Optimize a biological assay in a prepared laboratory
See the requirement-level assessment and its sources.
SCIENCE UNDER AUTOMATION
AI in Biological sciences: capabilities and evidence
Biology asks how living systems work across molecules, cells and organisms. An automated assay is one part of establishing a mechanism.
Autonomy · up to 5.5 / 10
Model interval: 3.2–5.5. Assessed 21 October 2026.
Two equally weighted workflow families: a bounded operational task and an investigation or deployment beyond that task. Inherited subfields use this parent scenario.
Calculation and work mix
Each requirement uses the operational scale from 0 (independent execution unestablished) to 4 (reliable independent execution in the stated setting). A workflow takes its lowest requirement level. The two workflows receive equal weight; the headline is 1 + 9 × weighted level / 4.
These levels are source-linked model assignments, not measurements reported by the papers. “Up to” is the upper model bound, not a probability or a forecast date.
Optimize a biological assay in a prepared laboratory: 2–3 / 4.
Discover and independently test a biological mechanism: 0–1 / 4.
Upper bound with 75:25 workflow weights: 6.6. With 25:75 weights: 4.4.
What has AI demonstrated?
A biofoundry couples ML and language models to enzyme design and measurement over four rounds, with fewer than 500 variants per enzyme.
- Test
- Peer-reviewed physical biofoundry experiments
- Comparison
- Comparators vary by study; see the linked sources.
- System and version
- Autonomous enzyme engineering platform · 2025-07-01
- Evidence checked
- 2026-10-21
The input sequence and measurable fitness objective are supplied. Two enzyme demonstrations do not establish general organism-level experimental autonomy.
What does the field require?
Optimize a biological assay in a prepared laboratory
- Propose candidates for a measurable objective
Autonomy level: 2–3 / 4.
Autonomous enzyme design starts from an input sequence and a defined fitness measurement.
Autonomous enzyme engineering platform - Construct and measure candidates
Autonomy level: 2–3 / 4.
The integrated biofoundry executes iterative construction and characterization.
Autonomous enzyme engineering platform - Choose subsequent rounds from measured feedback
Autonomy level: 2–3 / 4.
Four rounds of design and testing connect feedback to new candidate selection.
Autonomous enzyme engineering platform
Discover and independently test a biological mechanism
- Form a biologically meaningful causal hypothesis
Autonomy level: 1–2 / 4.
Co-Scientist proposes hypotheses conditioned on scientists’ objectives and prior evidence.
Accelerating scientific discovery with Co-Scientist - Select appropriate organisms, controls and interventions
Autonomy level: 0–1 / 4.
The validation applications rely on scientists to choose and execute the biological tests.
Accelerating scientific discovery with Co-Scientist - Validate causality beyond the original assay
Autonomy level: 1–2 / 4.
Researchers provide the physical validation; success in a configured assay does not resolve new biological contexts.
Accelerating scientific discovery with Co-Scientist · Autonomous enzyme engineering platform
Research tasks
Discover and independently test a biological mechanism
See the requirement-level assessment and its sources.
Can AI replace the whole workflow?
The results above measure specific tasks. The field assessment also requires completion of the connected workflow, including the requirements listed here. A field-wide replacement percentage has not been established.
Read the assessment method