Computational genomics
A large part of the work already happens inside software. The difficult boundary is between executing an analysis and knowing whether it answers the biological question.
SCIENCE UNDER AUTOMATION
AI across scientific fields — directory 1
Browse scientific disciplines and their research demands.
Theoretical physics
Removing the laboratory does not make the whole field easy to automate. Choosing a tractable question and finding a useful new description remain distinct from solving a specified problem.
Experimental molecular biology
An agent can reason about a protocol while an experiment still depends on instruments, specimens and troubleshooting. Automation becomes more plausible where those physical steps are standardized and connected.
Field ecology
Collecting observations can require access to a changing landscape. Models may accelerate analysis while sampling, local context and the time needed to observe change remain limiting.
Structural biology
82/84 top-1 domains have correct folds
Weather forecasting
12–24 hours of medium-range skill advantage
Algorithm design
Up to 70% faster for length-5 sorting
Mathematics
1.0 mean score in the official export
Materials science
36/57 targets synthesized in 17 days
Drug discovery
Experimental validation of a nominated compound
Astronomy
301 new exoplanets validated from Kepler archive candidates
Synthetic chemistry
Six demonstrated task types, including synthesis planning and experimental optimization
Neuroscience
524 million synaptic clefts automatically detected and associated
Seismology
Applied to data from 11,241 catalogued earthquakes
Computational pathology
Evaluated on 25 cancer subtyping and pathomics tasks
Radiology
6.4 vs 5.0 cancers detected per 1,000 screened
Computer science
Computing turns specifications into software and tests ideas through executable experiments. Problem selection and verification determine how far those workflows can run unaided.
Experimental physics
Experiments require working instruments, calibrated measurements and a physical interpretation that survives systematic checks.
Chemical sciences
Chemistry couples molecular proposals to synthesis, measurement and interpretation. A configured robotic loop can cover much of one experiment.
Biological sciences
Biology asks how living systems work across molecules, cells and organisms. An automated assay is one part of establishing a mechanism.
Clinical medicine
Clinical work connects diagnosis to treatment, follow-up and responses to complications in real patients.
Population health
Population health connects observations and forecasts to interventions whose effects must be measured in people.
Earth & environmental science
Earth science combines remote observations, physical samples, models and tests of processes that unfold in space and time.
Engineering
Engineering must turn requirements into an artifact that performs under physical constraints, including failure conditions.