DeepSeek模型分析及其在AI辅助蛋白质工程中的应用

李明辰; 钟博子韬; 余元玺; 姜帆; 张良; 谭扬; 虞慧群; 范贵生; 洪亮

doi:10.12211/2096-8280.2025-041

您当前的位置：

首页 >

文章列表页 >

DeepSeek模型分析及其在AI辅助蛋白质工程中的应用

特约评述 | 更新时间：2025-07-07

- DeepSeek模型分析及其在AI辅助蛋白质工程中的应用
- DeepSeek model analysis and its applications in AI-assistant protein engineering
- 合成生物学 2025年6卷第3期页码：636-650
- 作者机构：
  
  1.上海交通大学张江高等研究院，上海 201203
  2.华东理工大学信息科学与工程学院，上海 200237
- 作者简介：
  
  [ "李明辰（1998—），男，博士研究生。研究方向为人工智能。 E-mail：lmc@mail.ecust.edu.cn" ]
  [ "洪亮（1981—），男，教授，博士生导师。研究方向为分子生物物理，人工智能功能蛋白质设计以及药物分子设计。 E-mail：hongl3liang@sjtu.edu.cn" ]
- 基金信息：
  
  上海市2023年度“科技创新行动计划”计算生物学重点专项(23JS1400600)
- DOI：10.12211/2096-8280.2025-041
  中图分类号： Q816
- 收稿：2025-05-01，
  
  修回：2025-06-03，
  
  纸质出版：2025-06-30
- 稿件说明：
移动端阅览
李明辰，钟博子韬，余元玺，姜帆，张良，谭扬，虞慧群，范贵生，洪亮. DeepSeek模型分析及其在AI辅助蛋白质工程中的应用［J］. 合成生物学， 2025， 6（3）： 636-650

LI Mingchen， ZHONG Bozitao， YU Yuanxi， JIANG Fan， ZHANG Liang， TAN Yang， YU Huiqun， FAN Guisheng， HONG Liang. DeepSeek model analysis and its applications in AI-assistant protein engineering［J］. Synthetic Biology Journal， 2025， 6（3）： 636-650
李明辰，钟博子韬，余元玺，姜帆，张良，谭扬，虞慧群，范贵生，洪亮. DeepSeek模型分析及其在AI辅助蛋白质工程中的应用［J］. 合成生物学， 2025， 6（3）： 636-650 DOI： 10.12211/2096-8280.2025-041.

LI Mingchen， ZHONG Bozitao， YU Yuanxi， JIANG Fan， ZHANG Liang， TAN Yang， YU Huiqun， FAN Guisheng， HONG Liang. DeepSeek model analysis and its applications in AI-assistant protein engineering［J］. Synthetic Biology Journal， 2025， 6（3）： 636-650 DOI： 10.12211/2096-8280.2025-041.

摘要

2025年年初，杭州深度求索人工智能基础技术研究有限公司发布并开源了其自主研发的DeepSeek-R1对话大模型。该模型具备极低的推理成本和出色的思维链推理能力，在多种任务上能够媲美甚至超越闭源的GPT-4o和o1模型，引发了国际社会的高度关注。此外，DeepSeek模型在中文对话上的优异表现以及免费商用的策略，在国内引发了部署和使用的热潮，推动了人工智能技术的普惠与发展。本文围绕DeepSeek模型的架构设计、训练方法与推理机制进行系统性分析，探讨其核心技术在AI蛋白质研究中的迁移潜力与应用前景。DeepSeek模型融合了多项自主创新的前沿技术，包括多头潜在注意力机制、混合专家网络及其负载均衡、低精度训练等，显著降低了Transformer模型的训练和推理成本。尽管DeepSeek模型原生设计用于人类语言的理解与生成，但其优化技术对同样基于Transformer模型的蛋白质预训练语言模型具有重要的参考价值。借助DeepSeek所采用的关键技术，蛋白质语言模型在训练成本、推理成本等方面有望得到显著降低。

Abstract

In early 2025

Hangzhou DeepSeek AI Foundation Technology Research Co.

Ltd. released and open-sourced its independently developed DeepSeek-R1 conversational large language model. This model exhibits extremely low inference costs and outstanding chain-of-thought reasoning capabilities

performing comparably to

and in some tasks surpassing

proprietary models like GPT-4o and o1. This achievement has garnered significant international attention. Furthermore

DeepSeek’s excellent performance in Chinese conversations and its free-for-commercial-use strategy have ignited a wave of deployment and application within China

thereby promoting the widespread adoption and development of AI technology. This work systematically analyzes the architectural design

training methodology

and inference mechanisms of the DeepSeek model

exploring the transfer potential and application prospects of its core technologies in AI-assistant protein research. The DeepSeek model integrates several cutting-edge

independently innovated technologies

including a multi-head latent attention mechanism

mixture-of-experts (MoE) with load balancing

and low-precision training. These innovations have substantially reduced the training and inference costs for Transformer models. Although DeepSeek was originally designed for human language understanding and generation

its optimization techniques hold significant reference value for pre-trained language models with proteins

which are also based on the Transformer architecture. By leveraging the key technologies employed in DeepSeek

protein language models are expected to achieve substantial reductions in training and inference costs.

关键词

Keywords

references

余元玺 , 钟博子韬 , 洪亮 . 人工智能的诺奖时刻: 重塑科学的未来 [J ] . 物理 , 2025 , 54 ( 01 ): 25 - 29 .

FAN W Q , ZHOU Y , WANG S J , et al . Computational protein science in the era of large language models (LLMs) [EB/OL ] . arXiv , 2025 : 2501 . 10282 . ( 2025-01-25 )[ 2025-06-03 ] . https://arxiv.org/abs/2501.10282v2 https://arxiv.org/abs/2501.10282v2 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C/OL ] // Advances in Neural Information Processing Systems 30 (NIPS 2017 ), 2017 : 5998 - 6008 [2025-06-03] . https://proceedings.neurips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html https://proceedings.neurips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html

DeepSeek-AI , LIU A X , FENG B , et al . DeepSeek-V3 technical report [EB/OL ] . arXiv , 2024 : 2412 . 19437 v 1 . ( 2024-12-27 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2412.19437 https://doi.org/10.48550/arXiv.2412.19437 .

GUO D Y , YANG D J , ZHANG H W , et al . DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning [EB/OL ] . arXiv , 2025 : 2501 . 12948 . ( 2025-01-22 )[ 2025-06-03 ] . https://arxiv.org/abs/2501.12948v1 https://arxiv.org/abs/2501.12948v1 .

JAECH A , KALAI A , LERER A , et al . Openai o1 system card [EB/OL ] . arXiv , 2024 : 2412 . 16720 . ( 2024-12-21 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2412.16720 https://doi.org/10.48550/arXiv.2412.16720 .

BI X , CHEN D L , CHEN G T , et al . DeepSeek LLM: scaling open-source language models with longtermism [EB/OL ] . arXiv , 2024 : 2401 . 02954 . ( 2024-01-05 )[ 2025-06-03 ] . https://arxiv.org/abs/2401.02954v1 https://arxiv.org/abs/2401.02954v1 .

GUO D Y , ZHU Q H , YANG D J , et al . DeepSeek-Coder: when the large language model meets programming—the rise of code intelligence [EB/OL ] . arXiv , 2024 : 2401 . 14196 . ( 2024-01-26 )[ 2025-06-03 ] . https://arxiv.org/abs/2401.14196v2 https://arxiv.org/abs/2401.14196v2 .

DAI D M , DENG C Q , ZHAO C G , et al . DeepSeekMoE: towards ultimate expert specialization in mixture-of-experts language models [C/OL ] // Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) . Bangkok, Thailand. Stroudsburg, PA, USA: ACL , 2024 : 1280 - 1297 [2025-06-03] . https://doi.org/10.18653/v1/2024.acl-long.70 https://doi.org/10.18653/v1/2024.acl-long.70 .

TOUVRON H , MARTIN L , STONE K , et al . Llama 2: Open foundation and fine-tuned chat models [EB/OL ] . arXiv , 2023 : 2307 . 09288 . ( 2023-07-18 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2307.09288 https://doi.org/10.48550/arXiv.2307.09288 .

SHAO Z H , WANG P Y , ZHU Q H , et al . DeepSeekMath: pushing the limits of mathematical reasoning in open language models [EB/OL ] . arXiv , 2024 : 2402 . 03300 . ( 2024-02-05 )[ 2025-06-03 ] . https://arxiv.org/abs/2402.03300v3 https://arxiv.org/abs/2402.03300v3 .

DEEPSEEK-AI , LIU A X , FENG B , et al . DeepSeek-V2: a strong, economical, and efficient mixture-of-experts language model [EB/OL ] . arXiv , 2024 : 2405 . 04434 . ( 2024-06-19 )[ 2025-06-03 ] . https://arxiv.org/abs/2405.04434v5 https://arxiv.org/abs/2405.04434v5 .

DeepSeek-V2.5: a new open-source model combining general and coding capabilities [EB/OL ] . ( 2024-09-05 )[ 2025-06-03 ] . https://api-docs.deepseek.com/news/news0905 https://api-docs.deepseek.com/news/news0905 .

ZHAO W X , ZHOU K , LI J Y , et al . A survey of large language models [EB/OL ] . arXiv , 2023 : 2303 . 18223 . ( 2025-03-11 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2303.18223 https://doi.org/10.48550/arXiv.2303.18223 .

KWON W , LI Z H , ZHUANG S Y , et al . Efficient memory management for large language model serving with PagedAttention [C/OL ] // Proceedings of the 29th Symposium on Operating Systems Principles . October 23-26, 2023 , Koblenz, Germany. ACM , 2023 : 611 - 626 [2025-06-03] . https://doi.org/10.1145/3600006.36131 https://doi.org/10.1145/3600006.36131 .

SHAZEER N . Fast transformer decoding: one write-head is all you need [EB/OL ] . arXiv , 2019 : 1911 . 02150 . ( 2019-11-06 )[ 2025-06-03 ] . https://arxiv.org/abs/1911.02150v1 https://arxiv.org/abs/1911.02150v1 .

AINSLIE J , LEE-THORP J , DE JONG M , et al . GQA: training generalized multi-query transformer models from multi-head checkpoints [C/OL ] // Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing . Singapore , 2023 : 4895 - 4901 [2025-06-03] . https://doi.org/10.18653/v1/2023.emnlp-main.298 https://doi.org/10.18653/v1/2023.emnlp-main.298 .

DEVLIN J , CHANG M , LEE K , et al . Bert: pre-training of deep bidirectional transformers for language understanding [C/OL ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) . Minneapolis, Minnesota, USA: ACL , 2019 : 4171 - 4186 [2025-06-03] . https://doi.org/10.18653/v1/N19-1423 https://doi.org/10.18653/v1/N19-1423 .

LIN Z M , AKIN H , RAO R , et al . Evolutionary-scale prediction of atomic-level protein structure with a language model [J ] . Science , 2023 , 379 ( 6637 ): 1123 - 1130 .

KAPLAN J , MCCANDLISH S , HENIGHAN T , et al . Scaling laws for neural language models [EB/OL ] . arXiv , 2020 : 2001 . 08361 . ( 2020-01-23 )[ 2025-06-03 ] . https://arxiv.org/abs/2001.08361v1 https://arxiv.org/abs/2001.08361v1 .

HOFFMANN J , BORGEAUD S , MENSCH A , et al . Training compute-optimal large language models [EB/OL ] . arXiv , 2022 : 2203 . 15556 . ( 2022-03-29 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2203.15556 https://doi.org/10.48550/arXiv.2203.15556 .

JACOBS R A , JORDAN M I , NOWLAN S J , et al . Adaptive mixtures of local experts [J ] . Neural Computation , 1991 , 3 ( 1 ): 79 - 87 .

JORDAN M I , XU L . Convergence results for the EM approach to mixtures of experts architectures [J ] . Neural Networks , 1995 , 8 ( 9 ): 1409 - 1431 .

SHAZEER N , MIRHOSEINI A , MAZIARZ K , et al . Outrageously large neural networks: the sparsely-gated mixture-of-experts layer [C/OL ] // 5th International Conference on Learning Representations ICLR 2017 . (2017-02-06)[2025-06-03] . https://openreview.net/forum?id=B1ckMDqlg https://openreview.net/forum?id=B1ckMDqlg .

WEI MING T . DeepSeek V3 Training cost: here’s how it compares to Llama 3.1 (405B) [EB/OL ] . ( 2025-01-26 )[ 2025-06-03 ] . https://apxml.com/posts/training-cost-deepseek-v3-vs-llama-3 https://apxml.com/posts/training-cost-deepseek-v3-vs-llama-3 .

KAHAN W . IEEE standard 754 for binary floating-point arithmetic [EB/OL ] . Lecture Notes on the Status of IEEE , 1996 , 754 ( 94720-1776 ): 11 [ 2025-06-03 ] . https://people.eecs.berkeley.edu/~wkahan/ieee754status/IEEE754.PDF https://people.eecs.berkeley.edu/~wkahan/ieee754status/IEEE754.PDF .

MICIKEVICIUS P , STOSIC D , BURGESS N , et al . FP8 formats for deep learning [EB/OL ] . arXiv , 2022 : 2209 . 05433 . ( 2022-09-12 )[ 2025-06-03 ] . https://doi.org/10.48550/arXiv.2209.05433 https://doi.org/10.48550/arXiv.2209.05433 .

ZAMIRAI P , ZHANG J , ABERGER C R , et al . Revisiting BFloat16 training [EB/OL ] . arXiv , 2020 : 2010 . 06192 . ( 2020-10-13 )[ 2025-06-03 ] . https://arxiv.org/abs/2010.06192v2 https://arxiv.org/abs/2010.06192v2 .

FUJII K , NAKAMURA T , YOKOTA R . Balancing speed and stability: the trade-offs of FP 8 vs. BF16 training in LLMs[EB/OL ] . arXiv , 2024 : 2411 . 08719 . ( 2024-11-01 )[ 2025-06-03 ] . https://arxiv.org/abs/2411.08719v1 https://arxiv.org/abs/2411.08719v1 .

ALLEY E C , KHIMULYA G , BISWAS S , et al . Unified rational protein engineering with sequence-based deep representation learning [J ] . Nature Methods , 2019 , 16 ( 12 ): 1315 - 1322 .

HAYES T , RAO R , AKIN H , et al . Simulating 500 million years of evolution with a language model [J ] . Science , 2025 , 387 ( 6736 ): 850 - 858 .

MADANI A , KRAUSE B , GREENE E R , et al . Large language models generate functional protein sequences across diverse families [J ] . Nature Biotechnology , 2023 , 41 ( 8 ): 1099 - 1106 .

CHEN B , CHENG X Y , LI P , et al . xTrimoPGLM: unified 100-billion-parameter pretrained transformer for deciphering the language of proteins [J ] . Nature Methods , 2025 , 22 ( 5 ): 1028 - 1039 .

ELNAGGAR A , HEINZINGER M , DALLAGO C , et al . ProtTrans: toward understanding the language of life through self-supervised learning [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 10 ): 7112 - 7127 .

SU J , HAN C C , ZHOU Y Y , et al . SaProt: protein language modeling with structure-aware vocabulary [C/OL ] // The Twelfth International Conference on Learning Representations ICLR 2024 , 2024[2025-06-03] . https://openreview.net/forum?id=6MRm3G4NiU https://openreview.net/forum?id=6MRm3G4NiU .

LI M C , TAN Y , MA X Z , et al . ProSST: protein language modeling with quantized structure and disentangled attention [C/OL ] // Advances in Neural Information Processing Systems 37 (NeurIPS 2024 ), 2024 : 35700 - 35726 [2025-06-03] . https://proceedings.neurips.cc/paper_files/paper/2024/hash/3ed57b293db0aab7cc30c44f45262348-Abstract-Conference.html https://proceedings.neurips.cc/paper_files/paper/2024/hash/3ed57b293db0aab7cc30c44f45262348-Abstract-Conference.html .

MEIER J , RAO R , VERKUIL R , et al . Language models enable zero-shot prediction of the effects of mutations on protein function [C/OL ] // Advances in Neural Information Processing Systems 34 (NeurIPS 2021 ), 2021 : 29287 - 29303 [2025-06-03] . https://proceedings.neurips.cc/paper_files/paper/2021/hash/f51338d736f95dd42427296047067694-Abstract.html https://proceedings.neurips.cc/paper_files/paper/2021/hash/f51338d736f95dd42427296047067694-Abstract.html .

NOTIN P , DIAS M , FRAZER J , et al . Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval [C/OL ] // Proceedings of the 39th International Conference on Machine Learning , PMLR , 2022 , 162 : 16990 - 17017 [2025-06-03] . https://proceedings.mlr.press/v162/notin22a.html https://proceedings.mlr.press/v162/notin22a.html .

LUTZ I D , WANG S Z , NORN C , et al . Top-down design of protein architectures with reinforcement learning [J ] . Science , 2023 , 380 ( 6642 ): 266 - 273 .

WANG Y , TANG H , HUANG L C , et al . Self-play reinforcement learning guides protein engineering [J ] . Nature Machine Intelligence , 2023 , 5 ( 8 ): 845 - 860 .

WEI J , TAY Y , BOMMASANI R , et al . Emergent abilities of large language models [J/OL ] . Transactions on Machine Learning Research , 2022 . ( 2022-08-31 )[ 2025-06-03 ] . https://openreview.net/forum?id=yzkSU5zdwD https://openreview.net/forum?id=yzkSU5zdwD .

CHENG X Y , CHEN B , LI P , et al . Training compute-optimal protein language models [C/OL ] // Advances in Neural Information Processing Systems 37 (NeurIPS 2024) , 2024[2025-06-03] . https://proceedings.neurips.cc/paper_files/paper/2024/hash/8066ae1446b2bbccb5159587cc3b3bcc-Abstract-Conference.html https://proceedings.neurips.cc/paper_files/paper/2024/hash/8066ae1446b2bbccb5159587cc3b3bcc-Abstract-Conference.html .

HESSLOW D , ZANICHELLI N , NOTIN P , et al . RITA: a study on scaling up generative protein sequence models [EB/OL ] . arXiv , 2022 : 2205 . 05789 . ( 2022-07-14 )[ 2025-06-03 ] . https://arxiv.org/abs/2205.05789v2 https://arxiv.org/abs/2205.05789v2 .

VIEIRA L C , HANDOJO M L , WILKE C O . Scaling down for efficiency: medium-sized protein language models perform well at transfer learning on realistic datasets [EB/OL ] . bioRxiv , 2025 : 2024 .11. 22 .624936. ( 2025-05-08 )[ 2025-06-03 ] . https://doi.org/10.1101/2024.11.22.624936 https://doi.org/10.1101/2024.11.22.624936 .

GAN W S , WAN S C , YU P S . Model-as-a-service (MaaS): a survey [C/OL ] // 2023 IEEE International Conference on Big Data (BigData) . December 15-18, 2023 , Sorrento, Italy. IEEE , 2023 : 4636 - 4645 [2025-06-03] . https://ieeexplore.ieee.org/document/10386351 https://ieeexplore.ieee.org/document/10386351 .

GOLDFARB T , KODALI V K , PUJAR S , et al . NCBI RefSeq: reference sequence standards through 25 years of curation and annotation [J ] . Nucleic Acids Research , 2025 , 53 ( D1 ): D243 - D257 .

DYER S C , AUSTINE-ORIMOLOYE O , AZOV A G , et al . Ensembl 2025 [J ] . Nucleic Acids Research , 2025 , 53 ( D1 ): D948 - D957 .

The UniProt Consortium . UniProt: the universal protein knowledgebase in 2025 [J ] . Nucleic Acids Research , 2025 , 53 ( D1 ): D609 - D617 .

FOURNIER Q , VERNON R M , VAN DER SLOOT A , et al . Protein language models: is scaling necessary? [EB/OL ] . bioRxiv , 2024 : 09 . 23 . 614603 . ( 2024-09-23 )[ 2025-06-03 ] . https://doi.org/10.1101/2024.09.23.614603 https://doi.org/10.1101/2024.09.23.614603 .

BRANDES N , OFER D , PELEG Y , et al . ProteinBERT: a universal deep-learning model of protein sequence and function [J ] . Bioinformatics , 2022 , 38 ( 8 ): 2102 - 2110 .

WANG Z Y , ZHANG Q , HU S W , et al . Multi-level protein structure pre-training via prompt learning [C/OL ] // The Eleventh International Conference on Learning Representations ICLR 2023 . (2023-02-02)[2025-06-03] . https://openreview.net/forum?id=XGagtiJ8XC https://openreview.net/forum?id=XGagtiJ8XC .

ZHANG N Y , BI Z , LIANG X Z , et al . OntoProtein: protein pretraining with gene ontology embedding [C/OL ] // The Tenth International Conference on Learning Representations ICLR 2022 . (2022-01-29)[2025-06-03] . https://openreview.net/forum?id=yfe1VMYAXa4 https://openreview.net/forum?id=yfe1VMYAXa4 .

GELMAN S , JOHNSON B , FRESCHLIN C , et al . Biophysics-based protein language models for protein engineering [EB/OL ] . bioRxiv , 2025 : 2024 .03. 15 .585128. ( 2025-04-24 )[ 2025-06-03 ] . https://doi.org/10.1101/2024.03.15.585128 https://doi.org/10.1101/2024.03.15.585128 .

BORN J , MANICA M . Regression transformer enables concurrent sequence regression and generation for molecular language modelling [J ] . Nature Machine Intelligence , 2023 , 5 ( 4 ): 432 - 444 .

JIANG F , LI M C , DONG J J , et al . A general temperature-guided language model to design proteins of enhanced stability and activity [J ] . Science Advances , 2024 , 10 ( 48 ): eadr2641 .

DUMORTIER B , LIUTKUS A , CARRÉ C , et al . PeTriBERT: augmenting BERT with tridimensional encoding for inverse protein folding and design [EB/OL ] . bioRxiv , 2022 : 08 . 10 . 503344 . ( 2022-08-13 )[ 2025-06-03 ] . https://doi.org/10.1101/2022.08.10.503344 https://doi.org/10.1101/2022.08.10.503344 .

YANG K K , ZANICHELLI N , YEH H . Masked inverse folding with sequence transfer for protein representation learning [J ] . Protein Engineering, Design and Selection , 2022 , 36 : gzad015 .

DAUPARAS J , ANISHCHENKO I , BENNETT N , et al . Robust deep learning-based protein sequence design using ProteinMPNN [J ] . Science , 2022 , 378 ( 6615 ): 49 - 56 .

HSU C , VERKUIL R , LIU J , et al . Learning inverse folding from millions of predicted structures [C/OL ] // Proceedings of the 39th International Conference on Machine Learning , PMLR , 2022 , 162 : 8946 - 8970 [2025-06-03] . https://proceedings.mlr.press/v162/hsu22a.html https://proceedings.mlr.press/v162/hsu22a.html .

ZHENG Z X , DENG Y F , XUE D Y , et al . Structure-informed language models are protein designers [EB/OL ] . arXiv , 2023 : 2302 . 01649 . ( 2023-02-09 )[ 2025-06-03 ] . https://arxiv.org/abs/2302.01649v2 https://arxiv.org/abs/2302.01649v2 .

ZHANG Z B , LU J R , CHENTHAMARAKSHAN V , et al . Structure-informed protein language model [EB/OL ] . arXiv , 2024 : 2402 . 05856 . ( 2024-02-07 )[ 2025-06-03 ] . https://arxiv.org/abs/2402.05856v1 https://arxiv.org/abs/2402.05856v1 .

CHEN D X , HARTOUT P , PELLIZZONI P , et al . Endowing protein language models with structural knowledge [EB/OL ] . arXiv , 2024 : 2401 . 14819 .( 2024-01-26 )[ 2025-06-03 ] . https://arxiv.org/abs/2401.14819v1 https://arxiv.org/abs/2401.14819v1 .

TAN Y , LI M C , ZHOU B X , et al . Simple, efficient, and scalable structure-aware adapter boosts protein language models [J ] . Journal of Chemical Information and Modeling , 2024 , 64 ( 16 ): 6338 - 6349 .

CHENG J , NOVATI G , PAN J , et al . Accurate proteome-wide missense variant effect prediction with AlphaMissense [J ] . Science , 2023 , 381 ( 6664 ): eadg7492 .

TRUONG T F JR , BEPLER T . PoET: a generative model of protein families as sequences-of-sequences [C/OL ] // Advances in Neural Information Processing Systems(NeurIPS 2023 ), 2023 : 77379 - 415 [2025-06-03] . https://proceedings.neurips.cc/paper_files/paper/2023/hash/f4366126eba252699b280e8f93c0ab2f-Abstract-Conference.html https://proceedings.neurips.cc/paper_files/paper/2023/hash/f4366126eba252699b280e8f93c0ab2f-Abstract-Conference.html .

CHENG P , MAO C , TANG J , et al . Zero-shot prediction of mutation effects with multimodal deep representation learning guides protein engineering [J ] . Cell Research , 2024 , 34 ( 9 ): 630 - 647 .

OLSEN T H , BOYLES F , DEANE C M . Observed antibody space: a diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences [J ] . Protein Science , 2022 , 31 ( 1 ): 141 - 146 .

NGUYEN E , POLI M , DURRANT M G , et al . Sequence modeling and design from molecular to genome scale with Evo [J ] . Science , 2024 , 386 ( 6723 ): eado9336 .

RIESSELMAN A J , INGRAHAM J B , MARKS D S . Deep generative models of genetic variation capture the effects of mutations [J ] . Nature Methods , 2018 , 15 ( 10 ): 816 - 822 .

YU Y X , JIANG F , ZHONG B , et al . Entropy-driven zero-shot deep learning model selection for viral proteins [J ] . Physical Review Research , 2025 , 7 : 013229 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于机器视觉的高通量微生物克隆挑选工作站研制及应用

基于文本数据挖掘的蛋白功能预测：机遇与挑战

深度学习在基于序列的蛋白质互作预测中的应用进展

深度学习在蛋白质功能预测中的应用