Persistent Identifier
|
doi:10.5683/SP2/AARXSN |
Publication Date
|
2019-03-11 |
Title
| Application and evaluation of automated methods to extract neuroanatomical connectivity statements from free text |
Author
| French, Leon (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Lane, Suzanne (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Xu, Lydia (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Siu, Celia (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Kwok, Cathy (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Chen, Yigi (Department of Psychiatry and Centre for High-Throughput Biology, UBC)
Krebs, Claudia (Department of Cellular and Physiological Sciences, UBC)
Pavlidis, Paul (Department of Psychiatry and Centre for High-Throughput Biology, UBC) |
Point of Contact
|
Use email button above to contact.
UBC Research Data (University of British Columbia) |
Description
| Motivation: Automated annotation of neuroanatomical connectivity statements from the neuroscience literature would enable accessible and large-scale connectivity resources. Unfortunately, the connectivity findings are not formally encoded and occur as natural language text. This hinders aggregation, indexing, searching and integration of the reports. We annotated a set of 1377 abstracts for connectivity relations to facilitate automated extraction of connectivity relationships from neuroscience literature. We tested several baseline measures based on co-occurrence and lexical rules. We compare results from seven machine learning methods adapted from the protein interaction extraction domain that employ part-of-speech, dependency and syntax features.
Results: Co-occurrence based methods provided high recall with weak precision. The shallow linguistic kernel recalled 70.1% of the sentence-level connectivity statements at 50.3% precision. Owing to its speed and simplicity, we applied the shallow linguistic kernel to a large set of new abstracts. To evaluate the results, we compared 2688 extracted connections with the Brain Architecture Management System (an existing database of rat connectivity). The extracted connections were connected in the Brain Architecture Management System at a rate of 63.5%, compared with 51.1% for co-occurring brain region pairs. We found that precision increases with the recency and frequency of the extracted relationships.
|
Subject
| Medicine, Health and Life Sciences |
Topic Classification
| Open (Open Access Tag) |
Related Publication
| French L, Lane S, Xu L, et al. "Application and evaluation of automated methods to extract neuroanatomical connectivity statements from free text." Bioinformatics. 2012;28(22):2963-2970. doi:10.1093/bioinformatics/bts542. |
Notes
| http://hdl.handle.net/11272/10579 |
Producer
| Department of Psychiatry (Dept of Psych) https://psychiatry.ubc.ca/
Centre for High-Throughput Biology (CHiBi) http://www.chibi.ubc.ca/ |
Production Date
| 2012 |
Production Location
| Vancouver, BC |
Funding Information
| NSERC, NIH, CFI, MSFHR, CIHR |
Distributor
| University of British Columbia (UBC) https://www.ubc.ca/ |
Depositor
| Cuthill, Melissa |
Deposit Date
| 2019-03-11 |
Related Material
| http://msl-pavlidis-lab.sites.olt.ubc.ca/data-and-supplementary-information/the-whitetext-project/application-and-evaluation-of-automated-methods-to-extract-connectivity-statements-from-free-text/ |