# HRD prediction on TCGA-LUAD Source: [HRD prediction on TCGA-LUAD]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:24:39.912Z Evaluation of models for predicting Homologous Recombination Deficiency (HRD) status using the Lung Adenocarcinoma (LUAD) cohort from The Cancer Genome Atlas (TCGA). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | HRD prediction | | Dataset (including any stated split) | TCGA-LUAD | | Metric | AUC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [AUC](): Higher is better; unit: SCALAR. - [AUPRC](): Higher is better; unit: SCALAR. ## Recorded results | Method | AUC | Result date | Report paper | | --- | --- | --- | --- | | dwa + pcgrad | 0.734 | Not recorded | 68fa72771e209131cea56894 | | dwa | 0.733 | Not recorded | 68fa72771e209131cea56894 | | uncert | 0.732 | Not recorded | 68fa72771e209131cea56894 | | cagrad | 0.726 | Not recorded | 68fa72771e209131cea56894 | | dwa + graddrop | 0.726 | Not recorded | 68fa72771e209131cea56894 | | uncert + graddrop | 0.726 | Not recorded | 68fa72771e209131cea56894 | | uncert + cagrad | 0.724 | Not recorded | 68fa72771e209131cea56894 | | autol | 0.722 | Not recorded | 68fa72771e209131cea56894 | | pcgrad | 0.721 | Not recorded | 68fa72771e209131cea56894 | | autol + pcgrad | 0.72 | Not recorded | 68fa72771e209131cea56894 | | autol + cagrad | 0.719 | Not recorded | 68fa72771e209131cea56894 | | dwa + cagrad | 0.718 | Not recorded | 68fa72771e209131cea56894 | | uncert + pcgrad | 0.718 | Not recorded | 68fa72771e209131cea56894 | | baseline | 0.716 | Not recorded | 68fa72771e209131cea56894 | | graddrop | 0.711 | Not recorded | 68fa72771e209131cea56894 | | autol + graddrop | 0.708 | Not recorded | 68fa72771e209131cea56894 | | SOTA | 0.7 | Not recorded | 68fa72771e209131cea56894 | | naive | 0.696 | Not recorded | 68fa72771e209131cea56894 | ### dwa + pcgrad AUC: 0.734. Result ID: 69923ac73a6c3148490d791e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"dwa","gradient\_strategy":"pcgrad"}. This record does not assert independent reproduction. ### dwa AUC: 0.733. Result ID: 69923ac73a6c3148490d7917. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"dwa"}. This record does not assert independent reproduction. ### uncert AUC: 0.732. Result ID: 69923ac73a6c3148490d7918. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"uncertainty"}. This record does not assert independent reproduction. ### cagrad AUC: 0.726. Result ID: 69923ac73a6c3148490d791c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"gradient\_strategy":"cagrad"}. This record does not assert independent reproduction. ### dwa + graddrop AUC: 0.726. Result ID: 69923ac73a6c3148490d791d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"dwa","gradient\_strategy":"graddrop"}. This record does not assert independent reproduction. ### uncert + graddrop AUC: 0.726. Result ID: 69923ac73a6c3148490d7920. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"uncertainty","gradient\_strategy":"graddrop"}. This record does not assert independent reproduction. ### uncert + cagrad AUC: 0.724. Result ID: 69923ac73a6c3148490d7922. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"uncertainty","gradient\_strategy":"cagrad"}. This record does not assert independent reproduction. ### autol AUC: 0.722. Result ID: 69923ac73a6c3148490d7919. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"autol"}. This record does not assert independent reproduction. ### pcgrad AUC: 0.721. Result ID: 69923ac73a6c3148490d791b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"gradient\_strategy":"pcgrad"}. This record does not assert independent reproduction. ### autol + pcgrad AUC: 0.72. Result ID: 69923ac73a6c3148490d7924. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"autol","gradient\_strategy":"pcgrad"}. This record does not assert independent reproduction. ### autol + cagrad AUC: 0.719. Result ID: 69923ac73a6c3148490d7925. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"autol","gradient\_strategy":"cagrad"}. This record does not assert independent reproduction. ### dwa + cagrad AUC: 0.718. Result ID: 69923ac73a6c3148490d791f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"dwa","gradient\_strategy":"cagrad"}. This record does not assert independent reproduction. ### uncert + pcgrad AUC: 0.718. Result ID: 69923ac73a6c3148490d7921. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"uncertainty","gradient\_strategy":"pcgrad"}. This record does not assert independent reproduction. ### baseline AUC: 0.716. Result ID: 69923ac73a6c3148490d7915. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":false}. This record does not assert independent reproduction. ### graddrop AUC: 0.711. Result ID: 69923ac73a6c3148490d791a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"gradient\_strategy":"graddrop"}. This record does not assert independent reproduction. ### autol + graddrop AUC: 0.708. Result ID: 69923ac73a6c3148490d7923. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"autol","gradient\_strategy":"graddrop"}. This record does not assert independent reproduction. ### SOTA AUC: 0.7. Result ID: 69923ac73a6c3148490d7914. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### naive AUC: 0.696. Result ID: 69923ac73a6c3148490d7916. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"multi\_task":true,"weighting\_strategy":"naive"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.