ProteInfer, deep neural networks for protein functional inference
| Autor: | Sanderson, Theo, Bileschi, Maxwell L, Belanger, David, Colwell, Lucy J |
|---|---|
| Přispěvatelé: | Sanderson, Theo [0000-0003-4177-2851], Bileschi, Maxwell L [0000-0001-6771-0590], Belanger, David [0000-0001-7115-9009], Colwell, Lucy J [0000-0003-3148-0337], Apollo - University of Cambridge Repository |
| Rok vydání: | 2023 |
| Předmět: |
Model organisms
function learning General Immunology and Microbiology neural network none FOS: Clinical medicine General Neuroscience Immunology Proteins Computational Biology systems biology Infectious Disease prediction Cell Biology General Medicine Biochemistry & Proteomics General Biochemistry Genetics and Molecular Biology Neural Networks Computer Amino Acid Sequence protein Algorithms Software Structural Biology & Biophysics |
| Zdroj: | eLife. 12 |
| ISSN: | 2050-084X |
| DOI: | 10.7554/elife.80942 |
| Popis: | Peer reviewed: True Acknowledgements: We thank Babak Alipanahi, Jamie Smith, Eli Bixby, Drew Bryant, Shanqing Cai, Cory McLean, and Abhinay Ramaprasad. The static version of this manuscript uses a template made by Ricardo Henriques. TS receives funding from the Wellcome Trust through a Sir Henry Wellcome Postdoctoral Fellowship (210918/Z/18/Z). LJC receives funding from the Simons Foundation (Award 598399). This work was also supported by the Francis Crick Institute which receives its core funding from Cancer Research UK (FC001043), the UK Medical Research Council (FC001043), and the Wellcome Trust (FC001043). This research was funded in whole, or in part, by the Wellcome Trust (FC001043). For the purpose of Open Access, the authors have applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. Funder: Google; FundRef: http://dx.doi.org/10.13039/100006785 Predicting the function of a protein from its amino acid sequence is a long-standing challenge in bioinformatics. Traditional approaches use sequence alignment to compare a query sequence either to thousands of models of protein families or to large databases of individual protein sequences. Here we introduce ProteInfer, which instead employs deep convolutional neural networks to directly predict a variety of protein functions - Enzyme Commission (EC) numbers and Gene Ontology (GO) terms - directly from an unaligned amino acid sequence. This approach provides precise predictions which complement alignment-based methods, and the computational efficiency of a single neural network permits novel and lightweight software interfaces, which we demonstrate with an in-browser graphical interface for protein function prediction in which all computation is performed on the user's personal computer with no data uploaded to remote servers. Moreover, these models place full-length amino acid sequences into a generalised functional space, facilitating downstream analysis and interpretation. To read the interactive version of this paper, please visit https://google-research.github.io/proteinfer/. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|