Tao Jiang
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
Tao Jiang has a total of 249 co-authors. Here are the top co-authors by number of shared publications:
- Jianyang Zeng
School of Engineering, Westlake University, Hangzhou, China
9 shared publications - Paul Vitanyi
CWI University of Amsterdam
5 shared publications Hao Chen
Department of Computer Science and Engineering, University of California, Riverside, California 92521, USA
4 shared publicationsJianyang Zeng
Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China
4 shared publications- Lusheng Wang
City University of Hong Kong
4 shared publications - Ming Li
Dept of Computer Science University of California 93106 Santa Barbara CA USA
4 shared publications
Latest Publications
- Open Access
- 23 October 2025
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (12)
SHICEDO: single-cell Hi-C data enhancement with reduced over-smoothing
Motivation: Single-cell Hi-C (scHi-C) technologies have significantly advanced our understanding of the 3D genome organization. However, scHi-C data are often sparse and noisy, leading to substantial computational challenges in downstream analyses. Results: In this study, we introduce SHICEDO, a novel deep-learning model specifically designed to enhance scHi-C contact matrices by imputing missing or sparsely captured chromatin contacts through a generative adversarial framework. SHICEDO leverages the unique structural characteristics of scHi-C matrices to derive customized features that enable effective data enhancement. Additionally, the model incorporates a channel-wise attention mechanism to mitigate the over-smoothing issue commonly associated with scHi-C enhancement methods. Through simulations and real-data applications, we demonstrate that SHICEDO outperforms the state-of-the-art methods, achieving superior quantitative and qualitative results. Moreover, SHICEDO enhances key structural features in scHi-C data, thus enabling more precise delineation of chromatin structures such as A/B compartments, TAD-like domains, and chromatin loops. Availability and implementation: SHICEDO is publicly available at https://github.com/wmalab/SHICEDO.
- 23 October 2025
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (12)
Open AccessSHICEDO: single-cell Hi-C data enhancement with reduced over-smoothing
Motivation: Single-cell Hi-C (scHi-C) technologies have significantly advanced our understanding of the 3D genome organization. However, scHi-C data are often sparse and noisy, leading to substantial computational challenges in downstream analyses. Results: In this study, we introduce SHICEDO, a novel deep-learning model specifically designed to enhance scHi-C contact matrices by imputing missing or sparsely captured chromatin contacts through a generative adversarial framework. SHICEDO leverages the unique structural characteristics of scHi-C matrices to derive customized features that enable effective data enhancement. Additionally, the model incorporates a channel-wise attention mechanism to mitigate the over-smoothing issue commonly associated with scHi-C enhancement methods. Through simulations and real-data applications, we demonstrate that SHICEDO outperforms the state-of-the-art methods, achieving superior quantitative and qualitative results. Moreover, SHICEDO enhances key structural features in scHi-C data, thus enabling more precise delineation of chromatin structures such as A/B compartments, TAD-like domains, and chromatin loops. Availability and implementation: SHICEDO is publicly available at https://github.com/wmalab/SHICEDO.
- Open Access
- 7 November 2024
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 23, 4027-4035
A mini-review of single-cell Hi-C embedding methods
Single-cell Hi-C (scHi-C) techniques have significantly advanced our understanding of the 3D genome organization, providing crucial insights into the spatial genome architecture within individual nuclei. Numerous computational and statistical methods have been developed to analyze scHi-C data, with embedding methods playing a key role. Embedding reduces the dimensionality of complex scHi-C contact maps, making it easier to extract biologically meaningful patterns. These methods not only enhance cell clustering based on chromatin structures but also facilitate visualization and other downstream analyses. Most scHi-C embedding methods incorporate strategies such as normalization and imputation to address the inherent sparsity of scHi-C data, thereby further improving data quality and interpretability. In this review, we systematically examine the existing methods designed for scHi-C embedding, outlining their methodologies and discussing their capabilities in handling normalization and imputation. Additionally, we present a comprehensive benchmarking analysis to compare both embedding techniques and their clustering performances. This review serves as a practical guide for researchers seeking to select suitable scHi-C embedding tools, ultimately contributing to the understanding of the 3D organization of the genome.
- 7 November 2024
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 23, 4027-4035
Open AccessA mini-review of single-cell Hi-C embedding methods
Single-cell Hi-C (scHi-C) techniques have significantly advanced our understanding of the 3D genome organization, providing crucial insights into the spatial genome architecture within individual nuclei. Numerous computational and statistical methods have been developed to analyze scHi-C data, with embedding methods playing a key role. Embedding reduces the dimensionality of complex scHi-C contact maps, making it easier to extract biologically meaningful patterns. These methods not only enhance cell clustering based on chromatin structures but also facilitate visualization and other downstream analyses. Most scHi-C embedding methods incorporate strategies such as normalization and imputation to address the inherent sparsity of scHi-C data, thereby further improving data quality and interpretability. In this review, we systematically examine the existing methods designed for scHi-C embedding, outlining their methodologies and discussing their capabilities in handling normalization and imputation. Additionally, we present a comprehensive benchmarking analysis to compare both embedding techniques and their clustering performances. This review serves as a practical guide for researchers seeking to select suitable scHi-C embedding tools, ultimately contributing to the understanding of the 3D organization of the genome.
- Open Access
- 26 July 2024
- Published by Cold Spring Harbor Laboratory in Genome Research
- Vol. 34 (7) , 1052-1065
Reference-informed prediction of alternative splicing and splicing-altering mutations from sequences
Alternative splicing plays a crucial role in protein diversity and gene expression regulation in higher eukaryotes, and mutations causing dysregulated splicing underlie a range of genetic diseases. Computational prediction of alternative splicing from genomic sequences not only provides insight into gene-regulatory mechanisms but also helps identify disease-causing mutations and drug targets. However, the current methods for the quantitative prediction of splice site usage still have limited accuracy. Here, we present DeltaSplice, a deep neural network model optimized to learn the impact of mutations on quantitative changes in alternative splicing from the comparative analysis of homologous genes. The model architecture enables DeltaSplice to perform “reference-informed prediction” by incorporating the known splice site usage of a reference gene sequence to improve its prediction on splicing-altering mutations. We benchmarked DeltaSplice and several other state-of-the-art methods on various prediction tasks, including evolutionary sequence divergence on lineage-specific splicing and splicing-altering mutations in human populations and neurodevelopmental disorders, and demonstrated that DeltaSplice outperformed consistently. DeltaSplice predicted ∼15% of splicing quantitative trait loci (sQTLs) in the human brain as causal splicing-altering variants. It also predicted splicing-altering de novo mutations outside the splice sites in a subset of patients affected by autism and other neurodevelopmental disorders (NDDs), including 19 genes with recurrent splicing-altering mutations. Integration of splicing-altering mutations with other types of de novo mutation burdens allowed the prediction of eight novel NDD-risk genes. Our work expanded the capacity of in silico splicing models with potential applications in genetic diagnosis and the development of splicing-based precision medicine.
- 26 July 2024
- Published by Cold Spring Harbor Laboratory in Genome Research
- Vol. 34 (7) , 1052-1065
Open AccessReference-informed prediction of alternative splicing and splicing-altering mutations from sequences
Alternative splicing plays a crucial role in protein diversity and gene expression regulation in higher eukaryotes, and mutations causing dysregulated splicing underlie a range of genetic diseases. Computational prediction of alternative splicing from genomic sequences not only provides insight into gene-regulatory mechanisms but also helps identify disease-causing mutations and drug targets. However, the current methods for the quantitative prediction of splice site usage still have limited accuracy. Here, we present DeltaSplice, a deep neural network model optimized to learn the impact of mutations on quantitative changes in alternative splicing from the comparative analysis of homologous genes. The model architecture enables DeltaSplice to perform “reference-informed prediction” by incorporating the known splice site usage of a reference gene sequence to improve its prediction on splicing-altering mutations. We benchmarked DeltaSplice and several other state-of-the-art methods on various prediction tasks, including evolutionary sequence divergence on lineage-specific splicing and splicing-altering mutations in human populations and neurodevelopmental disorders, and demonstrated that DeltaSplice outperformed consistently. DeltaSplice predicted ∼15% of splicing quantitative trait loci (sQTLs) in the human brain as causal splicing-altering variants. It also predicted splicing-altering de novo mutations outside the splice sites in a subset of patients affected by autism and other neurodevelopmental disorders (NDDs), including 19 genes with recurrent splicing-altering mutations. Integration of splicing-altering mutations with other types of de novo mutation burdens allowed the prediction of eight novel NDD-risk genes. Our work expanded the capacity of in silico splicing models with potential applications in genetic diagnosis and the development of splicing-based precision medicine.
- Open Access
Reference-informed prediction of alternative splicing and splicing-altering mutations from sequences
Alternative splicing plays a crucial role in protein diversity and gene expression regulation in higher eukaryotes and mutations causing dysregulated splicing underlie a range of genetic diseases. Computational prediction of alternative splicing from genomic sequences not only provides insight into gene-regulatory mechanisms but also helps identify disease-causing mutations and drug targets. However, the current methods for the quantitative prediction of splice site usage still have limited accuracy. Here, we present DeltaSplice, a deep neural network model optimized to learn the impact of mutations on quantitative changes in alternative splicing from the comparative analysis of homologous genes. The model architecture enables DeltaSplice to perform “reference-informed prediction” by incorporating the known splice site usage of a reference gene sequence to improve its prediction on splicing-altering mutations. We benchmarked DeltaSplice and several other state-of-the-art methods on various prediction tasks, including evolutionary sequence divergence on lineage-specific splicing and splicing-altering mutations in human populations and neurodevelopmental disorders, and demonstrated that DeltaSplice outperformed consistently. DeltaSplice predicted ∼15% of splicing quantitative trait loci (sQTLs) in the human brain as causal splicing-altering variants. It also predicted splicing-altering de novo mutations outside the splice sites in a subset of patients affected by autism and other neurodevelopmental disorders, including 19 genes with recurrent splicing-altering mutations. Among the new candidate disease risk genes, MFN1 is involved in mitochondria fusion, which is frequently disrupted in autism patients. Our work expanded the capacity of in silico splicing models with potential applications in genetic diagnosis and the development of splicing-based precision medicine.
Open AccessReference-informed prediction of alternative splicing and splicing-altering mutations from sequences
Alternative splicing plays a crucial role in protein diversity and gene expression regulation in higher eukaryotes and mutations causing dysregulated splicing underlie a range of genetic diseases. Computational prediction of alternative splicing from genomic sequences not only provides insight into gene-regulatory mechanisms but also helps identify disease-causing mutations and drug targets. However, the current methods for the quantitative prediction of splice site usage still have limited accuracy. Here, we present DeltaSplice, a deep neural network model optimized to learn the impact of mutations on quantitative changes in alternative splicing from the comparative analysis of homologous genes. The model architecture enables DeltaSplice to perform “reference-informed prediction” by incorporating the known splice site usage of a reference gene sequence to improve its prediction on splicing-altering mutations. We benchmarked DeltaSplice and several other state-of-the-art methods on various prediction tasks, including evolutionary sequence divergence on lineage-specific splicing and splicing-altering mutations in human populations and neurodevelopmental disorders, and demonstrated that DeltaSplice outperformed consistently. DeltaSplice predicted ∼15% of splicing quantitative trait loci (sQTLs) in the human brain as causal splicing-altering variants. It also predicted splicing-altering de novo mutations outside the splice sites in a subset of patients affected by autism and other neurodevelopmental disorders, including 19 genes with recurrent splicing-altering mutations. Among the new candidate disease risk genes, MFN1 is involved in mitochondria fusion, which is frequently disrupted in autism patients. Our work expanded the capacity of in silico splicing models with potential applications in genetic diagnosis and the development of splicing-based precision medicine.
- Top Cited PapersOpen Access
- 29 February 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-15
Drug target prediction through deep learning functional representation of gene signatures
Many machine learning applications in bioinformatics currently rely on matching gene identities when analyzing input gene signatures and fail to take advantage of preexisting knowledge about gene functions. To further enable comparative analysis of OMICS datasets, including target deconvolution and mechanism of action studies, we develop an approach that represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We develop the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model and demonstrate that its application to the Broad Institute’s L1000 datasets results in more effective compound-target predictions than models based on gene identities alone. By integrating additional pharmacological activity data sources, FRoGS significantly increases the number of high-quality compound-target predictions relative to existing approaches, many of which are supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help uncover new relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.
- 29 February 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-15
Top Cited PapersOpen AccessDrug target prediction through deep learning functional representation of gene signatures
Many machine learning applications in bioinformatics currently rely on matching gene identities when analyzing input gene signatures and fail to take advantage of preexisting knowledge about gene functions. To further enable comparative analysis of OMICS datasets, including target deconvolution and mechanism of action studies, we develop an approach that represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We develop the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model and demonstrate that its application to the Broad Institute’s L1000 datasets results in more effective compound-target predictions than models based on gene identities alone. By integrating additional pharmacological activity data sources, FRoGS significantly increases the number of high-quality compound-target predictions relative to existing approaches, many of which are supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help uncover new relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.
- Open Access
- 28 September 2023
- Published by Springer Nature in Research Square
Drug target prediction through deep learning functional representation of gene signatures
Many machine learning applications in bioinformatics currently rely on gene identities extracted from input gene signatures, and fail to take advantage of preexisting knowledge about gene functions. We developed the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model. FRoGS represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We demonstrated that its application to L1000 datasets resulted in more effective compound-target predictions than models based on gene identities alone. Through further integration of additional pharmacological activity data sources, FRoGS significantly contributed to a large number of high-quality compound-target predictions, which were supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help more readily uncover relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.
- 28 September 2023
- Published by Springer Nature in Research Square
Open AccessDrug target prediction through deep learning functional representation of gene signatures
Many machine learning applications in bioinformatics currently rely on gene identities extracted from input gene signatures, and fail to take advantage of preexisting knowledge about gene functions. We developed the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model. FRoGS represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We demonstrated that its application to L1000 datasets resulted in more effective compound-target predictions than models based on gene identities alone. Through further integration of additional pharmacological activity data sources, FRoGS significantly contributed to a large number of high-quality compound-target predictions, which were supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help more readily uncover relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.
- 1 September 2023
- Published by Wiley in Quantitative Biology
- Vol. 11 (3) , 275-286
DeepRCI: predicting RNA‐chromatin interactions via deep learning with multi‐omics data
Chromatin‐associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes. Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. DeepRCI can serve as a useful tool for characterizing RNA‐chromatin interactions and studying the underlying gene regulatory code.Background: Chromatin‐associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes, including gene transcription, chromatin remodeling and cellular differentiation. Recently, numerous experimental techniques have been developed to characterize genome‐wide RNA‐chromatin interactions to understand their underlying biological functions. However, these experimental methods are generally expensive, time‐consuming, and limited in identifying all potential sites, while most of the existing computational methods are restricted to detecting only specific types of RNAs interacting with chromatin.Methods: Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. In this framework, we introduce a novel deep learning component called variformer and integrate multi‐omics data to capture intrinsic genomic features at both RNA and DNA levels.Results: Extensive experiments demonstrate that DeepRCI can detect RNA‐chromatin interactions more accurately when compared to the state‐of‐the‐art baseline prediction methods. Furthermore, the sequence features extracted by DeepRCI can be well matched to known critical gene regulatory components, indicating that our model can provide useful biological insights into understanding the underlying mechanisms of RNA‐chromatin interactions. In addition, based on the prediction results, we further delineate the relationships between RNA‐chromatin interactions and cellular functions, including gene expression and the modulation of cell states.Conclusions: In summary, DeepRCI can serve as a useful tool for characterizing RNA‐chromatin interactions and studying the underlying gene regulatory code.
- 1 September 2023
- Published by Wiley in Quantitative Biology
- Vol. 11 (3) , 275-286
DeepRCI: predicting RNA‐chromatin interactions via deep learning with multi‐omics data
Chromatin‐associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes. Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. DeepRCI can serve as a useful tool for characterizing RNA‐chromatin interactions and studying the underlying gene regulatory code.Background: Chromatin‐associated RNA (caRNA) acts as a ubiquitous epigenetic layer in eukaryotes, and has been reported to be essential in various biological processes, including gene transcription, chromatin remodeling and cellular differentiation. Recently, numerous experimental techniques have been developed to characterize genome‐wide RNA‐chromatin interactions to understand their underlying biological functions. However, these experimental methods are generally expensive, time‐consuming, and limited in identifying all potential sites, while most of the existing computational methods are restricted to detecting only specific types of RNAs interacting with chromatin.Methods: Here, we propose a highly interpretable computational framework, named DeepRCI, to identify the interactions between various types of RNAs and chromatin. In this framework, we introduce a novel deep learning component called variformer and integrate multi‐omics data to capture intrinsic genomic features at both RNA and DNA levels.Results: Extensive experiments demonstrate that DeepRCI can detect RNA‐chromatin interactions more accurately when compared to the state‐of‐the‐art baseline prediction methods. Furthermore, the sequence features extracted by DeepRCI can be well matched to known critical gene regulatory components, indicating that our model can provide useful biological insights into understanding the underlying mechanisms of RNA‐chromatin interactions. In addition, based on the prediction results, we further delineate the relationships between RNA‐chromatin interactions and cellular functions, including gene expression and the modulation of cell states.Conclusions: In summary, DeepRCI can serve as a useful tool for characterizing RNA‐chromatin interactions and studying the underlying gene regulatory code.
- 2 March 2023
- Published by Springer Nature
- p. 239-255
Truly Unsupervised Image-to-Image Translation with Contrastive Representation Learning
- 2 March 2023
- Published by Springer Nature
- p. 239-255
Truly Unsupervised Image-to-Image Translation with Contrastive Representation Learning
- 1 October 2021
- Published by Elsevier in Science of The Total Environment
- Vol. 790, 147974
Estimation of the biogeochemical reactivities of dissolved organic matter from modified biochars using color
- 1 October 2021
- Published by Elsevier in Science of The Total Environment
- Vol. 790, 147974
Estimation of the biogeochemical reactivities of dissolved organic matter from modified biochars using color