Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org
Abstract 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 natu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-11-01
|
| Series: | Brain Informatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40708-022-00174-4 |
| _version_ | 1828198073866649600 |
|---|---|
| author | Kayvan Bijari Yasmeen Zoubi Giorgio A. Ascoli |
| author_facet | Kayvan Bijari Yasmeen Zoubi Giorgio A. Ascoli |
| author_sort | Kayvan Bijari |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-04-12T10:31:29Z |
| format | Article |
| id | doaj.art-52280c30363e4045af40c61ffa36eea4 |
| institution | Directory Open Access Journal |
| issn | 2198-4018 2198-4026 |
| language | English |
| last_indexed | 2024-04-12T10:31:29Z |
| publishDate | 2022-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Brain Informatics |
| spelling | doaj.art-52280c30363e4045af40c61ffa36eea42022-12-22T03:36:50ZengSpringerOpenBrain Informatics2198-40182198-40262022-11-019111110.1186/s40708-022-00174-4Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.OrgKayvan Bijari0Yasmeen Zoubi1Giorgio A. Ascoli2College of Science, Neuroscience Program, George Mason UniversityCollege of Science, Neuroscience Program, George Mason UniversityCollege of Science, Neuroscience Program, George Mason UniversityAbstract 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.https://doi.org/10.1186/s40708-022-00174-4Metadata managementNeuro-curationNeuroinformaticsNatural language processingNamed entity recognitionMachine intelligence |
| spellingShingle | Kayvan Bijari Yasmeen Zoubi Giorgio A. Ascoli Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org Brain Informatics Metadata management Neuro-curation Neuroinformatics Natural language processing Named entity recognition Machine intelligence |
| title | Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org |
| title_full | Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org |
| title_fullStr | Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org |
| title_full_unstemmed | Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org |
| title_short | Assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on NeuroMorpho.Org |
| title_sort | assisted neuroscience knowledge extraction via machine learning applied to neural reconstruction metadata on neuromorpho org |
| topic | Metadata management Neuro-curation Neuroinformatics Natural language processing Named entity recognition Machine intelligence |
| url | https://doi.org/10.1186/s40708-022-00174-4 |
| work_keys_str_mv | AT kayvanbijari assistedneuroscienceknowledgeextractionviamachinelearningappliedtoneuralreconstructionmetadataonneuromorphoorg AT yasmeenzoubi assistedneuroscienceknowledgeextractionviamachinelearningappliedtoneuralreconstructionmetadataonneuromorphoorg AT giorgioaascoli assistedneuroscienceknowledgeextractionviamachinelearningappliedtoneuralreconstructionmetadataonneuromorphoorg |