xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Protein language models have shown remarkable success in learning biological information from protein sequences. However, most existing models are limited by either autoencoding or autoregressive pre-training objectives, which makes them struggle to handle protein understanding and generation tasks concurrently. We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework. Our key technical contribution is an exploration of the compatibility and the potential for joint optimization of the two types of objectives, which has led to a strategy for training xTrimoPGLM at an unprecedented scale of 100 billion parameters and 1 trillion training tokens. Our extensive experiments reveal that 1) xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories. The model also facilitates an atomic-resolution view of protein structures, leading to an advanced 3D structural prediction model that surpasses existing language model-based tools. 2) xTrimoPGLM not only can generate de novo protein sequences following the principles of natural ones, but also can perform programmable generation after supervised fine-tuning (SFT) on curated sequences. These results highlight the substantial capability and versatility of xTrimoPGLM in understanding and generating protein sequences, contributing to the evolving landscape of foundation models in protein science. Trained weight for the xTrimoPGLM model, and downstream datasets are available at https://huggingface.co/proteinglm .
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
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 2×
“Notably, an exponential increase in pre-training computations corresponds to linear growth in performance, thereby highlighting scaling effects [1, 2].”
BackgroundEvolutionary-scale prediction of atomic level protein structure with a language model
Lin, Z., Akin, H., Rao, R., Hie, B., Zhu, Z., Lu, W., Smetanin, N., Verkuil, R., Kabeli, O., Shmueli, Y., et al. (2022) · doi:10.1101/2022.07.20.500902 · Cited by 5,990
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016239118 · Cited by 3,286
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2019) · doi:10.1101/622803 · Cited by 3,280 · cited 6×
“, ESM [6, 36], or causal decoder-only PLMs, e.”
BackgroundMethodInfluentialEfficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J., Zhang, H., & Stoica, I. (2023) · Proceedings of the 29th Symposium on Operating Systems Principles · doi:10.1145/3600006.3613165 · Cited by 1,817
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., & Stoica, I. (2023) · arXiv · doi:10.48550/arxiv.2309.06180 · Cited by 1,802
ZDOCK: An initial‐stage protein‐docking algorithm
Chen, R., Li, L., & Weng, Z. (2003) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.10389 · Cited by 1,393 · cited 2×
“For the prediction of VH-VL complex structures, we compared ZDock [102], a rigid protein docking algorithm based on fast Fourier transform correlation techniques, ClusPro [103], a docking method using bioinformatics and computational chemistry techniques, EquiDock [104], a genetic evolution-based algorithm, HDOCK [105…”
MethodLarge language models generate functional protein sequences across diverse families
Madani, A., Krause, B., Greene, E. R., Subramanian, S., Mohr, B. P., Holton, J. M., Olmos, J. L., Xiong, C., Sun, Z. Z., Socher, R., et al. (2023) · Nature Biotechnology · doi:10.1038/s41587-022-01618-2 · Cited by 1,078 · cited 10×
“BERT[25] ProGen[9], ProGen2[13], ProtGPT2[26] ProtTrans[8], Ankh[27] xTrimoPGLM /”
BackgroundInfluentialEvaluating Protein Transfer Learning with TAPE
Rao, R., Bhattacharya, N., Thomas, N., Duan, Y., Chen, X., Canny, J., Abbeel, P., & Song, Y. S. (2019) · doi:10.1101/676825 · Cited by 719 · cited 2×
“The dataset applied in this task is initially sourced from Rocklin et al [76] and subsequently collected within the Task Assessing Protein Embeddings (TAPE) [77].”
MethodGQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Ainslie, J., Lee-Thorp, J., de Jong, M., Zemlyanskiy, Y., Lebron, F., & Sanghai, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.298 · Cited by 454
Cited by
Simulating 500 million years of evolution with a language model
Hayes, T., Rao, R., Akin, H., Sofroniew, N. J., Oktay, D., Lin, Z., Verkuil, R., Tran, V. Q., Deaton, J., Wiggert, M., et al. (2025) · Science · doi:10.1126/science.ads0018 · Cited by 937
Self-citationSimulating 500 million years of evolution with a language model
(2024) · doi:10.1101/2024.07.01.600583 · Cited by 937
Bilingual language model for protein sequence and structure
Heinzinger, M., Weissenow, K., Sanchez, J. G., Henkel, A., Mirdita, M., Steinegger, M., & Rost, B. (2024) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqae150 · Cited by 311
Fine-tuning protein language models boosts predictions across diverse tasks
Schmirler, R., Heinzinger, M., & Rost, B. (2024) · Nature Communications · doi:10.1038/s41467-024-51844-2 · Cited by 229
“I understand that the tasks are very diverse, but the sense that metrics like Precision and Recall give, where you see the trade-off, is hard to get from Spearman correlation from 0.72 to 0.736 for instance.”
InfluentialRevolutionizing peptide‐based drug discovery: Advances in the post‐AlphaFold era
Chang, L., Mondal, A., Singh, B., Martínez‐Noa, Y., & Perez, A. (2024) · WIREs Computational Molecular Science · doi:10.1002/wcms.1693 · Cited by 56
Metadata
- Authors
- Chen, B., Cheng, X., Li, P., Geng, Y.-A., Gong, J., Li, S., Bei, Z., Tan, X., Wang, B., Zeng, X., Liu, C., Zeng, A., Dong, Y., Tang, J., & Song, L.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2023-07-06
- OpenAlex
- W4383550741
- Cited by
- 107
- References
- 18
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein. https://app.cochat.ai/papers/10.1101/2023.07.05.547496
- The paper
- Chen, B., Cheng, X., Li, P., Geng, Y.-A., Gong, J., Li, S., Bei, Z., Tan, X., Wang, B., Zeng, X., Liu, C., Zeng, A., Dong, Y., Tang, J., & Song, L. (2023). xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2023.07.05.547496
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.