Research library
Biology and protein engineering: completion history
All area pages | Area definition | Scoring rubric
Created November 7, 2026. The three earlier snapshots are retrospective judgment-based estimates, not scores recorded at the time. The current assessment is unchanged. Historical confidence is very low; current confidence is low. Zero can indicate an evidence gap rather than absent capability.
Chart layout updated November 8, 2026: one graph with four dated lines. Scores and assessment dates are unchanged. Overlapping lines indicate equal values; point labels show November 7, 2026. The table below contains every date's exact values.
Scalable graph | Combined 14-page report
Percentage estimates
| Measurable outcome | Nov 7, 2025 (reconstructed) | May 7, 2026 (reconstructed) | Oct 7, 2026 (reconstructed) | Nov 7, 2026 (saved) |
|---|---|---|---|---|
| Design success | 40% | 40% | 40% | 40% |
| Functional prediction | 25% | 30% | 30% | 30% |
| Generalization | 20% | 25% | 25% | 25% |
| Research efficiency | 20% | 20% | 30% | 30% |
| Structural accuracy | 45% | 45% | 45% | 45% |
| Useful novelty | 25% | 25% | 25% | 25% |
Reconstruction notes and component scores
Components below are execution / breadth / agenda-setting / validation / sustained autonomous improvement, each out of 20. Their sum gives the percentage. The component values are judgments, not published statistics. Source links document evidence available by the cutoff, not the numerical estimate itself. The source section lists availability dates and version caveats. No area-wide average is calculated.
Design success
The experimental binder evidence was published in August 2025. No later comparable all-design functional success series justifies a changed judgment.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 15 / 10 / 5 / 5 / 5 = 40% | bind |
| 2026-05-07 (reconstructed) | 15 / 10 / 5 / 5 / 5 = 40% | bind |
| 2026-10-07 (reconstructed) | 15 / 10 / 5 / 5 / 5 = 40% | bind |
| 2026-11-07 (saved) | 15 / 10 / 5 / 5 / 5 = 40% | Original score and evidence |
Functional prediction
The preview supports limited genomic prediction in 2025. The January 2026 evaluation adds breadth, while prospective calibration remains unestablished.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | genome25 |
| 2026-05-07 (reconstructed) | 10 / 10 / 5 / 5 / 0 = 30% | genome |
| 2026-10-07 (reconstructed) | 10 / 10 / 5 / 5 / 0 = 30% | genome |
| 2026-11-07 (saved) | 10 / 10 / 5 / 5 / 0 = 30% | Original score and evidence |
Generalization
The initial preview supplies a narrow transfer proxy; the peer-reviewed holdout evaluation supports execution credit by May without proving broad cross-condition transfer.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 5 / 5 / 5 / 5 / 0 = 20% | genome25 |
| 2026-05-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | genome |
| 2026-10-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | genome |
| 2026-11-07 (saved) | 10 / 5 / 5 / 5 / 0 = 25% | Original score and evidence |
Research efficiency
Binder design provides an earlier workflow proxy, not end-to-end efficiency. August characterization throughput supports a higher execution and repeated-operation judgment.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 5 / 5 / 5 / 5 / 0 = 20% | bind |
| 2026-05-07 (reconstructed) | 5 / 5 / 5 / 5 / 0 = 20% | bind |
| 2026-10-07 (reconstructed) | 10 / 5 / 5 / 5 / 5 = 30% | sapp |
| 2026-11-07 (saved) | 10 / 5 / 5 / 5 / 5 = 30% | Original score and evidence |
Structural accuracy
The joint-structure result predates all snapshots. The same prospective verification and autonomy gaps persist.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 15 / 10 / 5 / 10 / 5 = 45% | fold |
| 2026-05-07 (reconstructed) | 15 / 10 / 5 / 10 / 5 = 45% | fold |
| 2026-10-07 (reconstructed) | 15 / 10 / 5 / 10 / 5 = 45% | fold |
| 2026-11-07 (saved) | 15 / 10 / 5 / 10 / 5 = 45% | Original score and evidence |
Useful novelty
Functional designed binders were already demonstrated. Sequence novelty still does not establish a new biological function, so no time-based increase is assigned.
| Assessment date | Component points | Evidence used |
|---|---|---|
| 2025-11-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | bind |
| 2026-05-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | bind |
| 2026-10-07 (reconstructed) | 10 / 5 / 5 / 5 / 0 = 25% | bind |
| 2026-11-07 (saved) | 10 / 5 / 5 / 5 / 0 = 25% | Original score and evidence |
Dated sources
All sources accessed November 7, 2026. Dates below are publication or conservative availability dates, as noted.
fold | 2024-05-08 - AlphaFold 3, Nature. Joint molecular-structure prediction; structural accuracy does not establish biological function.
genome25 | 2025-06-25 - AlphaGenome preview. Initial predictive genomics system; January 2026 update excluded from the 2025 assessment.
bind | 2025-08-27 - BindCraft, Nature. Experimentally tested protein binders; not autonomous selection of new biological functions.
genome | 2026-01-28 - AlphaGenome, Nature. Regulatory variant-effect evaluation; prospective cross-context validity still limited.
sapp | 2026-08-20 - Protein design validation platform, Nature Communications. Specialized protein characterization throughput; full functional validation cost unmeasured.
Future updates
Keep these reconstructions separate from subsequently recorded observations. Append new dated assessments with changed component scores and source evidence; do not silently replace historical reasoning. The shared historical-method notes describe how these snapshots were made.