The DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index.
Using deep learning to annotate the protein universe
Open accessPublished version of a preprint
Abstract
Understanding the relationship between amino acid sequence and protein function is a long-standing challenge with far-reaching scientific and translational implications. State-of-the-art alignment-based techniques cannot predict function for one-third of microbial protein sequences, hampering our ability to exploit data from diverse organisms. Here, we train deep learning models to accurately predict functional annotations for unaligned amino acid sequences across rigorous benchmark assessments built from the 17,929 families of the protein families database Pfam. The models infer known patterns of evolutionary substitutions and learn representations that accurately cluster sequences from unseen families. Combining deep models with existing methods significantly improves remote homology detection, suggesting that the deep models learn complementary information. This approach extends the coverage of Pfam by >9.5%, exceeding additions made over the last decade, and predicts function for 360 human reference proteome proteins with no previous Pfam annotation. These results suggest that deep learning models will be a core component of future protein annotation tools.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These embeddings can capture evolutionary traits of the proteins, as well as functional and structural characteristics.119”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [119]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Basic local alignment search tool
Altschul, S. F., Gish, W., Miller, W., Myers, E. W., & Lipman, D. J. (1990) · Journal of Molecular Biology · doi:10.1006/jmbi.1990.9999 · Cited by 98,669
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gapped BLAST and PSI-BLAST: a new generation of protein database search programs
Altschul, S. (1997) · Nucleic Acids Research · doi:10.1093/nar/25.17.3389 · Cited by 73,302
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Fast and sensitive protein alignment using DIAMOND
Buchfink, B., Xie, C., & Huson, D. H. (2015) · Nature Methods · doi:10.1038/nmeth.3176 · Cited by 14,201
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738
UniProt: the Universal Protein knowledgebase
Apweiler, R. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkh131 · Cited by 7,593
Research works printed but not linked: 1
- El-Gebali, S., Richardson, L. & Finn, R. Repeats in Pfam. EMBL-EBI Training https://doi.org/10.6019/TOL.Pfam_repeats-t.2018.00001.1 (2018). · DOI
Cited by
Sorted by citations
Paysan‐Lafosse, T., Blum, M., Chuguransky, S., Grego, T., Pinto, B. L., Salazar, G. A., Bileschi, M. L., Bork, P., Bridge, A. J., Colwell, L. J., et al. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac993 · Cited by 2,457
“A Google Research team is working on the development of ProtENN, a deep-learning method predicting functional annotations for unaligned amino acid sequences using Pfam families as a training set (31).”
Self-citationScientific discovery in the age of artificial intelligence.
Wang, H., Fu, T., Du, Y., Gao, W., Huang, K., Liu, Z., Chandak, P., Liu, S., Van Katwyk, P., Deac, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06221-2 · Cited by 1,823
InterPro: the protein sequence classification resource in 2025
Blum, M., Andreeva, A. E., Florentino, L. C., Chuguransky, S., Grego, T., Hobbs, E., Pinto, B. L., Orr, A., Paysan‐Lafosse, T., Ponamareva, I., et al. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae1082 · Cited by 1,240
“ProtENN2, trained on Pfam data, uses convolutional neural networks to annotate protein sequences with Pfam family labels ( 55 ).”
Self-citationMachine-learning-guided directed evolution for protein engineering
Yang, K. K., Wu, Z., & Arnold, F. H. (2019) · Nature Methods · doi:10.1038/s41592-019-0496-6 · Cited by 1,130
Artificial intelligence and illusions of understanding in scientific research
Messeri, L., & Crockett, M. J. (2024) · Nature · doi:10.1038/s41586-024-07146-0 · Cited by 707
“In biology, predictive AI tools are already being used for the automated annotation of protein function 50,51 and cell types 52 .”
Metadata
- Authors
- Bileschi, M. L., Belanger, D., Bryant, D. H., Sanderson, T., Carter, B., Sculley, D., Bateman, A., DePristo, M. A., & Colwell, L. J.
- Affiliations
- Google (United States) (US)
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- European Bioinformatics Institute (GB)
- Corresponding author
- Bileschi, Maxwell L.
- Colwell, Lucy J.
- ORCID
- Venue
- Nature Biotechnology
- Published
- 2022-02-21
- Volume
- 40
- Issue
- 6
- Pages
- 932-937
- ISSN
- 0733-222X (ISSN-L)
- 1087-0156
- 1546-1696
- OpenAlex
- W4213112325
- Cited by
- 332
- References
- 59
- Citations by year
- 2026: 39 · 2025: 66 · 2024: 70 · 2023: 73 · 2022: 45
- FWCI
- 20.90
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- Nature Biotechnology (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed (publishedVersion)
- Funders
- Wellcome Trust (210918/Z/18/Z)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Keywords
- protein function prediction, deep learning, Pfam, sequence annotation, remote homology detection, sequence clustering, microbial protein, human proteome, protein families
- MeSH terms
- Deep Learning, Amino Acid Sequence, Humans, Proteome, Databases, Protein, Proteomics, Molecular Sequence Annotation
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
