Efficient metadata mining of web-accessible neural morphologies

Akram, Masood A.; Ljungquist, Bengt; Ascoli, Giorgio A.

doi:10.1016/j.pbiomolbio.2021.05.005

Cited by 13 publications

(15 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unrestricted access to mined metadata on publicly shared repositories is vital to enable reproducibility, replicability, further scientific exploration, and data-driven computational modeling [ 5 , 14 , 33 ]. Within the domain of neural morphology, recent developments include detailed statistical analyses enabled by machine learning [ 8 ] and tools for organizing large amounts of data based on arbitrary combinations of user-selected metadata [ 1 ]. More broadly, the prominence of such endeavors is continuously growing in neuroscience [ 3 ].…”

Section: Discussionmentioning

confidence: 99%

Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org

2022

Self Cite

View full text Add to dashboard Cite

The amount of unstructured text produced daily in scholarly journals is enormous. Systematically identifying, sorting, and structuring information from such a volume of data is increasingly challenging for researchers even in delimited domains. Named entity recognition is a fundamental natural language processing tool that can be trained to annotate, structure, and extract information from scientific articles. Here, we harness state-of-the-art machine learning techniques and develop a smart neuroscience metadata suggestion system accessible by both humans through a user-friendly graphical interface and machines via Application Programming Interface. We demonstrate a practical application to the public repository of neural reconstructions, NeuroMorpho.Org, thus expanding the existing web-based metadata management system currently in use. Quantitative analysis indicates that the suggestion system reduces personnel labor by at least 50%. Moreover, our results show that larger training datasets with the same software architecture are unlikely to further improve performance without ad-hoc heuristics due to intrinsic ambiguities in neuroscience nomenclature. All components of this project are released open source for community enhancement and extensions to additional applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The morphological reconstructions of glial processes and neuronal dendrites utilized in this work were contributed to NeuroMorpho.Org by over 250 independent laboratories and reflect the distribution of published arbor tracings in neuroscience (Figure 1). These digital tracings of neurons and glia were downloaded from the database using the Summary Reporting web‐based functionality (Akram et al, 2022). This tool collates for every digital tracings the annotation of 35 distinct metadata fields, providing a detailed qualitative description of the cell (Parekh et al, 2015), as well as 21 morphometric measurements which capture the quantitative structural features of the arbor (Scorcioni et al, 2008).…”

Section: Methodsmentioning

confidence: 99%

Machine learning classification reveals robust morphometric biomarker of glial and neuronal arbors

Akram

Wei

Ascoli

2022

J of Neuroscience Research

Self Cite

View full text Add to dashboard Cite

Neurons and glia are the two main cell classes in the nervous systems of most animals. Although functionally distinct, neurons and glia are both characterized by multiple branching arbors stemming from the cell bodies. Glial processes are generally known to form smaller trees than neuronal dendrites. However, the full extent of morphological differences between neurons and glia in multiple species and brain regions has not yet been characterized, nor is it known whether these cells can be reliably distinguished based on geometric features alone. Here, we show that multiple supervised learning algorithms deployed on a large database of morphological reconstructions can systematically classify neuronal and glial arbors with nearly perfect accuracy and precision. Moreover, we report multiple morphometric properties, both size related and size independent, that differ substantially between these cell types. In particular, we newly identify an individual morphometric measurement, Average Branch Euclidean Length that can robustly separate neurons from glia across multiple animal models, a broad diversity of experimental conditions, and anatomical areas, with the notable exception of the cerebellum. We discuss the practical utility and physiological interpretation of this discovery.

show abstract

“…Morphological reconstructions of neurons and glia were obtained from NeuroMorpho.Org using the Summary Reporting web-based functionality (Akram et al, 2022). This tool collates for every digital tracings the annotation of 35 distinct metadata fields, providing a detailed qualitative description of the cell (Parekh et al, 2015), as well as 21 morphometric measurements which capture the quantitative structural features of the arbor (Scorcioni et al, 2008).…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Classification Reveals Robust Morphometric Biomarker of Glial and Neuronal Arbors

Akram

Wei

Ascoli

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Neurons and glia are the two main cell classes in the nervous systems of most animals. Although functionally distinct, neurons and glia are both characterized by multiple branching arbors stemming from the cell bodies. Glial processes are generally known to form smaller trees than neuronal dendrites. However, the full extent of morphological differences between neurons and glia in multiple species and brain regions has not yet been characterized, nor is it known whether these cells can be reliably distinguished based on geometric features alone. Here, we show that multiple supervised learning algorithms (K-nearest neighbor, random forest, and support vector machine) deployed on a large database of morphological reconstructions can systematically classify neuronal and glial arbors with nearly perfect accuracy and precision. Moreover, we report multiple morphometric properties, both size-related and size-independent, that differ substantially between these cell types. In particular, we newly identify an individual morphometric measurement, Average Branch Euclidean Length (ABEL) that can robustly separate neurons from glia across multiple animal models, a broad diversity of experimental conditions, and anatomical areas, with the notable exception of the cerebellum. We discuss the practical utility and physiological interpretation of this discovery.

show abstract

Efficient metadata mining of web-accessible neural morphologies

Cited by 13 publications

References 56 publications

Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org

Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org

Machine learning classification reveals robust morphometric biomarker of glial and neuronal arbors

Machine Learning Classification Reveals Robust Morphometric Biomarker of Glial and Neuronal Arbors

Contact Info

Product

Resources

About