The DOI matches its Crossref record; 76 of the 76 references it cites were found in a registry or an index.
ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Learning
Open accessPreprint — published as 10.1109/tpami.2021.3095381 · Paper page
Abstract
Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken from NLP. These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The LMs were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw protein LM- embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks. The first was a per-residue prediction of protein secondary structure (3-state accuracy Q3=81%-87%); the second were per-protein predictions of protein sub-cellular localization (ten-state accuracy: Q10=81%) and membrane vs. water-soluble (2-state accuracy Q2=91%). For the per-residue predictions the transfer of the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without using evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that protein LMs learned some of the grammar of the language of life . To facilitate future work, we released our models at https://github.com/agemagician/ProtTrans .
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
Berman, H. M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.235 · Cited by 40,196
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
UniProt: a worldwide hub of protein knowledge
The UniProt Consortium (2019) · Nucleic Acids Research · doi:10.1093/nar/gky1049 · Cited by 7,698
Amino acid substitution matrices from protein blocks.
Henikoff, S., & Henikoff, J. G. (1992) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.89.22.10915 · Cited by 6,218
MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets
Steinegger, M., & Söding, J. (2017) · Nature Biotechnology · doi:10.1038/nbt.3988 · Cited by 4,840
Self-citationIn-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537
Cited by
SignalP 6.0 predicts all five types of signal peptides using protein language models
Teufel, F., Almagro Armenteros, J. J., Johansen, A. R., Gíslason, M. H., Pihl, S. I., Tsirigos, K. D., Winther, O., Brunak, S., von Heijne, G., & Nielsen, H. (2022) · Nature Biotechnology · doi:10.1038/s41587-021-01156-3 · Cited by 2,867
A guide to machine learning for biologists
Greener, J. G., Kandathil, S. M., Moffat, L., & Jones, D. T. (2022) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-021-00407-0 · Cited by 2,127
Scientific 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
Wang, Y., Wang, W., Joty, S., & Hoi, S. C. H. (2021) · arXiv · doi:10.48550/arxiv.2109.00859 · Cited by 1,495
Self-citationWang, Y., Wang, W., Joty, S., & Hoi, S. C. H. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.685 · Cited by 1,495
Self-citationProtGPT2 is a deep unsupervised language model for protein design
Ferruz, N., Schmidt, S., & Höcker, B. (2022) · Nature Communications · doi:10.1038/s41467-022-32007-7 · Cited by 795
Language models enable zero-shot prediction of the effects of mutations on protein function
Meier, J., Rao, R., Verkuil, R., Liu, J., Sercu, T., & Rives, A. (2021) · doi:10.1101/2021.07.09.450648 · Cited by 635
The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human Genomics
Dalla-Torre, H., Gonzalez, L., Mendoza Revilla, J., Lopez Carranza, N., Henryk Grywaczewski, A., Oteri, F., Dallago, C., Trop, E., De Almeida, B. P., Sirelkhatim, H., et al. (2023) · doi:10.1101/2023.01.11.523679 · Cited by 680
Self-citationNucleotide Transformer: building and evaluating robust foundation models for human genomics
Dalla-Torre, H., Gonzalez, L., Mendoza-Revilla, J., Lopez Carranza, N., Grzywaczewski, A. H., Oteri, F., Dallago, C., Trop, E., de Almeida, B. P., Sirelkhatim, H., et al. (2025) · Nature Methods · doi:10.1038/s41592-024-02523-z · Cited by 772
Self-citationLarge-scale chemical language representations capture molecular structure and properties
Ross, J., Belgodere, B., Chenthamarakshan, V., Padhi, I., Mroueh, Y., & Das, P. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00580-7 · Cited by 590
Single-sequence protein structure prediction using a language model and deep learning
Chowdhury, R., Bouatta, N., Biswas, S., Floristean, C., Kharkar, A., Roy, K., Rochereau, C., Ahdritz, G., Zhang, J., Church, G. M., et al. (2022) · Nature Biotechnology · doi:10.1038/s41587-022-01432-w · Cited by 455
Genome-wide prediction of disease variant effects with a deep protein language model
Brandes, N., Goldman, G., Wang, C. H., Ye, C. J., & Ntranos, V. (2023) · Nature Genetics · doi:10.1038/s41588-023-01465-0 · Cited by 421
Rao, R., Liu, J., Verkuil, R., Meier, J., Canny, J. F., Abbeel, P., Sercu, T., & Rives, A. (2021) · doi:10.1101/2021.02.12.430858 · Cited by 350
The language of proteins: NLP, machine learning & protein sequences
Ofer, D., Brandes, N., & Linial, M. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.03.022 · Cited by 339
Transformer protein language models are unsupervised structure learners
Rao, R., Meier, J., Sercu, T., Ovchinnikov, S., & Rives, A. (2020) · doi:10.1101/2020.12.15.422761 · Cited by 341
Tubiana, J., Schneidman-Duhovny, D., & Wolfson, H. J. (2022) · Nature Methods · doi:10.1038/s41592-022-01490-7 · Cited by 274
Improved protein structure refinement guided by deep learning based accuracy estimation
Hiranuma, N., Park, H., Baek, M., Anishchenko, I., Dauparas, J., & Baker, D. (2021) · Nature Communications · doi:10.1038/s41467-021-21511-x · Cited by 243
(2023) · doi:10.1101/2023.12.07.570727 · Cited by 207
Rapid protein stability prediction using deep learning representations
Blaabjerg, L. M., Kassem, M. M., Good, L. L., Jonsson, N., Cagiada, M., Johansson, K. E., Boomsma, W., Stein, A., & Lindorff-Larsen, K. (2023) · eLife · doi:10.7554/elife.82593 · Cited by 177
Single-sequence protein structure prediction using supervised transformer protein language models
Wang, W., Peng, Z., & Yang, J. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00373-3 · Cited by 150
Predictomes, a classifier-curated database of AlphaFold-modeled protein-protein interactions
Schmid, E. W., & Walter, J. C. (2025) · Molecular Cell · doi:10.1016/j.molcel.2025.01.034 · Cited by 120
Masked inverse folding with sequence transfer for protein representation learning
(2022) · doi:10.1093/protein/gzad015 · Cited by 110
AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms
Bordin, N., Sillitoe, I., Nallapareddy, V., Rauer, C., Lam, S. D., Waman, V. P., Sen, N., Heinzinger, M., Littmann, M., Kim, S., et al. (2023) · Communications Biology · doi:10.1038/s42003-023-04488-9 · Cited by 103
Self-citationPepNN: a deep attention model for the identification of peptide binding sites
Abdin, O., Nim, S., Wen, H., & Kim, P. M. (2022) · Communications Biology · doi:10.1038/s42003-022-03445-2 · Cited by 104
Genomic language model predicts protein co-regulation and function
Hwang, Y., Cornman, A. L., Kellogg, E. H., Ovchinnikov, S., & Girguis, P. R. (2024) · Nature Communications · doi:10.1038/s41467-024-46947-9 · Cited by 99
Large language models improve annotation of prokaryotic viral proteins
Flamholz, Z. N., Biller, S. J., & Kelly, L. (2024) · Nature Microbiology · doi:10.1038/s41564-023-01584-8 · Cited by 92
Roche, R., Moussad, B., Shuvo, M. H., Tarafder, S., & Bhattacharya, D. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae039 · Cited by 85
Boadu, F., Cao, H., & Cheng, J. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad208 · Cited by 81
Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model
Zeng, Y., Wei, Z., Yuan, Q., Chen, S., Yu, W., Lu, Y., Gao, J., & Yang, Y. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad187 · Cited by 73
Protein language models trained on multiple sequence alignments learn phylogenetic relationships
Lupo, U., Sgarbossa, D., & Bitbol, A.-F. (2022) · Nature Communications · doi:10.1038/s41467-022-34032-y · Cited by 67
Deep contrastive learning enables genome-wide virtual screening
Jia, Y., Gao, B., Tan, J., Zheng, J., Hong, X., Zhu, W., Tan, H., Xiao, Y., Tan, L., Cai, H., et al. (2026) · Science · doi:10.1126/science.ads9530 · Cited by 66
Deep learning methods for protein function prediction
Boadu, F., Lee, A., & Cheng, J. (2025) · PROTEOMICS · doi:10.1002/pmic.202300471 · Cited by 53
(2023) · doi:10.1126/sciadv.abo5128 · Cited by 53
Nallapareddy, V., Bordin, N., Sillitoe, I., Heinzinger, M., Littmann, M., Waman, V. P., Sen, N., Rost, B., & Orengo, C. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad029 · Cited by 47
Self-citationEarly computational detection of potential high-risk SARS-CoV-2 variants
(2023) · doi:10.1016/j.compbiomed.2023.106618 · Cited by 46
Early Computational Detection of Potential High Risk SARS-CoV-2 Variants
Beguir, K., Skwark, M. J., Fu, Y., Pierrot, T., Carranza, N. L., Laterre, A., Kadri, I., Korched, A., Lowegard, A. U., Lui, B. G., et al. (2021) · doi:10.1101/2021.12.24.474095 · Cited by 46
CpG Transformer for imputation of single-cell methylomes
De Waele, G., Clauwaert, J., Menschaert, G., & Waegeman, W. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btab746 · Cited by 37
RAPPPID: towards generalizable protein interaction prediction with AWD-LSTM twin networks
Szymborski, J., & Emad, A. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac429 · Cited by 34
Expert-guided protein language models enable accurate and blazingly fast fitness prediction
Marquet, C., Schlensok, J., Abakarova, M., Rost, B., & Laine, E. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae621 · Cited by 33
Self-citationLeveraging protein language models for accurate multiple sequence alignments
(2023) · doi:10.1101/gr.277675.123 · Cited by 30
Improved prediction of MHC-peptide binding using protein language models
Hashemi, N., Hao, B., Ignatov, M., Paschalidis, I. C., Vakili, P., Vajda, S., & Kozakov, D. (2023) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2023.1207380 · Cited by 25
Design in the DARK: Learning Deep Generative Models for De Novo Protein Design
Moffat, L., Kandathil, S. M., & Jones, D. T. (2022) · doi:10.1101/2022.01.27.478087 · Cited by 25
Sen, N., Anishchenko, I., Bordin, N., Sillitoe, I., Velankar, S., Baker, D., & Orengo, C. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac187 · Cited by 25
Semantical and geometrical protein encoding toward enhanced bioactivity and thermostability
Tan, Y., Zhou, B., Zheng, L., Fan, G., & Hong, L. (2025) · eLife · doi:10.7554/elife.98033.4 · Cited by 20
AttSec: protein secondary structure prediction by capturing local patterns from attention map
(2023) · doi:10.1186/s12859-023-05310-3 · Cited by 16
Guan, C., Luo, J., Li, S., Tan, Z. L., Wang, Y., Chen, H., Yamamoto, N., Zhang, C., Lu, Y., Chen, J., et al. (2023) · ACS Omega · doi:10.1021/acsomega.3c05571 · Cited by 13
Self-citationProteinGLUE multi-task benchmark suite for self-supervised protein modeling
Capel, H., Weiler, R., Dijkstra, M., Vleugels, R., Bloem, P., & Feenstra, K. A. (2022) · Scientific Reports · doi:10.1038/s41598-022-19608-4 · Cited by 11
A probabilistic view of protein stability, conformational specificity, and design
Stern, J. A., Free, T. J., Stern, K. L., Gardiner, S., Dalley, N. A., Bundy, B. C., Price, J. L., Wingate, D., & Della Corte, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-42032-1 · Cited by 10
TransHLA: a Hybrid Transformer model for HLA-presented epitope detection
Lu, T., Wang, X., Nie, W., Huo, M., & Li, S. (2025) · GigaScience · doi:10.1093/gigascience/giaf008 · Cited by 10
Kandathil, S. M., Greener, J. G., Lau, A. M., & Jones, D. T. (2020) · doi:10.1101/2020.11.27.401232 · Cited by 8
Exploring the Knowledge of an Outstanding Protein to Protein Interaction Transformer
Yang, S., Cheng, P., Liu, Y., Feng, D., & Wang, S. (2024) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3381825 · Cited by 6
E2EDA: Protein Domain Assembly Based on End-to-End Deep Learning
(2023) · doi:10.1021/acs.jcim.3c01387 · Cited by 6
Hasan, A. K. M. M., Ahmed, A. Y., Mahbub, S., Rahman, M. S., & Bayzid, M. S. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad042 · Cited by 5
McWhite, C. D., & Singh, M. (2022) · doi:10.1101/2022.10.21.513099 · Cited by 4
TMVisDB: Annotation and 3D-visualization of Transmembrane Proteins
Olenyi, T., Marquet, C., Grekova, A., Houri, L., Heinzinger, M., Dallago, C., & Rost, B. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.168997 · Cited by 4
Self-citationEGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose Scoring
Wang, Z., Brand, R., Adolf-Bryfogle, J., Grewal, J., Qi, Y., Combs, S. A., Golovach, N., Alford, R., Rangwala, H., & Clark, P. M. (2024) · ACS Omega · doi:10.1021/acsomega.3c04889 · Cited by 3
Human FASTK preferentially binds single‐stranded and G‐rich RNA
(2025) · doi:10.1111/febs.70155 · Cited by 3
Semantical and geometrical protein encoding toward enhanced bioactivity and thermostability
Tan, Y., Zhou, B., Zheng, L., Fan, G., & Hong, L. (2025) · eLife · doi:10.7554/elife.98033 · Cited by 2
Metadata
- Authors
- Elnaggar, A., Heinzinger, M., Dallago, C., Rehawi, G., Wang, Y., Jones, L., Gibbs, T., Feher, T., Angerer, C., Steinegger, M., Bhowmik, D., & Rost, B.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2020-07-12
- OpenAlex
- W3040739508
- Cited by
- 354
- References
- 76
- Type
- posted content
- Language
- en
- Open access
- green
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.