Researchconnectomicscell typingfruit flyunsupervised clustering
Connectome-Based AI Assigns Neuronal Types Accurately
|
9.2
Researchers led by the Japan Advanced Institute of Science and Technology published a Nature Communications paper on Jan. 6, 2026 introducing NTAC, an AI that classifies neuronal types using synaptic connectivity alone. NTAC achieved over 90% accuracy in the fruit fly optic lobe, runs on a standard laptop in minutes, and attains ~70% unsupervised accuracy locally and 52% on full-brain datasets.
Scoring Rationale
High novelty and strong peer-reviewed validation, limited to connectomics scale and pending multimodal integration for mammalian brains.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
