Configuration

scELMo (fine-tuned, Chen et al. 2026)

Configuration of scELMo: supervised fine-tuning or adaptation on reference cell type labels (stratified 8:2 train/test split), each model's recommended workflow.

4 evaluations · 24 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

4 evaluations · 24 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (held-out test set) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Accuracy (held-out test set)	AUPRC (held-out test set; macro-averaged over classes)	AUROC (held-out test set; macro-averaged over classes)	Macro F1 (held-out test set)	Precision (held-out test set; described as global in the Methods, averaging not further defined)	Recall (held-out test set; described as global in the Methods, averaging not further defined)
scELMo (fine-tuned, Chen et al. 2026)Evaluation	Chen et al. 2026 supervised cell type annotation, ATAA, ATAA (Chen et al. 2026)	0.95 (best in column)	0.95 (best in column)	0.99 (best in column)	0.89 (best in column)	0.96 (best in column)	0.86 (best in column)
scELMo (fine-tuned, Chen et al. 2026)Evaluation	Chen et al. 2026 supervised cell type annotation, SEAAD, SEAAD (Chen et al. 2026)	0.88	0.78	0.93	0.79	0.82	0.77
scELMo (fine-tuned, Chen et al. 2026)Evaluation	Chen et al. 2026 supervised cell type annotation, HS, HS (Chen et al. 2026)	0.86	0.71	0.99 (best in column)	0.64	0.71	0.62
scELMo (fine-tuned, Chen et al. 2026)Evaluation	Chen et al. 2026 supervised cell type annotation, BMMC, BMMC (Chen et al. 2026)	0.8	0.61	0.86	0.51	0.58	0.51

All 24 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.95 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'Accuracy'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.89 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'Macro-F1'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.95 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'PR-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.96 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'Precision'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.86 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'Recall'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, ATAA Dataset subset: ATAA (Chen et al. 2026)	0.99 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, ATAA lit-cells-networks-20261011-chen2026-protocol-annotation-ataa Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'ATAA', column 'ROC-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.8 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Accuracy'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.51 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Macro-F1'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.61 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'PR-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.58 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Precision'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.51 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Recall'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.86 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'ROC-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.86 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'Accuracy'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.64 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'Macro-F1'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.71 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'PR-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.71 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'Precision'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.62 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'Recall'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, HS Dataset subset: HS (Chen et al. 2026)	0.99 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, HS lit-cells-networks-20261011-chen2026-protocol-annotation-hs Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'HS', column 'ROC-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.88 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'Accuracy'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.79 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'Macro-F1'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.78 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'PR-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.82 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'Precision'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.77 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'Recall'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, SEAAD Dataset subset: SEAAD (Chen et al. 2026)	0.93 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD lit-cells-networks-20261011-chen2026-protocol-annotation-seaad Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'SEAAD', column 'ROC-AUC'

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Original source · arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-cells-networks-20261011-chen2026-config-scelmo-fine-tuned

areas: single-cell; spatial-omics
contexts: research
method types: foundation_model
reported name: scELMo
foundation model eligible: true
training setting: supervised fine-tuning or adaptation on reference cell type labels (stratified 8:2 train/test split), each model's recommended workflow
access reuse: Public pretrained checkpoints as released by each model's authors
source locator: Methods: model-specific sections under 'Zero-shot cell type clustering', 'Continually-pretrained cell type clustering', 'Cell type annotation' and 'Perturbation prediction'
missing metadata: version: reason: unreported; note: Checkpoint names are printed for some models only (CellPLM 20231027_85M)
provenance note: scELMo as run by Chen et al. 2026: supervised fine-tuning or adaptation on reference cell type labels (stratified 8:2 train/test split), each model's recommended workflow.

Related records

configuration of: scELMo
system: scELMo on Chen et al. 2026 supervised cell type annotation, ATAA
system: scELMo on Chen et al. 2026 supervised cell type annotation, BMMC
system: scELMo on Chen et al. 2026 supervised cell type annotation, HS
system: scELMo on Chen et al. 2026 supervised cell type annotation, SEAAD

Suggest a correction