The circuit architecture of whole brains at the mesoscopic scale

Abstract

Vertebrate brains of even moderate size are composed of astronomically large numbers of neurons and show a great degree of individual variability at the microscopic scale. This variation is presumably the result of phenotypic plasticity and individual experience. At a larger scale, however, relatively stable species-typical spatial patterns are observed in neuronal architecture, e.g., the spatial distributions of somata and axonal projection patterns, probably the result of a genetically encoded developmental program. The mesoscopic scale of analysis of brain architecture is the transitional point between a microscopic scale where individual variation is prominent and the macroscopic level where a stable, species-typical neural architecture is observed. The empirical existence of this scale, implicit in neuroanatomical atlases, combined with advances in computational resources, makes studying the circuit architecture of entire brains a practical task. A methodology has previously been proposed that employs a shotgun-like grid-based approach to systematically cover entire brain volumes with injections of neuronal tracers. This methodology is being employed to obtain mesoscale circuit maps in mouse and should be applicable to other vertebrate taxa. The resulting large data sets raise issues of data representation, analysis, and interpretation, which must be resolved. Even for data representation the challenges are nontrivial: the conventional approach using regional connectivity matrices fails to capture the collateral branching patterns of projection neurons. Future success of this promising research enterprise depends on the integration of previous neuroanatomical knowledge, partly through the development of suitable computational tools that encapsulate such expertise.

Figure 1. The Mesoscale as a Transitional Scale between a Microscopic Scale where Large Interindividual Differences Exist, to a Larger Scale where a Species-Typical Pattern that Is Relatively Stable across Individuals Is Observed

The two schematic illustrations of distributions of neuronal somata represent two individuals, showing a transition between two brain regions (denoted in black and green) with differing densities of the neurons symbolized as filled triangles. At the microscale (top plot), the schematized density shows variations with large variations between individuals. At the mesoscopic scale (bottom plot), a smoother density is obtained that is relatively stable across individuals and shows a species-typical structure.

Figure 2. The Failure of Regional Connectivity Matrices to Capture Information about Collateral Branching Patterns, and the Utility of Retrograde Tracer Injections in Revealing Information about Such Collateral Branches

The two neuronal configurations in (A) and (D) both correspond to the same regional connectivity matrix (B and E). Nevertheless, these configurations are neurobiologically different: in (D), individual neurons from region A send branches to both regions B and C, ensuring synchrony between signals sent from the neuronal somata in A to targets in B and C. The difference can be characterized by adding a hidden node H to the connectivity matrices that represent the branch point (C and F). Double retrograde injections with two fluorescent tracers with different colors injected into the target regions, can unambiguously identify neurons sending collateral branches to regions B and C (G). A single retrograde injection into region B, if it fills the entire neuron (requiring both retrograde and anterograde transport at the branch point), can also reveal collateral branches (H).