{
  "title": "MMAPPR positive control — reference parameter manifest (maize gl13)",
  "purpose": "Independent MMAPPR2 reference for validating Haritica's MMAPPR page. Everything needed to fully recreate the reference, and the exact parameters a later Haritica run must match for a faithful comparison. The Haritica side is produced separately by the user after editing the MMAPPR page.",
  "dataset": {
    "accession": "PRJNA622294",
    "citation": "Li L, et al. The maize glossy13 gene, cloned via BSR-Seq and Seq-walking, encodes a putative ABC transporter required for the normal accumulation of epicuticular waxes. PLoS ONE 2013;8(12):e82333 (PMC3855708). RNA-seq reads deposited under BioProject PRJNA622294.",
    "organism": "Zea mays (maize), B73 reference",
    "design": "bulk-segregant pooled RNA-seq (BSR-Seq): for each of 3 independent EMS alleles, a glossy-mutant pool vs a wild-type-sibling pool",
    "layout": "paired-end ~101 bp, Illumina, RNA-Seq",
    "note": "Third-party dataset (Schnable lab gl13 study), independent of both MMAPPR2 and Haritica. THREE independent allele families all map to the same causal gene on chromosome 3 -> a triple positive control.",
    "expected_peak_chromosome": "3",
    "ground_truth_gene": {
      "symbol": "gl13 (glossy13)",
      "v3_id": "GRMZM2G118243",
      "function": "putative ABCG-subfamily ABC transporter (ortholog of Arabidopsis AtABCG32 / barley HvABCG31 / rice OsABCG31); epicuticular wax accumulation",
      "chr": "3",
      "agpv2_interval": "chr3:10,272,500-10,283,828 (B73 RefGen_v2 / AGPv2, per the cloning paper)",
      "validation": "multiple EMS alleles bearing premature termination codons + one knockout allele (Li et al. 2013)",
      "build_note": "This run aligns to B73 NAM-5.0 (v5); chromosome assignment (chr3) is build-robust. The exact v5 coordinate of the gl13 model is read from MMAPPR2's candidate table for the chr3 peak (generateCandidates on the v5 GTF)."
    },
    "families": {
      "N211B":        {"mutant_pool": "SRR11457982", "wildtype_pool": "SRR11457981"},
      "94-1001-1481": {"mutant_pool": "SRR11457984", "wildtype_pool": "SRR11457983"},
      "2-207-44":     {"mutant_pool": "SRR11457986", "wildtype_pool": "SRR11457985"}
    },
    "ena_md5_paired": {
      "SRR11457981": {"_1": "96afe30164945162db253d148f39ceaf", "_2": "194c36729c247841be487e8d3c105925"},
      "SRR11457982": {"_1": "ee4cd14ab307dd9368177aebda15903c", "_2": "57e3f500aa1b869186875f887dcf7d26"},
      "SRR11457983": {"_1": "46a19b3f23d8be89c7e503d9988cecf3", "_2": "3328ede1dc1d1598a21ae88c6180c10b"},
      "SRR11457984": {"_1": "65fe78d4d6c904eb908f1353cfab9497", "_2": "b5df841f8092b71d90c932ac36e04867"},
      "SRR11457985": {"_1": "77fbae6cd0ca31eb2c39b1b1184fbea9", "_2": "152d16533524986f2f58d3c415007ead"},
      "SRR11457986": {"_1": "84cc21cf9d56648489aa0b161d65f22f", "_2": "cc9d199b9f2f65f980e219666935f6ae"}
    }
  },
  "reference_genome": {
    "build": "B73 Zm-B73-REFERENCE-NAM-5.0 (v5), Ensembl Plants release-62",
    "fasta_url": "https://ftp.ebi.ac.uk/ensemblgenomes/pub/plants/release-62/fasta/zea_mays/dna/Zea_mays.Zm-B73-REFERENCE-NAM-5.0.dna.toplevel.fa.gz",
    "gtf_url": "https://ftp.ebi.ac.uk/ensemblgenomes/pub/plants/release-62/gtf/zea_mays/Zea_mays.Zm-B73-REFERENCE-NAM-5.0.62.gtf.gz",
    "note": "Chromosomes named 1-10 (+ scaf_* scaffolds, trimmed by MMAPPR2 includeScaffolds=FALSE)."
  },
  "alignment": {
    "tool": "HISAT2 2.2.1 (splice-aware paired-end RNA-seq aligner; GPL-3, run as a separate alignment tool, not bundled into Haritica)",
    "rationale": "Splice-aware PE aligner for ~101 bp RNA-seq. A basic index is built on the instance (genome not pre-staged); HISAT2 discovers junctions de novo and MMAPPR2's pileup uses simpleCigar=TRUE (junction reads excluded), so what matters is correct exonic placement. Shared BAMs let a later Haritica run (BAM mode) use identical alignments.",
    "index": "hisat2-build (basic, -p 96), built on the instance from the v5 FASTA"
  },
  "reference_tool": {
    "name": "MMAPPR2",
    "source": "github.com/jonathonthill/MMAPPR2",
    "commit": "37a5d0000d3484f44eef7f4328fd69531f0cecbe",
    "license": "GPL-3",
    "variant_caller": "Rsamtools::pileup (simpleCigar=TRUE; gmapR-free fork, refGenome is an Rsamtools FaFile)",
    "docker_image": "bioconductor/bioconductor_docker (RELEASE_3_20/3_21)",
    "licensing_note": "MMAPPR2 (GPL-3) is RUN only, as a separate reference tool on AWS, to generate reference numbers/figures. No MMAPPR2 source is copied or ported into closed-source Haritica. Posture identical to the DE control running GPL R DESeq2."
  },
  "mmappr2_parameters": {
    "minDepth": 20, "homozygoteCutoff": 0.95, "minBaseQuality": 20, "minMapQuality": 20,
    "fileAggregation": "simple", "distancePower": 4, "peakIntervalWidth": 0.80,
    "loessOptResolution": 0.001, "loessOptCutFactor": 0.1, "includeScaffolds": false,
    "algorithm": "per-position Euclidean distance across [A,C,G,T] pool allele frequencies ^ distancePower; per-chromosome AICc-optimized Loess (R loess family=symmetric, real trace.hat); prePeak (mean of per-chromosome fitted means + 3*summed-variance SE; >=50 SNPs/chr); peakRefinement (1000-replicate 50% subsample -> Loess refit -> KDE of argmax -> highest-density-region CI at peakIntervalWidth)"
  },
  "haritica_run_to_match_later": {
    "note": "Settings to configure on the Haritica MMAPPR page so the later plots are a faithful comparison.",
    "input_mode": "bam (feed the shared maize BAMs at s3://haritica-dev-references-107153401336/mmappr-poscontrol/bam/, aligned with HISAT2) OR fastq with a maize B73 NAM-5.0 reference",
    "reference_genome": "maize B73 NAM-5.0 (custom genome; not in Haritica's default catalog)",
    "ed_power": 4, "homozygote_cutoff": 0.95, "min_depth": 20, "min_base_quality": 20, "min_map_quality": 20,
    "pools": "Run each family: N211B (WT SRR11457981 vs MUT SRR11457982); 94-1001-1481 (WT SRR11457983 vs MUT SRR11457984); 2-207-44 (WT SRR11457985 vs MUT SRR11457986). All expect chr3."
  },
  "compute": {
    "provider": "AWS EC2 (account 107153401336, us-east-1)",
    "instance_type": "m6i.16xlarge (64 vCPU / 256 GB) on-demand, self-terminating, 250 GB gp3 (largest guaranteed non-Spot size at the 64-vCPU on-demand quota)",
    "ami": "ami-0521cb2d60cfbb1a6 (Amazon Linux 2023)",
    "rationale": "MMAPPR2 is computationally expensive (genome-wide pileup on the 2.4 Gb maize genome + per-chromosome AICc-Loess + 1000-replicate bootstrap), run for 3 families in parallel."
  }
}