Axonal Tree Morphology and Signal Propagation Dynamics Improve Interneuron Classification

Spike transmission failures in axons from mouse cortical pyramidal neurons in vivo

The propagation of action potentials along axons is traditionally considered to be reliable, as a consequence of the high safety factor of action potential propagation. However, numerical simulations have suggested that, at high frequencies, spikes could fail to invade distal axonal branches. Given the complex morphologies of axonal trees, with extensive branching and long-distance projections, spike propagation failures could be functionally important. To explore this experimentally in vivo, we used an axonal-targeted calcium indicator to image action potentials at axonal terminal branches in superficial layers from mouse somatosensory cortical pyramidal neurons. We activated axons with an extracellular electrode, varying stimulation frequencies, and computationally extracted axonal morphologies and associated calcium responses. We find that axonal boutons have higher calcium accumulations than their parent axons, as was reported in vitro. But, contrary to previous in vitro results, our data reveal spike failures in a significant subset of branches, as a function of branching geometry and spike frequency. The filtering is correlated with the geometric ratio of the branch diameters, as expected by cable theory. These findings suggest that axonal morphologies contribute to signal processing in the cortex.

Objective Supervised Machine Learning-Based Classification and Inference of Biological Neuronal Networks

The classification of biological neuron types and networks poses challenges to the full understanding of the human brain’s organisation and functioning. In this paper, we develop a novel objective classification model of biological neuronal morphology and electrical types and their networks, based on the attributes of neuronal communication using supervised machine learning solutions. This presents advantages compared to the existing approaches in neuroinformatics since the data related to mutual information or delay between neurons obtained from spike trains are more abundant than conventional morphological data. We constructed two open-access computational platforms of various neuronal circuits from the Blue Brain Project realistic models, named Neurpy and Neurgen. Then, we investigated how we could perform network tomography with cortical neuronal circuits for the morphological, topological and electrical classification of neurons. We extracted the simulated data of 10,000 network topology combinations with five layers, 25 morphological type (m-type) cells, and 14 electrical type (e-type) cells. We applied the data to several different classifiers (including Support Vector Machine (SVM), Decision Trees, Random Forest, and Artificial Neural Networks). We achieved accuracies of up to 70%, and the inference of biological network structures using network tomography reached up to 65% of accuracy. Objective classification of biological networks can be achieved with cascaded machine learning methods using neuron communication data. SVM methods seem to perform better amongst used techniques. Our research not only contributes to existing classification efforts but sets the road-map for future usage of brain–machine interfaces towards an in vivo objective classification of neurons as a sensing mechanism of the brain’s structure.

A Systematic Evaluation of Interneuron Morphology Representations for Cell Type Discrimination

Quantitative analysis of neuronal morphologies usually begins with choosing a particular feature representation in order to make individual morphologies amenable to standard statistics tools and machine learning algorithms. Many different feature representations have been suggested in the literature, ranging from density maps to intersection profiles, but they have never been compared side by side. Here we performed a systematic comparison of various representations, measuring how well they were able to capture the difference between known morphological cell types. For our benchmarking effort, we used several curated data sets consisting of mouse retinal bipolar cells and cortical inhibitory neurons. We found that the best performing feature representations were two-dimensional density maps, two-dimensional persistence images and morphometric statistics, which continued to perform well even when neurons were only partially traced. Combining these feature representations together led to further performance increases suggesting that they captured non-redundant information. The same representations performed well in an unsupervised setting, implying that they can be suitable for dimensionality reduction or clustering.