RESUMO
Longitudinal studies that continuously generate data enable the capture of temporal variations in experimentally observed parameters, facilitating the interpretation of results in a time-aware manner. We propose IL-VIS (incrementally learned visualizer), a new machine learning pipeline that incrementally learns and visualizes a progression trajectory representing the longitudinal changes in longitudinal studies. At each sampling time point in an experiment, IL-VIS generates a snapshot of the longitudinal process on the data observed thus far, a new feature that is beyond the reach of classical static models. We first verify the utility and correctness of IL-VIS using simulated data, for which the true progression trajectories are known. We find that it accurately captures and visualizes the trends and (dis)similarities between high-dimensional progression trajectories. We then apply IL-VIS to longitudinal multi-electrode array data from brain cortical organoids when exposed to different levels of quinolinic acid, a metabolite contributing to many neuroinflammatory diseases including Alzheimer's disease, and its blocking antibody. We uncover valuable insights into the organoids' electrophysiological maturation and response patterns over time under these conditions.
Assuntos
Aprendizado de Máquina , Estudos Longitudinais , Humanos , Organoides , Doença de Alzheimer/metabolismo , Encéfalo/fisiologiaRESUMO
A deeper understanding of the brain and its function remains one of the most significant scientific challenges. It not only is required to find cures for a plethora of brain-related diseases and injuries but also opens up possibilities for achieving technological wonders, such as brain-machine interface and highly energy-efficient computing devices. Central to the brain's function is its basic functioning unit (i.e., the neuron). There has been a tremendous effort to understand the underlying mechanisms of neuronal growth on both biochemical and biophysical levels. In the past decade, this increased understanding has led to the possibility of controlling and modulating neuronal growth in vitro through external chemical and physical methods. We provide a detailed overview of the most fundamental aspects of neuronal growth and discuss how researchers are using interdisciplinary ideas to engineer neuronal networks in vitro. We first discuss the biochemical and biophysical mechanisms of neuronal growth as we stress the fact that the biochemical or biophysical processes during neuronal growth are not independent of each other but, rather, are complementary. Next, we discuss how utilizing these fundamental mechanisms can enable control over neuronal growth for advanced neuroengineering and biomedical applications. At the end of this review, we discuss some of the open questions and our perspectives on the challenges and possibilities related to controlling and engineering the growth of neuronal networks, specifically in relation to the materials, substrates, model systems, modulation techniques, data science, and artificial intelligence.