Bing Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bing Song has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Tao Wang
Department of Bioinformatics and Computational Biology, UT MD Anderson Cancer Center, Houston, USA
5 shared publications - Fangjiang Wu
Peter O'Donnell Jr. School of Public Health, University of Texas Southwestern Medical Center, Dallas, TX, USA
2 shared publications - Junzhou Huang
The University of Texas at Arlington
2 shared publications - Kaiwen Wang
Department of Statistics and Data Science, Southern Methodist University , Dallas, TX 75205
2 shared publications - Saiyang Na
Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA
2 shared publications - Xinlei Wang
Department of Mathematics University of Texas at Arlington Arlington Texas USA
2 shared publications
Latest Publications
- 27 June 2025
- Published by Springer Nature in Nature Cancer
- Vol. 6 (9) , 1570-1584
Profiling antigen-binding affinity of B cell repertoires in tumors by deep learning predicts immune-checkpoint inhibitor treatment outcomes
The capability to profile the landscape of antigen-binding affinities of a vast number of antibodies (B cell receptors, BCRs) will provide a powerful tool to reveal biological insights. However, experimental approaches for detecting antibody–antigen interactions are costly and time-consuming and can only achieve low-to-mid throughput. In this work, we developed Cmai (contrastive modeling for antigen–antibody interactions) to address the prediction of binding between antibodies and antigens that can be scaled to high-throughput sequencing data. We devised a biomarker based on the output from Cmai to map the antigen-binding affinities of BCR repertoires. We found that the abundance of tumor antigen-targeting antibodies is predictive of immune-checkpoint inhibitor (ICI) treatment response. We also found that, during immune-related adverse events (irAEs) caused by ICI, humoral immunity is preferentially responsive to intracellular antigens from the organs affected by the irAEs. We used Cmai to construct a BCR-based irAE risk score, which predicted the timing of the occurrence of irAEs.
- 27 June 2025
- Published by Springer Nature in Nature Cancer
- Vol. 6 (9) , 1570-1584
Profiling antigen-binding affinity of B cell repertoires in tumors by deep learning predicts immune-checkpoint inhibitor treatment outcomes
The capability to profile the landscape of antigen-binding affinities of a vast number of antibodies (B cell receptors, BCRs) will provide a powerful tool to reveal biological insights. However, experimental approaches for detecting antibody–antigen interactions are costly and time-consuming and can only achieve low-to-mid throughput. In this work, we developed Cmai (contrastive modeling for antigen–antibody interactions) to address the prediction of binding between antibodies and antigens that can be scaled to high-throughput sequencing data. We devised a biomarker based on the output from Cmai to map the antigen-binding affinities of BCR repertoires. We found that the abundance of tumor antigen-targeting antibodies is predictive of immune-checkpoint inhibitor (ICI) treatment response. We also found that, during immune-related adverse events (irAEs) caused by ICI, humoral immunity is preferentially responsive to intracellular antigens from the organs affected by the irAEs. We used Cmai to construct a BCR-based irAE risk score, which predicted the timing of the occurrence of irAEs.
- Open Access
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
AlphaEpi: Enhancing B Cell Epitope Prediction with AlphaFold 3
Accurately identifying conformational B-cell epitopes, which involve complex protein structures, is essential in modern immunology and vaccine development. Traditional methods like X-ray crystallography provide precise data but are costly and time-consuming. This has led to the rise of computational methods, especially deep learning algorithms, which offer more efficient and cost-effective solutions. A major challenge in predicting conformational epitopes based on structure is the limited availability of experimentally validated structural data. Structural prediction tools can help address this issue but still rely on provided sequence information and complex algorithms, which can introduce noise and affect accuracy. Moreover, effectively aligning and fusing structural features with evolutionary sequence information remains another challenge. To address these challenges, we introduce AlphaEpi, an innovative model that combines the advanced structure prediction capabilities of AlphaFold 3 with deep learning graph neural networks. Additionally, we propose for the first time a dynamic selector module that allows the model to adjust its processing strategy based on the reliability of the structure and sequence information, addressing the challenge posed by unreliable structural data. Moreover, a novel graph fusion module integrates structural and evolutionary information, effectively solving the disparities in the integration process of structure and sequence data. Results show that by integrating advanced structural prediction technologies AlphaFold 3 with deep learning graph neural networks, AlphaEpi significantly surpasses baseline results, establishing itself as the state-of-the-art. This advancement furthers the development of B-cell epitope prediction and has significant implications for biological research.
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessAlphaEpi: Enhancing B Cell Epitope Prediction with AlphaFold 3
Accurately identifying conformational B-cell epitopes, which involve complex protein structures, is essential in modern immunology and vaccine development. Traditional methods like X-ray crystallography provide precise data but are costly and time-consuming. This has led to the rise of computational methods, especially deep learning algorithms, which offer more efficient and cost-effective solutions. A major challenge in predicting conformational epitopes based on structure is the limited availability of experimentally validated structural data. Structural prediction tools can help address this issue but still rely on provided sequence information and complex algorithms, which can introduce noise and affect accuracy. Moreover, effectively aligning and fusing structural features with evolutionary sequence information remains another challenge. To address these challenges, we introduce AlphaEpi, an innovative model that combines the advanced structure prediction capabilities of AlphaFold 3 with deep learning graph neural networks. Additionally, we propose for the first time a dynamic selector module that allows the model to adjust its processing strategy based on the reliability of the structure and sequence information, addressing the challenge posed by unreliable structural data. Moreover, a novel graph fusion module integrates structural and evolutionary information, effectively solving the disparities in the integration process of structure and sequence data. Results show that by integrating advanced structural prediction technologies AlphaFold 3 with deep learning graph neural networks, AlphaEpi significantly surpasses baseline results, establishing itself as the state-of-the-art. This advancement furthers the development of B-cell epitope prediction and has significant implications for biological research.
- Open Access
- 10 October 2024
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 121 (42)
Biochemical and structural insights into a 5’ to 3’ RNA ligase reveal a potential role in tRNA ligation
ATP-grasp superfamily enzymes contain a hand-like ATP-binding fold and catalyze a variety of reactions using a similar catalytic mechanism. More than 30 protein families are categorized in this superfamily, and they are involved in a plethora of cellular processes and human diseases. Here, we identify C12orf29 (RLIG1) as an atypical ATP-grasp enzyme that ligates RNA. Human RLIG1 and its homologs autoadenylate on an active site Lys residue as part of a reaction intermediate that specifically ligates RNA halves containing a 5’-phosphate and a 3’-hydroxyl. RLIG1 binds tRNA in cells and can ligate tRNA within the anticodon loop in vitro. Transcriptomic analyses of Rlig1 knockout mice revealed significant alterations in global tRNA levels in the brains of female mice, but not in those of male mice. Furthermore, crystal structures of a RLIG1 homolog from Yasminevirus bound to nucleotides revealed a minimal and atypical RNA ligase fold with a conserved active site architecture that participates in catalysis. Collectively, our results identify RLIG1 as an RNA ligase and suggest its involvement in tRNA biology.
- 10 October 2024
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 121 (42)
Open AccessBiochemical and structural insights into a 5’ to 3’ RNA ligase reveal a potential role in tRNA ligation
ATP-grasp superfamily enzymes contain a hand-like ATP-binding fold and catalyze a variety of reactions using a similar catalytic mechanism. More than 30 protein families are categorized in this superfamily, and they are involved in a plethora of cellular processes and human diseases. Here, we identify C12orf29 (RLIG1) as an atypical ATP-grasp enzyme that ligates RNA. Human RLIG1 and its homologs autoadenylate on an active site Lys residue as part of a reaction intermediate that specifically ligates RNA halves containing a 5’-phosphate and a 3’-hydroxyl. RLIG1 binds tRNA in cells and can ligate tRNA within the anticodon loop in vitro. Transcriptomic analyses of Rlig1 knockout mice revealed significant alterations in global tRNA levels in the brains of female mice, but not in those of male mice. Furthermore, crystal structures of a RLIG1 homolog from Yasminevirus bound to nucleotides revealed a minimal and atypical RNA ligase fold with a conserved active site architecture that participates in catalysis. Collectively, our results identify RLIG1 as an RNA ligase and suggest its involvement in tRNA biology.
- Open Access
- 8 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Author Correction: Comparative analysis of dimension reduction methods for cytometry by time-of-flight data
- 8 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Open AccessAuthor Correction: Comparative analysis of dimension reduction methods for cytometry by time-of-flight data
- Open Access
- 1 April 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-18
Comparative analysis of dimension reduction methods for cytometry by time-of-flight data
While experimental and informatic techniques around single cell sequencing (scRNA-seq) are advanced, research around mass cytometry (CyTOF) data analysis has severely lagged behind. CyTOF data are notably different from scRNA-seq data in many aspects. This calls for the evaluation and development of computational methods specific for CyTOF data. Dimension reduction (DR) is one of the critical steps of single cell data analysis. Here, we benchmark the performances of 21 DR methods on 110 real and 425 synthetic CyTOF samples. We find that less well-known methods like SAUCIE, SQuaD-MDS, and scvis are the overall best performers. In particular, SAUCIE and scvis are well balanced, SQuaD-MDS excels at structure preservation, whereas UMAP has great downstream analysis performance. We also find that t-SNE (along with SQuad-MDS/t-SNE Hybrid) possesses the best local structure preservation. Nevertheless, there is a high level of complementarity between these tools, so the choice of method should depend on the underlying data structure and the analytical needs.
- 1 April 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-18
Open AccessComparative analysis of dimension reduction methods for cytometry by time-of-flight data
While experimental and informatic techniques around single cell sequencing (scRNA-seq) are advanced, research around mass cytometry (CyTOF) data analysis has severely lagged behind. CyTOF data are notably different from scRNA-seq data in many aspects. This calls for the evaluation and development of computational methods specific for CyTOF data. Dimension reduction (DR) is one of the critical steps of single cell data analysis. Here, we benchmark the performances of 21 DR methods on 110 real and 425 synthetic CyTOF samples. We find that less well-known methods like SAUCIE, SQuaD-MDS, and scvis are the overall best performers. In particular, SAUCIE and scvis are well balanced, SQuaD-MDS excels at structure preservation, whereas UMAP has great downstream analysis performance. We also find that t-SNE (along with SQuad-MDS/t-SNE Hybrid) possesses the best local structure preservation. Nevertheless, there is a high level of complementarity between these tools, so the choice of method should depend on the underlying data structure and the analytical needs.
- 4 August 2022
- Published by Springer Nature in Nature Methods
- Vol. 19 (8) , 950-958
Sprod for de-noising spatially resolved transcriptomics data based on position and image information
Spatially resolved transcriptomics (SRT) provide gene expression close to, or even superior to, single-cell resolution while retaining the physical locations of sequencing and often also providing matched pathology images. However, SRT expression data suffer from high noise levels, due to the shallow coverage in each sequencing unit and the extra experimental steps required to preserve the locations of sequencing. Fortunately, such noise can be removed by leveraging information from the physical locations of sequencing, and the tissue organization reflected in corresponding pathology images. In this work, we developed Sprod, based on latent graph learning of matched location and imaging data, to impute accurate SRT gene expression. We validated Sprod comprehensively and demonstrated its advantages over previous methods for removing drop-outs in single-cell RNA-sequencing data. We showed that, after imputation by Sprod, differential expression analyses, pathway enrichment and cell-to-cell interaction inferences are more accurate. Overall, we envision de-noising by Sprod to become a key first step towards empowering SRT technologies for biomedical discoveries.
- 4 August 2022
- Published by Springer Nature in Nature Methods
- Vol. 19 (8) , 950-958
Sprod for de-noising spatially resolved transcriptomics data based on position and image information
Spatially resolved transcriptomics (SRT) provide gene expression close to, or even superior to, single-cell resolution while retaining the physical locations of sequencing and often also providing matched pathology images. However, SRT expression data suffer from high noise levels, due to the shallow coverage in each sequencing unit and the extra experimental steps required to preserve the locations of sequencing. Fortunately, such noise can be removed by leveraging information from the physical locations of sequencing, and the tissue organization reflected in corresponding pathology images. In this work, we developed Sprod, based on latent graph learning of matched location and imaging data, to impute accurate SRT gene expression. We validated Sprod comprehensively and demonstrated its advantages over previous methods for removing drop-outs in single-cell RNA-sequencing data. We showed that, after imputation by Sprod, differential expression analyses, pathway enrichment and cell-to-cell interaction inferences are more accurate. Overall, we envision de-noising by Sprod to become a key first step towards empowering SRT technologies for biomedical discoveries.
- Open Access
- 6 January 2021
- Published by Springer Nature in BMC Bioinformatics
- Vol. 22 (1) , 1-21
mixIndependR: a R package for statistical independence testing of loci in database of multi-locus genotypes
Background: Multi-locus genotype data are widely used in population genetics and disease studies. In evaluating the utility of multi-locus data, the independence of markers is commonly considered in many genomic assessments. Generally, pairwise non-random associations are tested by linkage disequilibrium; however, the dependence of one panel might be triplet, quartet, or other. Therefore, a compatible and user-friendly software is necessary for testing and assessing the global linkage disequilibrium among mixed genetic data.Results: This study describes a software package for testing the mutual independence of mixed genetic datasets. Mutual independence is defined as no non-random associations among all subsets of the tested panel. The new R package “mixIndependR” calculates basic genetic parameters like allele frequency, genotype frequency, heterozygosity, Hardy–Weinberg equilibrium, and linkage disequilibrium (LD) by mutual independence from population data, regardless of the type of markers, such as simple nucleotide polymorphisms, short tandem repeats, insertions and deletions, and any other genetic markers. A novel method of assessing the dependence of mixed genetic panels is developed in this study and functionally analyzed in the software package. By comparing the observed distribution of two common summary statistics (the number of heterozygous loci [K] and the number of share alleles [X]) with their expected distributions under the assumption of mutual independence, the overall independence is tested.Conclusion: The package “mixIndependR” is compatible to all categories of genetic markers and detects the overall non-random associations. Compared to pairwise disequilibrium, the approach described herein tends to have higher power, especially when number of markers is large. With this package, more multi-functional or stronger genetic panels can be developed, like mixed panels with different kinds of markers. In population genetics, the package “mixIndependR” makes it possible to discover more about admixture of populations, natural selection, genetic drift, and population demographics, as a more powerful method of detecting LD. Moreover, this new approach can optimize variants selection in disease studies and contribute to panel combination for treatments in multimorbidity. Application of this approach in real data is expected in the future, and this might bring a leap in the field of genetic technology.Availability: The R packagemixIndependR,is available on the Comprehensive R Archive Network (CRAN) at:https://cran.r-project.org/web/packages/mixIndependR/index.html.
- 6 January 2021
- Published by Springer Nature in BMC Bioinformatics
- Vol. 22 (1) , 1-21
Open AccessmixIndependR: a R package for statistical independence testing of loci in database of multi-locus genotypes
Background: Multi-locus genotype data are widely used in population genetics and disease studies. In evaluating the utility of multi-locus data, the independence of markers is commonly considered in many genomic assessments. Generally, pairwise non-random associations are tested by linkage disequilibrium; however, the dependence of one panel might be triplet, quartet, or other. Therefore, a compatible and user-friendly software is necessary for testing and assessing the global linkage disequilibrium among mixed genetic data.Results: This study describes a software package for testing the mutual independence of mixed genetic datasets. Mutual independence is defined as no non-random associations among all subsets of the tested panel. The new R package “mixIndependR” calculates basic genetic parameters like allele frequency, genotype frequency, heterozygosity, Hardy–Weinberg equilibrium, and linkage disequilibrium (LD) by mutual independence from population data, regardless of the type of markers, such as simple nucleotide polymorphisms, short tandem repeats, insertions and deletions, and any other genetic markers. A novel method of assessing the dependence of mixed genetic panels is developed in this study and functionally analyzed in the software package. By comparing the observed distribution of two common summary statistics (the number of heterozygous loci [K] and the number of share alleles [X]) with their expected distributions under the assumption of mutual independence, the overall independence is tested.Conclusion: The package “mixIndependR” is compatible to all categories of genetic markers and detects the overall non-random associations. Compared to pairwise disequilibrium, the approach described herein tends to have higher power, especially when number of markers is large. With this package, more multi-functional or stronger genetic panels can be developed, like mixed panels with different kinds of markers. In population genetics, the package “mixIndependR” makes it possible to discover more about admixture of populations, natural selection, genetic drift, and population demographics, as a more powerful method of detecting LD. Moreover, this new approach can optimize variants selection in disease studies and contribute to panel combination for treatments in multimorbidity. Application of this approach in real data is expected in the future, and this might bring a leap in the field of genetic technology.Availability: The R packagemixIndependR,is available on the Comprehensive R Archive Network (CRAN) at:https://cran.r-project.org/web/packages/mixIndependR/index.html.