# Mutation Prediction on TCGA-STAD

Source: [Mutation Prediction on TCGA-STAD](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:44:03.906Z

Evaluation of models predicting specific genetic mutations (e.g., MSI, BRAF, TP53) within the TCGA Stomach Adenocarcinoma (STAD) cohort.

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 | Mutation Prediction |
| Dataset (including any stated split) | TCGA-STAD |
| Metric | FBXW7 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [FBXW7](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=FBXW7>): Higher is better; unit: PERCENT.

- [MSI](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=MSI>): Higher is better; unit: PERCENT.

- [TMB](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=TMB>): Higher is better; unit: PERCENT.

- [BRAF](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=BRAF>): Higher is better; unit: PERCENT.

- [ALK](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=ALK>): Higher is better; unit: PERCENT.

- [ERBB4](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=ERBB4>): Higher is better; unit: PERCENT.

- [KRAS](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=KRAS>): Higher is better; unit: PERCENT.

- [PIK3CA](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=PIK3CA>): Higher is better; unit: PERCENT.

- [SMAD4](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=SMAD4>): Higher is better; unit: PERCENT.

- [TP53](<https://www.sota2.com/research/sota/mutation-prediction-on-tcga-stad.md?metric=TP53>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FBXW7 | Result date | Report paper |
| --- | --- | --- | --- |
| Kather et al. \[9\] | 74 | Not recorded | 68fa6cdc1e209131cea365d5 |
| LA-MIL | 72 | Not recorded | 68fa6cdc1e209131cea365d5 |
| T-MIL | 71 | Not recorded | 68fa6cdc1e209131cea365d5 |
| Fu et al. \[6\] | 47 | Not recorded | 68fa6cdc1e209131cea365d5 |

### Kather et al. \[9\]

FBXW7: 74. Result ID: 698f471d3a6c314849f7a2fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cdc1e209131cea365d5.md>)

Recorded evaluation configuration: {"Prediction level":"tile-wise average pooling","Training":"single model per target"}. This record does not assert independent reproduction.

### LA-MIL

FBXW7: 72. Result ID: 698f471d3a6c314849f7a300.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cdc1e209131cea365d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cdc1e209131cea365d5.md>)

[Implementation](<https://github.com/agentdr1/LA_MIL>)

Recorded evaluation configuration: {"Attention":"local self-attention","Prediction level":"WSI-level","Training":"multi-target model"}. This record does not assert independent reproduction.

### T-MIL

FBXW7: 71. Result ID: 698f471d3a6c314849f7a2ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cdc1e209131cea365d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Attention":"global self-attention","Prediction level":"WSI-level","Training":"multi-target model"}. This record does not assert independent reproduction.

### Fu et al. \[6\]

FBXW7: 47. Result ID: 698f471d3a6c314849f7a2fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cdc1e209131cea365d5.md>)

Recorded evaluation configuration: {"Prediction level":"tile-wise average pooling","Training":"single model per target"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.