{ "schema_version": "1.0.0", "description": "Verified public FASTQ reads, alignment derivatives and regenerated indexes. File sizes and checksums identify the actual downloadable objects; originals remain preserved privately.", "records": [ { "release_file_id": "M-RAW-001", "source_file_id": "M-FILE-031", "assay_id": "M-ASSAY-004", "sample_ids": [ "M-SAMPLE-002" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-001_resection_tumour_rna_grch37.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-001_resection_tumour_rna_grch37.bam", "storage": "external", "format": "BAM", "reference_build": "GRCh37", "bytes": 494203491, "sha256": "54420248ab183182bb7a312ce6574ace38c91f1ca1b53f394e90fbfd730f3859", "record_count": 13970734, "role": "tumour_RNA_alignment", "companion_file_id": "M-RAW-002", "generated_from_release_file_id": null, "source_relationship": "metadata_sanitized_alignment", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T15:43:10.865934+00:00", "integrity_verification": "Full authenticated and anonymous public-object SHA-256 readbacks match the approved local file; anonymous HEAD, range response and CORS verified.", "data_record_preservation": "Full source/output normalized record digests agree; all read names, sequences, qualities and alignment fields preserved except declared read-group metadata.", "metadata_transform": "Read-group identifiers replaced with public identifiers; private header metadata removed; alignment-reference dictionary retained.", "purpose_and_limitations": "Bulk tumour RNA alignment; exact GRCh37 sequence dictionary retained. Original RNA header supplied no reference MD5 values.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-002", "source_file_id": "M-FILE-032", "assay_id": "M-ASSAY-004", "sample_ids": [ "M-SAMPLE-002" ], "data_class": "regenerated_alignment_index", "filename": "m-raw-001_resection_tumour_rna_grch37.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-001_resection_tumour_rna_grch37.bam.bai", "storage": "external", "format": "BAI", "reference_build": "GRCh37", "bytes": 2619272, "sha256": "f286853c08fbf1b5bfa7853ca2a884e3a2b60f2d8b8f42ba2eb0597bf34b2b60", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-001", "generated_from_release_file_id": "M-RAW-001", "source_relationship": "replacement_index_regenerated_from_released_BAM", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T15:43:10.865934+00:00", "integrity_verification": "Full authenticated and anonymous public-object SHA-256 readbacks match the approved local file; anonymous HEAD, range response and CORS verified.", "data_record_preservation": "Regenerated against the released BAM and validated by index counts and indexed queries; not a copy of the source index.", "metadata_transform": "Index regenerated after BAM metadata transformation.", "purpose_and_limitations": "Companion BAI; download with its matching released BAM.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-003", "source_file_id": "M-FILE-028", "assay_id": "M-ASSAY-003", "sample_ids": [ "M-SAMPLE-004" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-003_matched_normal_dna_grch37.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-003_matched_normal_dna_grch37.bam", "storage": "external", "format": "BAM", "reference_build": "GRCh37", "bytes": 2144790350, "sha256": "d998b8c74aa7a63ad14489f50f66bb41391cf70f9cd06eb56883327eef239786", "record_count": 53128875, "role": "matched_normal_DNA_alignment", "companion_file_id": "M-RAW-004", "generated_from_release_file_id": null, "source_relationship": "metadata_sanitized_alignment", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T15:43:10.865934+00:00", "integrity_verification": "Full authenticated and anonymous public-object SHA-256 readbacks match the approved local file; anonymous HEAD, range response and CORS verified.", "data_record_preservation": "Full source/output normalized record digests agree; all read names, sequences, qualities and alignment fields preserved except declared read-group metadata.", "metadata_transform": "Read-group identifiers replaced with public identifiers; private header metadata removed; alignment-reference dictionary retained.", "purpose_and_limitations": "Matched-normal targeted panel DNA alignment. The Tempus report identifies the matched-normal specimen as blood collected 28 January 2025 and received 30 January 2025. Preservation is not specified here.", "license_status": "per_dataset_release_policy", "source_ids": [ "M-SOURCE-002" ] }, { "release_file_id": "M-RAW-004", "source_file_id": "M-FILE-029", "assay_id": "M-ASSAY-003", "sample_ids": [ "M-SAMPLE-004" ], "data_class": "regenerated_alignment_index", "filename": "m-raw-003_matched_normal_dna_grch37.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-003_matched_normal_dna_grch37.bam.bai", "storage": "external", "format": "BAI", "reference_build": "GRCh37", "bytes": 4538856, "sha256": "d7d48722ce3273fdcfa16f4612f84e08ff38ae1ae216188b4c6c8d004a08e55e", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-003", "generated_from_release_file_id": "M-RAW-003", "source_relationship": "replacement_index_regenerated_from_released_BAM", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T15:43:10.865934+00:00", "integrity_verification": "Full authenticated and anonymous public-object SHA-256 readbacks match the approved local file; anonymous HEAD, range response and CORS verified.", "data_record_preservation": "Regenerated against the released BAM and validated by index counts and indexed queries; not a copy of the source index.", "metadata_transform": "Index regenerated after BAM metadata transformation.", "purpose_and_limitations": "Companion BAI; download with its matching released BAM. The Tempus report identifies the matched-normal specimen as blood collected 28 January 2025 and received 30 January 2025. Preservation is not specified here.", "license_status": "per_dataset_release_policy", "source_ids": [ "M-SOURCE-002" ] }, { "release_file_id": "M-RAW-007", "source_file_id": "M-FILE-015", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-002", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-007_caris_primary_tumour_rna_r1.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-007_caris_primary_tumour_rna_r1.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 1015024932, "sha256": "31f29613e42f172533415c34b5d54311542a013d4e12a53903e3dae0a23dc09c", "record_count": 14875459, "role": "RNA_reads_R1", "companion_file_id": "M-RAW-008", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:00:44.486840+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename and normalized gzip headers; compressed deflate payload and all decompressed FASTQ bytes retained exactly.", "purpose_and_limitations": "Caris primary tumour bulk RNA; specimen-level mapping to primary rectal tumour. Exact block/aliquot and original pipeline metadata remain requested. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates." }, { "release_file_id": "M-RAW-008", "source_file_id": "M-FILE-016", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-002", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-008_caris_primary_tumour_rna_r2.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-008_caris_primary_tumour_rna_r2.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 1063566484, "sha256": "9758220620bc9fe618af849578605f77938d2474ae4f1472e3d3fe9bfe150153", "record_count": 14875459, "role": "RNA_reads_R2", "companion_file_id": "M-RAW-007", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:01:36.065342+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename and normalized gzip headers; compressed deflate payload and all decompressed FASTQ bytes retained exactly.", "purpose_and_limitations": "Caris primary tumour bulk RNA; specimen-level mapping to primary rectal tumour. Exact block/aliquot and original pipeline metadata remain requested. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates." }, { "release_file_id": "M-RAW-005", "source_file_id": "M-FILE-005", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-008", "sample_ids": [ "M-SAMPLE-007" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-005_caris_specimen_unresolved_rna_r1.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-005_caris_specimen_unresolved_rna_r1.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 860056338, "sha256": "6b2d588b8b549b51f48345d6ffdd8b4b5d44b4219ba3b81902b604280b4f4eb8", "record_count": 10120768, "role": "RNA_reads_R1", "companion_file_id": "M-RAW-006", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:02:24.838676+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename; gzip header already canonical, original compressed bytes retained exactly.", "purpose_and_limitations": "Additional Caris RNA; tissue source, collection date and tumour fraction remain unconfirmed. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates." }, { "release_file_id": "M-RAW-006", "source_file_id": "M-FILE-006", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-008", "sample_ids": [ "M-SAMPLE-007" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-006_caris_specimen_unresolved_rna_r2.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-006_caris_specimen_unresolved_rna_r2.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 893425129, "sha256": "c876f919b92859dfaa1428198647ba87b68f50ad30162b8c553857efd67de01d", "record_count": 10120768, "role": "RNA_reads_R2", "companion_file_id": "M-RAW-005", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:03:14.184267+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename; gzip header already canonical, original compressed bytes retained exactly.", "purpose_and_limitations": "Additional Caris RNA; tissue source, collection date and tumour fraction remain unconfirmed. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates." }, { "release_file_id": "M-RAW-013", "source_file_id": "M-FILE-027", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-004", "sample_ids": [ "M-SAMPLE-002" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-013_tempus_resection_tumour_rna_read1.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-013_tempus_resection_tumour_rna_read1.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 703418709, "sha256": "f4486f8be6554c751aff51ad5e6457e919d0113498c85988956511be1362b6d7", "record_count": 13837280, "role": "RNA_reads_ordinal_1", "companion_file_id": "M-RAW-014", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:03:46.122387+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename and normalized gzip headers; compressed deflate payload and all decompressed FASTQ bytes retained exactly.", "purpose_and_limitations": "Tempus RNA archive from rectal resection specimen; original read ordinals 1 and 3 retained. Matching instrument/inline-sequence identifiers establish corresponding records; exact library read structure remains requested. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed. Vendor read ordinals are 1 and 3. No claim that a biological mate or index read 2 is missing; vendor chemistry/read-structure confirmation is needed. The associated released BAM contains 13,970,734 unpaired SAM records; these raw files contain 13,837,280 matching records each. BAM read names include merged/pair processing suffixes. The exact transformation is not documented here, so raw-read and alignment-record counts are not directly comparable.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates.", "source_read_ordinal": 1 }, { "release_file_id": "M-RAW-014", "source_file_id": "M-FILE-027", "generated_from_source_file_id": null, "assay_id": "M-ASSAY-004", "sample_ids": [ "M-SAMPLE-002" ], "data_class": "unaligned_sequence_reads", "filename": "m-raw-014_tempus_resection_tumour_rna_read3.fastq.gz", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-014_tempus_resection_tumour_rna_read3.fastq.gz", "storage": "external", "format": "FASTQ_GZIP", "reference_build": null, "bytes": 712079610, "sha256": "96770bf6b27a792f2528a550372912f04e5e5c3afae616ded6b806ee6bc116e3", "record_count": 13837280, "role": "RNA_reads_ordinal_3", "companion_file_id": "M-RAW-013", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:04:22.006353+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All decompressed FASTQ bytes preserved exactly; only gzip container metadata normalized.", "metadata_transform": "Public-safe filename and normalized gzip headers; compressed deflate payload and all decompressed FASTQ bytes retained exactly.", "purpose_and_limitations": "Tempus RNA archive from rectal resection specimen; original read ordinals 1 and 3 retained. Matching instrument/inline-sequence identifiers establish corresponding records; exact library read structure remains requested. Bulk RNA, not single-cell data. Original pipeline/reference checksum and exact library structure remain requested. Pair identity/order and biological bytes verified; no new alignment or variant analysis performed. Vendor read ordinals are 1 and 3. No claim that a biological mate or index read 2 is missing; vendor chemistry/read-structure confirmation is needed. The associated released BAM contains 13,970,734 unpaired SAM records; these raw files contain 13,837,280 matching records each. BAM read names include merged/pair processing suffixes. The exact transformation is not documented here, so raw-read and alignment-record counts are not directly comparable.", "license_status": "per_dataset_release_policy", "reference_note": "Unaligned native reads; associated assay build does not define FASTQ coordinates.", "source_read_ordinal": 3 }, { "release_file_id": "M-RAW-009", "source_file_id": "M-FILE-007", "generated_from_source_file_id": "M-FILE-007", "assay_id": "M-ASSAY-008", "sample_ids": [ "M-SAMPLE-007" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-009_caris_specimen_unresolved_rna.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-009_caris_specimen_unresolved_rna.bam", "storage": "external", "format": "BAM", "reference_build": "GRCh38", "bytes": 1050057991, "sha256": "6183dbd553ca0c1d4c4f5e9a6166f6d20991872c6c469a6f36c7365b8bf6a3d6", "record_count": 26199362, "role": "RNA_alignment", "companion_file_id": "M-RAW-010", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:05:17.783574+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All non-RG alignment record content preserved; read-group/header metadata sanitized.", "metadata_transform": "Identifying header fields sanitized; scientific records retained.", "purpose_and_limitations": "Additional Caris RNA; tissue source, collection date and tumour fraction remain unconfirmed. No new biological analysis or clinical interpretation performed. Source sequence dictionary retained; verify exact reference FASTA/checksums before reanalysis.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-010", "source_file_id": null, "generated_from_source_file_id": "M-FILE-007", "assay_id": "M-ASSAY-008", "sample_ids": [ "M-SAMPLE-007" ], "data_class": "regenerated_alignment_index", "filename": "m-raw-009_caris_specimen_unresolved_rna.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-009_caris_specimen_unresolved_rna.bam.bai", "storage": "external", "format": "BAI", "reference_build": "GRCh38", "bytes": 4240152, "sha256": "a16970447d52f12ed1f590c184d4ce5f35ae63fdcba639dcbc5686a96f5238de", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-009", "generated_from_release_file_id": "M-RAW-009", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:05:20.225391+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "Regenerated and checked against released BAM.", "metadata_transform": "Index regenerated from the released companion file.", "purpose_and_limitations": "Additional Caris RNA; tissue source, collection date and tumour fraction remain unconfirmed. No new biological analysis or clinical interpretation performed. Source sequence dictionary retained; verify exact reference FASTA/checksums before reanalysis.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-011", "source_file_id": "M-FILE-014", "generated_from_source_file_id": "M-FILE-014", "assay_id": "M-ASSAY-002", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-011_caris_primary_tumour_rna.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-011_caris_primary_tumour_rna.bam", "storage": "external", "format": "BAM", "reference_build": "GRCh38", "bytes": 1398673979, "sha256": "36ae0376418707bb971615e42cf456630a996dec5b59cebc4bbd920695d44c54", "record_count": 40256834, "role": "RNA_alignment", "companion_file_id": "M-RAW-012", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:06:31.313550+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All non-RG alignment record content preserved; read-group/header metadata sanitized.", "metadata_transform": "Identifying header fields sanitized; scientific records retained.", "purpose_and_limitations": "Primary rectal tumour specimen-level mapping; exact block/aliquot and original pipeline checksum remain requested. No new biological analysis or clinical interpretation performed. Source sequence dictionary retained; verify exact reference FASTA/checksums before reanalysis.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-012", "source_file_id": null, "generated_from_source_file_id": "M-FILE-014", "assay_id": "M-ASSAY-002", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "regenerated_alignment_index", "filename": "m-raw-011_caris_primary_tumour_rna.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-011_caris_primary_tumour_rna.bam.bai", "storage": "external", "format": "BAI", "reference_build": "GRCh38", "bytes": 3095104, "sha256": "3e7f649a3c40dcc29f582371a0cd2d18d945b4d89d86c5ecf8a91b5577075173", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-011", "generated_from_release_file_id": "M-RAW-011", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T17:06:33.545018+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "Regenerated and checked against released BAM.", "metadata_transform": "Index regenerated from the released companion file.", "purpose_and_limitations": "Primary rectal tumour specimen-level mapping; exact block/aliquot and original pipeline checksum remain requested. No new biological analysis or clinical interpretation performed. Source sequence dictionary retained; verify exact reference FASTA/checksums before reanalysis.", "license_status": "per_dataset_release_policy" }, { "release_file_id": "M-RAW-015", "source_file_id": "M-FILE-017", "generated_from_source_file_id": "M-FILE-017", "assay_id": "M-ASSAY-005", "sample_ids": [ "M-SAMPLE-005" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-015_natera_normal_input_dna.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-015_natera_normal_input_dna.bam", "storage": "external", "format": "BAM", "reference_build": "GRCh37_hs37d5", "bytes": 5741775270, "sha256": "a614b322e64bb58ff9d77c8819d740040d80c3f85ea617a9c1f14f017682eaba", "record_count": 116879500, "role": "normal_input_DNA_alignment", "companion_file_id": "M-RAW-016", "generated_from_release_file_id": null, "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T18:04:08.224064+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "All non-RG alignment record content preserved; read-group/header metadata sanitized.", "metadata_transform": "Identifying BAM header and read-group fields sanitized; non-RG alignment record content retained.", "purpose_and_limitations": "Sequencing file role verified from retained analysis records. Physical source material and collection date remain unconfirmed; normal input does not imply blood. Reference dictionary matches GRCh37/hs37d5; original reference MD5s were not supplied.", "license_status": "per_dataset_release_policy", "provider_id": "natera", "provider": "Natera", "assay_label": "Natera matched-normal exome", "specimens": [ { "sample_id": "M-SAMPLE-005", "label": "Natera matched-normal exome specimen", "anatomical_site": "not_confirmed", "role": "matched_normal", "collection_date": null, "date_precision": "unknown", "preservation": "not_confirmed", "provenance_status": "file_role_verified_from_retained_analysis_records", "source_ids": [ "M-SOURCE-006", "M-SOURCE-007", "M-SOURCE-012" ], "notes": "Sequencing file role verified as matched normal from retained analysis records. Physical source material and collection date remain unconfirmed." } ], "source_ids": [ "M-SOURCE-009", "M-SOURCE-012" ], "provenance_summary": "Sequencing file role verified from retained analysis records; physical source and collection date remain unconfirmed. No new biological analysis or clinical interpretation performed. GRCh37/hs37d5 dictionary confirmed from sequence names and lengths; no original reference MD5 values supplied. Physical source and collection date remain unconfirmed; normal input does not imply blood." }, { "release_file_id": "M-RAW-016", "source_file_id": "M-FILE-018", "generated_from_source_file_id": "M-FILE-017", "assay_id": "M-ASSAY-005", "sample_ids": [ "M-SAMPLE-005" ], "data_class": "regenerated_alignment_index", "filename": "m-raw-015_natera_normal_input_dna.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-015_natera_normal_input_dna.bam.bai", "storage": "external", "format": "BAI", "reference_build": "GRCh37_hs37d5", "bytes": 4293312, "sha256": "920e472e573b2d6388cf32ec53cfd70373509ae46cde8231f63a453acc1304c7", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-015", "generated_from_release_file_id": "M-RAW-015", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T18:04:10.942780+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved file; anonymous HEAD, byte-range and CORS checks passed.", "data_record_preservation": "Regenerated and checked against released BAM.", "metadata_transform": "Index regenerated from the released companion BAM.", "purpose_and_limitations": "Sequencing file role verified from retained analysis records. Physical source material and collection date remain unconfirmed; normal input does not imply blood. Reference dictionary matches GRCh37/hs37d5; original reference MD5s were not supplied.", "license_status": "per_dataset_release_policy", "provider_id": "natera", "provider": "Natera", "assay_label": "Natera matched-normal exome", "specimens": [ { "sample_id": "M-SAMPLE-005", "label": "Natera matched-normal exome specimen", "anatomical_site": "not_confirmed", "role": "matched_normal", "collection_date": null, "date_precision": "unknown", "preservation": "not_confirmed", "provenance_status": "file_role_verified_from_retained_analysis_records", "source_ids": [ "M-SOURCE-006", "M-SOURCE-007", "M-SOURCE-012" ], "notes": "Sequencing file role verified as matched normal from retained analysis records. Physical source material and collection date remain unconfirmed." } ], "source_ids": [ "M-SOURCE-009", "M-SOURCE-012" ], "provenance_summary": "Sequencing file role verified from retained analysis records; physical source and collection date remain unconfirmed. No new biological analysis or clinical interpretation performed. GRCh37/hs37d5 dictionary confirmed from sequence names and lengths; no original reference MD5 values supplied. Physical source and collection date remain unconfirmed; normal input does not imply blood." }, { "release_file_id": "M-RAW-017", "source_file_id": "M-FILE-010", "generated_from_source_file_id": "M-FILE-010", "assay_id": "M-ASSAY-001", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "aligned_sequence_reads", "filename": "m-raw-017_caris_primary_tumour_dna.bam", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-017_caris_primary_tumour_dna.bam", "storage": "external", "format": "BAM", "reference_build": "hg38_custom_masked_noHap", "reference_details": { "reference_build": "hg38_custom_masked_noHap", "reference_fasta_basename": "hg38.pU2AF1_Y_PAR_masked.noHap.fa", "source_header_contig_count": 152, "source_reference_MD5_entries_present": 0, "interpretation": "Custom masked hg38 reference identified by vendor processing metadata; obtain the exact FASTA/checksum for reanalysis." }, "bytes": 12301791569, "sha256": "3636d66e00a9efbc7ff2c1fb08d96ecd1a3d24d4c7748041e94cb95068c8f693", "record_count": 291350769, "role": "tumour_DNA_alignment", "companion_file_id": "M-RAW-018", "generated_from_release_file_id": null, "source_relationship": "metadata_sanitized_alignment", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": true, "public_read_without_credentials": true, "verified_at": "2026-10-07T23:07:38.266341+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved local file; anonymous HEAD, range and CORS passed.", "data_record_preservation": "Complete source/output scientific record digests match across 291,350,769 alignments; all non-RG alignment content retained.", "metadata_transform": "Private header metadata removed; read groups replaced with public identifiers; original reference dictionary retained.", "purpose_and_limitations": "Custom masked hg38 reference; exact FASTA/checksum required for reproducible reanalysis. File mapping is specimen-level; exact block/aliquot remains unconfirmed.", "license_status": "per_dataset_release_policy", "provider_id": "caris", "provider": "Caris", "group": "Raw sequencing", "title": "Caris primary rectal tumour DNA alignment", "description": "DNA alignment from the initial rectal biopsy; report collection date 27 March 2024.", "specimens": [ { "sample_id": "M-SAMPLE-001", "label": "Initial rectal primary biopsy", "anatomical_site": "rectum", "role": "primary_tumour", "collection_date": "2024-03-27", "date_precision": "day", "preservation": "FFPE_reported", "provenance_status": "primary_Caris_report_confirmed", "source_ids": [ "M-SOURCE-001", "M-SOURCE-006" ], "notes": "Rectal biopsy collected 27 March 2024; Caris report issued 3 June 2026. The molecular testing date is not the biopsy date." } ], "assay_label": "Caris primary DNA", "source_ids": [ "M-SOURCE-001", "M-SOURCE-006", "M-SOURCE-009" ], "related_report_ids": [ "RPT-CARIS" ], "provenance_summary": "Mapped to the initial rectal biopsy collected 27 March 2024, at specimen level. Exact source BAM block/aliquot mapping remains unconfirmed.", "preparation": "All non-RG alignment record content preserved; read-group/header metadata sanitized.", "browse_modality": "dna", "browse_type": "Tumour DNA alignments and indexes" }, { "release_file_id": "M-RAW-018", "source_file_id": null, "generated_from_source_file_id": "M-FILE-010", "assay_id": "M-ASSAY-001", "sample_ids": [ "M-SAMPLE-001" ], "data_class": "alignment_index", "filename": "m-raw-017_caris_primary_tumour_dna.bam.bai", "path": null, "download_url": "https://alexander-young-cancer-data.alextisyoung.workers.dev/releases/2026-10-07/raw/m-raw-017_caris_primary_tumour_dna.bam.bai", "storage": "external", "format": "BAI", "reference_build": "hg38_custom_masked_noHap", "reference_details": { "reference_build": "hg38_custom_masked_noHap", "reference_fasta_basename": "hg38.pU2AF1_Y_PAR_masked.noHap.fa", "source_header_contig_count": 152, "source_reference_MD5_entries_present": 0, "interpretation": "Custom masked hg38 reference identified by vendor processing metadata; obtain the exact FASTA/checksum for reanalysis." }, "bytes": 4221952, "sha256": "804dbdc5e83c1f049447496359b7ec8d0d69443cb799267b4f78dfab9cc7dd06", "record_count": null, "role": "BAM_index", "companion_file_id": "M-RAW-017", "generated_from_release_file_id": "M-RAW-017", "source_relationship": "regenerated_index", "preparation_status": "verified_for_release", "availability": "verified_public_download", "included_in_release": true, "sequence_reads": false, "public_read_without_credentials": true, "verified_at": "2026-10-07T23:07:40.347901+00:00", "integrity_verification": "Full authenticated and anonymous SHA-256 readbacks match the approved local file; anonymous HEAD, range and CORS passed.", "data_record_preservation": "Regenerated index checked against all 291,350,769 BAM records.", "metadata_transform": "Index regenerated from the prepared BAM.", "purpose_and_limitations": "Custom masked hg38 reference; exact FASTA/checksum required for reproducible reanalysis. File mapping is specimen-level; exact block/aliquot remains unconfirmed.", "license_status": "per_dataset_release_policy", "provider_id": "caris", "provider": "Caris", "group": "Raw sequencing", "title": "Caris primary rectal tumour DNA alignment index", "description": "Regenerated index for the matching primary rectal tumour DNA BAM.", "specimens": [ { "sample_id": "M-SAMPLE-001", "label": "Initial rectal primary biopsy", "anatomical_site": "rectum", "role": "primary_tumour", "collection_date": "2024-03-27", "date_precision": "day", "preservation": "FFPE_reported", "provenance_status": "primary_Caris_report_confirmed", "source_ids": [ "M-SOURCE-001", "M-SOURCE-006" ], "notes": "Rectal biopsy collected 27 March 2024; Caris report issued 3 June 2026. The molecular testing date is not the biopsy date." } ], "assay_label": "Caris primary DNA", "source_ids": [ "M-SOURCE-001", "M-SOURCE-006", "M-SOURCE-009" ], "related_report_ids": [ "RPT-CARIS" ], "provenance_summary": "Mapped to the initial rectal biopsy collected 27 March 2024, at specimen level. Exact source BAM block/aliquot mapping remains unconfirmed.", "preparation": "Regenerated and checked against the prepared BAM.", "browse_modality": "dna", "browse_type": "Tumour DNA alignments and indexes" } ], "updated": "2026-10-07", "status": "release_1.4" }