Capability benchmark · Biology
scGPT adapts generative pretrained transformers to single-cell biology
scGPT adapts generative pretrained transformers to single-cell biology: capability signal for AI systems on research-adjacent tasks.
Summary
The Nature Methods paper introduces scGPT, a generative pretrained transformer trained on more than 33 million cells for single-cell biology. The authors report transfer-learning results across tasks including cell-type annotation, batch integration, multi-omic integration, perturbation-response prediction and gene-network inference.
AI role
AI systems are tested on research-adjacent capabilities relevant to biology.
Narrative role
This is supporting evidence for whether AI systems can perform research-adjacent tasks needed before stronger discovery or acceleration claims.
Caveat
Benchmark, model, or tool performance is an upstream capability indicator, not proof of new scientific discovery.