Result

Hit rate (unweighted mean of per-target experimental success rates over 12 targets) of BindCraft default settings on BindCraft 12-target benchmark set

46.3% Hit rate (unweighted mean of per-target experimental success rates over 12 targets)

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

Tested configuration: BindCraft default settings
Protocol: BindCraft experimental success rate averaged over its 12 benchmark targets
Dataset: BindCraft 12-target benchmark set
Procedure: BindCraft experimental success rate averaged over its 12 benchmark targets
Evaluation: BindCraft experimental success rate over its 12 benchmark targets
Coverage: Not reported scored / Not reported eligible
Uncertainty: Not reported by the source: No interval is printed.
Evidence: Author-reported evaluation · source checkedOne-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%'

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split: Not reported
Adaptation: Not reported
Scoring implementation: Per-target share of tested designs with observed binding

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

1 evidence row 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
Reported result 46.3% Individual claims	One-shot design of functional protein binders with BindCraft (Pacesa et al., Nature 2025) Original source ↗ 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%' Version: Nature, version of record; Europe PMC JATS full text for PMC12507698 Retrieved: 2026-10-22T11:55:00Z	source checked ["source-hash-verification","independent-cell-check","ai-assisted-source-review"] · 2026-10-22T15:00:00Z author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details 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. Field: `attributes.printed_value` Source artifact SHA-256: `74bd2902d46460ec387ed6ee46b5bf8fe61b9ea09f2d7be4daa2046ac7e59d5d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `74bd2902d46460ec387ed6ee46b5bf8fe61b9ea09f2d7be4daa2046ac7e59d5d` Extraction artifact

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-result-bindcraft-mean-success-rate

denominator: 12
denominator note: 12 targets. Per-target design denominators range from 6 to 53 and are not pooled; each target contributes its own rate to the mean.
metric: hit-rate
metric direction: higher
metric qualifier: unweighted mean of per-target experimental success rates over 12 targets
missing metadata: uncertainty: note: No interval is printed.; reason: unreported
numeric value: 46.3
printed value: 46.3%
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: 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%'
source warnings: The paper's headline 46.3% cannot be reconciled with the per-target counts the same paper prints. The ten per-target rates stated in the Results prose (PD-1 13/53, PD-L1 7/9, IFNAR2 3/9, CD45 4/16, sCLDN1 6/7, BBF-14 6/11, Der f7 4/10, Der f21 4/7, Bet v1 2/7, SpCas9 6/6) sum to 526.613 percentage points. A displayed 46.3% as an unweighted mean over twelve targets requires a total in [555.0, 556.2), so CrSAS-6 (denominator 9) and CbAgo (denominator 12), whose numerators appear only inside the Fig. 1b graphic, would have to contribute between 28.387 and 29.587 points. No integer pair x/9 + y/12 does: the nearest are 1/9 + 2/12 at 27.778 points (mean 46.20%) and 2/9 + 1/12 at 30.556 points (mean 46.43%). A pooled rate over all designs does not fit either: 55 binders of 135 printed designs, plus x of 9 and y of 12, gives no integer fit over 156 designs, the nearest being 46.15%. The source states only 'an average success rate of 46.3%' and never defines the basis, so the discrepancy cannot be resolved from the paper; explanations it does not settle include a Fig. 1b denominator differing from the prose, a different twelve-target set, or a weighting. The gap is about a tenth of a percentage point, so this is a minor internal inconsistency, not a wrong headline. Do not treat 46.3% as derivable from this paper's per-target counts, and do not compare it with another paper's average as though its basis were known. Checked 2026-10-22 against artifact 74bd2902d46460ec387ed6ee46b5bf8fe61b9ea09f2d7be4daa2046ac7e59d5d; locators Introduction final paragraph and the Results per-target counts.
unit: percent
unit detail: percent of designs tested, averaged over targets

Related records

evaluation: BindCraft experimental success rate over its 12 benchmark targets

Suggest a correction