Yijia-Xiao/Protein-LLM-Survey

Large Language Models in Protein: A Comprehensive Survey

194

26 commits

updated Apr 2, 2025

arxiv.org/pdf/2502.17504

See the code

README

Large Language Models in Protein: A Comprehensive Survey

LLM Methods for Protein Understanding and Prediction

Protein Sequence Models

Paper	Published in	Resources
Unified rational protein engineering with sequence-based deep representation learning	Nature Methods, 2019	Code
Learning protein sequence embeddings using information from structure	ICLR, 2019	Code
Mutation effect estimation on protein–protein interactions using deep contextualized representation learning	NAR Genomics and Bioinformatics, 2020	Code
Prottrans: Toward understanding the language of life through self-supervised learning	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021	Code
Modeling protein using large-scale pretrain language model	arXiv preprint, 2021	Code
Single-sequence protein structure prediction using a language model and deep learning	Nature Biotechnology, 2022	Code
Bertology meets biology: Interpreting attention in protein language models	arXiv preprint, 2020	Code
Learning the language of viral evolution and escape	Science, 2021	Code
TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses	bioRxiv, 2021	Code
xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein	arXiv e-prints, 2024	Model&Data
Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning	Nature Communications, 2023	Code
Enzyme function prediction using contrastive learning	Science, 2023	Code

Evolutionary Scale Modeling (ESM) Series

Paper	Published in	Resources
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences	PNAS, 2021	Code
Language models enable zero-shot prediction of the effects of mutations on protein function	Advances in Neural Information Processing Systems, 2021	Code
Learning inverse folding from millions of predicted structures	ICML, 2022	Code
Evolutionary-scale prediction of atomic-level protein structure with a language model	Science, 2023	Code
Simulating 500 million years of evolution with a language model	bioRxiv, 2024	Code

MSA-based Models

Paper	Published in	Resources
MSA transformer	ICML, 2021	Code
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval	ICML, 2022	Code
Leveraging protein language models for accurate multiple sequence alignments	Genome Research, 2023	Code
PoET: A generative model of protein families as sequences-of-sequences	Neurips, 2023	Code
Deep transfer learning for inter-chain contact predictions of transmembrane protein complexes	Nature Communications, 2023	Code

Structure-Integrated Models

Paper	Published in	Resources
A systematic study of joint representation learning on protein sequences and structures	arXiv preprint, 2023	Code
Saprot: Protein language modeling with structure-aware vocabulary	bioRxiv, 2023	Code
Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models	arXiv preprint, 2024	Code
Multi-level Protein Structure Pre-training via Prompt Learning	ICLR, 2023	Code
Structure-informed protein language models are robust predictors for variant effects	Human Genetics, 2024	N/A
Integration of pre-trained protein language models into geometric deep learning networks	Communications Biology, 2023	Code
Structure-Informed Protein Language Model	arXiv preprint, 2024	Code
S-PLM: Structure-Aware Protein Language Model via Contrastive Learning Between Sequence and Structure	Advanced Science, 2024	Code
CCPL: Cross-modal Contrastive Protein Learning	Pattern Recognition, 2024	N/A

Knowledge-Enhanced Models

Paper	Published in	Resources
OntoProtein: Protein Pretraining With Gene Ontology Embedding	ICLR, 2022	Code
ProteinCLIP: enhancing protein language models with natural language	bioRxiv, 2024	Code
ProteinBERT: a universal deep-learning model of protein sequence and function	Bioinformatics, 2022	Code
Protein Representation Learning via Knowledge Enhanced Primary Structure Reasoning	ICLR, 2023	Code
MolBind: Multimodal Alignment of Language, Molecules, and Proteins	arXiv preprint, 2024	N/A

Protein Description and Annotation Models

Paper	Published in	Resources
Prot2text: Multimodal protein’s function generation with gnns and transformers	AAAI, 2024	Code
Protranslator: zero-shot protein function prediction using textual description	International Conference on Research in Computational Molecular Biology, 2022	Code
Multilingual translation for zero-shot biomedical classification using BioTranslator	Nature Communications, 2023	Code
Biot5: Enriching cross-modal integration in biology with chemical knowledge and natural language associations	EMNLP, 2023	Code
BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning	ACL, 2024	Code
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts	ICML, 2023	Code
ProtChatGPT: Towards Understanding Proteins with Large Language Models	arXiv, 2024	N/A
ProteinChat: Towards Achieving ChatGPT-Like Functionalities on Protein 3D Structures	TechRxiv, 2023	N/A

LLM Methods for Protein Engineering and Generation

Generative Models (Protein Decoder)

Paper	Published in	Resources
Large language models generate functional protein sequences across diverse families	Nature Biotechnology, 2023	Code
ProtGPT2: Deep Unsupervised Language Model for Protein Design	Nature Communications, 2022	Code
ProGen2: Exploring the Boundaries of Protein Language Models	Cell Systems, 2023	Code
IgLM: Infilling Language Modeling for Antibody Sequence Design	Cell Systems, 2023	Code
PALM-H3: Targeted Antibody Generation for SARS-CoV-2	Nature Communications, 2024	Code
Integrating protein language models and automatic biofoundry for enhanced protein evolution	Nature Communications, 2025	Code

Protein Encoder Models

Paper	Published in	Resources
ProtST: Multi-modality Learning of Protein Sequences and Biomedical Texts	ICML 2023	Code
ProteinBERT: a universal deep-learning model of protein sequence and function	Bioinformatics, 2022	Code
Bertology meets biology: Interpreting attention in protein language models	arXiv preprint, 2020	Code
Prottrans: Toward understanding the language of life through self-supervised learning	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021	Code
Modeling protein using large-scale pretrain language model	arXiv preprint, 2021	Code

Encoder-Decoder Models

Paper	Published in	Resources
ProstT5: Bilingual Modeling of Protein Sequence and Structure	bioRxiv, 2023	Code
Fold2Seq: A Joint Sequence–Fold Embedding-based Generative Model for Protein Design	ICML 2021	Code
Ankh: Optimized Protein Language Model for Efficient Generation	arXiv, 2023	Code

Interactive and Multimodal Models

Paper	Published in	Resources
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding	arXiv, 2024	Code
ProteinChat: ChatGPT-like Functionalities on Protein 3D Structures	Authorea Preprints, 2023	Code
ProtChatGPT: Towards Understanding Proteins with Large Language Models	arXiv, 2024	Code
ProteinDT: A Text-guided Protein Design Framework	arXiv, 2023	Code

Traditional Experimental Methods for Protein

X-ray Crystallography

Paper	Published in	Resources
Artificial intelligence to solve the X-ray crystallography phase problem: a case study report	BiorXiv, 2021	N/A

Nuclear Magnetic Resonance (NMR) Spectroscopy

Paper	Published in	Resources
FID-Net: A versatile deep neural network architecture for NMR spectral reconstruction and virtual decoupling	Journal of Biomolecular NMR, 2021	Code
Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning	Angewandte Chemie, 2020	Code

Cryo-EM

Paper	Published in	Resources
CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks	Nature Methods, 2021	Code
CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial Learning	IEEE Transactions on Computational Imaging , 2021	Code
Deep learning-based mixed-dimensional Gaussian mixture model for characterizing variability in cryo-EM	Nature Methods, 2021	Code
3dflex: determining structure and motion of flexible proteins from cryo-em	Nature Methods, 2023	Code
Cryostar: leveraging structural priors and constraints for cryo-em heterogeneous reconstruction	Nature Methods, 2024	Code

Protein Datasets: Training Data and Benchmarks

Pretraining Dataset

Dataset Name	Description	Resources
UniProtKB/Swiss-Prot	Manually curated protein database with detailed functional annotations	Link
UniProtKB/TrEMBL	Automatically annotated protein database with computational analysis	Link
UniRef Clusters	Clustered protein sequences for reduced redundancy and efficient searches	Link
Pfam	Database of protein families and domains	Link
PDB	Database of 3D structures of biological macromolecules	Link
BFD	Large database of clustered protein sequences	Link
UniParc	Non-redundant archive of protein sequences from public databases	Link
PIR	Comprehensive annotated protein sequence database	Link
AlphaFoldDB	Database of predicted protein structures using AI	Link

Benchmark

Paper	Published in	Resources
Critical assessment of methods of protein structure prediction (CASP)—Round XV	Proteins: Structure, Function, and Bioinformatics	Link
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	Neurips, 2023	Code
Evaluating protein transfer learning with tape	Neurips, 2019	Code
CATH–a hierarchic classification of protein domain structures	Structure, 1997	Link
Peer: a comprehensive and multi-task benchmark for protein sequence understanding	Neurips, 2022	Code
ExplorEnz: the primary source of the IUBMB enzyme list	Nucleic acids research, 2009	Link
HIPPIE: Integrating protein interaction networks with experiment based quality scores	PloS One, 2012	Link
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding	arXiv, 2019	Code

Protein LLM Biomolecular Interactions

Paper	Published in	Resources
Accurate structure prediction of biomolecular interactions with AlphaFold 3	Nature, 8 May 2024	Code
ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction	COLM	Code
Protein-Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools	Journal of Proteome Research	N/A

awes

comprehensive

large-language-models

llm

papers

papers-with-code

protein

survey

Contributors

11 commits

9 commits

3 commits

2 commits

Similar repos

yangkky/Machine-learning-for-proteins

Listing of papers about machine learning for proteins.

1,717

facebookresearch/esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

4,172

PKU-YuanGroup/ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

209

Lyu6PosHao/ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

209

agemagician/ProtTrans

ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was…

1,323

HICAI-ZJU/Scientific-LLM-Survey

Scientific Large Language Models: A Survey on Biological & Chemical Domains

361

ColinFX/Prot2Text-V2

Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment

Synthyra/Protify

Low code molecular property prediction

Yijia-Xiao/Protein-LLM-Survey

Large Language Models in Protein: A Comprehensive Survey

194

26 commits

updated Apr 2, 2025

arxiv.org/pdf/2502.17504

See the code

README

Large Language Models in Protein: A Comprehensive Survey

LLM Methods for Protein Understanding and Prediction

Protein Sequence Models

Paper	Published in	Resources
Unified rational protein engineering with sequence-based deep representation learning	Nature Methods, 2019	Code
Learning protein sequence embeddings using information from structure	ICLR, 2019	Code
Mutation effect estimation on protein–protein interactions using deep contextualized representation learning	NAR Genomics and Bioinformatics, 2020	Code
Prottrans: Toward understanding the language of life through self-supervised learning	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021	Code
Modeling protein using large-scale pretrain language model	arXiv preprint, 2021	Code
Single-sequence protein structure prediction using a language model and deep learning	Nature Biotechnology, 2022	Code
Bertology meets biology: Interpreting attention in protein language models	arXiv preprint, 2020	Code
Learning the language of viral evolution and escape	Science, 2021	Code
TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses	bioRxiv, 2021	Code
xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein	arXiv e-prints, 2024	Model&Data
Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning	Nature Communications, 2023	Code
Enzyme function prediction using contrastive learning	Science, 2023	Code

Evolutionary Scale Modeling (ESM) Series

Paper	Published in	Resources
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences	PNAS, 2021	Code
Language models enable zero-shot prediction of the effects of mutations on protein function	Advances in Neural Information Processing Systems, 2021	Code
Learning inverse folding from millions of predicted structures	ICML, 2022	Code
Evolutionary-scale prediction of atomic-level protein structure with a language model	Science, 2023	Code
Simulating 500 million years of evolution with a language model	bioRxiv, 2024	Code

MSA-based Models

Paper	Published in	Resources
MSA transformer	ICML, 2021	Code
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval	ICML, 2022	Code
Leveraging protein language models for accurate multiple sequence alignments	Genome Research, 2023	Code
PoET: A generative model of protein families as sequences-of-sequences	Neurips, 2023	Code
Deep transfer learning for inter-chain contact predictions of transmembrane protein complexes	Nature Communications, 2023	Code

Structure-Integrated Models

Paper	Published in	Resources
A systematic study of joint representation learning on protein sequences and structures	arXiv preprint, 2023	Code
Saprot: Protein language modeling with structure-aware vocabulary	bioRxiv, 2023	Code
Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models	arXiv preprint, 2024	Code
Multi-level Protein Structure Pre-training via Prompt Learning	ICLR, 2023	Code
Structure-informed protein language models are robust predictors for variant effects	Human Genetics, 2024	N/A
Integration of pre-trained protein language models into geometric deep learning networks	Communications Biology, 2023	Code
Structure-Informed Protein Language Model	arXiv preprint, 2024	Code
S-PLM: Structure-Aware Protein Language Model via Contrastive Learning Between Sequence and Structure	Advanced Science, 2024	Code
CCPL: Cross-modal Contrastive Protein Learning	Pattern Recognition, 2024	N/A

Knowledge-Enhanced Models

Paper	Published in	Resources
OntoProtein: Protein Pretraining With Gene Ontology Embedding	ICLR, 2022	Code
ProteinCLIP: enhancing protein language models with natural language	bioRxiv, 2024	Code
ProteinBERT: a universal deep-learning model of protein sequence and function	Bioinformatics, 2022	Code
Protein Representation Learning via Knowledge Enhanced Primary Structure Reasoning	ICLR, 2023	Code
MolBind: Multimodal Alignment of Language, Molecules, and Proteins	arXiv preprint, 2024	N/A

Protein Description and Annotation Models

Paper	Published in	Resources
Prot2text: Multimodal protein’s function generation with gnns and transformers	AAAI, 2024	Code
Protranslator: zero-shot protein function prediction using textual description	International Conference on Research in Computational Molecular Biology, 2022	Code
Multilingual translation for zero-shot biomedical classification using BioTranslator	Nature Communications, 2023	Code
Biot5: Enriching cross-modal integration in biology with chemical knowledge and natural language associations	EMNLP, 2023	Code
BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning	ACL, 2024	Code
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts	ICML, 2023	Code
ProtChatGPT: Towards Understanding Proteins with Large Language Models	arXiv, 2024	N/A
ProteinChat: Towards Achieving ChatGPT-Like Functionalities on Protein 3D Structures	TechRxiv, 2023	N/A

LLM Methods for Protein Engineering and Generation

Generative Models (Protein Decoder)

Paper	Published in	Resources
Large language models generate functional protein sequences across diverse families	Nature Biotechnology, 2023	Code
ProtGPT2: Deep Unsupervised Language Model for Protein Design	Nature Communications, 2022	Code
ProGen2: Exploring the Boundaries of Protein Language Models	Cell Systems, 2023	Code
IgLM: Infilling Language Modeling for Antibody Sequence Design	Cell Systems, 2023	Code
PALM-H3: Targeted Antibody Generation for SARS-CoV-2	Nature Communications, 2024	Code
Integrating protein language models and automatic biofoundry for enhanced protein evolution	Nature Communications, 2025	Code

Protein Encoder Models

Paper	Published in	Resources
ProtST: Multi-modality Learning of Protein Sequences and Biomedical Texts	ICML 2023	Code
ProteinBERT: a universal deep-learning model of protein sequence and function	Bioinformatics, 2022	Code
Bertology meets biology: Interpreting attention in protein language models	arXiv preprint, 2020	Code
Prottrans: Toward understanding the language of life through self-supervised learning	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021	Code
Modeling protein using large-scale pretrain language model	arXiv preprint, 2021	Code

Encoder-Decoder Models

Paper	Published in	Resources
ProstT5: Bilingual Modeling of Protein Sequence and Structure	bioRxiv, 2023	Code
Fold2Seq: A Joint Sequence–Fold Embedding-based Generative Model for Protein Design	ICML 2021	Code
Ankh: Optimized Protein Language Model for Efficient Generation	arXiv, 2023	Code

Interactive and Multimodal Models

Paper	Published in	Resources
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding	arXiv, 2024	Code
ProteinChat: ChatGPT-like Functionalities on Protein 3D Structures	Authorea Preprints, 2023	Code
ProtChatGPT: Towards Understanding Proteins with Large Language Models	arXiv, 2024	Code
ProteinDT: A Text-guided Protein Design Framework	arXiv, 2023	Code

Traditional Experimental Methods for Protein

X-ray Crystallography

Paper	Published in	Resources
Artificial intelligence to solve the X-ray crystallography phase problem: a case study report	BiorXiv, 2021	N/A

Nuclear Magnetic Resonance (NMR) Spectroscopy

Paper	Published in	Resources
FID-Net: A versatile deep neural network architecture for NMR spectral reconstruction and virtual decoupling	Journal of Biomolecular NMR, 2021	Code
Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning	Angewandte Chemie, 2020	Code

Cryo-EM

Paper	Published in	Resources
CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks	Nature Methods, 2021	Code
CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial Learning	IEEE Transactions on Computational Imaging , 2021	Code
Deep learning-based mixed-dimensional Gaussian mixture model for characterizing variability in cryo-EM	Nature Methods, 2021	Code
3dflex: determining structure and motion of flexible proteins from cryo-em	Nature Methods, 2023	Code
Cryostar: leveraging structural priors and constraints for cryo-em heterogeneous reconstruction	Nature Methods, 2024	Code

Protein Datasets: Training Data and Benchmarks

Pretraining Dataset

Dataset Name	Description	Resources
UniProtKB/Swiss-Prot	Manually curated protein database with detailed functional annotations	Link
UniProtKB/TrEMBL	Automatically annotated protein database with computational analysis	Link
UniRef Clusters	Clustered protein sequences for reduced redundancy and efficient searches	Link
Pfam	Database of protein families and domains	Link
PDB	Database of 3D structures of biological macromolecules	Link
BFD	Large database of clustered protein sequences	Link
UniParc	Non-redundant archive of protein sequences from public databases	Link
PIR	Comprehensive annotated protein sequence database	Link
AlphaFoldDB	Database of predicted protein structures using AI	Link

Benchmark

Paper	Published in	Resources
Critical assessment of methods of protein structure prediction (CASP)—Round XV	Proteins: Structure, Function, and Bioinformatics	Link
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	Neurips, 2023	Code
Evaluating protein transfer learning with tape	Neurips, 2019	Code
CATH–a hierarchic classification of protein domain structures	Structure, 1997	Link
Peer: a comprehensive and multi-task benchmark for protein sequence understanding	Neurips, 2022	Code
ExplorEnz: the primary source of the IUBMB enzyme list	Nucleic acids research, 2009	Link
HIPPIE: Integrating protein interaction networks with experiment based quality scores	PloS One, 2012	Link
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding	arXiv, 2019	Code

Protein LLM Biomolecular Interactions

Paper	Published in	Resources
Accurate structure prediction of biomolecular interactions with AlphaFold 3	Nature, 8 May 2024	Code
ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction	COLM	Code
Protein-Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools	Journal of Proteome Research	N/A

awes

comprehensive

large-language-models

llm

papers

papers-with-code

protein

survey

Similar repos

yangkky/Machine-learning-for-proteins

Listing of papers about machine learning for proteins.

1,717

facebookresearch/esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

4,172

PKU-YuanGroup/ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

209

Lyu6PosHao/ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

209

agemagician/ProtTrans

ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was…

1,323

HICAI-ZJU/Scientific-LLM-Survey

Scientific Large Language Models: A Survey on Biological & Chemical Domains

361

ColinFX/Prot2Text-V2

Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment

Synthyra/Protify

Low code molecular property prediction

Contributors

11 commits

9 commits

3 commits

2 commits