[study] ZWU2022_VIBRIO_TIMECOURSE (PRJNA852380)

config/ZWU2022_VIBRIO_TIMECOURSE.config

@@ -0,0 +1,66 @@
+/*
+ * AREE :: run configuration for ZWU2022_VIBRIO_TIMECOURSE (PRJNA852380)
+ *
+ * Deposited by Zhejiang Wanli University, no publication found. 9-month-old
+ * intertidal oysters (Qingdao), digestive gland; untreated controls and
+ * oysters 1, 3, 6, 12 and 24 h after Vibrio exposure, three libraries per
+ * group. Vibrio species, dose and route are not in the deposit.
+ *
+ * Five prespecified comparisons, each time point vs the untreated controls.
+ * Default = the meta_analysis_primary one (24 h):
+ *
+ *   nextflow run workflows/rnaseq -config config/ZWU2022_VIBRIO_TIMECOURSE.config \
+ *     -profile local,workstation
+ *
+ *   --comparison_id vibrio_12h_vs_control --treatment_level V12h
+ *   --comparison_id vibrio_6h_vs_control  --treatment_level V6h
+ *   --comparison_id vibrio_3h_vs_control  --treatment_level V3h
+ *   --comparison_id vibrio_1h_vs_control  --treatment_level V1h
+ *
+ *   aree fetch-samplesheet --bioproject PRJNA852380 --study ZWU2022_VIBRIO_TIMECOURSE \
+ *     --label-field sample_alias \
+ *     --label-pattern '^(?P<group>control|V1h|V3h|V6h|V12h|V24h)_?(?P<replicate>[1-3])$' \
+ *     --condition-attribute group --attribute replicate --attribute isolate --attribute tissue \
+ *     --attribute age --attribute isolation_source --attribute collection_date
+ */
+
+includeConfig 'base.config'
+
+params {
+    mode = 'raw_reanalysis'
+
+    rnaseq {
+        study_id           = 'ZWU2022_VIBRIO_TIMECOURSE'
+        // Null so --comparison_id on the command line takes effect.
+        comparison_id      = null
+        genome_assembly    = 'GCF_963853765.1'
+        annotation_version = 'GCF_963853765.1-RS_2024_06'
+        processed_results  = null
+    }
+
+    comparison_id = 'vibrio_24h_vs_control'
+
+    sample_sheet = 'data/studies/ZWU2022_VIBRIO_TIMECOURSE/samplesheet.tsv'
+
+    control_level   = 'control'
+    treatment_level = 'V24h'
+
+    // FASTQ are not committed (59 GB for all 18 runs). Verify against ENA's MD5s
+    // from data/studies/ZWU2022_VIBRIO_TIMECOURSE/fastq_manifest.tsv.
+    reads = 'data/raw/ZWU2022_VIBRIO_TIMECOURSE/SRR*_{1,2}.fastq.gz'
+
+    transcript_fasta = 'data/reference/GCF_963853765.1/rna.fna'
+    gtf              = 'data/reference/GCF_963853765.1/genomic.gtf'
+    tx2gene          = 'data/reference/GCF_963853765.1/tx2gene.tsv'
+    salmon_index     = null
+
+    outdir = 'results/rnaseq/ZWU2022_VIBRIO_TIMECOURSE'
+}
+
+process {
+    // 18 HiSeq X Ten 2x150 libraries, 20.6-27.6 M read pairs. Sized for a 16 GB machine.
+    withName: 'SALMON_INDEX' { cpus = 8;  memory = '12 GB'; time = '4h'  }
+    withName: 'SALMON_QUANT' { cpus = 8;  memory = '12 GB'; time = '2h'  }
+    withName: 'TRIM_FASTP'   { cpus = 4;  memory = '8 GB';  time = '2h'  }
+    withName: 'FASTQC'       { cpus = 2;  memory = '4 GB';  time = '1h'  }
+}

data/studies/ZWU2022_VIBRIO_TIMECOURSE/ZWU2022_VIBRIO_TIMECOURSE_vibrio_12h_vs_control_workflow_manifest.json

@@ -0,0 +1,109 @@
+{
+  "workflow_name": "aree-rnaseq",
+  "workflow_version": "0.1.0-scaffold",
+  "mode": "raw_reanalysis",
+  "study_id": "ZWU2022_VIBRIO_TIMECOURSE",
+  "comparison_id": "vibrio_12h_vs_control",
+  "input_files": [
+    {
+      "name": "ZWU2022_VIBRIO_TIMECOURSE_vibrio_12h_vs_control_dge_standardized.tsv",
+      "sha256": "b859f699cec7ac7e68671c7fc2d822c2276b3561d62c26af901c9eea3dd3d96f"
+    }
+  ],
+  "parameters": {
+    "mode": "raw_reanalysis",
+    "study_id": "ZWU2022_VIBRIO_TIMECOURSE",
+    "comparison_id": "vibrio_12h_vs_control",
+    "outdir": "results/rnaseq/ZWU2022_VIBRIO_TIMECOURSE",
+    "exclude_samples": [],
+    "control_levels": [
+      "control"
+    ],
+    "treatment_levels": [
+      "V12h"
+    ],
+    "replicate_unit": null,
+    "covariates": [],
+    "single_end": false,
+    "se_adapter": null,
+    "tag_seq": false,
+    "viral_reference": null
+  },
+  "deseq2_design": {
+    "design": "~condition",
+    "covariates_requested": [],
+    "covariates_used": [],
+    "covariates_dropped_constant": [],
+    "tag_seq": false,
+    "length_model": "tximport average transcript length offsets",
+    "n_libraries_or_units": 6,
+    "residual_df": 4
+  },
+  "software_versions": {
+    "DIFFERENTIAL_EXPRESSION_DESEQ2": {
+      "bioconductor-deseq2": "1.42.1",
+      "bioconductor-tximport": "1.30.0",
+      "r-base": "4.3.2"
+    },
+    "FASTQC": {
+      "fastqc": "0.12.1"
+    },
+    "SALMON_INDEX": {
+      "salmon": "2.3.4"
+    },
+    "SALMON_QUANT": {
+      "salmon": "2.3.4"
+    },
+    "SAMPLE_QC": {
+      "multiqc": "1.9"
+    },
+    "STANDARDIZE_OUTPUT": {
+      "pandas": "2.3.3",
+      "python": "3.9.6"
+    },
+    "TRIM_FASTP": {
+      "fastp": "1.3.6"
+    },
+    "EMIT_MANIFEST": {
+      "python": "3.9.6"
+    }
+  },
+  "software_versions_not_captured": {
+    "RENDER_REPORT": "renders this manifest, so it runs afterwards; its versions.yml is published to rnaseq/reports/"
+  },
+  "container_engine": null,
+  "reference": {
+    "genome_assembly": "GCF_963853765.1",
+    "annotation_version": "GCF_963853765.1-RS_2024_06",
+    "transcript_fasta": "data/reference/GCF_963853765.1/rna.fna",
+    "gtf": "data/reference/GCF_963853765.1/genomic.gtf",
+    "tx2gene": "data/reference/GCF_963853765.1/tx2gene.tsv",
+    "salmon_index": null,
+    "files": [
+      {
+        "name": "genomic.gtf",
+        "sha256": "ab5443f889932ef3e860d47e23801dd94a2b6a4a508f807e0349dfaccea79600"
+      },
+      {
+        "name": "rna.fna",
+        "sha256": "297d49baac2fd3187db957c3dcd150e58ed2a61c3867b61dbdd83ba9b683c386"
+      },
+      {
+        "name": "tx2gene.tsv",
+        "sha256": "170cae75beb05c1afd9b7b3dbed4bdeb4225c16f9aab757ccc00c2b449092d18"
+      }
+    ],
+    "bundle": null
+  },
+  "workflow_start": "2026-10-16T20:13:54.448549-07:00",
+  "qc_metrics": {
+    "mean_reads_per_sample": null,
+    "mean_mapping_rate_percent": null,
+    "n_samples": null,
+    "note": "QC metrics are not populated in processed_results_harmonization mode or in this unexecuted scaffold run."
+  },
+  "viral_load": null,
+  "warnings": [
+    "reference_bundle_provenance_missing: no reference_provenance.json beside the reference files; fetch them with `aree fetch-reference` to record where they came from"
+  ]
+}