From 42c09af7e94b699cbdfbe061fa962683636b0cd6 Mon Sep 17 00:00:00 2001 From: Dave Rogers Date: Mon, 9 Nov 2026 19:16:10 -0800 Subject: [PATCH 1/3] Give HPRC_R2's gaps and T2T chromosome tables a data type (#765) AnVIL_HPRC_R2's gaps BEDs and t2t_chromosomes.tsv files (462 each) had no data_type: their value-map rows were seeded and declared nothing. Both now declare `annotations`, scoped to AnVIL_HPRC_R2 because `gaps` and `sequences` are generic words. HPRC files both under each assembly's annotation/chrom_assignment/ folder, and the HPRC Data Explorer's catalog lists them as "ChromAlias Gaps" and "ChromAlias T2T". The GenomeAnnotationActivity reason now names them among the kinds it covers. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01VF7tbFa5ZTmYWZ6JWKiBBS Co-authored-by: cc-claude-tools --- src/meta_disco/rules/activities.yaml | 2 +- src/meta_disco/rules/value_map.yaml | 15 +++++++++++++++ tests/test_value_map.py | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-) diff --git a/src/meta_disco/rules/activities.yaml b/src/meta_disco/rules/activities.yaml index 828234f8..983495d6 100644 --- a/src/meta_disco/rules/activities.yaml +++ b/src/meta_disco/rules/activities.yaml @@ -190,7 +190,7 @@ activities: reason: >- Features found in one genome sequence and written in its own coordinates (HPRC_R2's RepeatMasker, centromeric satellite, segmental duplication and liftoff gene annotations of - each assembly, #682) describe that sequence, so they take every dimension but their own + each assembly, #682, and its gaps and telomere-to-telomere sequences, #765) describe that sequence, so they take every dimension but their own kind, and its samples. An annotation of a genome sequence is not a callset, so the sequence's variant kind and origin pass too; a callset's annotation is a VariantProcessingActivity, which is why the input is a sequence or an assembly only. diff --git a/src/meta_disco/rules/value_map.yaml b/src/meta_disco/rules/value_map.yaml index c46faccf..8b2d448e 100644 --- a/src/meta_disco/rules/value_map.yaml +++ b/src/meta_disco/rules/value_map.yaml @@ -443,6 +443,13 @@ rows: seeded_from: ["anvil/anvil15/AnVIL_IGVF_Mouse_R1/20260928T183417Z"] - id: "data_type.gaps" match: {slot: data_type, value: "gaps"} + scope: {source: anvil, dataset: AnVIL_HPRC_R2} + declares: {data_type: annotations} + reason: >- + The `gaps` table-name span (#765): each file is a BED of one assembly's gaps, on the + assembly's own sequences. HPRC files it under the assembly's `annotation/chrom_assignment/` + folder, and the HPRC Data Explorer's annotations catalog lists it as "ChromAlias Gaps". + Scoped to this dataset: elsewhere the word need not name an assembly's annotation. seeded_from: ["anvil/anvil15/AnVIL_HPRC_R2/20260920T175642Z"] - id: "data_type.kallisto_single_cell_rnaseq_output" match: {slot: data_type, value: "kallisto single cell RNAseq output"} @@ -474,6 +481,14 @@ rows: seeded_from: ["anvil/anvil15/AnVIL_HPRC_R2/20260920T175642Z"] - id: "data_type.sequences" match: {slot: data_type, value: "sequences"} + scope: {source: anvil, dataset: AnVIL_HPRC_R2} + declares: {data_type: annotations} + reason: >- + The `t2t_sequences` table's span (#765): each file (`.t2t_chromosomes.tsv`) is a table of + one assembly's telomere-to-telomere sequences, each with its chromosome and its gaps. HPRC + files it under the assembly's `annotation/chrom_assignment/` folder, and the HPRC Data + Explorer's annotations catalog lists it as "ChromAlias T2T". Scoped to this dataset: + elsewhere a `sequences` table could hold the sequences themselves. seeded_from: ["anvil/anvil15/AnVIL_HPRC_R2/20260920T175642Z"] - id: "data_type.sparse_gene_count_matrix" match: {slot: data_type, value: "sparse gene count matrix"} diff --git a/tests/test_value_map.py b/tests/test_value_map.py index 2ddc5317..196b0f29 100644 --- a/tests/test_value_map.py +++ b/tests/test_value_map.py @@ -1008,8 +1008,6 @@ def test_a_row_value_must_be_a_string(tmp_path): "data_modality.transcriptomic", "data_type.alignments", "data_type.chains", - "data_type.gaps", - "data_type.sequences", ] @@ -1019,7 +1017,7 @@ def test_the_bundled_table_covers_every_hprc_fixture_value(hprc_fixture_root): queued = review_queue(hprc_fixture_root, load_value_map(), datasets=HPRC_DATASETS) assert all(e.row_id is not None for e in queued), [e.raw_value for e in queued if e.row_id is None] assert sorted({e.row_id for e in queued if e.row_id is not None}) == SEEDED_IN_BUNDLED_TABLE - assert len(queued) == 7 + assert len(queued) == 5 def test_the_bundled_table_covers_hprc_and_leaves_the_named_values_seeded(): From a31467b71b9801278d9d59b1912f8dfaecfd75bf Mon Sep 17 00:00:00 2001 From: Dave Rogers Date: Mon, 9 Nov 2026 19:33:31 -0800 Subject: [PATCH 2/3] Regenerate the reports from run 20261109_191616 (#765) Classified and reconciled at 42c09af. Against run 20261104_183742, only AnVIL_HPRC_R2's data_type moved: annotations 2,772 -> 3,696 and not_classified 3,709 -> 2,785 (924 files). The review queue loses the gaps and sequences rows; the rules report shows each firing 462 times. The other reports change only their run id and commit. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01VF7tbFa5ZTmYWZ6JWKiBBS Co-authored-by: cc-claude-tools --- docs/anvil-coverage-report.md | 2 +- docs/consistency-report.md | 2 +- docs/coverage-dashboard.html | 2 +- docs/reconcile-dashboard.html | 2 +- docs/reconcile-report.md | 43 +++++++++++++++++++---------------- docs/review-queue-report.md | 6 ++--- docs/review-queue.html | 6 ++--- docs/rules-dashboard.html | 2 +- docs/rules-report.md | 20 ++++++++++++---- docs/unprocessable-report.md | 2 +- 10 files changed, 51 insertions(+), 36 deletions(-) diff --git a/docs/anvil-coverage-report.md b/docs/anvil-coverage-report.md index e8bbda83..766871e4 100644 --- a/docs/anvil-coverage-report.md +++ b/docs/anvil-coverage-report.md @@ -1,6 +1,6 @@ # AnVIL Classification Coverage Report -Classification run: **2026-11-04 18:37:42** +Classification run: **2026-11-09 19:16:16** Source: **708,088** files across **12** open-access datasets on [explore.anvilproject.org](https://explore.anvilproject.org/). Processed **708,088** files. diff --git a/docs/consistency-report.md b/docs/consistency-report.md index 8f57814f..d796ba22 100644 --- a/docs/consistency-report.md +++ b/docs/consistency-report.md @@ -1,6 +1,6 @@ # Self-Consistency Report -Run: **output/anvil/20261104_183742** — 708,088 records, 10 rules +Run: **output/anvil/20261109_191616** — 708,088 records, 10 rules **Total violations: 0** Cross-field invariants over classified records (#314). *Active* is how many records a rule tested; a rule with 0 active is **vacuous** (no matching data in this run), not verified-clean. diff --git a/docs/coverage-dashboard.html b/docs/coverage-dashboard.html index c96f77e6..fec65230 100644 --- a/docs/coverage-dashboard.html +++ b/docs/coverage-dashboard.html @@ -61,7 +61,7 @@

AnVIL Classification Coverage Dashboard // Data injected by generate script - const DATA = {"total": 708088, "run_time": "2026-11-04 18:37:42", "datasets": [{"name": "ANVIL_T2T_CHRY", "count": 309979}, {"name": "ANVIL_T2T", "count": 289204}, {"name": "ANVIL_1000G_high_coverage_2019", "count": 26016}, {"name": "ANVIL_HPRC", "count": 23185}, {"name": "AnVIL_HPRC_R2", "count": 16271}, {"name": "ANVIL_NIA_CARD_Coriell_Cell_Lines_Open", "count": 12534}, {"name": "ANVIL_1000G_PRIMED_data_model", "count": 11493}, {"name": "AnVIL_IGVF_Mouse_R1", "count": 6786}, {"name": "AnVIL_ENCORE_RS293", "count": 3752}, {"name": "ANVIL_nhp_dGTEx_V1", "count": 3591}, {"name": "AnVIL_MAGE", "count": 3285}, {"name": "AnVIL_ENCORE_293T", "count": 1992}], "dimensions": [{"field": "data_modality", "label": "Data Modality", "classified": 379527, "not_classified": 328561, "conflict": 0, "values": [{"name": "genomic", "count": 349747, "extensions": [{"ext": ".vcf", "count": 201645}, {"ext": "(none)", "count": 124470}, {"ext": ".cram", "count": 10555}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".bed", "count": 1715}, {"ext": ".bam", "count": 1688}, {"ext": ".fa", "count": 936}, {"ext": ".gfa", "count": 326}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".gbz", "count": 2}]}, {"name": "not_classified", "count": 328561, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".txt", "count": 42477}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".fast5", "count": 12509}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10071}, {"ext": ".bed", "count": 9768}, {"ext": ".bam", "count": 2757}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".cram", "count": 68}, {"ext": ".vcf", "count": 23}, {"ext": ".csv", "count": 18}, {"ext": ".fasta", "count": 14}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".fa", "count": 4}, {"ext": ".fna", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 23822, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".tsv", "count": 24}]}, {"name": "transcriptomic", "count": 5930, "extensions": [{"ext": ".bw", "count": 2536}, {"ext": ".bam", "count": 2329}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}, {"ext": ".bed", "count": 12}, {"ext": ".csv", "count": 3}, {"ext": ".txt", "count": 2}]}, {"name": "epigenomic.methylation", "count": 28, "extensions": [{"ext": ".bed", "count": 28}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".txt", "count": 42477, "why": "No rule determined a value for data_modality"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "FASTQ modality cannot be determined from reads alone \u2014 could be genomic, transcriptomic, or epigenomic depending on assay"}, {"ext": ".fast5", "count": 12509, "why": "No rule determined a value for data_modality"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10071, "why": "No rule determined a value for data_modality"}, {"ext": ".bed", "count": 9768, "why": "No rule determined a value for data_modality"}, {"ext": ".bam", "count": 2757, "why": "No rule determined a value for data_modality"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for data_modality"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for data_modality"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for data_modality"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for data_modality"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for data_modality"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for data_modality"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for data_modality"}, {"ext": ".cram", "count": 68, "why": "No rule determined a value for data_modality"}, {"ext": ".vcf", "count": 23, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for data_modality"}, {"ext": ".fasta", "count": 14, "why": "No rule determined a value for data_modality"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for data_modality"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for data_modality"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".fa", "count": 4, "why": "No rule determined a value for data_modality"}, {"ext": ".fna", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for data_modality"}], "conflict_breakdown": [], "notes": ""}, {"field": "data_type", "label": "Data Type", "classified": 685435, "not_classified": 22653, "conflict": 0, "values": [{"name": "index", "count": 224726, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".crai", "count": 10317}, {"ext": ".bai", "count": 2742}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".pbi", "count": 7}]}, {"name": "variants.gvcf", "count": 168825, "extensions": [{"ext": ".vcf", "count": 166321}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "variants.genomicsdb", "count": 124335, "extensions": [{"ext": "(none)", "count": 124335}]}, {"name": "qc_report", "count": 37548, "extensions": [{"ext": ".txt", "count": 37548}]}, {"name": "variants.multi_sample", "count": 34703, "extensions": [{"ext": ".vcf", "count": 34703}]}, {"name": "reads", "count": 24383, "extensions": [{"ext": ".fastq", "count": 21270}, {"ext": ".bam", "count": 3113}]}, {"name": "not_classified", "count": 22653, "extensions": [{"ext": "(none)", "count": 10069}, {"ext": ".txt", "count": 4929}, {"ext": ".bed", "count": 2771}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".vcf", "count": 23}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "alignments", "count": 14284, "extensions": [{"ext": ".cram", "count": 10623}, {"ext": ".bam", "count": 3661}]}, {"name": "checksum", "count": 14233, "extensions": [{"ext": ".md5", "count": 14233}]}, {"name": "raw_signal", "count": 12522, "extensions": [{"ext": ".fast5", "count": 12509}, {"ext": ".pod5", "count": 11}, {"ext": "(none)", "count": 2}]}, {"name": "annotations.coverage", "count": 9533, "extensions": [{"ext": ".bed", "count": 6997}, {"ext": ".bw", "count": 2536}]}, {"name": "genotypes", "count": 5708, "extensions": [{"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}]}, {"name": "log", "count": 3637, "extensions": [{"ext": ".log", "count": 3637}]}, {"name": "images", "count": 3074, "extensions": [{"ext": ".png", "count": 3074}]}, {"name": "sample_table", "count": 2854, "extensions": [{"ext": ".psam", "count": 2854}]}, {"name": "annotations", "count": 1755, "extensions": [{"ext": ".bed", "count": 1755}]}, {"name": "assembly", "count": 960, "extensions": [{"ext": ".fa", "count": 936}, {"ext": ".fasta", "count": 24}]}, {"name": "quantification", "count": 634, "extensions": [{"ext": ".sf", "count": 634}]}, {"name": "pangenome", "count": 449, "extensions": [{"ext": ".gfa", "count": 314}, {"ext": "(none)", "count": 135}]}, {"name": "expression_matrix", "count": 419, "extensions": [{"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}, {"ext": ".csv", "count": 3}, {"ext": ".txt", "count": 2}]}, {"name": "variants.single_sample", "count": 340, "extensions": [{"ext": ".vcf", "count": 340}]}, {"name": "variants.sites_only", "count": 281, "extensions": [{"ext": ".vcf", "count": 281}]}, {"name": "array_signal", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}, {"name": "pangenome.reference", "count": 28, "extensions": [{"ext": ".gfa", "count": 12}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".gbz", "count": 2}]}, {"name": "sample_map", "count": 24, "extensions": [{"ext": ".tsv", "count": 24}]}, {"name": "sequence", "count": 20, "extensions": [{"ext": ".fasta", "count": 14}, {"ext": ".fa", "count": 4}, {"ext": ".fna", "count": 2}]}], "not_classified_breakdown": [{"ext": "(none)", "count": 10069, "why": "No rule determined a value for data_type"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for data_type"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for data_type"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for data_type"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for data_type"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for data_type"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for data_type"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for data_type"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for data_type"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for data_type"}, {"ext": ".vcf", "count": 23, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for data_type"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for data_type"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for data_type"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for data_type"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for data_type"}], "conflict_breakdown": [], "notes": ""}, {"field": "platform", "label": "Platform", "classified": 72979, "not_classified": 635109, "conflict": 0, "values": [{"name": "not_classified", "count": 635109, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".bed", "count": 11523}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 3512}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".h5ad", "count": 350}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 21}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "ILLUMINA", "count": 30949, "extensions": [{"ext": ".fastq", "count": 20166}, {"ext": ".cram", "count": 10623}, {"ext": ".idat", "count": 160}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "ONT", "count": 13985, "extensions": [{"ext": ".fast5", "count": 12509}, {"ext": ".bam", "count": 1328}, {"ext": ".fastq", "count": 137}, {"ext": ".pod5", "count": 11}]}, {"name": "PACBIO", "count": 2901, "extensions": [{"ext": ".bam", "count": 1934}, {"ext": ".fastq", "count": 967}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for platform"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for platform"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for platform"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".bed", "count": 11523, "why": "No rule determined a value for platform"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 3512, "why": "No rule determined a value for platform"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for platform"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for platform"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for platform"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for platform"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for platform"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for platform"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for platform"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for platform"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for platform"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for platform"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for platform"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for platform"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for platform"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for platform"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for platform"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for platform"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for platform"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for platform"}], "conflict_breakdown": [], "notes": "**Note**: Platform is inherently unknowable for most derived formats (VCF, BED, PLINK). It is read from a BAM/CRAM `@RG PL` header, FASTQ read name patterns, a nanopore signal file's extension, and an Illumina IDAT's run log, from whose scan software the array scanner is inferred (#603). The high not-classified rate is expected."}, {"field": "reference_assembly", "label": "Reference Assembly", "classified": 295802, "not_classified": 412278, "conflict": 8, "values": [{"name": "not_classified", "count": 412278, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".crai", "count": 10317}, {"ext": ".pgen", "count": 2853}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".gff3", "count": 1386}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 456}, {"ext": ".h5ad", "count": 350}, {"ext": ".gfa", "count": 314}, {"ext": ".paf", "count": 296}, {"ext": ".sam", "count": 192}, {"ext": ".bed", "count": 36}, {"ext": ".vcf", "count": 26}, {"ext": ".csv", "count": 21}, {"ext": ".pbi", "count": 7}, {"ext": ".fasta", "count": 3}, {"ext": ".bam", "count": 2}, {"ext": ".chain", "count": 1}, {"ext": ".dict", "count": 1}]}, {"name": "t2t-chm13.20200921.withGRCh38chrY.chrEBV.chrYKI270740v1r", "count": 111756, "extensions": [{"ext": ".vcf", "count": 108478}, {"ext": ".cram", "count": 3202}, {"ext": ".bam", "count": 76}]}, {"name": "T2T-CHM13v2.0", "count": 87747, "extensions": [{"ext": ".vcf", "count": 83804}, {"ext": ".cram", "count": 3481}, {"ext": ".bam", "count": 462}]}, {"name": "not_applicable", "count": 65767, "extensions": [{"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".bed", "count": 3922}, {"ext": ".log", "count": 3637}, {"ext": ".bam", "count": 3113}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 936}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 24}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}]}, {"name": "GRCh38", "count": 20705, "extensions": [{"ext": ".vcf", "count": 9186}, {"ext": ".cram", "count": 3837}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".bam", "count": 2341}, {"ext": ".pvar", "count": 1427}, {"ext": ".bed", "count": 817}, {"ext": ".chain", "count": 462}, {"ext": ".gff3", "count": 88}, {"ext": ".gfa", "count": 6}, {"ext": ".dict", "count": 3}, {"ext": ".dist", "count": 3}, {"ext": ".fasta", "count": 3}, {"ext": ".gbwt", "count": 3}, {"ext": ".gg", "count": 3}, {"ext": ".min", "count": 3}, {"ext": ".snarls", "count": 3}, {"ext": ".trans", "count": 3}, {"ext": ".xg", "count": 3}, {"ext": ".fna", "count": 2}, {"ext": ".delta", "count": 1}, {"ext": ".fa", "count": 1}, {"ext": ".gbz", "count": 1}, {"ext": ".hal", "count": 1}, {"ext": ".hapl", "count": 1}, {"ext": ".paf", "count": 1}, {"ext": ".pgen", "count": 1}, {"ext": ".sizes", "count": 1}]}, {"name": "CHM13", "count": 7395, "extensions": [{"ext": ".bed", "count": 6744}, {"ext": ".chain", "count": 462}, {"ext": ".gff3", "count": 90}, {"ext": ".vcf", "count": 54}, {"ext": ".fasta", "count": 7}, {"ext": ".gfa", "count": 6}, {"ext": ".dict", "count": 4}, {"ext": ".dist", "count": 3}, {"ext": ".fa", "count": 3}, {"ext": ".gbwt", "count": 3}, {"ext": ".gg", "count": 3}, {"ext": ".min", "count": 3}, {"ext": ".snarls", "count": 3}, {"ext": ".trans", "count": 3}, {"ext": ".xg", "count": 3}, {"ext": ".gbz", "count": 1}, {"ext": ".hal", "count": 1}, {"ext": ".hapl", "count": 1}, {"ext": ".sizes", "count": 1}]}, {"name": "GRCh37", "count": 1463, "extensions": [{"ext": ".pvar", "count": 1427}, {"ext": ".vcf", "count": 34}, {"ext": ".bed", "count": 2}]}, {"name": "Mmul_10", "count": 422, "extensions": [{"ext": ".bam", "count": 372}, {"ext": ".cram", "count": 49}, {"ext": ".vcf", "count": 1}]}, {"name": "mCalJa1.2.pat.X", "count": 334, "extensions": [{"ext": ".bam", "count": 314}, {"ext": ".cram", "count": 19}, {"ext": ".vcf", "count": 1}]}, {"name": "CHM13Y_EBV_v1.1", "count": 95, "extensions": [{"ext": ".bam", "count": 94}, {"ext": ".vcf", "count": 1}]}, {"name": "T2T-CHM13v1.0", "count": 59, "extensions": [{"ext": ".vcf", "count": 59}]}, {"name": "t2t-chm13.20200921.HG002chrY.chrEBV", "count": 35, "extensions": [{"ext": ".cram", "count": 35}]}, {"name": "T2T-CHM13v1.1", "count": 24, "extensions": [{"ext": ".vcf", "count": 24}]}, {"name": "conflict", "count": 8, "extensions": [{"ext": ".bed", "count": 2}, {"ext": ".xg", "count": 2}, {"ext": ".chain", "count": 1}, {"ext": ".dict", "count": 1}, {"ext": ".fasta", "count": 1}, {"ext": ".gff3", "count": 1}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for reference_assembly"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for reference_assembly"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".pgen", "count": 2853, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for reference_assembly"}, {"ext": ".gff3", "count": 1386, "why": "No rule determined a value for reference_assembly"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for reference_assembly"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sizes", "count": 456, "why": "No rule determined a value for reference_assembly"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for reference_assembly"}, {"ext": ".gfa", "count": 314, "why": "No rule determined a value for reference_assembly"}, {"ext": ".paf", "count": 296, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bed", "count": 36, "why": "No rule determined a value for reference_assembly"}, {"ext": ".vcf", "count": 26, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for reference_assembly"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".fasta", "count": 3, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bam", "count": 2, "why": "No rule determined a value for reference_assembly"}, {"ext": ".chain", "count": 1, "why": "No rule determined a value for reference_assembly"}, {"ext": ".dict", "count": 1, "why": "No rule determined a value for reference_assembly"}], "conflict_breakdown": [{"ext": ".bed", "competing": "CHM13 vs GRCh38", "count": 2}, {"ext": ".xg", "competing": "CHM13 vs GRCh38", "count": 2}, {"ext": ".chain", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".dict", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".fasta", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".gff3", "competing": "CHM13 vs GRCh38", "count": 1}], "notes": ""}, {"field": "assay_type", "label": "Assay Type", "classified": 30999, "not_classified": 677089, "conflict": 0, "values": [{"name": "not_classified", "count": 677089, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134541}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".fast5", "count": 12509}, {"ext": ".bed", "count": 11511}, {"ext": ".cram", "count": 10623}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 4675}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 21}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "RNA-seq", "count": 5281, "extensions": [{"ext": ".bw", "count": 2536}, {"ext": ".bam", "count": 2099}, {"ext": ".sf", "count": 634}, {"ext": ".bed", "count": 12}]}, {"name": "sc/snRNA-seq", "count": 414, "extensions": [{"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}]}, {"name": "Genotyping array", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for assay_type"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134541, "why": "No rule determined a value for assay_type"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for assay_type"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "No rule determined a value for assay_type"}, {"ext": ".fast5", "count": 12509, "why": "No rule determined a value for assay_type"}, {"ext": ".bed", "count": 11511, "why": "No rule determined a value for assay_type"}, {"ext": ".cram", "count": 10623, "why": "No rule determined a value for assay_type"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 4675, "why": "No rule determined a value for assay_type"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for assay_type"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for assay_type"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for assay_type"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for assay_type"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for assay_type"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for assay_type"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for assay_type"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for assay_type"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for assay_type"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for assay_type"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for assay_type"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for assay_type"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for assay_type"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for assay_type"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for assay_type"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for assay_type"}], "conflict_breakdown": [], "notes": "**Note**: Like platform, assay type is inherently unknowable for most derived formats. It is determined only by a rule that sees evidence of the assay: a STAR `@PG` line, filename patterns (STAR, Salmon, expression BED), an IDAT's header, whose chip type and probe count name the BeadChip (#603), and extension where the format implies it (`.svs` histology, a `.h5ad` / `.loom` / `.mtx` single-cell matrix `sc/snRNA-seq`, and a tar whose members are one of these, #533). Nothing infers it from the modality (#88), reads file size, or infers WGS from a long-read platform (#430). The high not-classified rate is expected."}, {"field": "instrument_model", "label": "Instrument Model", "classified": 38450, "not_classified": 669638, "conflict": 0, "values": [{"name": "not_classified", "count": 669638, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".bed", "count": 11523}, {"ext": ".cram", "count": 10555}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 6090}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".h5ad", "count": 350}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".fast5", "count": 115}, {"ext": ".csv", "count": 21}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "PromethION", "count": 12394, "extensions": [{"ext": ".fast5", "count": 12394}]}, {"name": "Revio", "count": 684, "extensions": [{"ext": ".bam", "count": 684}]}, {"name": "Illumina iScan", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}, {"name": "Illumina NovaSeq X", "count": 68, "extensions": [{"ext": ".cram", "count": 68}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for instrument_model"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for instrument_model"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for instrument_model"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "No rule determined a value for instrument_model"}, {"ext": ".bed", "count": 11523, "why": "No rule determined a value for instrument_model"}, {"ext": ".cram", "count": 10555, "why": "No rule determined a value for instrument_model"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 6090, "why": "No rule determined a value for instrument_model"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for instrument_model"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for instrument_model"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for instrument_model"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for instrument_model"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for instrument_model"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for instrument_model"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for instrument_model"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for instrument_model"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for instrument_model"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for instrument_model"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for instrument_model"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for instrument_model"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for instrument_model"}, {"ext": ".fast5", "count": 115, "why": "No rule determined a value for instrument_model"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for instrument_model"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for instrument_model"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for instrument_model"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for instrument_model"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for instrument_model"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for instrument_model"}], "conflict_breakdown": [], "notes": "**Note**: Inference reads the instrument model from a BAM/CRAM `@RG PM` value that names exactly one model (#532) and from an IDAT's run log naming the iScan's software (#603); a read-name serial prefix is a vendor numbering convention and is not read. Most files carry no such value, so the high not-classified rate is expected. This report reads inference only; the submitter tables, which reconcile reads, name models far more often."}, {"field": "variant_kind", "label": "Variant Kind", "classified": 419357, "not_classified": 288731, "conflict": 0, "values": [{"name": "small", "count": 293230, "extensions": [{"ext": ".vcf", "count": 166391}, {"ext": "(none)", "count": 124335}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "not_classified", "count": 288731, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".vcf", "count": 35124}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10270}, {"ext": ".txt", "count": 4929}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bed", "count": 2771}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".gfa", "count": 326}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".xg", "count": 8}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gbwt", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".gbz", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 125974, "extensions": [{"ext": ".txt", "count": 37550}, {"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".cram", "count": 10623}, {"ext": ".bed", "count": 8752}, {"ext": ".bam", "count": 6774}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".bw", "count": 2536}, {"ext": ".fa", "count": 940}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}, {"ext": ".csv", "count": 3}, {"ext": ".fna", "count": 2}]}, {"name": "structural", "count": 153, "extensions": [{"ext": ".vcf", "count": 153}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".vcf", "count": 35124, "why": "no caller line: GenomicsDBImport of inputs whose callers the header does not name"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10270, "why": "No rule determined a value for variant_kind"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for variant_kind"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for variant_kind"}, {"ext": ".pvar", "count": 2854, "why": "not a VCF: a PLINK 2 .pvar records no step of its own"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for variant_kind"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for variant_kind"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for variant_kind"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for variant_kind"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for variant_kind"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for variant_kind"}, {"ext": ".gfa", "count": 326, "why": "No rule determined a value for variant_kind"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for variant_kind"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for variant_kind"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for variant_kind"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for variant_kind"}, {"ext": ".xg", "count": 8, "why": "No rule determined a value for variant_kind"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gbwt", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gbz", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for variant_kind"}], "conflict_breakdown": [], "notes": "**Note**: Read from the caller that made a VCF: its header's producing step, walked back through steps that keep the kind, or a `##source` naming one tool, looked up in `rules/callers.yaml` (#654); a GenomicsDB workspace's from the caller its own `vcfheader.vcf` names, found the same way (#678). Not applicable to a file whose rule says it holds no variants. An index, a VCF genotyped from a GenomicsDB workspace (whose header names the import but not the caller) and a merge of such VCFs take their parents' kind only at reconcile, which this report does not read."}, {"field": "variant_origin", "label": "Variant Origin", "classified": 419369, "not_classified": 288719, "conflict": 0, "values": [{"name": "germline", "count": 293395, "extensions": [{"ext": ".vcf", "count": 166556}, {"ext": "(none)", "count": 124335}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "not_classified", "count": 288719, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".vcf", "count": 35112}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10270}, {"ext": ".txt", "count": 4929}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bed", "count": 2771}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".gfa", "count": 326}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".xg", "count": 8}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gbwt", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".gbz", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 125974, "extensions": [{"ext": ".txt", "count": 37550}, {"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".cram", "count": 10623}, {"ext": ".bed", "count": 8752}, {"ext": ".bam", "count": 6774}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".bw", "count": 2536}, {"ext": ".fa", "count": 940}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}, {"ext": ".csv", "count": 3}, {"ext": ".fna", "count": 2}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".vcf", "count": 35112, "why": "no caller line: GenomicsDBImport of inputs whose callers the header does not name"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10270, "why": "No rule determined a value for variant_origin"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for variant_origin"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for variant_origin"}, {"ext": ".pvar", "count": 2854, "why": "not a VCF: a PLINK 2 .pvar records no step of its own"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for variant_origin"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for variant_origin"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for variant_origin"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for variant_origin"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for variant_origin"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for variant_origin"}, {"ext": ".gfa", "count": 326, "why": "No rule determined a value for variant_origin"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for variant_origin"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for variant_origin"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for variant_origin"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for variant_origin"}, {"ext": ".xg", "count": 8, "why": "No rule determined a value for variant_origin"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gbwt", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gbz", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for variant_origin"}], "conflict_breakdown": [], "notes": "**Note**: Germline or somatic, read from the caller a VCF's header names, or the caller of the calls a GenomicsDB workspace imported, found as for the kind and looked up in `rules/callers.yaml` (#658, #678). A caller with a somatic mode (Sniffles2) gives its origin only where its command line shows the mode was off. Not applicable to a file whose rule says it holds no variants. An index, a VCF genotyped from a workspace, a merge of such VCFs and a filtered callset take their parents' origin only at reconcile, which this report does not read."}]}; + const DATA = {"total": 708088, "run_time": "2026-11-09 19:16:16", "datasets": [{"name": "ANVIL_T2T_CHRY", "count": 309979}, {"name": "ANVIL_T2T", "count": 289204}, {"name": "ANVIL_1000G_high_coverage_2019", "count": 26016}, {"name": "ANVIL_HPRC", "count": 23185}, {"name": "AnVIL_HPRC_R2", "count": 16271}, {"name": "ANVIL_NIA_CARD_Coriell_Cell_Lines_Open", "count": 12534}, {"name": "ANVIL_1000G_PRIMED_data_model", "count": 11493}, {"name": "AnVIL_IGVF_Mouse_R1", "count": 6786}, {"name": "AnVIL_ENCORE_RS293", "count": 3752}, {"name": "ANVIL_nhp_dGTEx_V1", "count": 3591}, {"name": "AnVIL_MAGE", "count": 3285}, {"name": "AnVIL_ENCORE_293T", "count": 1992}], "dimensions": [{"field": "data_modality", "label": "Data Modality", "classified": 379527, "not_classified": 328561, "conflict": 0, "values": [{"name": "genomic", "count": 349747, "extensions": [{"ext": ".vcf", "count": 201645}, {"ext": "(none)", "count": 124470}, {"ext": ".cram", "count": 10555}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".bed", "count": 1715}, {"ext": ".bam", "count": 1688}, {"ext": ".fa", "count": 936}, {"ext": ".gfa", "count": 326}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".gbz", "count": 2}]}, {"name": "not_classified", "count": 328561, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".txt", "count": 42477}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".fast5", "count": 12509}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10071}, {"ext": ".bed", "count": 9768}, {"ext": ".bam", "count": 2757}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".cram", "count": 68}, {"ext": ".vcf", "count": 23}, {"ext": ".csv", "count": 18}, {"ext": ".fasta", "count": 14}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".fa", "count": 4}, {"ext": ".fna", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 23822, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".tsv", "count": 24}]}, {"name": "transcriptomic", "count": 5930, "extensions": [{"ext": ".bw", "count": 2536}, {"ext": ".bam", "count": 2329}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}, {"ext": ".bed", "count": 12}, {"ext": ".csv", "count": 3}, {"ext": ".txt", "count": 2}]}, {"name": "epigenomic.methylation", "count": 28, "extensions": [{"ext": ".bed", "count": 28}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".txt", "count": 42477, "why": "No rule determined a value for data_modality"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "FASTQ modality cannot be determined from reads alone \u2014 could be genomic, transcriptomic, or epigenomic depending on assay"}, {"ext": ".fast5", "count": 12509, "why": "No rule determined a value for data_modality"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10071, "why": "No rule determined a value for data_modality"}, {"ext": ".bed", "count": 9768, "why": "No rule determined a value for data_modality"}, {"ext": ".bam", "count": 2757, "why": "No rule determined a value for data_modality"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for data_modality"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for data_modality"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for data_modality"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for data_modality"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for data_modality"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for data_modality"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for data_modality"}, {"ext": ".cram", "count": 68, "why": "No rule determined a value for data_modality"}, {"ext": ".vcf", "count": 23, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for data_modality"}, {"ext": ".fasta", "count": 14, "why": "No rule determined a value for data_modality"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for data_modality"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for data_modality"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for data_modality"}, {"ext": ".fa", "count": 4, "why": "No rule determined a value for data_modality"}, {"ext": ".fna", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for data_modality"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for data_modality"}], "conflict_breakdown": [], "notes": ""}, {"field": "data_type", "label": "Data Type", "classified": 685435, "not_classified": 22653, "conflict": 0, "values": [{"name": "index", "count": 224726, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".crai", "count": 10317}, {"ext": ".bai", "count": 2742}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".pbi", "count": 7}]}, {"name": "variants.gvcf", "count": 168825, "extensions": [{"ext": ".vcf", "count": 166321}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "variants.genomicsdb", "count": 124335, "extensions": [{"ext": "(none)", "count": 124335}]}, {"name": "qc_report", "count": 37548, "extensions": [{"ext": ".txt", "count": 37548}]}, {"name": "variants.multi_sample", "count": 34703, "extensions": [{"ext": ".vcf", "count": 34703}]}, {"name": "reads", "count": 24383, "extensions": [{"ext": ".fastq", "count": 21270}, {"ext": ".bam", "count": 3113}]}, {"name": "not_classified", "count": 22653, "extensions": [{"ext": "(none)", "count": 10069}, {"ext": ".txt", "count": 4929}, {"ext": ".bed", "count": 2771}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".vcf", "count": 23}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "alignments", "count": 14284, "extensions": [{"ext": ".cram", "count": 10623}, {"ext": ".bam", "count": 3661}]}, {"name": "checksum", "count": 14233, "extensions": [{"ext": ".md5", "count": 14233}]}, {"name": "raw_signal", "count": 12522, "extensions": [{"ext": ".fast5", "count": 12509}, {"ext": ".pod5", "count": 11}, {"ext": "(none)", "count": 2}]}, {"name": "annotations.coverage", "count": 9533, "extensions": [{"ext": ".bed", "count": 6997}, {"ext": ".bw", "count": 2536}]}, {"name": "genotypes", "count": 5708, "extensions": [{"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}]}, {"name": "log", "count": 3637, "extensions": [{"ext": ".log", "count": 3637}]}, {"name": "images", "count": 3074, "extensions": [{"ext": ".png", "count": 3074}]}, {"name": "sample_table", "count": 2854, "extensions": [{"ext": ".psam", "count": 2854}]}, {"name": "annotations", "count": 1755, "extensions": [{"ext": ".bed", "count": 1755}]}, {"name": "assembly", "count": 960, "extensions": [{"ext": ".fa", "count": 936}, {"ext": ".fasta", "count": 24}]}, {"name": "quantification", "count": 634, "extensions": [{"ext": ".sf", "count": 634}]}, {"name": "pangenome", "count": 449, "extensions": [{"ext": ".gfa", "count": 314}, {"ext": "(none)", "count": 135}]}, {"name": "expression_matrix", "count": 419, "extensions": [{"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}, {"ext": ".csv", "count": 3}, {"ext": ".txt", "count": 2}]}, {"name": "variants.single_sample", "count": 340, "extensions": [{"ext": ".vcf", "count": 340}]}, {"name": "variants.sites_only", "count": 281, "extensions": [{"ext": ".vcf", "count": 281}]}, {"name": "array_signal", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}, {"name": "pangenome.reference", "count": 28, "extensions": [{"ext": ".gfa", "count": 12}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".gbz", "count": 2}]}, {"name": "sample_map", "count": 24, "extensions": [{"ext": ".tsv", "count": 24}]}, {"name": "sequence", "count": 20, "extensions": [{"ext": ".fasta", "count": 14}, {"ext": ".fa", "count": 4}, {"ext": ".fna", "count": 2}]}], "not_classified_breakdown": [{"ext": "(none)", "count": 10069, "why": "No rule determined a value for data_type"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for data_type"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for data_type"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for data_type"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for data_type"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for data_type"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for data_type"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for data_type"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for data_type"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for data_type"}, {"ext": ".vcf", "count": 23, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for data_type"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for data_type"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for data_type"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for data_type"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for data_type"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for data_type"}], "conflict_breakdown": [], "notes": ""}, {"field": "platform", "label": "Platform", "classified": 72979, "not_classified": 635109, "conflict": 0, "values": [{"name": "not_classified", "count": 635109, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".bed", "count": 11523}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 3512}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".h5ad", "count": 350}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 21}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "ILLUMINA", "count": 30949, "extensions": [{"ext": ".fastq", "count": 20166}, {"ext": ".cram", "count": 10623}, {"ext": ".idat", "count": 160}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "ONT", "count": 13985, "extensions": [{"ext": ".fast5", "count": 12509}, {"ext": ".bam", "count": 1328}, {"ext": ".fastq", "count": 137}, {"ext": ".pod5", "count": 11}]}, {"name": "PACBIO", "count": 2901, "extensions": [{"ext": ".bam", "count": 1934}, {"ext": ".fastq", "count": 967}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for platform"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for platform"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for platform"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".bed", "count": 11523, "why": "No rule determined a value for platform"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 3512, "why": "No rule determined a value for platform"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for platform"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for platform"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for platform"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for platform"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for platform"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for platform"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for platform"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for platform"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for platform"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for platform"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for platform"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for platform"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for platform"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for platform"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for platform"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for platform"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for platform"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for platform"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for platform"}], "conflict_breakdown": [], "notes": "**Note**: Platform is inherently unknowable for most derived formats (VCF, BED, PLINK). It is read from a BAM/CRAM `@RG PL` header, FASTQ read name patterns, a nanopore signal file's extension, and an Illumina IDAT's run log, from whose scan software the array scanner is inferred (#603). The high not-classified rate is expected."}, {"field": "reference_assembly", "label": "Reference Assembly", "classified": 295802, "not_classified": 412278, "conflict": 8, "values": [{"name": "not_classified", "count": 412278, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".crai", "count": 10317}, {"ext": ".pgen", "count": 2853}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".gff3", "count": 1386}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 456}, {"ext": ".h5ad", "count": 350}, {"ext": ".gfa", "count": 314}, {"ext": ".paf", "count": 296}, {"ext": ".sam", "count": 192}, {"ext": ".bed", "count": 36}, {"ext": ".vcf", "count": 26}, {"ext": ".csv", "count": 21}, {"ext": ".pbi", "count": 7}, {"ext": ".fasta", "count": 3}, {"ext": ".bam", "count": 2}, {"ext": ".chain", "count": 1}, {"ext": ".dict", "count": 1}]}, {"name": "t2t-chm13.20200921.withGRCh38chrY.chrEBV.chrYKI270740v1r", "count": 111756, "extensions": [{"ext": ".vcf", "count": 108478}, {"ext": ".cram", "count": 3202}, {"ext": ".bam", "count": 76}]}, {"name": "T2T-CHM13v2.0", "count": 87747, "extensions": [{"ext": ".vcf", "count": 83804}, {"ext": ".cram", "count": 3481}, {"ext": ".bam", "count": 462}]}, {"name": "not_applicable", "count": 65767, "extensions": [{"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".bed", "count": 3922}, {"ext": ".log", "count": 3637}, {"ext": ".bam", "count": 3113}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 936}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 24}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}]}, {"name": "GRCh38", "count": 20705, "extensions": [{"ext": ".vcf", "count": 9186}, {"ext": ".cram", "count": 3837}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".bam", "count": 2341}, {"ext": ".pvar", "count": 1427}, {"ext": ".bed", "count": 817}, {"ext": ".chain", "count": 462}, {"ext": ".gff3", "count": 88}, {"ext": ".gfa", "count": 6}, {"ext": ".dict", "count": 3}, {"ext": ".dist", "count": 3}, {"ext": ".fasta", "count": 3}, {"ext": ".gbwt", "count": 3}, {"ext": ".gg", "count": 3}, {"ext": ".min", "count": 3}, {"ext": ".snarls", "count": 3}, {"ext": ".trans", "count": 3}, {"ext": ".xg", "count": 3}, {"ext": ".fna", "count": 2}, {"ext": ".delta", "count": 1}, {"ext": ".fa", "count": 1}, {"ext": ".gbz", "count": 1}, {"ext": ".hal", "count": 1}, {"ext": ".hapl", "count": 1}, {"ext": ".paf", "count": 1}, {"ext": ".pgen", "count": 1}, {"ext": ".sizes", "count": 1}]}, {"name": "CHM13", "count": 7395, "extensions": [{"ext": ".bed", "count": 6744}, {"ext": ".chain", "count": 462}, {"ext": ".gff3", "count": 90}, {"ext": ".vcf", "count": 54}, {"ext": ".fasta", "count": 7}, {"ext": ".gfa", "count": 6}, {"ext": ".dict", "count": 4}, {"ext": ".dist", "count": 3}, {"ext": ".fa", "count": 3}, {"ext": ".gbwt", "count": 3}, {"ext": ".gg", "count": 3}, {"ext": ".min", "count": 3}, {"ext": ".snarls", "count": 3}, {"ext": ".trans", "count": 3}, {"ext": ".xg", "count": 3}, {"ext": ".gbz", "count": 1}, {"ext": ".hal", "count": 1}, {"ext": ".hapl", "count": 1}, {"ext": ".sizes", "count": 1}]}, {"name": "GRCh37", "count": 1463, "extensions": [{"ext": ".pvar", "count": 1427}, {"ext": ".vcf", "count": 34}, {"ext": ".bed", "count": 2}]}, {"name": "Mmul_10", "count": 422, "extensions": [{"ext": ".bam", "count": 372}, {"ext": ".cram", "count": 49}, {"ext": ".vcf", "count": 1}]}, {"name": "mCalJa1.2.pat.X", "count": 334, "extensions": [{"ext": ".bam", "count": 314}, {"ext": ".cram", "count": 19}, {"ext": ".vcf", "count": 1}]}, {"name": "CHM13Y_EBV_v1.1", "count": 95, "extensions": [{"ext": ".bam", "count": 94}, {"ext": ".vcf", "count": 1}]}, {"name": "T2T-CHM13v1.0", "count": 59, "extensions": [{"ext": ".vcf", "count": 59}]}, {"name": "t2t-chm13.20200921.HG002chrY.chrEBV", "count": 35, "extensions": [{"ext": ".cram", "count": 35}]}, {"name": "T2T-CHM13v1.1", "count": 24, "extensions": [{"ext": ".vcf", "count": 24}]}, {"name": "conflict", "count": 8, "extensions": [{"ext": ".bed", "count": 2}, {"ext": ".xg", "count": 2}, {"ext": ".chain", "count": 1}, {"ext": ".dict", "count": 1}, {"ext": ".fasta", "count": 1}, {"ext": ".gff3", "count": 1}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for reference_assembly"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for reference_assembly"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".pgen", "count": 2853, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for reference_assembly"}, {"ext": ".gff3", "count": 1386, "why": "No rule determined a value for reference_assembly"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for reference_assembly"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sizes", "count": 456, "why": "No rule determined a value for reference_assembly"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for reference_assembly"}, {"ext": ".gfa", "count": 314, "why": "No rule determined a value for reference_assembly"}, {"ext": ".paf", "count": 296, "why": "No rule determined a value for reference_assembly"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bed", "count": 36, "why": "No rule determined a value for reference_assembly"}, {"ext": ".vcf", "count": 26, "why": "no VCF header lines (no run of '#' lines starting the read head)"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for reference_assembly"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".fasta", "count": 3, "why": "No rule determined a value for reference_assembly"}, {"ext": ".bam", "count": 2, "why": "No rule determined a value for reference_assembly"}, {"ext": ".chain", "count": 1, "why": "No rule determined a value for reference_assembly"}, {"ext": ".dict", "count": 1, "why": "No rule determined a value for reference_assembly"}], "conflict_breakdown": [{"ext": ".bed", "competing": "CHM13 vs GRCh38", "count": 2}, {"ext": ".xg", "competing": "CHM13 vs GRCh38", "count": 2}, {"ext": ".chain", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".dict", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".fasta", "competing": "CHM13 vs GRCh38", "count": 1}, {"ext": ".gff3", "competing": "CHM13 vs GRCh38", "count": 1}], "notes": ""}, {"field": "assay_type", "label": "Assay Type", "classified": 30999, "not_classified": 677089, "conflict": 0, "values": [{"name": "not_classified", "count": 677089, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134541}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".fast5", "count": 12509}, {"ext": ".bed", "count": 11511}, {"ext": ".cram", "count": 10623}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 4675}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 21}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "RNA-seq", "count": 5281, "extensions": [{"ext": ".bw", "count": 2536}, {"ext": ".bam", "count": 2099}, {"ext": ".sf", "count": 634}, {"ext": ".bed", "count": 12}]}, {"name": "sc/snRNA-seq", "count": 414, "extensions": [{"ext": ".h5ad", "count": 350}, {"ext": "(none)", "count": 64}]}, {"name": "Genotyping array", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for assay_type"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134541, "why": "No rule determined a value for assay_type"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for assay_type"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "No rule determined a value for assay_type"}, {"ext": ".fast5", "count": 12509, "why": "No rule determined a value for assay_type"}, {"ext": ".bed", "count": 11511, "why": "No rule determined a value for assay_type"}, {"ext": ".cram", "count": 10623, "why": "No rule determined a value for assay_type"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 4675, "why": "No rule determined a value for assay_type"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for assay_type"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for assay_type"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for assay_type"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for assay_type"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for assay_type"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for assay_type"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for assay_type"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for assay_type"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for assay_type"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for assay_type"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for assay_type"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for assay_type"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for assay_type"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for assay_type"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for assay_type"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for assay_type"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for assay_type"}], "conflict_breakdown": [], "notes": "**Note**: Like platform, assay type is inherently unknowable for most derived formats. It is determined only by a rule that sees evidence of the assay: a STAR `@PG` line, filename patterns (STAR, Salmon, expression BED), an IDAT's header, whose chip type and probe count name the BeadChip (#603), and extension where the format implies it (`.svs` histology, a `.h5ad` / `.loom` / `.mtx` single-cell matrix `sc/snRNA-seq`, and a tar whose members are one of these, #533). Nothing infers it from the modality (#88), reads file size, or infers WGS from a long-read platform (#430). The high not-classified rate is expected."}, {"field": "instrument_model", "label": "Instrument Model", "classified": 38450, "not_classified": 669638, "conflict": 0, "values": [{"name": "not_classified", "count": 669638, "extensions": [{"ext": ".vcf", "count": 201668}, {"ext": ".tbi", "count": 169531}, {"ext": "(none)", "count": 134605}, {"ext": ".txt", "count": 42479}, {"ext": ".csi", "count": 41186}, {"ext": ".fastq", "count": 21270}, {"ext": ".bed", "count": 11523}, {"ext": ".cram", "count": 10555}, {"ext": ".crai", "count": 10317}, {"ext": ".bam", "count": 6090}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bai", "count": 2742}, {"ext": ".bw", "count": 2536}, {"ext": ".g.vcf", "count": 2504}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".sf", "count": 634}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".h5ad", "count": 350}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".fast5", "count": 115}, {"ext": ".csv", "count": 21}, {"ext": ".pod5", "count": 11}, {"ext": ".dict", "count": 9}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 25144, "extensions": [{"ext": ".md5", "count": 14233}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".fa", "count": 940}, {"ext": ".gfa", "count": 326}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".xg", "count": 8}, {"ext": ".gbwt", "count": 6}, {"ext": ".fna", "count": 2}, {"ext": ".gbz", "count": 2}]}, {"name": "PromethION", "count": 12394, "extensions": [{"ext": ".fast5", "count": 12394}]}, {"name": "Revio", "count": 684, "extensions": [{"ext": ".bam", "count": 684}]}, {"name": "Illumina iScan", "count": 160, "extensions": [{"ext": ".idat", "count": 160}]}, {"name": "Illumina NovaSeq X", "count": 68, "extensions": [{"ext": ".cram", "count": 68}]}], "not_classified_breakdown": [{"ext": ".vcf", "count": 201668, "why": "No rule determined a value for instrument_model"}, {"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": "(none)", "count": 134605, "why": "No rule determined a value for instrument_model"}, {"ext": ".txt", "count": 42479, "why": "No rule determined a value for instrument_model"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".fastq", "count": 21270, "why": "No rule determined a value for instrument_model"}, {"ext": ".bed", "count": 11523, "why": "No rule determined a value for instrument_model"}, {"ext": ".cram", "count": 10555, "why": "No rule determined a value for instrument_model"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": ".bam", "count": 6090, "why": "No rule determined a value for instrument_model"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for instrument_model"}, {"ext": ".pvar", "count": 2854, "why": "No rule determined a value for instrument_model"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".bw", "count": 2536, "why": "No rule determined a value for instrument_model"}, {"ext": ".g.vcf", "count": 2504, "why": "No rule determined a value for instrument_model"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for instrument_model"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for instrument_model"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for instrument_model"}, {"ext": ".sf", "count": 634, "why": "No rule determined a value for instrument_model"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for instrument_model"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for instrument_model"}, {"ext": ".h5ad", "count": 350, "why": "No rule determined a value for instrument_model"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for instrument_model"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for instrument_model"}, {"ext": ".fast5", "count": 115, "why": "No rule determined a value for instrument_model"}, {"ext": ".csv", "count": 21, "why": "No rule determined a value for instrument_model"}, {"ext": ".pod5", "count": 11, "why": "No rule determined a value for instrument_model"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for instrument_model"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for instrument_model"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for instrument_model"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for instrument_model"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for instrument_model"}], "conflict_breakdown": [], "notes": "**Note**: Inference reads the instrument model from a BAM/CRAM `@RG PM` value that names exactly one model (#532) and from an IDAT's run log naming the iScan's software (#603); a read-name serial prefix is a vendor numbering convention and is not read. Most files carry no such value, so the high not-classified rate is expected. This report reads inference only; the submitter tables, which reconcile reads, name models far more often."}, {"field": "variant_kind", "label": "Variant Kind", "classified": 419357, "not_classified": 288731, "conflict": 0, "values": [{"name": "small", "count": 293230, "extensions": [{"ext": ".vcf", "count": 166391}, {"ext": "(none)", "count": 124335}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "not_classified", "count": 288731, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".vcf", "count": 35124}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10270}, {"ext": ".txt", "count": 4929}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bed", "count": 2771}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".gfa", "count": 326}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".xg", "count": 8}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gbwt", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".gbz", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 125974, "extensions": [{"ext": ".txt", "count": 37550}, {"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".cram", "count": 10623}, {"ext": ".bed", "count": 8752}, {"ext": ".bam", "count": 6774}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".bw", "count": 2536}, {"ext": ".fa", "count": 940}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}, {"ext": ".csv", "count": 3}, {"ext": ".fna", "count": 2}]}, {"name": "structural", "count": 153, "extensions": [{"ext": ".vcf", "count": 153}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".vcf", "count": 35124, "why": "no caller line: GenomicsDBImport of inputs whose callers the header does not name"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10270, "why": "No rule determined a value for variant_kind"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for variant_kind"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for variant_kind"}, {"ext": ".pvar", "count": 2854, "why": "not a VCF: a PLINK 2 .pvar records no step of its own"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for variant_kind"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for variant_kind"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for variant_kind"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for variant_kind"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for variant_kind"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for variant_kind"}, {"ext": ".gfa", "count": 326, "why": "No rule determined a value for variant_kind"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for variant_kind"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for variant_kind"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for variant_kind"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for variant_kind"}, {"ext": ".xg", "count": 8, "why": "No rule determined a value for variant_kind"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gbwt", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for variant_kind"}, {"ext": ".gbz", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for variant_kind"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for variant_kind"}], "conflict_breakdown": [], "notes": "**Note**: Read from the caller that made a VCF: its header's producing step, walked back through steps that keep the kind, or a `##source` naming one tool, looked up in `rules/callers.yaml` (#654); a GenomicsDB workspace's from the caller its own `vcfheader.vcf` names, found the same way (#678). Not applicable to a file whose rule says it holds no variants. An index, a VCF genotyped from a GenomicsDB workspace (whose header names the import but not the caller) and a merge of such VCFs take their parents' kind only at reconcile, which this report does not read."}, {"field": "variant_origin", "label": "Variant Origin", "classified": 419369, "not_classified": 288719, "conflict": 0, "values": [{"name": "germline", "count": 293395, "extensions": [{"ext": ".vcf", "count": 166556}, {"ext": "(none)", "count": 124335}, {"ext": ".g.vcf", "count": 2504}]}, {"name": "not_classified", "count": 288719, "extensions": [{"ext": ".tbi", "count": 169531}, {"ext": ".csi", "count": 41186}, {"ext": ".vcf", "count": 35112}, {"ext": ".crai", "count": 10317}, {"ext": "(none)", "count": 10270}, {"ext": ".txt", "count": 4929}, {"ext": ".pgen", "count": 2854}, {"ext": ".pvar", "count": 2854}, {"ext": ".bed", "count": 2771}, {"ext": ".bai", "count": 2742}, {"ext": ".gff3", "count": 1565}, {"ext": ".chain", "count": 926}, {"ext": ".tsv", "count": 899}, {"ext": ".fai", "count": 477}, {"ext": ".gzi", "count": 466}, {"ext": ".bigwig", "count": 462}, {"ext": ".sizes", "count": 458}, {"ext": ".gfa", "count": 326}, {"ext": ".paf", "count": 297}, {"ext": ".sam", "count": 192}, {"ext": ".csv", "count": 18}, {"ext": ".dict", "count": 9}, {"ext": ".xg", "count": 8}, {"ext": ".pbi", "count": 7}, {"ext": ".dist", "count": 6}, {"ext": ".gbwt", "count": 6}, {"ext": ".gg", "count": 6}, {"ext": ".min", "count": 6}, {"ext": ".snarls", "count": 6}, {"ext": ".trans", "count": 6}, {"ext": ".gbz", "count": 2}, {"ext": ".hal", "count": 2}, {"ext": ".hapl", "count": 2}, {"ext": ".delta", "count": 1}]}, {"name": "not_applicable", "count": 125974, "extensions": [{"ext": ".txt", "count": 37550}, {"ext": ".fastq", "count": 21270}, {"ext": ".md5", "count": 14233}, {"ext": ".fast5", "count": 12509}, {"ext": ".cram", "count": 10623}, {"ext": ".bed", "count": 8752}, {"ext": ".bam", "count": 6774}, {"ext": ".log", "count": 3637}, {"ext": ".png", "count": 3074}, {"ext": ".psam", "count": 2854}, {"ext": ".bw", "count": 2536}, {"ext": ".fa", "count": 940}, {"ext": ".sf", "count": 634}, {"ext": ".h5ad", "count": 350}, {"ext": ".idat", "count": 160}, {"ext": ".fasta", "count": 38}, {"ext": ".tsv", "count": 24}, {"ext": ".pod5", "count": 11}, {"ext": ".csv", "count": 3}, {"ext": ".fna", "count": 2}]}], "not_classified_breakdown": [{"ext": ".tbi", "count": 169531, "why": "No reason recorded"}, {"ext": ".csi", "count": 41186, "why": "No reason recorded"}, {"ext": ".vcf", "count": 35112, "why": "no caller line: GenomicsDBImport of inputs whose callers the header does not name"}, {"ext": ".crai", "count": 10317, "why": "No reason recorded"}, {"ext": "(none)", "count": 10270, "why": "No rule determined a value for variant_origin"}, {"ext": ".txt", "count": 4929, "why": "No rule determined a value for variant_origin"}, {"ext": ".pgen", "count": 2854, "why": "No rule determined a value for variant_origin"}, {"ext": ".pvar", "count": 2854, "why": "not a VCF: a PLINK 2 .pvar records no step of its own"}, {"ext": ".bed", "count": 2771, "why": "No rule determined a value for variant_origin"}, {"ext": ".bai", "count": 2742, "why": "No reason recorded"}, {"ext": ".gff3", "count": 1565, "why": "No rule determined a value for variant_origin"}, {"ext": ".chain", "count": 926, "why": "No rule determined a value for variant_origin"}, {"ext": ".tsv", "count": 899, "why": "No rule determined a value for variant_origin"}, {"ext": ".fai", "count": 477, "why": "No reason recorded"}, {"ext": ".gzi", "count": 466, "why": "No reason recorded"}, {"ext": ".bigwig", "count": 462, "why": "No rule determined a value for variant_origin"}, {"ext": ".sizes", "count": 458, "why": "No rule determined a value for variant_origin"}, {"ext": ".gfa", "count": 326, "why": "No rule determined a value for variant_origin"}, {"ext": ".paf", "count": 297, "why": "No rule determined a value for variant_origin"}, {"ext": ".sam", "count": 192, "why": "No rule determined a value for variant_origin"}, {"ext": ".csv", "count": 18, "why": "No rule determined a value for variant_origin"}, {"ext": ".dict", "count": 9, "why": "No rule determined a value for variant_origin"}, {"ext": ".xg", "count": 8, "why": "No rule determined a value for variant_origin"}, {"ext": ".pbi", "count": 7, "why": "No reason recorded"}, {"ext": ".dist", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gbwt", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gg", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".min", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".snarls", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".trans", "count": 6, "why": "No rule determined a value for variant_origin"}, {"ext": ".gbz", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".hal", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".hapl", "count": 2, "why": "No rule determined a value for variant_origin"}, {"ext": ".delta", "count": 1, "why": "No rule determined a value for variant_origin"}], "conflict_breakdown": [], "notes": "**Note**: Germline or somatic, read from the caller a VCF's header names, or the caller of the calls a GenomicsDB workspace imported, found as for the kind and looked up in `rules/callers.yaml` (#658, #678). A caller with a somatic mode (Sniffles2) gives its origin only where its command line shows the mode was off. Not applicable to a file whose rule says it holds no variants. An index, a VCF genotyped from a workspace, a merge of such VCFs and a filtered callset take their parents' origin only at reconcile, which this report does not read."}]}; document.getElementById('run-time').textContent = DATA.run_time; diff --git a/docs/reconcile-dashboard.html b/docs/reconcile-dashboard.html index fc67a50e..ee3aa599 100644 --- a/docs/reconcile-dashboard.html +++ b/docs/reconcile-dashboard.html @@ -118,7 +118,7 @@

Inheritance: what each file takes from its parents