[study] LI2018_HEAT_TIDAL (PRJNA407831)

config/LI2018_HEAT_TIDAL.config

@@ -0,0 +1,82 @@
+/*
+ * AREE :: run configuration for LI2018_HEAT_TIDAL (PRJNA407831)
+ *
+ * Li et al. 2018, Front Physiol 9:825 (doi:10.3389/fphys.2018.00825).
+ * Common-garden F1 of four wild populations (Bayuquan, Laoting x intertidal
+ * J / subtidal X), three tanks each, 35 C seawater for 24 h; gill of five
+ * oysters per tank pooled into one library at 0, 6 and 24 h (36 libraries).
+ *
+ * Three prespecified comparisons. Default = the meta_analysis_primary one:
+ *
+ *   nextflow run workflows/rnaseq -config config/LI2018_HEAT_TIDAL.config \
+ *     -profile local,workstation
+ *
+ *   # heat, 6 h
+ *   --comparison_id heat_35c_6h_vs_0h \
+ *     --control_level BYQ_J_0,BYQ_X_0,LT_J_0,LT_X_0 --treatment_level BYQ_J_6,BYQ_X_6,LT_J_6,LT_X_6
+ *
+ *   # constitutive difference, thermally tolerant (intertidal) vs sensitive
+ *   # (subtidal) populations before heating, fitted on populations
+ *   --comparison_id intertidal_vs_subtidal_0h \
+ *     --control_level BYQ_X_0,LT_X_0 --treatment_level BYQ_J_0,LT_J_0 --replicate_unit population
+ *
+ * The sample sheet comes from the deposited sample aliases (e.g. BYQJ241 =
+ * Bayuquan, J, 24 h, tank 1):
+ *
+ *   aree fetch-samplesheet --bioproject PRJNA407831 --study LI2018_HEAT_TIDAL \
+ *     --label-field sample_alias \
+ *     --label-pattern '^(?P<population>(?P<site>BYQ|LT)(?P<zone>J|X))(?P<hours>0|6|24)(?P<tank>[1-3])$' \
+ *     --condition-attribute site --condition-attribute zone --condition-attribute hours \
+ *     --attribute population --attribute tank --attribute isolate --attribute temp \
+ *     --attribute specimen_voucher --attribute geo_loc_name --attribute tissue
+ */
+
+includeConfig 'base.config'
+
+params {
+    mode = 'raw_reanalysis'
+
+    rnaseq {
+        study_id           = 'LI2018_HEAT_TIDAL'
+        // Null so --comparison_id on the command line takes effect (the
+        // workflow prefers params.rnaseq.comparison_id over the flat param).
+        comparison_id      = null
+        genome_assembly    = 'GCF_963853765.1'
+        annotation_version = 'GCF_963853765.1-RS_2024_06'
+        processed_results  = null
+    }
+
+    comparison_id = 'heat_35c_24h_vs_0h'
+
+    sample_sheet = 'data/studies/LI2018_HEAT_TIDAL/samplesheet.tsv'
+
+    // All four populations pooled in each arm (3 tanks each; 0 h has 11).
+    control_level   = 'BYQ_J_0,BYQ_X_0,LT_J_0,LT_X_0'
+    treatment_level = 'BYQ_J_24,BYQ_X_24,LT_J_24,LT_X_24'
+
+    // LT-I_0h_2, discarded by the authors as an outlier ("One sample of
+    // LT-I_0h_2 was used as an outlier and was abandoned"), is alias LTJ02.
+    // Prespecified for every comparison; outside a comparison's arms it has no effect.
+    exclude_samples = 'LTJ02'
+
+    // FASTQ are not committed (94.1 GB for all 36 runs). Verify against ENA's MD5s:
+    //   awk -F'\t' 'NR>1 {print $4"  "$1"_"$2".fastq.gz"}' \
+    //     data/studies/LI2018_HEAT_TIDAL/fastq_manifest.tsv > md5sums.txt && md5sum -c md5sums.txt
+    reads = 'data/raw/LI2018_HEAT_TIDAL/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/LI2018_HEAT_TIDAL'
+}
+
+process {
+    // 36 HiSeq paired-end libraries (125/150 bp), 13.4-16.7 M read pairs each.
+    // Sized to fit 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/LI2018_HEAT_TIDAL/LI2018_HEAT_TIDAL_heat_35c_24h_vs_0h_workflow_manifest.json

@@ -0,0 +1,86 @@
+{
+  "workflow_name": "aree-rnaseq",
+  "workflow_version": "0.1.0-scaffold",
+  "mode": "raw_reanalysis",
+  "study_id": "LI2018_HEAT_TIDAL",
+  "comparison_id": "heat_35c_24h_vs_0h",
+  "input_files": [
+    {
+      "name": "LI2018_HEAT_TIDAL_heat_35c_24h_vs_0h_dge_standardized.tsv",
+      "sha256": "7ee0991017e13382766947990bd276595058d2c3c1ea4342c9e5da5d712b516b"
+    }
+  ],
+  "parameters": {
+    "mode": "raw_reanalysis",
+    "study_id": "LI2018_HEAT_TIDAL",
+    "comparison_id": "heat_35c_24h_vs_0h",
+    "outdir": "results/rnaseq/LI2018_HEAT_TIDAL",
+    "exclude_samples": [
+      "LTJ02"
+    ],
+    "control_levels": [
+      "BYQ_J_0",
+      "BYQ_X_0",
+      "LT_J_0",
+      "LT_X_0"
+    ],
+    "treatment_levels": [
+      "BYQ_J_24",
+      "BYQ_X_24",
+      "LT_J_24",
+      "LT_X_24"
+    ],
+    "replicate_unit": null,
+    "single_end": false,
+    "se_adapter": null,
+    "viral_reference": null
+  },
+  "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"
+  },
+  "workflow_start": "2026-10-12T23:07:53.333627-07:00",
+  "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": [
+    "samples_excluded_by_curation: LTJ02 (see the study registry for the reason)"
+  ]
+}