peaks, bigWigs, QC only, or differential accessibility/binding?"
]
},
"atacseq_peaks_qc": {
"display_name": "ATAC-seq QC and peak calling",
"route_when": ["atacseq", "accessibility", "differential_accessibility"],
"preferred_workflow": "nf-core/atacseq",
"preferred_tools": ["nextflow", "fastqc", "multiqc", "macs2", "bedtools", "deeptools"],
"optional_tools": ["homer"],
"local_executor": "plugins/ngs-analysis/scripts/run_atacseq_peaks_qc.py",
"read_qc_executor": "plugins/ngs-analysis/scripts/run_fastq_assay_package.py --lane epigenomics_peaks",
"local_light_workflow": "bowtie2_samtools_macs2_bedtools_deeptools",
"local_light_tools": ["samtools", "bowtie2", "macs2", "bedtools", "deeptools"],
"local_outputs": [
"run_manifest.json",
"validation/samples.normalized.tsv",
"workflow/atacseq_command_plan.json",
"qc/atac_qc_contract.json",
"qc/atacseq_qc_summary.tsv",
"qc/atacseq_qc_summary.json",
"qc/*.flagstat.txt",
"qc/*.frip_reads.txt",
"qc/*.insert_sizes.txt",
"qc/*.tss_matrix.gz",
"qc/*.tss_profile.png",
"qc/*.tss_heatmap.png",
"peaks/*.narrowPeak",
"peaks/consensus_peaks.bed",
"tracks/*.bw",
"tracks/browser_tracks.tsv",
"tracks/ucsc_track_lines.txt",
"tracks/igv_session.xml",
"motifs/motif_summary.tsv",
"visualizations/index.html",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"What genome build, blacklist, and mitochondrial contig names should be used?",
"Are there biological replicates, conditions, and batches?",
"Should outputs include QC only, peaks, consensus peaks, bigWigs, or differential accessibility?",
"Should Tn5 shifting be handled by the workflow?",
"Which QC gates are required: TSS enrichment, FRiP, insert-size periodicity, blacklist overlap, or replicate concordance?"
]
},
"chip_cutrun_peaks_qc": {
"display_name": "ChIP-seq, CUT&RUN, and CUT&Tag QC and peak calling",
"route_when": ["chipseq", "cutandrun", "cutandtag", "differential_binding"],
"preferred_workflows": ["nf-core/chipseq", "nf-core/cutandrun"],
"preferred_tools": ["nextflow", "fastqc", "multiqc", "macs2", "bedtools", "deeptools"],
"optional_tools": ["homer"],
"local_executor": "plugins/ngs-analysis/scripts/run_chip_cutrun_peaks_qc.py",
"read_qc_executor": "plugins/ngs-analysis/scripts/run_fastq_assay_package.py --lane epigenomics_peaks",
"local_light_workflow": "bowtie2_samtools_macs2_bedtools_deeptools",
"local_light_tools": ["samtools", "bowtie2", "macs2", "bedtools", "deeptools"],
"local_outputs": [
"run_manifest.json",
"validation/samples.normalized.tsv",
"workflow/chip_cutrun_command_plan.json",
"qc/chip_cutrun_qc_contract.json",
"qc/chip_cutrun_qc_summary.tsv",
"qc/chip_cutrun_qc_summary.json",
"qc/*.flagstat.txt",
"qc/*.frip_reads.txt",
"qc/*.insert_sizes.txt",
"peaks/*Peak",
"peaks/consensus_peaks.bed",
"tracks/*.bw",
"tracks/browser_tracks.tsv",
"tracks/ucsc_track_lines.txt",
"tracks/igv_session.xml",
"motifs/motif_enrichment_plan.json",
"motifs/motif_summary.tsv",
"visualizations/index.html",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Is this ChIP-seq, CUT&RUN, or CUT&Tag?",
"What target class is being profiled: TF, histone mark, chromatin regulator, or custom?",
"Are input DNA, IgG, no-antibody, or spike-in controls available?",
"Should peaks be called in narrow or broad mode?",
"Should outputs include peaks, bigWigs, consensus peaks, count matrices, or differential binding?"
]
},
"amplicon_microbiome": {
"display_name": "Amplicon microbiome analysis",
"route_when": ["amplicon_microbiome", "taxonomic_profile"],
"preferred_workflow": "nf-core/ampliseq",
"preferred_tools": ["nextflow"],
"optional_tools": ["qiime2", "dada2", "cutadapt"],
"local_executor": "plugins/ngs-analysis/scripts/run_amplicon_microbiome.py",
"read_qc_executor": "plugins/ngs-analysis/scripts/run_fastq_assay_package.py --lane amplicon_microbiome",
"local_light_tools": ["qiime2", "dada2", "cutadapt"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"manifest/lineage.tsv",
"validation/samples.normalized.tsv",
"qc/seqkit_stats.tsv",
"fastqc/multiqc/multiqc_browser_helper.html",
"visualizations/localhost_launch_hint.txt",
"amplicon_analysis_status.json",
"qc_verdict.json after successful execution",
"qc_interpretation.json after successful execution",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"methods/amplicon_methods.json",
"workflow/amplicon_backend_status.json",
"workflow/amplicon_backend_plan.json",
"workflow/amplicon_backend_command_plan.json",
"methods/amplicon_backend_methods.json",
"workflow/qiime2_manifest.tsv",
"qiime2/table.qza when --backend qiime2 executes",
"qiime2/taxonomy.qza when a taxonomy classifier is provided",
"dada2/dada2_backend_state.rds when --backend dada2 executes",
"tables/alpha_diversity.tsv when --asv-table is provided",
"tables/asv_table.tsv or exported ASV table after backend execution",
"tables/representative_sequences.fasta when --backend dada2 executes",
"visualizations/beta_diversity_pcoa_bray_curtis.png when --asv-table has at least two matched samples or --allow-synthetic-diversity is set",
"visualizations/taxa_barplot_<rank>.png when --taxonomy-table is provided",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Which marker was sequenced: 16S, 18S, ITS, COI, or another amplicon?",
"What primer sequences and orientation were used?",
"Are reads paired-end and should they be merged?",
"Which taxonomy database should be used?",
"Is the goal ASV table only or diversity/statistical analysis too?"
]
},
"shotgun_metagenomics": {
"display_name": "Shotgun metagenomics profiling",
"route_when": ["shotgun_metagenomics", "taxonomic_profile", "functional_profile"],
"preferred_workflow": "nf-core/taxprofiler",
"preferred_tools": ["nextflow", "kraken2", "bracken"],
"optional_tools": ["kneaddata", "metaphlan", "humann"],
"local_executor": "plugins/ngs-analysis/scripts/run_shotgun_metagenomics.py",
"read_qc_executor": "plugins/ngs-analysis/scripts/run_fastq_assay_package.py --lane shotgun_metagenomics",
"local_light_tools": ["kraken2", "bracken", "kneaddata", "humann"],
"run_envelope_schema": "plugins/ngs-analysis/references/run-envelope-schema.json",
"local_outputs": [
"run_manifest.json",
"manifest/lineage.tsv",
"validation/samples.normalized.tsv",
"qc/seqkit_stats.tsv",
"fastqc/multiqc/multiqc_browser_helper.html",
"visualizations/localhost_launch_hint.txt",
"qc_verdict.json after successful execution",
"qc_interpretation.json after successful execution",
"taxonomic_classification_status.json",
"workflow/shotgun_backend_command_plan.json",
"qc/metagenomics_database_status.json",
"host_depletion/ when --host-reference executes",
"taxonomic_classification/*.kraken.report",
"taxonomic_classification/*.bracken.tsv",
"functional_profile/ when --run-humann executes",
"visualizations/index.html",
"visualizations/visualization_manifest.json",
"visualizations/kraken_top_taxa_barplot.png when Kraken reports are available",
"visualizations/bracken_relative_abundance_heatmap.png when Bracken tables are provided",
"visualizations/humann_pathway_heatmap.png when HUMAnN pathabundance is provided",
"visualizations/humann_gene_family_heatmap.png when HUMAnN genefamilies is provided",
"artifact_index.json",
"summary.md"
],
"essential_questions": [
"Should host reads be removed, and what host reference should be used?",
"Is the goal taxonomic profiling, functional profiling, assembly, or all of these?",
"Which database family should be used: Kraken2/Bracken, MetaPhlAn, HUMAnN, or custom?",
"Are reads paired-end or single-end?",
"Are there negative controls or batch variables that should be carried into QC?"
]
}
}
}
SHA-256: 637cacb20832184f47450a2d3246719ab633302f8334bc6e8eb49659675cc549