eLife Assessment
This study presents SynaptoGen, a differentiable extension of connectome models that links gene expression, protein-protein interaction probabilities, synaptic multiplicity, and synaptic weights, and demonstrates its use in reinforcement learning agents and a C. elegans-inspired case study. The work is a valuable contribution to computational connectomics and neuro-inspired machine learning, with solid mathematical and computational evidence supporting the proposed optimization framework. However, the broader biological and synthetic-biology claims - particularly genomic control of synaptogenesis and drug-discovery applications - are currently overstated and would benefit from a more tempered framing and clearer articulation of biological limitations.