Protocol

BindCraft best per-target binder affinity

Evidence concern: excluded from comparisons

Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption

Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites'

Dissociation constant of the highest-affinity BindCraft binder per target, without experimental sequence optimisation.

12 evaluations · 12 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.

12 recorded evaluations, 12 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

12 evaluations · 12 results. Different protocols are not a single leaderboard.

Protocol: BindCraft best per-target binder affinity

Sorted by Dissociation constant (binder2; by SPR) (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 (binder2; by SPR)	Dissociation constant (binder1; by SPR)	Dissociation constant (binder10; apparent affinity by SPR)	Dissociation constant (binder2; apparent KD (Kd*) by BLI in a bivalent Fc-fusion format; the exact value could not be determined)	Dissociation constant (binder2; by BLI)	Dissociation constant (binder3 and binder10; apparent affinities by SPR; complete titration curves were challenging to obtain)	Dissociation constant (binder4; apparent KD (Kd*) by SPR)	Dissociation constant (binder4; by SPR)	Dissociation constant (binder4; dimeric form of CrSAS-6)	Dissociation constant (binder4; monomeric form of CrSAS-6)	Dissociation constant (binder5; by SPR)
BindCraft default settingsEvaluation	BindCraft binder design target Der f7	12.8 nM (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target Bet v1	120 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target BBF-14	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	20.9 nM	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target CbAgo	Not reported	Not reported	Not reported	Not reported	5 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target CD45	Not reported	14.7 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target CrSAS-6	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	5.7 μM	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target CrSAS-6	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	4.2 μM	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target Der f21	Not reported	Not reported	793 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target IFNAR2	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	260 nM
BindCraft default settingsEvaluation	BindCraft binder design target PD-1	Not reported	Not reported	Not reported	lower than 1 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target PD-L1	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	615 nM	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft binder design target SpCas9	Not reported	Not reported	Not reported	Not reported	Not reported	in the range of 300 nM	Not reported	Not reported	Not reported	Not reported	Not reported

All 12 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: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target BBF-14	20.9 nM Dissociation constant (binder4; by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against BBF-14 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Targeting unexplored binding sites', paragraph 3: 'Binder4showed a Kd of 20.9 nM for BBF-14, as determined by SPR'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target Bet v1	120 nM Dissociation constant (binder2; by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against Bet v1 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 5: 'Binder2 showed a 120 nM binding affinity by SPR'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target CbAgo	5 nM Dissociation constant (binder2; by BLI) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against CbAgo uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Modulating multi-domain nucleases', paragraph 5: 'We found that binder2 binds to CbAgo with a Kd of 5 nM, as determined by BLI'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target CD45	14.7 nM Dissociation constant (binder1; by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against CD45 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Binders targeting cell-surface receptors', last paragraph: 'The best performing binder1 showed a Kd of 14.7 nM'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target CrSAS-6	5.7 μM Dissociation constant (binder4; monomeric form of CrSAS-6) micromolar · 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against CrSAS-6 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Targeting unexplored binding sites', last paragraph: 'Binder4 binds with 5.7 μM affinity to the monomeric form of CrSAS-6'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target CrSAS-6	4.2 μM Dissociation constant (binder4; dimeric form of CrSAS-6) micromolar · 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against CrSAS-6 (dimer) uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Targeting unexplored binding sites', last paragraph: 'and 4.2 μM affinity to the dimeric form'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target Der f21	793 nM Dissociation constant (binder10; apparent affinity by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against Der f21 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 4: 'The best performing binder10 showed an apparent affinity of 793 nM'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target Der f7	12.8 nM Dissociation constant (binder2; by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against Der f7 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 2: 'with binder2 showing the highest binding affinity with a Kd of 12.8 nM'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target IFNAR2	260 nM Dissociation constant (binder5; by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against IFNAR2 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Binders targeting cell-surface receptors', paragraph 4: 'The top performing binder5 against IFNAR2 showed an affinity of 260 nM by SPR'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target PD-1	lower than 1 nM Dissociation constant (binder2; apparent KD (Kd*) by BLI in a bivalent Fc-fusion format; the exact value could not be determined) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against PD-1 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Binders targeting cell-surface receptors', paragraph 1: 'with the best binder showing an apparent dissociation constant (Kd*) lower than 1 nM (Fig. 2a,b), although the exact Kd could not be determined due to the extremely slow dissociation rate and avidity effect from the Fc-fusion construct'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target PD-L1	615 nM Dissociation constant (binder4; apparent KD (Kd*) by SPR) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against PD-L1 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Binders targeting cell-surface receptors', paragraph 3: 'The top performing binder4 against PD-L1 showed a Kd* of 615 nM'
Configuration: BindCraft default settings	Protocol: BindCraft best per-target binder affinity Dataset: BindCraft binder design target SpCas9	in the range of 300 nM Dissociation constant (binder3 and binder10; apparent affinities by SPR; complete titration curves were challenging to obtain) 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 Supplementary Data 1 has one row per tested design with a Binding column holding 1, 0 or an empty cell. Treating the non-empty cells as the tested set reproduces the prose counts for BBF-14 (11 tested, 6 binding), Bet v1 (7, 2), CD45 (16, 4), Der f7 (10, 4), Der f21 (7, 4), IFNAR2 (9, 3), PD-1 (53, 13), SpCas9 (6, 6) and CLDN1 (7, 6), but not for PD-L1 (13 non-empty rows with 11 binding against 9 tested with 7 binding in the prose), CrSAS-6 (10 non-empty rows against 9 tested) or CbAgo (2 non-empty rows against 12 tested). The row filter is therefore ambiguous and no value is computed from these rows.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Supplementary Data 1 (41586_2025_9429_MOESM4_ESM.csv), columns Target, DesignName, Binding; Results prose; Fig. 1b caption Fig. 1b's caption defines success as binding observed on SPR, but the PD-1 screen was BLI in a bivalent Fc-fusion format and the CLDN1 screen used soluble analogues. The 46.3% average therefore pools targets measured under different endpoints.One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Fig. 1b caption; Results 'Binders targeting cell-surface receptors' and 'Targeting unexplored binding sites' Methods, coverage and source BindCraft best binder affinity against SpCas9 uc-binder-20261022-protocol-bindcraft-best-affinity Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Modulating multi-domain nucleases', paragraph 2: 'The top performing binder3 and 10 showed apparent binding affinities in the range of 300 nM by SPR, although complete titration curves were challenging to obtain'

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.

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: 12

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

One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Original source · Nature, version of record; Europe PMC JATS full text for PMC12507698

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: uc-binder-20261022-protocol-bindcraft-best-affinity

areas: proteins-complexes; protein-structure
contexts: research
aggregation: Minimum over the binders identified for the target.
comparison limit: A best-of value over a small selected set. Several values are apparent constants (Kd*) from poor fits or from a bivalent Fc-fusion construct, which inflates apparent affinity through avidity, and are not comparable with monovalent fitted constants.
limitations: Best-of-subset, not a distribution; no uncertainty is printed.; Mixed assays and mixed construct formats: SPR, BLI, monovalent and bivalent Fc fusion.; Several values are apparent constants (Kd*) rather than fitted monovalent constants.; Developer-reported.
metric: dissociation-constant
metric direction: lower
metric qualifier: best per-target KD without experimental sequence optimisation
protocol: The best binder identified in the per-target screen is titrated by SPR, or by BLI for PD-1 and CbAgo, and the dissociation constant is reported. Fig. 1b marks values as estimated (Kd*) where the fit was poor.
review: artifact sha256: 74bd2902d46460ec387ed6ee46b5bf8fe61b9ea09f2d7be4daa2046ac7e59d5d; method: source-hash-verification; independent-cell-check; ai-assisted-source-review; method note: Re-downloaded from Europe PMC (HTTP 200, 226,059 bytes) and the SHA-256 recomputed and matched. Own flattening of the JATS XML; every quoted locator sentence and every printed value checked verbatim against it by a parser written for this review.; 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://www.ebi.ac.uk/europepmc/webservices/rest/PMC12507698/fullTextXML; 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: Fig. 1b caption; Figs. 2, 3 and 4; Extended Data Figs. 3 and 5
unit: nanomolar
version: Nature 2025 version of record; Figs. 1b, 2, 3 and 4

Related records

assessment: BindCraft best binder affinity against BBF-14
assessment: BindCraft best binder affinity against Bet v1
assessment: BindCraft best binder affinity against CbAgo
assessment: BindCraft best binder affinity against CD45
assessment: BindCraft best binder affinity against CrSAS-6
assessment: BindCraft best binder affinity against CrSAS-6 (dimer)
assessment: BindCraft best binder affinity against Der f21
assessment: BindCraft best binder affinity against Der f7
assessment: BindCraft best binder affinity against IFNAR2
assessment: BindCraft best binder affinity against PD-1
assessment: BindCraft best binder affinity against PD-L1
assessment: BindCraft best binder affinity against SpCas9
assessed by: Design a new binder to a chosen target

Suggest a correction