Research library
Biology and protein engineering
View the four-date completion graphs and reconstruction notes.
Promise and evidence
AI could improve our understanding of biological systems and the design of useful enzymes, proteins, and interventions. AlphaFold 3 demonstrates prediction of biomolecular complexes. Predicted structure, actual biological function, and clinical benefit are distinct outcomes.
Apply the shared measurement protocol. Targets are proposed.
Dated baseline coverage
All linked measurable-outcome files below contain an evidence baseline reviewed November 7, 2026, with source dates, findings, limitations and follow-up measurements. These distinguish measured results from proxies and unknown values; they do not assert that proposed milestones are achieved. See the baseline coverage notes.
Progress estimates
Judgment-based estimates as of November 7, 2026, using the same 0–100% scale and five-part rubric as mathematics. 0% anchors the period before ChatGPT's public release in 2022; 100% requires AI to manage this field's continuing advancement without human participation. Confidence is low. These are evidence-based judgments, not empirical completion measurements, forecasts or percentages of jobs replaced.
| Measurable outcome | Estimated progress | Execution / breadth / agenda / validation / improvement (each out of 20) |
|---|---|---|
| Design success | 40% | 15 / 10 / 5 / 5 / 5 |
| Functional prediction | 30% | 10 / 10 / 5 / 5 / 0 |
| Generalization | 25% | 10 / 5 / 5 / 5 / 0 |
| Research efficiency | 30% | 10 / 5 / 5 / 5 / 5 |
| Structural accuracy | 45% | 15 / 10 / 5 / 10 / 5 |
| Useful novelty | 25% | 10 / 5 / 5 / 5 / 0 |
Each linked outcome explains its score, cites its dated evidence baseline and identifies the next measurement. Zero indicates no qualifying post-anchor progress established by the reviewed evidence for that outcome, not proof of no relevant capability. Do not average these overlapping indicators into a field-wide percentage or interpret their differences as a precise ranking of fields. All outcomes reaching 100% would still require a separate field-wide demonstration of sustained autonomous advancement.
Measurable features
| Feature | Measurement and acceptance rule |
|---|---|
| Structural accuracy | Accuracy against subsequently released experimental structures using preregistered structural and interface metrics; split by molecular class and similarity to training data. |
| Functional prediction | Prospective prediction error and calibration for measured binding, enzyme activity, or cellular response. Use new experiments rather than only retrospective databases. |
| Design success | Experimentally functional designs / all synthesized AI proposals, with explicit activity, stability, and specificity requirements. |
| Useful novelty | Designs or mechanisms judged substantively different from known sequences and functions; sequence difference alone does not establish a new function. |
| Research efficiency | Experimental cycles, human hours, elapsed time, and total cost per independently validated functional result. |
| Generalization | Performance on held-out protein families, cell types, and experimental conditions, reported separately. |
Evidence requirements
Freeze predictions before experiments and preserve all designed candidates, including failed ones. Use controls, biological replicates, independent assays, and a second laboratory. Record sequence and family overlap with known data. Do not count a favorable predicted structure as experimental confirmation of activity or mechanism.
Proposed milestones
Prospectively evaluate 100 proposals against a frozen functional specification and an equal-budget expert or established computational baseline.
Obtain ten experimentally confirmed functional designs, with at least three independently reproduced and their novelty explicitly classified.
Achieve at least 20% better prespecified functional performance or 25% lower total discovery cost without degrading required specificity and stability.
Reproduce improvements across three unrelated biological task families. Track whether each completed research cycle improves the next cycle's prediction and design success on fresh targets; this is stronger evidence of accelerating discovery than static structure accuracy.