Protocol

AlphaProteo best per-target binder affinity by HTRF

Lowest dissociation constant measured among a target's expressed yeast-display hits, by homogeneous time-resolved fluorescence.

25 evaluations · 25 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.

25 recorded evaluations, 25 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

25 evaluations · 25 results. Different protocols are not a single leaderboard.

Protocol: AlphaProteo best per-target binder affinity by HTRF

Sorted by Dissociation constant (best KD by HTRF among the designs tested for this design system) (lower 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	Dissociation constant (best KD by HTRF among the designs tested for this design system)	Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs)	Dissociation constant (best KD among the 95 published RFdiffusion designs, measured by the AlphaProteo authors using HTRF (asterisk in Table 1))	Dissociation constant (best KD by HTRF among the designs tested for this design system; hotspot conditioning)	Dissociation constant (best KD by HTRF among the designs tested for this design system; subset made without hotspot conditioning, marked with a dagger)
AlphaProteo v1Evaluation	AlphaProteo binder design target IL-7RA	0.08 (best in column)	Not reported	Not reported	Not reported	Not reported
AlphaProteo v2Evaluation	AlphaProteo binder design target PD-L1	0.18	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target VEGF-A	0.48	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target TrkA	0.96	Not reported	Not reported	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target PD-L1	1.56	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target PD-L1	3.4	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target IL-17A	8.4	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target BHRF1	8.5	Not reported	Not reported	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target IL-7RA	14.1	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1 with improved filtersEvaluation	AlphaProteo binder design target SC2RBD	33	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1 with improved filtersEvaluation	AlphaProteo binder design target PD-L1	47	Not reported	Not reported	Not reported	Not reported
AlphaProteo v2Evaluation	AlphaProteo binder design target TrkA	60	Not reported	Not reported	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target TrkA	370	Not reported	Not reported	Not reported	Not reported
AlphaProteo v1Evaluation	AlphaProteo binder design target SC2RBD	Not reported	Not reported	Not reported	Not reported	26
AlphaProteo v1Evaluation	AlphaProteo binder design target SC2RBD	Not reported	Not reported	Not reported	30	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target BHRF1	Not reported	8.5	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target IL-17A	Not reported	8.4	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target IL-7RA	Not reported	0.082 (best in column)	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target PD-L1	Not reported	0.18	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target SC2RBD	Not reported	26	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target TrkA	Not reported	0.96	Not reported	Not reported	Not reported
AlphaProteo, pooled over tested design systemsEvaluation	AlphaProteo binder design target VEGF-A	Not reported	0.48	Not reported	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target IL-7RA	Not reported	Not reported	14*	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target PD-L1	Not reported	Not reported	1.6* (best in column)	Not reported	Not reported
Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authorsEvaluation	AlphaProteo binder design target TrkA	Not reported	Not reported	370*	Not reported	Not reported

All 25 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: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-7RA	14.1 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors on IL-7RA (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'RFdiffusion (our measurement)', column 'IL-7RA'
Configuration: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	1.56 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors on PD-L1 (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'RFdiffusion (our measurement)', column 'PD-L1'
Configuration: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target TrkA	370 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors on TrkA (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'RFdiffusion (our measurement)', column 'TrkA'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target BHRF1	8.5 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on BHRF1 (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'BHRF1'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-17A	8.4 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on IL-17A (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'IL-17A'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-7RA	0.08 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on IL-7RA (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'IL-7RA'
Configuration: AlphaProteo v1 with improved filters	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	47 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 with improved filters on PD-L1 (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1 with improved filters', column 'PD-L1'
Configuration: AlphaProteo v1 with improved filters	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target SC2RBD	33 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 with improved filters on SC2RBD (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1 with improved filters', column 'SC2RBD'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	3.4 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on PD-L1 (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'PD-L1'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target SC2RBD	26 Dissociation constant (best KD by HTRF among the designs tested for this design system; subset made without hotspot conditioning, marked with a dagger) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on SC2RBD (best KD by HTRF, Table S2, no-hotspot subset) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'SC2RBD' (dagger subset)
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target SC2RBD	30 Dissociation constant (best KD by HTRF among the designs tested for this design system; hotspot conditioning) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on SC2RBD (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'SC2RBD'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target TrkA	0.96 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on TrkA (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'TrkA'
Configuration: AlphaProteo v1	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target VEGF-A	0.48 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v1 on VEGF-A (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v1', column 'VEGF-A'
Configuration: AlphaProteo v2	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	0.18 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v2 on PD-L1 (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v2', column 'PD-L1'
Configuration: AlphaProteo v2	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target TrkA	60 Dissociation constant (best KD by HTRF among the designs tested for this design system) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo v2 on TrkA (best KD by HTRF, Table S2) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table S2, 'Binding KD (nM)' block, row 'AlphaProteo v2', column 'TrkA'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target BHRF1	8.5 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on BHRF1, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'BHRF1'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-17A	8.4 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on IL-17A, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'IL-17A'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-7RA	0.082 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on IL-7RA, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'IL-7RA'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	0.18 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on PD-L1, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'PD-L1'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target SC2RBD	26 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on SC2RBD, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'SC2RBD'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target TrkA	0.96 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on TrkA, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'TrkA'
Configuration: AlphaProteo, pooled over tested design systems	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target VEGF-A	0.48 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source AlphaProteo on VEGF-A, pooled over tested design systems (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'VEGF-A'
Configuration: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target IL-7RA	14* Dissociation constant (best KD among the 95 published RFdiffusion designs, measured by the AlphaProteo authors using HTRF (asterisk in Table 1)) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs on IL-7RA, measured by the AlphaProteo authors (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'RFdiffusion', column 'IL-7RA'
Configuration: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target PD-L1	1.6* Dissociation constant (best KD among the 95 published RFdiffusion designs, measured by the AlphaProteo authors using HTRF (asterisk in Table 1)) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs on PD-L1, measured by the AlphaProteo authors (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'RFdiffusion', column 'PD-L1'
Configuration: Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors	Protocol: AlphaProteo best per-target binder affinity by HTRF Dataset: AlphaProteo binder design target TrkA	370* Dissociation constant (best KD among the 95 published RFdiffusion designs, measured by the AlphaProteo authors using HTRF (asterisk in Table 1)) nanomolar · lower Uncertainty: Not reported by the source: No interval is printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table S2 prints the RFdiffusion yeast-display success rate for IL-7RA as 16.8% and Table 1 rounds it to 17, but Section S4.1 states it in the text as '16% versus 33%'. Section S4.1 also states TrkA as '0% (versus 6%)' where Table S2 prints 0.0 and 6.3. The table values are recorded; the text rounds down rather than to nearest.De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1; Table S2; Section S4.1 Methods, coverage and source Published RFdiffusion designs on TrkA, measured by the AlphaProteo authors (best KD by HTRF, Table 1) uc-binder-20261022-protocol-alphaproteo-htrf-kd Aggregation: Not reported De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'RFdiffusion', column 'TrkA'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 19
External evaluations: 6

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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 2026-10-22-1b7cf027e4f6
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 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Original source · arXiv version 1, posted 2024-09-12; full-text PDF (49 pages)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: uc-binder-20261022-protocol-alphaproteo-htrf-kd

areas: proteins-complexes; protein-structure
contexts: research
aggregation: Minimum over the expressed hits for the target.
comparison limit: A best-of value over a selected subset, so it describes the best design found, not the distribution. Section S4.2 reports that HTRF gave KD values about 10-fold higher than previously published BLI values for the BINDI and LCB1 control binders, so HTRF values are not interchangeable with BLI or SPR values.
limitations: Best-of-subset, not a distribution; no uncertainty is printed.; Measured by HTRF, which Section S4.2 shows disagrees with published BLI values by about 10-fold for two control binders.; Developer-reported.; The subset titrated is the yeast hits that expressed in E. coli (Table S3), so the affinity values carry the expression filter as well as the design and binding filters.; Same-assay disagreement with the RFdiffusion publication. For the re-tested RFdiffusion designs Table S2 prints HTRF KD values of 14.1 nM (IL-7RA), 1.56 nM (PD-L1) and 370 nM (TrkA) against published BLI values of 30 nM, 1400 nM and 328 nM. Section S4.2 states that for PD-L1 the authors did not use the published best design: 'we found a design with 1000-fold better KD (RFD_PDL1_76, KD=1.6 nM) than the published "best" design (RFD_PDL1_77, KD =1.4 uM). Therefore, we compared our results to the higher-affinity PD-L1 binder'. The published values are not recorded as results because Watson et al. was not retrieved. HTRF and BLI are different assays, so these pairs are not a like-for-like contradiction; Section S4.2 also reports AlphaProteo's own BINDI and LCB1 controls coming out about 10-fold higher by HTRF than the published BLI values.
metric: dissociation-constant
metric direction: lower
metric qualifier: best per-target KD by HTRF among expressed hits
protocol: Yeast-display hits selected for follow-up were subcloned, expressed in E. coli and titrated by HTRF. The reported value is the best (lowest) KD per target. HTRF measures both species in solution at equilibrium, unlike BLI, where one species is immobilised.
review: artifact sha256: 953b35644c0fa06ff090d7614c2e19525831f8fde50242e176d54474133c5a42; method: source-hash-verification; independent-cell-check; ai-assisted-source-review; method note: Re-downloaded with curl (HTTP 200, 12,333,400 bytes) and the SHA-256 recomputed and matched. Own text layer made with pdftotext -layout (poppler 26.08.0), reproducing the extraction pass's 2,811 lines. Table 1, Table S2, Table S3 and Sections S1.2.1, S2, S4.1 and S4.2 read cell by cell and compared with every record. Column assignment re-derived arithmetically rather than trusted.; note: Reviewed in docs/reviews/use-cases/binder-2026-10-22.md. Automated AI review of the source transcription only; it is not human scientific review and nothing here was reproduced experimentally.; retrieval url: https://arxiv.org/pdf/2409.08022v1; reviewed at: 2026-10-22T15:00:00Z; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed
source locator: Table 1, 'Binding KD (nM)' block; Table S2; Section S4.2
unit: nanomolar
version: arXiv:2409.08022v1 Sections S1.3 and S4.2; Table 1

Related records

Suggest a correction