Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.

ProteinBERT: a universal deep-learning model of protein sequence and function

Open access
Brandes, Nadav, Ofer, Dan, Peleg, Yam, Rappoport, Nadav, Linial, Michal · 2022 · Bioinformatics

Published version of a preprint

Abstract

Summary: Self-supervised deep language modeling has shown unprecedented success across natural language tasks, and has recently been repurposed to biological sequences. However, existing models and pretraining methods are designed and optimized for text analysis. We introduce ProteinBERT, a deep language model specifically designed for proteins. Our pretraining scheme combines language modeling with a novel task of Gene Ontology (GO) annotation prediction. We introduce novel architectural elements that make the model highly efficient and flexible to long sequences. The architecture of ProteinBERT consists of both local and global representations, allowing end-to-end processing of these types of inputs and outputs. ProteinBERT obtains near state-of-the-art performance, and sometimes exceeds it, on multiple benchmarks covering diverse protein properties (including protein structure, post-translational modifications and biophysical attributes), despite using a far smaller and faster model than competing deep-learning methods. Overall, ProteinBERT provides an efficient framework for rapidly training protein predictors, even with limited labeled data. Availability and implementation: Code and pretrained model weights are available at https://github.com/nadavbra/protein_bert. Supplementary information: Supplementary data are available at Bioinformatics online.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/bioinformatics/btac020

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1. The ProteinBERT architecture. ProteinBERT’s architecture is inspired by BERT. Unlike standard Transformers, ProteinBERT supports both local (sequential) and global data. The model consists of six transformer-like blocks manipulating local (left side) and global (right side) representations. Each such block manipulates these representations by fully connected and convolutional layers (in the case of local representations), with skip connections and normalization layers between them. The local representations affect the global representations through a global attention layer, and the global representations affect the local representations through a broadcast fully connected layer
Fig. 1. The ProteinBERT architecture. ProteinBERT’s architecture is inspired by BERT. Unlike standard Transformers, ProteinBERT supports both local (sequential) and global data. The model consists of six transformer-like blocks manipulating local (left side) and global (right side) representations. Each such block manipulates these representations by fully connected and convolutional layers (in the case of local representations), with skip connections and normalization layers between them. The local representations affect the global representations through a global attention layer, and the global representations affect the local representations through a broadcast fully connected layerCC BY · PubMed Central
Fig. 2. Pretraining loss. Training-set loss over the two pretraining tasks: (i) protein sequence language modeling, and (ii) GO annotation recovery. Losses were evaluated with input sequence length of 128, 512 or 1024 tokens on the first 100 batches of the dataset
Fig. 2. Pretraining loss. Training-set loss over the two pretraining tasks: (i) protein sequence language modeling, and (ii) GO annotation recovery. Losses were evaluated with input sequence length of 128, 512 or 1024 tokens on the first 100 batches of the datasetCC BY · PubMed Central
Fig. 3. The impact of pretraining on downstream tasks. Performance of fine-tuned ProteinBERT models over the four TAPE benchmarks as a function of pretraining amount (measured by the number of processed proteins). Similar plots for all nine benchmarks are shown in Supplementary Figure S1
Fig. 3. The impact of pretraining on downstream tasks. Performance of fine-tuned ProteinBERT models over the four TAPE benchmarks as a function of pretraining amount (measured by the number of processed proteins). Similar plots for all nine benchmarks are shown in Supplementary Figure S1CC BY · PubMed Central
Fig. 4. Performance across sequence lengths. Test-set performance of fine-tuned ProteinBERT models with different input sequence lengths. Sequence lengths (e.g. 512, 1024, etc.) always encode proteins of shorter lengths (e.g. a protein of 700 residues will be encoded as a 1024-long sequence). Boxplot distributions are over the 371 pretraining snapshots used in Figure 3
Fig. 4. Performance across sequence lengths. Test-set performance of fine-tuned ProteinBERT models with different input sequence lengths. Sequence lengths (e.g. 512, 1024, etc.) always encode proteins of shorter lengths (e.g. a protein of 700 residues will be encoded as a 1024-long sequence). Boxplot distributions are over the 371 pretraining snapshots used in Figure 3CC BY · PubMed Central
Fig. 5. Global attention before and after fine-tuning on signal peptide prediction. Global attention values obtained for two selected proteins: Outer membrane protein P.IIC (piiC) in neisseria gonorrhoeae (top), and Gamma carbonic anhydrase-like 2, mitochondrial protein (GAMMACAL2) in arabidopsis (bottom). piiC has a signal peptide at positions 1–25 (ending with the amino-acid sequence SAARA). GAMMACAL2 has no signal peptide. The left panels (red colors) show the attention values obtained by the generic ProteinBERT model, after pretraining, it as a language model on UniRef90 (but before fine-tuning it on any specific task). The heatmap shows the global attention values at each residue of the protein by each of the 24 attention heads of the model. The bar plot shows the total attention at each residue by summing the attention values across all attention heads. The right panels show the difference in attention values after fine-tuning ProteinBERT on the signal peptide task. The heatmap shows the increase (green) or decrease (purple) of attention across all positions and attention heads. The bar plot shows the total difference in attention at each residue by summing the differences across all attention heads. Note that, each attention head necessarily sums up to 100%. Accordingly, differences sum up to 0%
Fig. 5. Global attention before and after fine-tuning on signal peptide prediction. Global attention values obtained for two selected proteins: Outer membrane protein P.IIC (piiC) in neisseria gonorrhoeae (top), and Gamma carbonic anhydrase-like 2, mitochondrial protein (GAMMACAL2) in arabidopsis (bottom). piiC has a signal peptide at positions 1–25 (ending with the amino-acid sequence SAARA). GAMMACAL2 has no signal peptide. The left panels (red colors) show the attention values obtained by the generic ProteinBERT model, after pretraining, it as a language model on UniRef90 (but before fine-tuning it on any specific task). The heatmap shows the global attention values at each residue of the protein by each of the 24 attention heads of the model. The bar plot shows the total attention at each residue by summing the attention values across all attention heads. The right panels show the difference in attention values after fine-tuning ProteinBERT on the signal peptide task. The heatmap shows the increase (green) or decrease (purple) of attention across all positions and attention heads. The bar plot shows the total difference in attention at each residue by summing the differences across all attention heads. Note that, each attention head necessarily sums up to 100%. Accordingly, differences sum up to 0%CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 44 references

Research works printed but not linked: 2

  1. Abadi, 2016, 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI16), 265
  2. Radford, 2019, Language models are unsupervised multitask learners, OpenAI Blog, 1, 9

Cited by

See all 1,009

Metadata

Authors
Brandes, N., Ofer, D., Peleg, Y., Rappoport, N., & Linial, M.
Affiliations
  • Hebrew University of Jerusalem (IL)
  • Deep Trading Ltd. , Haifa 3508401, Israel
  • Ben-Gurion University of the Negev (IL)
  • Department of Biological Chemistry, The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem, Jerusalem 9190401, Israel
Corresponding author
Brandes, Nadav
Venue
Bioinformatics
Published
2022-02-10
Volume
38
Issue
8
Pages
2102-2110
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
OpenAlex
W4205773061
Cited by
1,009
References
44
Citations by year
2026: 248 · 2025: 355 · 2024: 241 · 2023: 127 · 2022: 34
FWCI
62.19
Type
journal article
Language
en
Open access
Locations
  • Bioinformatics (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Israel Science Foundation (2753/20)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
protein sequence representation, protein function prediction, protein structure prediction, long sequence modeling
MeSH terms
Deep Learning, Amino Acid Sequence, Language, Natural Language Processing, Proteins

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: ProteinBERT: a universal deep-learning model of protein sequence and function. https://app.cochat.ai/papers/10.1093/bioinformatics/btac020
The paper
Brandes, N., Ofer, D., Peleg, Y., Rappoport, N., & Linial, M. (2022). ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics. https://doi.org/10.1093/bioinformatics/btac020

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.