Gan Liu
Research Subjects
Gan Liu has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Zhen Xie
MOE Key Laboratory of Bioinformatics and Bioinformatics Division, Center for Synthetic and Systems Biology, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China.
5 shared publications - Xuegong Zhang
MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University , Beijing 100084
3 shared publications - Hui Ning
MOE Key Laboratory of Bioinformatics and Bioinformatics Division, Center for Synthetic and Systems Biology, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China
2 shared publications Huiya Huang
Beijing SyngenTech Co., LTD, Zhongguancun Life Science Park, Changping District, Beijing, 102206, China
2 shared publications- Jin Gu
MOE Key Laboratory of Bioinformatics and Bioinformatics Division, Center for Synthetic and System Biology, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Liang He
Microsoft Research AI for Science, Beijing, China
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 18 November 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 10076
ERNIE-RNA: an RNA language model with structure-enhanced representations
Existing RNA language models (RLMs) largely overlook structural information in RNA sequences, leading to incomplete feature extraction and suboptimal performance on downstream tasks. In this study, we present ERNIE-RNA (Enhanced Representations with Base-Pairing Restriction for RNA Modeling), an RNA pre-trained language model based on a modified BERT (Bidirectional Encoder Representations from Transformers). Notably, ERNIE-RNA's attention maps exhibit superior ability to capture RNA structural features through zero-shot prediction, outperforming conventional methods like RNAfold and RNAstructure, suggesting that ERNIE-RNA naturally develops comprehensive representations of RNA architecture during pre-training. Moreover, after fine-tuning, ERNIE-RNA achieves state-of-the-art (SOTA) performance across various downstream tasks, including RNA structure and function predictions. In summary, ERNIE-RNA provides versatile features that can be effectively applied to a wide range of research tasks. Our findings highlight that integrating key knowledge-based priors into the BERT framework may enhance the performance of other language models.
- 18 November 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 10076
Top Cited PapersOpen AccessERNIE-RNA: an RNA language model with structure-enhanced representations
Existing RNA language models (RLMs) largely overlook structural information in RNA sequences, leading to incomplete feature extraction and suboptimal performance on downstream tasks. In this study, we present ERNIE-RNA (Enhanced Representations with Base-Pairing Restriction for RNA Modeling), an RNA pre-trained language model based on a modified BERT (Bidirectional Encoder Representations from Transformers). Notably, ERNIE-RNA's attention maps exhibit superior ability to capture RNA structural features through zero-shot prediction, outperforming conventional methods like RNAfold and RNAstructure, suggesting that ERNIE-RNA naturally develops comprehensive representations of RNA architecture during pre-training. Moreover, after fine-tuning, ERNIE-RNA achieves state-of-the-art (SOTA) performance across various downstream tasks, including RNA structure and function predictions. In summary, ERNIE-RNA provides versatile features that can be effectively applied to a wide range of research tasks. Our findings highlight that integrating key knowledge-based priors into the BERT framework may enhance the performance of other language models.
- Open Access
Impact of B18R-Encoding Messenger Ribonucleic Acid Co-Delivery on Neutralizing Antibody Production in Self-Amplifying Messenger Ribonucleic Acid Vaccines
Objectives: The COVID-19 pandemic has brought mRNA vaccines to the forefront due to their widespread use. In this study, we explored the potential advantages of the self-amplifying mRNA (saRNA) vaccine over conventional mRNA vaccines. Methods: Initially, we optimized lipid nanoparticle formulations and employed dT20 affinity chromatography purification to improve the intracellular expression of saRNA. Subsequently, we demonstrated that saRNA exhibited sustained expression for up to one month, both in vitro and in vivo, in contrast to mRNA. Finally, we developed a saRNA-based COVID-19 vaccine and achieved superior immune protection in mice compared to mRNA vaccine by co-delivering the B18R-encoding mRNA. Results: The co-delivery of B18R-mRNA with the saRNA vaccine significantly enhanced neutralizing antibody responses, outperforming those induced by the mRNA vaccine alone. This co-delivery strategy effectively regulated the early innate immune activation triggered by saRNA, facilitating a more robust adaptive immune response. Conclusions: The optimization strategies we used in this study highlight the potential of saRNA vaccines to offer stronger and more durable immune protection. The insights gained from this study not only promote the advancement of saRNA vaccine development but also provide practical guidance for their broader application in the fight against infectious diseases.
Open AccessImpact of B18R-Encoding Messenger Ribonucleic Acid Co-Delivery on Neutralizing Antibody Production in Self-Amplifying Messenger Ribonucleic Acid Vaccines
Objectives: The COVID-19 pandemic has brought mRNA vaccines to the forefront due to their widespread use. In this study, we explored the potential advantages of the self-amplifying mRNA (saRNA) vaccine over conventional mRNA vaccines. Methods: Initially, we optimized lipid nanoparticle formulations and employed dT20 affinity chromatography purification to improve the intracellular expression of saRNA. Subsequently, we demonstrated that saRNA exhibited sustained expression for up to one month, both in vitro and in vivo, in contrast to mRNA. Finally, we developed a saRNA-based COVID-19 vaccine and achieved superior immune protection in mice compared to mRNA vaccine by co-delivering the B18R-encoding mRNA. Results: The co-delivery of B18R-mRNA with the saRNA vaccine significantly enhanced neutralizing antibody responses, outperforming those induced by the mRNA vaccine alone. This co-delivery strategy effectively regulated the early innate immune activation triggered by saRNA, facilitating a more robust adaptive immune response. Conclusions: The optimization strategies we used in this study highlight the potential of saRNA vaccines to offer stronger and more durable immune protection. The insights gained from this study not only promote the advancement of saRNA vaccine development but also provide practical guidance for their broader application in the fight against infectious diseases.
- Open Access
ERNIE-RNA: An RNA Language Model with Structure-enhanced Representations
With large amounts of unlabeled RNA sequences data produced by high-throughput sequencing technologies, pre-trained RNA language models have been developed to estimate semantic space of RNA molecules, which facilities the understanding of grammar of RNA language. However, existing RNA language models overlook the impact of structure when modeling the RNA semantic space, resulting in incomplete feature extraction and suboptimal performance across various downstream tasks. In this study, we developed a RNA pre-trained language model named ERNIE-RNA ( E nhanced R eprese n tations with base-pa i ring r e striction for RNA modeling) based on a modified BERT (Bidirectional Encoder Representations from Transformers) by incorporating base-pairing restriction with no MSA (Multiple Sequence Alignment) information. We found that the attention maps from ERNIE-RNA with no fine-tuning are able to capture RNA structure in the zero-shot experiment more precisely than conventional methods such as fine-tuned RNAfold and RNAstructure, suggesting that the ERNIE-RNA can provide comprehensive RNA structural representations. Furthermore, ERNIE-RNA achieved SOTA (state-of-the-art) performance after fine-tuning for various downstream tasks, including RNA structural and functional predictions. In summary, our ERNIE-RNA model provides general features which can be widely and effectively applied in various subsequent research tasks. Our results indicate that introducing key knowledge-based prior information in the BERT framework may be a useful strategy to enhance the performance of other language models.
Open AccessERNIE-RNA: An RNA Language Model with Structure-enhanced Representations
With large amounts of unlabeled RNA sequences data produced by high-throughput sequencing technologies, pre-trained RNA language models have been developed to estimate semantic space of RNA molecules, which facilities the understanding of grammar of RNA language. However, existing RNA language models overlook the impact of structure when modeling the RNA semantic space, resulting in incomplete feature extraction and suboptimal performance across various downstream tasks. In this study, we developed a RNA pre-trained language model named ERNIE-RNA ( E nhanced R eprese n tations with base-pa i ring r e striction for RNA modeling) based on a modified BERT (Bidirectional Encoder Representations from Transformers) by incorporating base-pairing restriction with no MSA (Multiple Sequence Alignment) information. We found that the attention maps from ERNIE-RNA with no fine-tuning are able to capture RNA structure in the zero-shot experiment more precisely than conventional methods such as fine-tuned RNAfold and RNAstructure, suggesting that the ERNIE-RNA can provide comprehensive RNA structural representations. Furthermore, ERNIE-RNA achieved SOTA (state-of-the-art) performance after fine-tuning for various downstream tasks, including RNA structural and functional predictions. In summary, our ERNIE-RNA model provides general features which can be widely and effectively applied in various subsequent research tasks. Our results indicate that introducing key knowledge-based prior information in the BERT framework may be a useful strategy to enhance the performance of other language models.
- 24 November 2023
- Published by Elsevier in Cancer Letters
- Vol. 581, 216485
The spatial and single-cell analysis reveals remodeled immune microenvironment induced by synthetic oncolytic adenovirus treatment
- 24 November 2023
- Published by Elsevier in Cancer Letters
- Vol. 581, 216485
The spatial and single-cell analysis reveals remodeled immune microenvironment induced by synthetic oncolytic adenovirus treatment
- Open Access
- 8 November 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-11
Rational design of microRNA-responsive switch for programmable translational control in mammalian cells
Artificial RNA translation modulation usually relies on multiple components, such as RNA binding proteins (RBPs) or microRNAs (miRNAs) for off-switches and double-inverter cascades for on-switches. Recently, translational circular RNAs (circRNAs) were developed as promising alternatives for linear messenger RNAs (mRNAs). However, circRNAs still lack straightforward and programmable translation control strategies. Here, we rationally design a programmable miRNA-responsive internal ribosome entry site (IRES) translation activation and repression (PROMITAR) platform capable of implementing miRNA-based translation upregulation and downregulation in a single RNA construct. Based on the PROMITAR platform, we construct logic gates and cell-type classifier circRNAs and successfully identify desired mammalian cell types. We also demonstrate the potential therapeutic application of our platform for targeted cancer cell killing by encoding a cytotoxic protein in our engineered circRNAs. We expect our platform to expand the toolbox for RNA synthetic biology and provide an approach for potential biomedical applications in the future.
- 8 November 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-11
Open AccessRational design of microRNA-responsive switch for programmable translational control in mammalian cells
Artificial RNA translation modulation usually relies on multiple components, such as RNA binding proteins (RBPs) or microRNAs (miRNAs) for off-switches and double-inverter cascades for on-switches. Recently, translational circular RNAs (circRNAs) were developed as promising alternatives for linear messenger RNAs (mRNAs). However, circRNAs still lack straightforward and programmable translation control strategies. Here, we rationally design a programmable miRNA-responsive internal ribosome entry site (IRES) translation activation and repression (PROMITAR) platform capable of implementing miRNA-based translation upregulation and downregulation in a single RNA construct. Based on the PROMITAR platform, we construct logic gates and cell-type classifier circRNAs and successfully identify desired mammalian cell types. We also demonstrate the potential therapeutic application of our platform for targeted cancer cell killing by encoding a cytotoxic protein in our engineered circRNAs. We expect our platform to expand the toolbox for RNA synthetic biology and provide an approach for potential biomedical applications in the future.
- Open Access
- 16 March 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-17
Integrated transcriptome study of the tumor microenvironment for treatment response prediction in male predominant hypopharyngeal carcinoma
The efficacy of the first-line treatment for hypopharyngeal carcinoma (HPC), a predominantly male cancer, at advanced stage is only about 50% without reliable molecular indicators for its prognosis. In this study, HPC biopsy samples collected before and after the first-line treatment are classified into different groups according to treatment responses. We analyze the changes of HPC tumor microenvironment (TME) at the single-cell level in response to the treatment and identify three gene modules associated with advanced HPC prognosis. We estimate cell constitutions based on bulk RNA-seq of our HPC samples and build a binary classifier model based on non-malignant cell subtype abundance in TME, which can be used to accurately identify treatment-resistant advanced HPC patients in time and enlarge the possibility to preserve their laryngeal function. In summary, we provide a useful approach to identify gene modules and a classifier model as reliable indicators to predict treatment responses in HPC.
- 16 March 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-17
Open AccessIntegrated transcriptome study of the tumor microenvironment for treatment response prediction in male predominant hypopharyngeal carcinoma
The efficacy of the first-line treatment for hypopharyngeal carcinoma (HPC), a predominantly male cancer, at advanced stage is only about 50% without reliable molecular indicators for its prognosis. In this study, HPC biopsy samples collected before and after the first-line treatment are classified into different groups according to treatment responses. We analyze the changes of HPC tumor microenvironment (TME) at the single-cell level in response to the treatment and identify three gene modules associated with advanced HPC prognosis. We estimate cell constitutions based on bulk RNA-seq of our HPC samples and build a binary classifier model based on non-malignant cell subtype abundance in TME, which can be used to accurately identify treatment-resistant advanced HPC patients in time and enlarge the possibility to preserve their laryngeal function. In summary, we provide a useful approach to identify gene modules and a classifier model as reliable indicators to predict treatment responses in HPC.