Configuration

BindCraft default settings

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'

BindCraft run with the published default settings: AlphaFold2 multimer models 1-5 for design, ProteinMPNN with solubility weights for core and surface redesign, and AlphaFold2 monomer reprediction with the default confidence and Rosetta filters.

23 evaluations · 24 results

Overview

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

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

Evaluations and results

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

Sorted by Count (designs with an observed binding signal (SPR), out of designs tested) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Count (designs with an observed binding signal (SPR), out of designs tested)	Dissociation constant (binder2; by SPR)	Count (designs with an observed binding signal (BLI, bivalent Fc-fusion format), out of designs tested)	Count (designs with an observed binding signal (SPR against full-length apo SpCas9), out of designs tested)	Count (designs with an observed binding signal (SPR prescreen at 10 micromolar against immobilised PD-L1-Fc, then SPR titration), out of designs tested)	Count (designs with an observed binding signal (SPR prescreen at 10 micromolar against immobilised soluble claudin-1 analogues), out of designs tested)	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)	Hit rate (range of per-target experimental success rates over 12 targets)	Hit rate (unweighted mean of per-target experimental success rates over 12 targets)
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target BBF-14	6 showed binding (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target CD45	4 showed binding on SPR	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target Der f21	detect binding for four designs by SPR	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target Der f7	identified 4 binders	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target IFNAR2	binding for three out of nine designs	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target Bet v1	two successful designs	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target Claudin1	Not reported	Not reported	Not reported	Not reported	Not reported	all except binder17 to bind to sCLDN1-14 and sCLDN1-18	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target PD-1	Not reported	Not reported	a binding signal for 13 binders	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target PD-L1	Not reported	Not reported	Not reported	Not reported	seven showed a binding signal	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft per-target binding screen, hit where a binding signal was observed, BindCraft binder design target SpCas9	Not reported	Not reported	Not reported	All six tested binders bound the full-length apo SpCas9 enzyme	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target BBF-14	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	20.9 nM	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target Bet v1	Not reported	120 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target CbAgo	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	5 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target CD45	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	14.7 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target CrSAS-6	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	5.7 μM	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target CrSAS-6	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	4.2 μM	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target Der f21	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	793 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 best per-target binder affinity, BindCraft binder design target Der f7	Not reported	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	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, 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	Not reported	Not reported	Not reported	Not reported	Not reported	260 nM	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target PD-1	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	lower than 1 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target PD-L1	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	615 nM	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft best per-target binder affinity, BindCraft binder design target SpCas9	Not reported	Not reported	Not reported	Not reported	Not reported	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	Not reported	Not reported
BindCraft default settingsEvaluation	BindCraft experimental success rate averaged over its 12 benchmark targets, BindCraft 12-target benchmark set	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	10% to 100%	46.3%

All 24 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target BBF-14	6 showed binding Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against BBF-14 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Targeting unexplored binding sites', paragraph 3: 'We purified the 11 top-scoring designs from which 6 showed binding (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target Bet v1	two successful designs Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against Bet v1 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 5: 'we identified two successful designs from seven tested binders against the birch allergen Bet v1 (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target CD45	4 showed binding on SPR Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against CD45 uc-binder-20261022-protocol-bindcraft-binding-screen 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: 'We tested 16 binders experimentally, out of which 4 showed binding on SPR (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target Claudin1	all except binder17 to bind to sCLDN1-14 and sCLDN1-18 Count (designs with an observed binding signal (SPR prescreen at 10 micromolar against immobilised soluble claudin-1 analogues), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against Claudin1 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Targeting unexplored binding sites', paragraph 2: 'We tested seven binders and found all except binder17 to bind to sCLDN1-14 and sCLDN1-18 (Supplementary Fig. 4a)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target Der f21	detect binding for four designs by SPR Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against Der f21 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 4: 'we evaluated seven binders against Der f21 and could detect binding for four designs by SPR (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target Der f7	identified 4 binders Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against Der f7 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Masking allergenic epitopes', paragraph 2: 'We examined 10 designs against Der f7 experimentally and identified 4 binders (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target IFNAR2	binding for three out of nine designs Count (designs with an observed binding signal (SPR), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against IFNAR2 uc-binder-20261022-protocol-bindcraft-binding-screen 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: 'for IFNAR2 we could detect binding for three out of nine designs (Fig. 1b)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target PD-1	a binding signal for 13 binders Count (designs with an observed binding signal (BLI, bivalent Fc-fusion format), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against PD-1 uc-binder-20261022-protocol-bindcraft-binding-screen 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: 'We purified and screened 53 designs for binding using biolayer interferometry (BLI) in a bivalent Fc-fusion format. We observed a binding signal for 13 binders'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target PD-L1	seven showed a binding signal Count (designs with an observed binding signal (SPR prescreen at 10 micromolar against immobilised PD-L1-Fc, then SPR titration), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against PD-L1 uc-binder-20261022-protocol-bindcraft-binding-screen 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: 'We tested nine designs against PD-L1 out of which seven showed a binding signal (Supplementary Fig. 3a)'
Configuration: BindCraft default settings	Protocol: BindCraft per-target binding screen, hit where a binding signal was observed Dataset: BindCraft binder design target SpCas9	All six tested binders bound the full-length apo SpCas9 enzyme Count (designs with an observed binding signal (SPR against full-length apo SpCas9), out of designs tested) count · higher Uncertainty: Not applicable: An exact count. 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 binding screen against SpCas9 uc-binder-20261022-protocol-bindcraft-binding-screen Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Results 'Modulating multi-domain nucleases', paragraph 2: 'All six tested binders bound the full-length apo SpCas9 enzyme (Supplementary Fig. 5a)'
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'
Configuration: BindCraft default settings	Protocol: BindCraft experimental success rate averaged over its 12 benchmark targets Dataset: BindCraft 12-target benchmark set	46.3% Hit rate (unweighted mean of per-target experimental success rates over 12 targets) percent · higher 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 experimental success rate over its 12 benchmark targets uc-binder-20261022-protocol-bindcraft-mean-success-rate-12-targets Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Introduction, final paragraph: 'The binder affinities lie predominantly in the nanomolar range, with success rates from 10% to 100%, with an average success rate of 46.3%'
Configuration: BindCraft default settings	Protocol: BindCraft experimental success rate averaged over its 12 benchmark targets Dataset: BindCraft 12-target benchmark set	10% to 100% Hit rate (range of per-target experimental success rates over 12 targets) percent · higher Uncertainty: Not applicable: The value is itself a range over targets, not an estimate with an interval. 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 experimental success rate over its 12 benchmark targets uc-binder-20261022-protocol-bindcraft-mean-success-rate-12-targets Aggregation: Not reported One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) · Introduction, final paragraph: 'with success rates from 10% to 100%'

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

Use this configuration

How it works, versions and access

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-config-bindcraft-default

areas: proteins-complexes; protein-structure
contexts: research
method types: specialist
access reuse: Run by the pipeline's own authors.
foundation model eligible: false
method role: design
parameters: AlphaFold2 multimer models 1-5 for design with target flexibility; negative helicity loss default -0.3; MPNNsol core and surface redesign with the interface kept intact; AlphaFold2 monomer model 1 reprediction; AF2 confidence plus Rosetta physics filters. The design pipeline is run for 200 trajectories or until 100 designs pass the in silico filters, and about 10 designs from the top 20 by i_pTM are picked for experimental testing.
reported name: BindCraft
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
selection: About 10 designs from the top 20 ranked by i_pTM are chosen for testing.
source locator: Methods 'Binder design'; Results 'Accurate design of de novo binders'
version: Nature 2025 version of record

Related records

configuration of: BindCraft
uses model: ProteinMPNN
system: BindCraft best binder affinity against BBF-14
system: BindCraft best binder affinity against Bet v1
system: BindCraft best binder affinity against CbAgo
system: BindCraft best binder affinity against CD45
system: BindCraft best binder affinity against CrSAS-6
system: BindCraft best binder affinity against CrSAS-6 (dimer)
system: BindCraft best binder affinity against Der f21
system: BindCraft best binder affinity against Der f7
system: BindCraft best binder affinity against IFNAR2
system: BindCraft best binder affinity against PD-1
system: BindCraft best binder affinity against PD-L1
system: BindCraft best binder affinity against SpCas9
system: BindCraft experimental success rate over its 12 benchmark targets
system: BindCraft binding screen against BBF-14
system: BindCraft binding screen against Bet v1
system: BindCraft binding screen against CbAgo
system: BindCraft binding screen against CD45
system: BindCraft binding screen against Claudin1
system: BindCraft binding screen against CrSAS-6
system: BindCraft binding screen against Der f21
system: BindCraft binding screen against Der f7
system: BindCraft binding screen against IFNAR2
system: BindCraft binding screen against PD-1
system: BindCraft binding screen against PD-L1
system: BindCraft binding screen against SpCas9

Suggest a correction