Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs) of AlphaProteo, pooled over tested design systems on AlphaProteo binder design target PD-L1
0.18 Dissociation constant (best per-target KD by HTRF among expressed hits, non-optimised designs)
Methods
- Tested configuration
- AlphaProteo, pooled over tested design systems
- Protocol
- AlphaProteo best per-target binder affinity by HTRF
- Dataset
- AlphaProteo binder design target PD-L1
- Procedure
- AlphaProteo best per-target binder affinity by HTRF
- Evaluation
- AlphaProteo on PD-L1, pooled over tested design systems (best KD by HTRF, Table 1)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source: No interval is printed.
- Evidence
- Author-reported evaluation · source checkedDe novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'PD-L1'
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
- Best (lowest) KD among expressed hits, by HTRF
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 0.18 Individual claims | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'PD-L1' Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | 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 detailsReviewed 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: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. Extraction artifact SHA-256: |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) · Original source · arXiv version 1, posted 2024-09-12; full-text PDF (49 pages)
Technical metadata and extraction receipts
Stable ID: uc-binder-20261022-result-alphaproteo-table1-kd-pdl1
- denominator
- 159
- denominator note
- 159 designs tested; the KD is the best among the subset that was a yeast hit and expressed in E. coli (Table S3).
- metric
- dissociation-constant
- metric direction
- lower
- metric qualifier
- best per-target KD by HTRF among expressed hits, non-optimised designs
- missing metadata
- uncertainty: note: No interval is printed.; reason: unreported
- numeric value
- 0.18
- printed value
- 0.18
- review
- artifact sha256: 953b35644c0fa06ff090d7614c2e19525831f8fde50242e176d54474133c5a42; method: source-hash-verification; independent-cell-check; ai-assisted-source-review; method note: Re-downloaded with curl (HTTP 200, 12,333,400 bytes) and the SHA-256 recomputed and matched. Own text layer made with pdftotext -layout (poppler 26.08.0), reproducing the extraction pass's 2,811 lines. Table 1, Table S2, Table S3 and Sections S1.2.1, S2, S4.1 and S4.2 read cell by cell and compared with every record. Column assignment re-derived arithmetically rather than trusted.; note: Reviewed in docs/reviews/use-cases/binder-2026-10-22.md. Automated AI review of the source transcription only; it is not human scientific review and nothing here was reproduced experimentally.; retrieval url: https://arxiv.org/pdf/2409.08022v1; reviewed at: 2026-10-22T15:00:00Z; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed
- source locator
- Table 1, 'Binding KD (nM)' block, row 'AlphaProteo', column 'PD-L1'
- source warnings
- Table 1's AlphaProteo column for PD-L1 pools three different design systems, so it is not one method's success rate. Section S2 states: 'We experimentally tested a design system containing the v1 model against all 7 targets, a v1-based system with an improved filter against SC2RBD and PD-L1, and a v2-based system on PD-L1 and TrkA (Table S2) ... For simplicity, the results in Table 1 are pooled over all tested designs for each target.' The Table S2 per-system denominators sum to this cell's denominator (94 + 31 + 34 = 159), confirming the pooling. Use the Table S2 per-system evaluations to say what one design system achieved: changing only the filter moved PD-L1 from 9.6% over 94 designs to 16.1% over 31. Do not read this cell as a single method's rate in any cross-method comparison. Reviewed 2026-10-22 against artifact 953b35644c0fa06ff090d7614c2e19525831f8fde50242e176d54474133c5a42.
- unit
- nanomolar