# Cross-cell-type generalization on Replogle perturbations (test)

Source: [Cross-cell-type generalization on Replogle perturbations (test)](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test>)

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

Data updated: 2026-03-10T09:01:16.164Z

Evaluation of cross-cell-type generalization performance on the test split of the Replogle perturbations dataset, reporting correlation metrics (Pearson/Spearman) and various error measures (MSE, MAE, W1, W2).

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 | Cross-cell-type generalization |
| Dataset (including any stated split) | Replogle perturbations (test) |
| Metric | Pearson Correlation (DEG) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Pearson Correlation (DEG)](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=Pearson%20Correlation%20(DEG)>): Higher is better; unit: SCALAR.

- [Spearman Correlation (DEG)](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=Spearman%20Correlation%20(DEG)>): Higher is better; unit: SCALAR.

- [MSE](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=MSE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [MAE](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=MAE>): Lower is better; unit: SCALAR.

- [MSE (PCA 50)](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=MSE%20(PCA%2050)>): Lower is better; unit: SCALAR.

- [W1 Error](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=W1%20Error>): Lower is better; unit: SCALAR.

- [W2 Error](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=W2%20Error>): Lower is better; unit: SCALAR.

- [Energy Cost](<https://www.sota2.com/research/sota/cross-cell-type-generalization-on-replogle-perturbations-test.md?metric=Energy%20Cost>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Pearson Correlation (DEG) | Result date | Report paper |
| --- | --- | --- | --- |
| PT-RAG | 0.633 | Not recorded | 69afa56e2d603e6de3e43945 |
| STATE+GenePT | 0.631 | Not recorded | 69afa56e2d603e6de3e43945 |
| STATE | 0.624 | Not recorded | 69afa56e2d603e6de3e43945 |
| Vanilla RAG | 0.396 | Not recorded | 69afa56e2d603e6de3e43945 |

### PT-RAG

Pearson Correlation (DEG): 0.633. Result ID: 69afddd66dbb7075b95862d3.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56e2d603e6de3e43945.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa56e2d603e6de3e43945.md>)

[Implementation](<https://github.com/difra100/PT-RAG_ICLR>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### STATE+GenePT

Pearson Correlation (DEG): 0.631. Result ID: 69afddd66dbb7075b95862d1.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56e2d603e6de3e43945.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### STATE

Pearson Correlation (DEG): 0.624. Result ID: 69afddd66dbb7075b95862d0.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56e2d603e6de3e43945.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Vanilla RAG

Pearson Correlation (DEG): 0.396. Result ID: 69afddd66dbb7075b95862d2.

[Reporting paper](<https://www.sota2.com/research/paper/69afa56e2d603e6de3e43945.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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