Predicting human protein function with multi-task deep neural networks
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UniProt: the universal protein knowledgebase
The UniProt Consortium (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1099 · Cited by 4,436
Expansion of the Gene Ontology knowledgebase and resources
The Gene Ontology Consortium (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1108 · Cited by 1,850
DeepTox: toxicity prediction using deep learning
Mayr, A., Klambauer, G., Unterthiner, T., & Hochreiter, S. (2016) · Frontiers in Environmental Science · doi:10.3389/fenvs.2015.00080 · Cited by 1,081 · cited 1×
“This modelling approach has been previously applied to virtual screening [30], toxicity prediction [31] and prediction of protein biophysical features including secondary structure, solvent accessibility, transmembrane segments and signal peptides [32].”
A large-scale evaluation of computational protein function prediction
Radivojac, P., Clark, W. T., Oron, T. R., Schnoes, A. M., Wittkop, T., Sokolov, A., Graim, K., Funk, C., Verspoor, K., Ben-Hur, A., et al. (2013) · Nature Methods · doi:10.1038/nmeth.2340 · Cited by 1,028 · cited 2×
“To answer this question, we firstly evaluated the F max performance of all compared methods following the practice in CAFA [20,21].”
Self-citationAccurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
Wang, S., Sun, S., Li, Z., Zhang, R., & Xu, J. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005324 · Cited by 931
FFPred 3: feature-based function prediction for all Gene Ontology domains
Cozzetto, D., Minneci, F., Currant, H., & Jones, D. T. (2016) · Scientific Reports · doi:10.1038/srep31865 · Cited by 127
Self-citation
Cited by
DeepGOPlus: improved protein function prediction from sequence
Kulmanov, M., & Hoehndorf, R. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz595 · Cited by 473
Zhou, N., Jiang, Y., Bergquist, T. R., Lee, A. J., Kacsoh, B. Z., Crocker, A. W., Lewis, K. A., Georghiou, G., Nguyen, H. N., Hamid, M. N., et al. (2019) · Genome Biology · doi:10.1186/s13059-019-1835-8 · Cited by 452
Self-citationMachine learning: a powerful tool for gene function prediction in plants
Mahood, E. H., Kruse, L. H., & Moghe, G. D. (2020) · Applications in Plant Sciences · doi:10.1002/aps3.11376 · Cited by 153
DeepSS2GO: protein function prediction from secondary structure
Song, F. V., Su, J., Huang, S., Zhang, N., Li, K., Ni, M., & Liao, M. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae196 · Cited by 26
Zhang, C., Lane, L., Omenn, G. S., & Zhang, Y. (2019) · Journal of Proteome Research · doi:10.1021/acs.jproteome.9b00537 · Cited by 22
Metadata
- Authors
- Fa, R., Cozzetto, D., Wan, C., & Jones, D. T.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2018-06-11
- Volume
- 13
- Issue
- 6
- Pages
- e0198216
- ISSN
- 1932-6203 (ISSN-L)
- OpenAlex
- W2952218450
- Cited by
- 87
- References
- 6
- FWCI
- 3.92
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.