OnCo
technologiesTechnologyEmerging

GEARS and perturbation prediction benchmarks

GEARS is a graph model predicting the effect of gene knockouts; the perturbation benchmarks around it showed how hard the problem is.

GEARS (Nature Biotechnology 2023) used gene-gene graphs to predict unseen perturbations; 2024-25 benchmark studies found many foundation models barely beat simple baselines, sharpening evaluation standards (e.g. Virtual Cell Challenge).

Generic schematic · not to scale · placeholder for the ai computation front
Flagged finding · Neural network

How it works

GEARS is a graph neural network over gene relationships.

Strengths
  • Combinatorial perturbations
Limitations
  • Weak baselines exposed field-wide
Since
2023

Latest papers

top
Latest papers · live from Europe PMC
Open in Europe PMC

Query for this technology: (TITLE:"GEARS and perturbation prediction benchmarks" OR ABSTRACT:"GEARS and perturbation prediction benchmarks") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about GEARS and perturbation prediction benchmarks, not a curated reading list.

Connected

4top