| Configuration: CpGPT Cancer-100M fine-tuned on 20,499 DMR-informed CpGs | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.996 AUPRC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.9950 to 0.9970. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCpGPT on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'CpGPT', column 'Test AUPRC' |
|---|
| Configuration: CpGPT Cancer-100M fine-tuned on 20,499 DMR-informed CpGs | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.99 AUROC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.9715 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCpGPT on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'CpGPT', column 'Test AUROC' |
|---|
| Configuration: CpGPT Cancer-100M fine-tuned on 20,499 DMR-informed CpGs | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.949 AUROC (GI cancer vs non-cancer, validation partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.8887 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCpGPT on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'CpGPT', column 'Validation AUROC' |
|---|
| Configuration: Elastic Net on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.981 AUPRC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.9494 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceElastic Net on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Elastic Net', column 'Test AUPRC' |
|---|
| Configuration: Elastic Net on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.942 AUROC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.8587 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceElastic Net on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Elastic Net', column 'Test AUROC' |
|---|
| Configuration: Elastic Net on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.93 AUROC (GI cancer vs non-cancer, validation partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.7928 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceElastic Net on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Elastic Net', column 'Validation AUROC' |
|---|
| Configuration: GBM on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.955 AUPRC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.9122 to 0.9978. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGBM on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'GBM', column 'Test AUPRC' |
|---|
| Configuration: GBM on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.846 AUROC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.7322 to 0.9602. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGBM on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'GBM', column 'Test AUROC' |
|---|
| Configuration: GBM on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.877 AUROC (GI cancer vs non-cancer, validation partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.7917 to 0.9617. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGBM on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'GBM', column 'Validation AUROC' |
|---|
| Configuration: Random Forest on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.948 AUPRC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.8985 to 0.9965. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom Forest on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Random Forest', column 'Test AUPRC' |
|---|
| Configuration: Random Forest on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.841 AUROC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.7573 to 0.9243. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom Forest on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Random Forest', column 'Test AUROC' |
|---|
| Configuration: Random Forest on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.793 AUROC (GI cancer vs non-cancer, validation partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.5946 to 0.9920. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom Forest on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'Random Forest', column 'Validation AUROC' |
|---|
| Configuration: SVM radial on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.983 AUPRC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.9488 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSVM radial on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'SVM radial', column 'Test AUPRC' |
|---|
| Configuration: SVM radial on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.957 AUROC (GI cancer vs non-cancer, held-out test partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.8736 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSVM radial on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'SVM radial', column 'Test AUROC' |
|---|
| Configuration: SVM radial on 20,499 DMR-informed CpGs (caret) | Protocol: Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features Dataset: EpiPanGI Dx plasma cfDNA targeted bisulfite methylation (GSE149438, 300 samples) | 0.937 AUROC (GI cancer vs non-cancer, validation partition, mean over three split-runs) unitless · higher Uncertainty: 95% CI 0.8126 to 1.0000. Across three split-runs, bounded to the valid range 0 to 1 (Table 3 footnote) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSVM radial on GSE149438 DMR-informed split-runs (Xu and Feng 2026) ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs Aggregation: Not reported An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation · Table 3, row 'SVM radial', column 'Validation AUROC' |
|---|