Section S4.1 states that the RFdiffusion arm is the published designs re-tested, not a rerun
Evaluation actor of Published RFdiffusion designs, re-synthesised and tested by the AlphaProteo authors
Section S4.1, verbatim: 'Published experimental success rates of RFdiffusion were based on 96-well biolayer interferometry (BLI) measurements [S28], which are impractical for us to perform on our own designs. Therefore, to quantitatively compare success rates, we downloaded sequences of the published RFdiffusion designs and synthesized and tested them by yeast display (Section S1.2) alongside our own designs. Our results matched the published success rates for PD-L1 but were 2-fold lower for IL-7RA (16% versus 33%) and 0% for TrkA (versus 6%) (Table S2). This is potentially due to differences between the yeast surface environment versus purified proteins, as well as our use of 10- to 20-fold lower target concentrations (0.5-1 uM versus 10 uM in [S28]), which may exclude lower-affinity hits.' Section S4.1 therefore states a shared assay and does not state a shared selection funnel: the AlphaProteo candidates were chosen by the authors' own filter from a larger in silico set, while the RFdiffusion candidates are the 95 designs the RFdiffusion authors published.
The AlphaProteo authors did not run RFdiffusion. Section S4.1 states that they downloaded the published RFdiffusion design sequences and synthesised and tested those by yeast display alongside their own designs, because the published RFdiffusion rates rest on 96-well BLI measurements that were impractical for them to perform.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field evaluation_actor Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
| Source location Section S4.1 Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
| Claimed value Section S4.1, verbatim: 'Published experimental success rates of RFdiffusion were based on 96-well biolayer interferometry (BLI) measurements [S28], which are impractical for us to perform on our own designs. Therefore, to quantitatively compare success rates, we downloaded sequences of the published RFdiffusion designs and synthesized and tested them by yeast display (Section S1.2) alongside our own designs. Our results matched the published success rates for PD-L1 but were 2-fold lower for IL-7RA (16% versus 33%) and 0% for TrkA (versus 6%) (Table S2). This is potentially due to differences between the yeast surface environment versus purified proteins, as well as our use of 10- to 20-fold lower target concentrations (0.5-1 uM versus 10 uM in [S28]), which may exclude lower-affinity hits.' Section S4.1 therefore states a shared assay and does not state a shared selection funnel: the AlphaProteo candidates were chosen by the authors' own filter from a larger in silico set, while the RFdiffusion candidates are the 95 designs the RFdiffusion authors published. Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
| Description The AlphaProteo authors did not run RFdiffusion. Section S4.1 states that they downloaded the published RFdiffusion design sequences and synthesised and tested those by yeast display alongside their own designs, because the published RFdiffusion rates rest on 96-well BLI measurements that were impractical for them to perform. Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
| Relationship: subject uc-binder-20261022-config-rfdiffusion-published-designs-alphaproteo-yeast Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
| Name Section S4.1 states that the RFdiffusion arm is the published designs re-tested, not a rerun Context-only references | De novo design of high-affinity protein binders with AlphaProteo (Zambaldi et al., arXiv 2024) Section S4.1 Version: arXiv version 1, posted 2024-09-12; full-text PDF (49 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the arXiv v1 PDF on 2026-10-22. |
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-claim-alphaproteo-s41-rfdiffusion-arm
- field
- evaluation_actor
- 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
- Section S4.1
- value
- Section S4.1, verbatim: 'Published experimental success rates of RFdiffusion were based on 96-well biolayer interferometry (BLI) measurements [S28], which are impractical for us to perform on our own designs. Therefore, to quantitatively compare success rates, we downloaded sequences of the published RFdiffusion designs and synthesized and tested them by yeast display (Section S1.2) alongside our own designs. Our results matched the published success rates for PD-L1 but were 2-fold lower for IL-7RA (16% versus 33%) and 0% for TrkA (versus 6%) (Table S2). This is potentially due to differences between the yeast surface environment versus purified proteins, as well as our use of 10- to 20-fold lower target concentrations (0.5-1 uM versus 10 uM in [S28]), which may exclude lower-affinity hits.' Section S4.1 therefore states a shared assay and does not state a shared selection funnel: the AlphaProteo candidates were chosen by the authors' own filter from a larger in silico set, while the RFdiffusion candidates are the 95 designs the RFdiffusion authors published.