TOXIFY: a deep learning approach to classify animal venom proteins
- ECU Author/Contributor (non-ECU co-authors, if there are any, appear on document)
- T. Jeffrey,Brewer,Michael S. Cole (Creator)
- Institution
- East Carolina University (ECU )
- Web Site: http://www.ecu.edu/lib/
Abstract: In the era of Next-Generation Sequencing and shotgun proteomics, the sequencesof animal toxigenic proteins are being generated at rates exceeding the pace oftraditional means for empirical toxicity verification. To facilitate the automation oftoxin identification from protein sequences, we trained Recurrent Neural Networkswith Gated Recurrent Units on publicly available datasets. The resulting models areavailable via the novel software package TOXIFY, allowing users to infer the probabilityof a given protein sequence being a venom protein. TOXIFY is more than 20X fasterand uses over an order of magnitude less memory than previously published methods.Additionally, TOXIFY is more accurate, precise, and sensitive at classifying venomproteins.
Additional Information
- Publication
- Other
- Language: English
- Date: 2019
- Keywords
- Venom, Deep learning, Protein classification, Transcriptome, Proteome
| Title | Location & Link | Type of Relationship |
| TOXIFY: a deep learning approach to classify animal venom proteins | http://hdl.handle.net/10342/8341 | The described resource references, cites, or otherwise points to the related resource. |