{"built":"2026-10-30","sources":[{"what":"TCGA PanCancer Atlas MC3 public somatic mutation calls","file":"mc3.v0.2.8.PUBLIC.maf.gz","gdc_file_id":"1c8cfe5f-e52d-41ba-94da-f15ea1337efc","url":"https://api.gdc.cancer.gov/data/1c8cfe5f-e52d-41ba-94da-f15ea1337efc","size_bytes":753339089,"md5":"639ad8f8386e98dacc22e439188aa8fa","version":"MC3 v0.2.8 PUBLIC","access":"open","credit":"The TCGA Research Network; Ellrott K et al. Scalable open science approach for mutation calling of tumor exomes using multiple genomic pipelines. Cell Systems 6(3):271-281 (2018)."},{"what":"PanCanAtlas merged sample quality annotations (patient -> cancer type)","file":"merged_sample_quality_annotations.tsv","gdc_file_id":"1a7d7be8-675d-4e60-a105-19d4121bdebf","url":"https://api.gdc.cancer.gov/data/1a7d7be8-675d-4e60-a105-19d4121bdebf","size_bytes":8463670,"md5":"05ddd2270fb1fb24fbdc2fe9bf7384e5","access":"open","page":"https://gdc.cancer.gov/about-data/publications/pancanatlas"},{"what":"GDC cases API, project_id for patients missing from the annotation table","url":"https://api.gdc.cancer.gov/cases","patients":5},{"what":"Protein length of the MC3 transcript","url":"https://grch37.rest.ensembl.org/lookup/id","note":"Ensembl GRCh37 REST, Translation.length of the exact ENST id; MC3 Protein_position has no '/length'","transcripts":19707},{"what":"Pfam domains","url":"https://www.ebi.ac.uk/interpro/api/entry/pfam/protein/reviewed/<UniProt>/","licence":"Pfam / InterPro: CC0","note":"shown only where UniProt length == Ensembl translation length"},{"what":"UniProt accession and length","url":"https://rest.uniprot.org/uniprotkb/stream","licence":"CC BY 4.0"},{"what":"Signature descriptions used for labels","credit":"Alexandrov LB et al. The repertoire of mutational signatures in human cancer. Nature 578:94-101 (2020), CC BY 4.0","note":"labels come from verbal descriptions turned into coarse prototypes; no COSMIC matrices are used or redistributed"},{"what":"cancerhotspots.org v2 single-residue list, test comparison only, not redistributed","url":"https://www.cancerhotspots.org/api/hotspots/single","md5":"db5ad852400c3c3d5f2452a9822864b3"}],"filters":{"FILTER_tokens_kept":["PASS","native_wga_mix","wga"],"one_tumour_per_patient":true,"counts":{"maf_rows":3600963,"maf_tumour_aliquots":10295,"passing_rows":3224675,"filter_token_counts":{"PASS":2907335,"wga":308568,"oxog":181627,"nonpreferredpair":162930,"common_in_exac":25372,"native_wga_mix":13099,"StrandBias":11718,"gapfiller":1405},"patients_passing":10183,"patients_typed_by_sqa":10177,"patients_typed_by_gdc_api":5,"patients_untyped_dropped":1,"tumour_aliquots_with_passing_calls":10182,"tumours_kept_one_per_patient":10182,"hypermutated_tumours":912,"passing_rows_kept":3224656,"coding_rows_kept":2710434,"snv_rows_kept":3061532,"cancer_types":{"BRCA":1020,"LUAD":567,"UCEC":530,"LGG":511,"HNSC":507,"PRAD":495,"THCA":492,"LUSC":485,"SKCM":466,"STAD":439,"OV":412,"BLCA":411,"GBM":393,"COAD":385,"KIRC":369,"LIHC":363,"CESC":289,"KIRP":281,"SARC":236,"ESCA":184,"PCPG":179,"PAAD":177,"TGCT":145,"LAML":140,"READ":135,"THYM":122,"ACC":92,"MESO":81,"UVM":80,"KICH":66,"UCS":57,"DLBC":37,"CHOL":36}}},"hotspots":{"method":"per-residue binomial, uniform over protein length within gene, weighted counts, BH","hypermutated_rule":"> 500 passing coding mutations -> weight 500/n_coding","q_max":0.01,"min_tumours":3,"stats":{"missense_calls":1716319,"missense_on_main_transcript":1712214,"missense_gene_without_length":0,"missense_tested":1711984,"tests_pan":1416145,"hotspots_pan":976,"genes_with_pan_hotspot":750,"tests_per_type":1622360,"hotspots_per_type":1116}},"signatures":{"method":"Poisson (KL) NMF, multiplicative updates, bootstrap replicates, Hungarian matching","nmf_cap_snvs":2000,"selection":{"rule":"largest K with min stability >= 0.80, mean stability >= 0.90 and median reconstruction cosine gain >= 0.002 over K-1","reps":8,"chosen_K":7,"table":[{"K":2,"stability_mean":0.9999888287782381,"stability_min":0.9999850284255989,"reconstruction_median_cosine":0.8011269223104482,"reconstruction_gain":0.8011269223104482},{"K":3,"stability_mean":0.9999653474167287,"stability_min":0.9999150779267225,"reconstruction_median_cosine":0.8371811828008062,"reconstruction_gain":0.03605426049035798},{"K":4,"stability_mean":0.9708918139284488,"stability_min":0.906932447825638,"reconstruction_median_cosine":0.8723693230764301,"reconstruction_gain":0.03518814027562389},{"K":5,"stability_mean":0.9999145598643147,"stability_min":0.9997837272417263,"reconstruction_median_cosine":0.8799988716109262,"reconstruction_gain":0.0076295485344960445},{"K":6,"stability_mean":0.9997664108428658,"stability_min":0.9989550935354728,"reconstruction_median_cosine":0.8862133559504168,"reconstruction_gain":0.006214484339490678},{"K":7,"stability_mean":0.9997060606853738,"stability_min":0.9986419320038116,"reconstruction_median_cosine":0.8999610257025621,"reconstruction_gain":0.013747669752145253},{"K":8,"stability_mean":0.960306446182809,"stability_min":0.7753214869908726,"reconstruction_median_cosine":0.899354433393823,"reconstruction_gain":-0.0006065923087390512},{"K":9,"stability_mean":0.9547021140372771,"stability_min":0.7886817160846932,"reconstruction_median_cosine":0.9083987173539501,"reconstruction_gain":0.00904428396012702},{"K":10,"stability_mean":0.94776236741364,"stability_min":0.6315214967767933,"reconstruction_median_cosine":0.9057040208553643,"reconstruction_gain":-0.00269469649858578},{"K":11,"stability_mean":0.9092093065937121,"stability_min":0.5648440870844929,"reconstruction_median_cosine":0.902493774232511,"reconstruction_gain":-0.0032102466228532966},{"K":12,"stability_mean":0.9426941907395117,"stability_min":0.6260835188870437,"reconstruction_median_cosine":0.9174730230715002,"reconstruction_gain":0.014979248838989268},{"K":13,"stability_mean":0.9273835649736657,"stability_min":0.47632692710045255,"reconstruction_median_cosine":0.9211651751943737,"reconstruction_gain":0.0036921521228734377},{"K":14,"stability_mean":0.8856510580097199,"stability_min":0.4060795606583999,"reconstruction_median_cosine":0.9249120446125219,"reconstruction_gain":0.0037468694181481688}]},"context_check":{"snvs":3061532,"context_len_11":3061532,"context_mid_equals_ref":3061532,"snvs_used":3061532,"snvs_with_strand":3061532}},"licences":{"site_data":"derived from open-access TCGA MC3; follow the NIH/TCGA data use guidance","excluded":"No COSMIC data, no controlled-access data"}}