{ "specification": { "reference": "TK1151/GWHBCHF-derived display reference; VCF Chr01-08 preserved in source, numeric derivative chr1-8", "source_VCF": "/home/whj/rubber_dandelion_omics/build_runtime/resequencing_variants_CRA009020_20260829/variants/CRA009020_TK1151.pass.vcf.gz", "samples_before_QC": 126, "trait": "natural rubber content %", "source_phenotype": "Yang et al. 2023 additional workbook Table S7 column C", "sample_evidence": "128 exact unique counts; 2 parents excluded; R09 unconfirmed excluded", "population": "one biparental F1 family; exploratory additive association", "QC": { "biallelic_SNPs_only": true, "chromosomes": [ 1, 2, 3, 4, 5, 6, 7, 8 ], "minimum_sample_genotype_DP": 5, "maximum_variant_missingness": 0.1, "minimum_MAF": 0.05, "maximum_sample_missingness": 0.15, "HWE_filter": "not applied to F1 family", "LD_pruning": { "window_kb": 50, "step_variants": 5, "r2": 0.2 }, "minimum_observed_genotype_classes": 2, "reason": "F1 fixed heterozygosity may have MAF0.5 but no dosage variability; exclude unidentifiable effects before association fitting" }, "models": { "GLM": "PLINK1.9 additive linear model; intercept + PC1-PC3", "MLM": "GCTA MLMA; additive effect + intercept + PC1-PC3 + genomic relationship random effect" }, "shared_inputs": "same final QC markers/samples; PCA/kinship built once; GRM from LD-pruned set", "thresholds": { "Bonferroni": "0.05/number of valid tests per model", "suggestive": "1/number of valid tests", "BH_FDR": "q<=0.05 reported separately" }, "resource_request": { "scheduler": "Slurm normal", "cpus": 2, "memory_GiB": 4, "GPU": false }, "source_inputs_read_only": true, "scientific_limits": [ "Read-count supported material identity; author bin genotype consistency unresolved", "Single family, limited population extrapolation; association is not causation", "Mean phenotype only; raw replicates/environment details unavailable" ], "planned_validation": [ "VCF/phenotype exact sample strings, exclusion policy and source hashes", "post-QC final sample/marker calls/alleles", "sample order identical for PCA, GRM and both models", "compare selected independent regressions/model effect/p-value calculations", "QQ/calibration, phenotype residuals, valid p-values, true n", "plots align with complete downloadable statistics", "real public queries/downloads/bilingual rendered desktop/mobile" ] }, "actual_run": { "samples": 126, "QC_SNPs": 1109918, "per_chr_QC_counts": { "1": 188379, "2": 159241, "3": 164713, "4": 127504, "5": 109120, "6": 128372, "7": 131783, "8": 102199 }, "final_sample_ids": [ "F1-1", "F1-2", "F1-5", "F1-6", "F1-7", "F1-8", "F1-9", "F1-11", "F1-12", "F1-13", "F1-15", "F1-16", "F1-18", "F1-19", "F1-20", "F1-21", "F1-26", "F1-29", "F1-30", "F1-31", "F1-32", "F1-33", "F1-34", "F1-36", "F1-37", "F1-38", "F1-40", "F1-41", "F1-42", "F1-43", "F1-44", "F1-45", "F1-46", "F1-48", "F1-49", "F1-51", "F1-53", "F1-55", "F1-56", "F1-58", "F1-61", "F1-62", "F1-63", "F1-64", "F1-65", "F1-66", "F1-68", "F1-71", "F1-72", "F1-73", "F1-74", "F1-75", "F1-76", "F1-77", "F1-78", "F1-79", "F1-80", "F1-81", "F1-82", "F1-83", "F1-84", "F1-85", "F1-86", "F1-87", "F1-88", "F1-89", "F1-90", "F1-91", "F1-92", "F1-93", "F1-94", "F1-95", "F1-96", "F1-97", "F1-98", "F1-99", "F1-100", "F1-101", "F1-102", "F1-103", "F1-104", "F1-105", "F1-106", "F1-107", "F1-108", "F1-109", "F1-110", "F1-111", "F1-112", "F1-113", "F1-114", "F1-115", "F1-116", "F1-117", "F1-118", "F1-119", "F1-120", "F1-121", "F1-122", "F1-123", "F1-124", "F1-125", "F1-126", "F1-127", "F1-128", "F1-129", "F1-130", "F1-131", "F1-132", "F1-133", "F1-134", "F1-135", "F1-136", "F1-137", "F1-138", "F1-139", "F1-140", "F1-141", "F1-142", "F1-143", "F1-144", "F1-145", "F1-146", "F1-147", "F1-148", "F1-149" ], "pruned_SNPs": 434572, "models": [ "GLM", "MLM" ], "source_VCF": "/home/whj/rubber_dandelion_omics/build_runtime/resequencing_variants_CRA009020_20260829/variants/CRA009020_TK1151.pass.vcf.gz", "source_VCF_bytes": 18246511770, "finished_at": "2026-10-14T11:15:50.722643+08:00", "variant_QC": "DP>=5; missing<=0.1; MAF>=0.05; biallelic SNP Chr01-08", "sample_QC": "missing<=0.15", "covariates": [ "PC1", "PC2", "PC3" ], "kinship": "GCTA standardized GRM from LD-pruned markers", "identity_policy": "unique exact FASTQ reads correspondence; parents/R09 excluded; author bin input unresolved", "actual_scheduler_allocation": { "job_id": "154", "cpus": "12", "memory_MB": "6144", "GPU": false, "QC_workers": 6 }, "dosage_variability_QC": { "markers_before": 1111311, "nonsegregating_dosage_removed": 1393, "markers_after": 1109918, "criterion": "at least2 observed diploid genotype classes; constant heterozygosity excluded; no phenotype based selection" }, "original_source_full_checksum": { "source_path": "/home/whj/rubber_dandelion_omics/build_runtime/resequencing_variants_CRA009020_20260829/variants/CRA009020_TK1151.pass.vcf.gz", "source_bytes": 18246511770, "source_sha256": "68da4ddabaff5358462c23f69f71eb6980c4faff0c2666415e0e8b6d89a719bc", "source_stat_unchanged": true, "aligned_native_first_block_equal": true, "elapsed_seconds": 3611.4901111125946 } }, "software": { "plink19": "PLINK v1.90b7.2 64-bit (11 Dec 2023)\n", "gcta": "*******************************************************************\n* Genome-wide Complex Trait Analysis (GCTA)\n* version v1.95.1 Linux\n* Built at Feb 2 2026 16:51:42, by GCC 8.4\n* (C) 2010-present, Yang Lab, Westlake University\n* Please report bugs to Jian Yang \n*******************************************************************\nAnalysis started at 09:07:41 CST on Wed Oct 14 2026.\nHostname: SuperServer\n\nWarning: Warning: No output file specified. Using default output file 'output'.\nAccepted options:\nError: \n invalid option \"--version\".\n\nAn error occurs, please che", "bcftools": "bcftools 1.13\nUsing htslib 1.13+ds\nCopyright (C) 2021 Genome Research Ltd.\nLicense Expat: The MIT/Expat license\nThis is free software: you are free to change and redistribute it.\nThere is NO WARRANTY, to the extent permitted by law.\n" }, "raw_result_columns": { "GLM": [ "CHR", "SNP", "BP", "A1", "TEST", "NMISS", "BETA", "SE", "L95", "U95", "STAT", "P" ], "MLM": [ "Chr", "SNP", "bp", "A1", "A2", "Freq", "b", "se", "p" ] }, "gene_annotation": { "source": "/home/whj/rubber_dandelion_omics/build_runtime/resequencing_variants_CRA009020_20260829/variants/CRA009020_gene_variants.sqlite3", "reference": "TK1151", "gene_records": 45224, "nearest_gene_definition": "overlapping gene interval, else minimum distance to stored interval boundary; proximity only", "source_coordinate_export": "reference_gene_coordinates.tsv inside workflow.zip", "coordinate_export_SHA256": "dc45eb73fa30746f11ef9ccd4aefafa637c8c3f8f853bcc593f1e5e3b4489121" }, "site_interpretation": "single-family exploratory association; author bin genotype consistency remains unresolved", "threshold_display_revision": { "default": "screening", "p_threshold": 0.0001, "minus_log10_p": 4.0, "basis": "user-specified fixed exploratory screening threshold", "empirical_calibration_performed": false, "original_association_values_unchanged": true, "retained_references": [ "suggestive 1/M", "Bonferroni 0.05/M", "BH FDR q<=0.05" ] }, "candidate_gene_policy": { "p_threshold": 0.0001, "gene_assignment": "reuse existing nearest / overlapping gene mapping, exact native IDs and gene coordinates", "unique_union_genes": 206, "genes_supported_by_both_models": 131, "not_causal_validation": true, "no_LD_window_invented": true, "source_annotation_verified": true } }