Bing He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bing He has a total of 525 co-authors. Here are the top co-authors by number of shared publications:
- Jianhua Yao
AI for Life Sciences Lab, Tencent, Shenzhen, China
20 shared publications - Ge Zhang
Department of Microbial and Biochemical Pharmacy, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, China
16 shared publications - Aiping Lu
School of Chinese Medicine, Hong Kong Baptist University, Hong Kong SAR, China
15 shared publications - Baosheng Guo
Division of Sports Medicine and Adult Reconstructive Surgery Department of Orthopedic Surgery State Key Laboratory of Pharmaceutical Biotechnology Nanjing Drum Tower Hospital Nanjing University Nanjing Jiangsu P. R. China
10 shared publications - Yu Zhao
AI for Life Sciences Lab, Tencent, Shenzhen, China
10 shared publications - Defang Li
Featured Laboratory for Biosynthesis and Target Discovery of Active Components of Traditional Chinese Medicine, School of Traditional Chinese Medicine, Binzhou Medical University, Yantai, China
7 shared publications
Latest Publications
- Open Access
- 24 September 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition
T-cell receptor (TCR) recognition of antigenic peptides presented by human leukocyte antigen (HLA) molecules underpins adaptive immunity and T cell-based immunotherapy. However, the scarcity of complete interaction data and TCR cross-reactivity challenge robust prediction. Here, we present UpTCR, a unified progressive knowledge-transfer foundation model that learns from incomplete data to predict TCR-antigen-HLA binding. UpTCR progressively transfers knowledge from dimeric and trimeric interactions to tetrameric complexes and uses soft contrastive learning to mitigate false negatives. It outperforms existing methods in predicting TCR binding specificity and antigen-HLA binding affinity, particularly for neoantigens, and reveals pairwise residue-level interactions across the tetramer. UpTCR also transfers effectively to breast cancer cohorts with limited data. Prospective validation against melanoma antigen variants identifies eight immunogenic peptides that elicit T cell responses and one variant associated with immune escape. These findings establish UpTCR as a generalizable and interpretable tool for studying antigen recognition and advancing TCR-based immunotherapies.
- 24 September 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessUpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition
T-cell receptor (TCR) recognition of antigenic peptides presented by human leukocyte antigen (HLA) molecules underpins adaptive immunity and T cell-based immunotherapy. However, the scarcity of complete interaction data and TCR cross-reactivity challenge robust prediction. Here, we present UpTCR, a unified progressive knowledge-transfer foundation model that learns from incomplete data to predict TCR-antigen-HLA binding. UpTCR progressively transfers knowledge from dimeric and trimeric interactions to tetrameric complexes and uses soft contrastive learning to mitigate false negatives. It outperforms existing methods in predicting TCR binding specificity and antigen-HLA binding affinity, particularly for neoantigens, and reveals pairwise residue-level interactions across the tetramer. UpTCR also transfers effectively to breast cancer cohorts with limited data. Prospective validation against melanoma antigen variants identifies eight immunogenic peptides that elicit T cell responses and one variant associated with immune escape. These findings establish UpTCR as a generalizable and interpretable tool for studying antigen recognition and advancing TCR-based immunotherapies.
- Open Access
- 2 September 2026
- Published by Springer Nature in Genome Biology
Epitope-conditioned generation of T-cell receptor β-chain CDR3 candidates using a pre-trained transformer model
- 2 September 2026
- Published by Springer Nature in Genome Biology
Open AccessEpitope-conditioned generation of T-cell receptor β-chain CDR3 candidates using a pre-trained transformer model
- Open Access
- 19 August 2026
- Published by Springer Nature in Nature Biotechnology
- p. 1-13
A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability
Experimentally validated prospective, blinded benchmarks are needed to separate durable advances from hype in computational antibody design. Here AIntibody, a challenge inspired by the Critical Assessment of Structure Prediction, tests 511 artificial intelligence (AI)-designed or predicted antibodies from 29 organizations on three tasks: in silico affinity maturation from phase 1 sequencing outputs, affinity ranking within heavy-chain complementarity-determining region 3 (HCDR3) clusters of a selection output and CDR design of proteins not included in a selection output. Validated with diverse experimental assays, several groups produced developable antibodies with affinities <100 pM. However, these successes were exceptions that did not transfer across tasks. Affinity-matured antibodies were modeled effectively. Except for one model, predicting high-affinity clones from clustered HCDR3 datasets was worse than random clone picking. Out-of-library design was highly variable for most method submissions, with many failing to outperform standard selections. The AIntibody challenge shows that AI can optimize antibodies in defined, biologically grounded regimes, in addition to highlighting critical gaps including affinity prediction and library-inspired antibody design and cross-task generalization.
- 19 August 2026
- Published by Springer Nature in Nature Biotechnology
- p. 1-13
Open AccessA blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability
Experimentally validated prospective, blinded benchmarks are needed to separate durable advances from hype in computational antibody design. Here AIntibody, a challenge inspired by the Critical Assessment of Structure Prediction, tests 511 artificial intelligence (AI)-designed or predicted antibodies from 29 organizations on three tasks: in silico affinity maturation from phase 1 sequencing outputs, affinity ranking within heavy-chain complementarity-determining region 3 (HCDR3) clusters of a selection output and CDR design of proteins not included in a selection output. Validated with diverse experimental assays, several groups produced developable antibodies with affinities <100 pM. However, these successes were exceptions that did not transfer across tasks. Affinity-matured antibodies were modeled effectively. Except for one model, predicting high-affinity clones from clustered HCDR3 datasets was worse than random clone picking. Out-of-library design was highly variable for most method submissions, with many failing to outperform standard selections. The AIntibody challenge shows that AI can optimize antibodies in defined, biologically grounded regimes, in addition to highlighting critical gaps including affinity prediction and library-inspired antibody design and cross-task generalization.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12468-12479
TCRTSdesign: End-to-End Co-Design of Antigen-Specific TCR Sequences and Structures
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12468-12479
Open AccessTCRTSdesign: End-to-End Co-Design of Antigen-Specific TCR Sequences and Structures
- 1 April 2026
- Published by Springer Nature in Nature Biotechnology
Scalable homology detection with ERAST
Homology search plays a fundamental role in computational biology, enabling the identification of evolutionary relationships and functional similarities among biological sequences. However, current homology search methods, including BLAST, Foldseek and MMseqs2, often struggle to efficiently and accurately process the vast scale of biological databases. Here we introduce ERAST (efficient retrieval-augmented search tool), a solution designed to handle approximately 1 billion biological sequences within the largest vector database to date. ERAST combines large language models and vector database technology to provide both efficient and precise searches for homologous biological sequences. It enhances search quality by integrating preretrieval, retrieval and postretrieval optimization stages, and supports both nucleotide and protein sequences. Through advanced indexing techniques, fine-grained segmentation and metadata integration, ERAST achieves better precision while operating approximately 50 times faster than Foldseek and 50,000 times faster than TM-align. This performance allows ERAST to conduct accurate searches against billions of biological sequences in mere milliseconds. The vector database integrated with ERAST can be accessed at https://ai4s.tencent.com/erast .
- 1 April 2026
- Published by Springer Nature in Nature Biotechnology
Scalable homology detection with ERAST
Homology search plays a fundamental role in computational biology, enabling the identification of evolutionary relationships and functional similarities among biological sequences. However, current homology search methods, including BLAST, Foldseek and MMseqs2, often struggle to efficiently and accurately process the vast scale of biological databases. Here we introduce ERAST (efficient retrieval-augmented search tool), a solution designed to handle approximately 1 billion biological sequences within the largest vector database to date. ERAST combines large language models and vector database technology to provide both efficient and precise searches for homologous biological sequences. It enhances search quality by integrating preretrieval, retrieval and postretrieval optimization stages, and supports both nucleotide and protein sequences. Through advanced indexing techniques, fine-grained segmentation and metadata integration, ERAST achieves better precision while operating approximately 50 times faster than Foldseek and 50,000 times faster than TM-align. This performance allows ERAST to conduct accurate searches against billions of biological sequences in mere milliseconds. The vector database integrated with ERAST can be accessed at https://ai4s.tencent.com/erast .
- Open Access
- 19 March 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Functional protein design and enhancement with ontology reinforcement iteration
The discrepancy between computational modeling and experimental performance remains a major challenge in protein engineering. We present ORI (Ontology Reinforcement Iteration), a scalable framework integrating ontology-conditioned decoding with reinforcement learning from experimental feedback (RLWF). ORI leverages structured ontologies as semantic prompts to impose multi-level constraints, enabling controllable and interpretable protein generation. A closed-loop iterative workflow—comprising generation, experimental measurement, and model updating—enables continuous optimization under real-world objectives. We demonstrate ORI’s practical applicability through diverse tasks, including enzymatic activity optimization, thermal stability enhancement, and multifunctional protein engineering. Using this framework, we engineer variants with substantial improvements over natural baselines, such as a lysozyme with 100-fold higher activity, a chitinase stable at 85 °C, and dual-function enzymes exhibiting both lysozyme and chitinase activities. These results establish ORI as a robust technical platform for efficient, multi-objective protein engineering in real-world experimental settings.
- 19 March 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessFunctional protein design and enhancement with ontology reinforcement iteration
The discrepancy between computational modeling and experimental performance remains a major challenge in protein engineering. We present ORI (Ontology Reinforcement Iteration), a scalable framework integrating ontology-conditioned decoding with reinforcement learning from experimental feedback (RLWF). ORI leverages structured ontologies as semantic prompts to impose multi-level constraints, enabling controllable and interpretable protein generation. A closed-loop iterative workflow—comprising generation, experimental measurement, and model updating—enables continuous optimization under real-world objectives. We demonstrate ORI’s practical applicability through diverse tasks, including enzymatic activity optimization, thermal stability enhancement, and multifunctional protein engineering. Using this framework, we engineer variants with substantial improvements over natural baselines, such as a lysozyme with 100-fold higher activity, a chitinase stable at 85 °C, and dual-function enzymes exhibiting both lysozyme and chitinase activities. These results establish ORI as a robust technical platform for efficient, multi-objective protein engineering in real-world experimental settings.
- Open Access
Optimizing broadly neutralizing antibodies via all-atom interaction modeling and pre-trained language models
Antibody optimization is a fundamental challenge, and the identification of antibody-antigen interactions is crucial in the optimization process. However, current methods cannot accurately predict antibody–antigen interactions due to the lack of all-atom modeling, thus being unable to improve the time-consuming and costly traditional optimization techniques. We present InterAb, a novel model developed for predicting antibody-antigen interactions and optimizing antibodies through all-atom modeling and antibody language models. Leveraging the proposed all-atom modeling approach, AtomInter, and pre-trained antibody language models, InterAb outperforms existing methods in predicting antibody specificity and antibody-antigen binding affinity. In the antibody library we constructed, InterAb successfully identified antibodies capable of binding to influenza A virus. An antibody optimization framework, InterAb-Opt, was further developed for the optimization of broadly neutralizing antibodies. For R1-32 antibody, biolayer interferometry results reveal that 85%, 80%, 90%, and 67.5% of the 40 optimized antibodies exhibit enhanced binding affinities to wild-type SARS-CoV-2, Lambda, BQ.1.1, and EG.5.1, respectively, with a maximum improvement of up to 96-fold. For the newly emerging BA.2.86 and KP.3, 55% and 52.5% of the optimized antibodies notably transition from non-binding to binding. Neutralization assays demonstrated that the optimized antibody exhibited enhanced neutralization activity across multiple targets, highlighting the capability of InterAb-Opt in engineering broadly neutralizing antibodies. This technology enables precise analysis of antibody-antigen interactions and optimization of broadly neutralizing antibodies, holding promise for addressing challenges in immune evasion and vaccine design.
Open AccessOptimizing broadly neutralizing antibodies via all-atom interaction modeling and pre-trained language models
Antibody optimization is a fundamental challenge, and the identification of antibody-antigen interactions is crucial in the optimization process. However, current methods cannot accurately predict antibody–antigen interactions due to the lack of all-atom modeling, thus being unable to improve the time-consuming and costly traditional optimization techniques. We present InterAb, a novel model developed for predicting antibody-antigen interactions and optimizing antibodies through all-atom modeling and antibody language models. Leveraging the proposed all-atom modeling approach, AtomInter, and pre-trained antibody language models, InterAb outperforms existing methods in predicting antibody specificity and antibody-antigen binding affinity. In the antibody library we constructed, InterAb successfully identified antibodies capable of binding to influenza A virus. An antibody optimization framework, InterAb-Opt, was further developed for the optimization of broadly neutralizing antibodies. For R1-32 antibody, biolayer interferometry results reveal that 85%, 80%, 90%, and 67.5% of the 40 optimized antibodies exhibit enhanced binding affinities to wild-type SARS-CoV-2, Lambda, BQ.1.1, and EG.5.1, respectively, with a maximum improvement of up to 96-fold. For the newly emerging BA.2.86 and KP.3, 55% and 52.5% of the optimized antibodies notably transition from non-binding to binding. Neutralization assays demonstrated that the optimized antibody exhibited enhanced neutralization activity across multiple targets, highlighting the capability of InterAb-Opt in engineering broadly neutralizing antibodies. This technology enables precise analysis of antibody-antigen interactions and optimization of broadly neutralizing antibodies, holding promise for addressing challenges in immune evasion and vaccine design.
- Open Access
- 10 December 2025
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
De novo design of epitope-specific antibodies via a structure-driven computational workflow
Accurate modeling of antibody-antigen complex structures holds significant potential for advancing biomedical research and the design of therapeutic antibodies. Compared to general proteins, progress in antibody structure prediction and design has been slow, and antibody discovery is still based on time-consuming animal immunization or library screening methods. Here, we present tFold System, a high-throughput computational workflow that integrates antibody structure prediction (tFold-Ab), antibody-antigen complex modeling (tFold-Ag), structure-guided virtual screening, and de novo epitope-specific antibody design. Using this system, we de novo design monoclonal antibodies (mAbs) against four therapeutically relevant antigens: influenza hemagglutinin (Flu A), PD-1, PD-L1, and SARS-CoV-2 RBD (SC2RBD). Experimental validation by surface plasmon resonance (SPR) following high-throughput screening via phage display shows the designed antibodies achieve nanomolar binding affinities and precise epitope targeting, demonstrating the efficiency of the integrated computational-experimental pipeline. Our results demonstrate that tFold System overcomes key limitations of existing methods by enabling rapid, high-throughput antibody discovery against user-defined epitopes.
- 10 December 2025
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessDe novo design of epitope-specific antibodies via a structure-driven computational workflow
Accurate modeling of antibody-antigen complex structures holds significant potential for advancing biomedical research and the design of therapeutic antibodies. Compared to general proteins, progress in antibody structure prediction and design has been slow, and antibody discovery is still based on time-consuming animal immunization or library screening methods. Here, we present tFold System, a high-throughput computational workflow that integrates antibody structure prediction (tFold-Ab), antibody-antigen complex modeling (tFold-Ag), structure-guided virtual screening, and de novo epitope-specific antibody design. Using this system, we de novo design monoclonal antibodies (mAbs) against four therapeutically relevant antigens: influenza hemagglutinin (Flu A), PD-1, PD-L1, and SARS-CoV-2 RBD (SC2RBD). Experimental validation by surface plasmon resonance (SPR) following high-throughput screening via phage display shows the designed antibodies achieve nanomolar binding affinities and precise epitope targeting, demonstrating the efficiency of the integrated computational-experimental pipeline. Our results demonstrate that tFold System overcomes key limitations of existing methods by enabling rapid, high-throughput antibody discovery against user-defined epitopes.
- Open Access
- 20 November 2025
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 6 (1)
Adding highly variable genes to spatially variable genes can improve cell type clustering performance in spatial transcriptomics data
Motivation: Spatial transcriptomics has allowed researchers to analyze transcriptome data in its tissue sample’s spatial context. Various methods have been developed for detecting spatially variable genes (SV genes), whose gene expression over the tissue space shows strong spatial autocorrelation. Such genes are often used to define clusters in cells or spots downstream. However, highly variable (HV) genes, whose quantitative gene expressions show significant variation from cell to cell, are conventionally used in clustering analyses. Results: In this report, we investigate whether adding highly variable genes to spatially variable genes can improve the cell type clustering performance in spatial transcriptomics data. We tested the clustering performance of HV genes, SV genes, and the union of both gene sets (concatenation) on over 50 real spatial transcriptomics datasets across multiple platforms, using a variety of spatial and non-spatial metrics. Our results show that combining HV genes and SV genes can improve overall cell-type clustering performance. Availability and implementation: All data and code used in this evaluation study can be found in the following link: https://github.com/lanagarmire/ST_benchmark.
- 20 November 2025
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 6 (1)
Open AccessAdding highly variable genes to spatially variable genes can improve cell type clustering performance in spatial transcriptomics data
Motivation: Spatial transcriptomics has allowed researchers to analyze transcriptome data in its tissue sample’s spatial context. Various methods have been developed for detecting spatially variable genes (SV genes), whose gene expression over the tissue space shows strong spatial autocorrelation. Such genes are often used to define clusters in cells or spots downstream. However, highly variable (HV) genes, whose quantitative gene expressions show significant variation from cell to cell, are conventionally used in clustering analyses. Results: In this report, we investigate whether adding highly variable genes to spatially variable genes can improve the cell type clustering performance in spatial transcriptomics data. We tested the clustering performance of HV genes, SV genes, and the union of both gene sets (concatenation) on over 50 real spatial transcriptomics datasets across multiple platforms, using a variety of spatial and non-spatial metrics. Our results show that combining HV genes and SV genes can improve overall cell-type clustering performance. Availability and implementation: All data and code used in this evaluation study can be found in the following link: https://github.com/lanagarmire/ST_benchmark.
- Open Access
- 14 October 2025
- Published by Springer Nature in Cell Discovery
- Vol. 11 (1) , 82
A pan-disease and population-level single-cell TCRαβ repertoire reference
Recent advances in single-cell technology enable the simultaneous capture of T cell receptor (TCR) sequences and gene expression (GEX), providing an integrated view of T cell function. However, linking TCRαβ information and T cell phenotypes at the population level to elucidate their disease association remains an unaddressed gap. Here, by constructing a large-scale reference of paired single-cell RNA/TCR sequencing (scRNA/TCR-seq) comprising more than 2 million T cells from 70 studies, 1017 biological samples, 583 individuals, and 46 disease conditions, along with their single-cell transcriptome, full-length paired TCR, and human leukocyte antigen (HLA) genotypes, we revealed the intrinsic features of germline-encoded TCR-major histocompatibility complex (MHC) restriction in CD4+/CD8+ lineages. We also observed widely existing public TCRαβs across the population, associated with higher clonal expansion levels and shared HLA alleles. The most publicly shared TCRs are likely to target epitopes from common viruses, such as Epstein-Barr virus (EBV), cytomegalovirus (CMV), and influenza A virus (IAV). Furthermore, we introduced TCR-DeepInsight, a computational framework to identify HLA-shared and disease-associated TCRαβ clusters that exhibit similar TCR sequence and GEX profiles, extensible for researchers to incorporate their data with our reference and characterize potentially functional TCRs. In summary, our work presents a panoramic scTCRαβ reference and computational methods for TCR study.
- 14 October 2025
- Published by Springer Nature in Cell Discovery
- Vol. 11 (1) , 82
Open AccessA pan-disease and population-level single-cell TCRαβ repertoire reference
Recent advances in single-cell technology enable the simultaneous capture of T cell receptor (TCR) sequences and gene expression (GEX), providing an integrated view of T cell function. However, linking TCRαβ information and T cell phenotypes at the population level to elucidate their disease association remains an unaddressed gap. Here, by constructing a large-scale reference of paired single-cell RNA/TCR sequencing (scRNA/TCR-seq) comprising more than 2 million T cells from 70 studies, 1017 biological samples, 583 individuals, and 46 disease conditions, along with their single-cell transcriptome, full-length paired TCR, and human leukocyte antigen (HLA) genotypes, we revealed the intrinsic features of germline-encoded TCR-major histocompatibility complex (MHC) restriction in CD4+/CD8+ lineages. We also observed widely existing public TCRαβs across the population, associated with higher clonal expansion levels and shared HLA alleles. The most publicly shared TCRs are likely to target epitopes from common viruses, such as Epstein-Barr virus (EBV), cytomegalovirus (CMV), and influenza A virus (IAV). Furthermore, we introduced TCR-DeepInsight, a computational framework to identify HLA-shared and disease-associated TCRαβ clusters that exhibit similar TCR sequence and GEX profiles, extensible for researchers to incorporate their data with our reference and characterize potentially functional TCRs. In summary, our work presents a panoramic scTCRαβ reference and computational methods for TCR study.