Yantong Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yantong Cai has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Guangchuang Yu
Department of Bioinformatics School of Basic Medical Sciences Southern Medical University Guangzhou China
2 shared publications - Hao Zhao
Tsinghua University, Beijing, China
2 shared publications - Bin Yang
Dermatology Hospital of Southern Medical University Guangzhou Guangdong China
1 shared publication Bingdong Liu
Department of Bioinformatics, School of Basic Medical Sciences, Southern Medical University, Guangzhou, China
1 shared publicationErqiang Hu
Department of Bioinformatics, School of Basic Medical Sciences, Southern Medical University, Guangzhou, China
1 shared publication- Guoliang Wang
Tsinghua University, China
1 shared publication
Latest Publications
- 17 November 2026
- Published by Oxford University Press (OUP) in British Journal of Dermatology
Immune microenvironment types provide additional insight into clinical heterogeneity in systemic sclerosis
In systemic sclerosis, current clinical descriptors do not fully explain why patients with similar serological profiles can have very different degrees of skin involvement. We identified 14 immune microenvironment types (IMTs) by integrating newly generated peripheral-blood scRNA-seq data with curated publicly available scRNA-seq datasets, and subsequently evaluated their spatial and clinical relevance using publicly available spatial and bulk transcriptomic datasets. The most clinically meaningful associations were observed in skin. These tissue states provide additional clinical resolution beyond serological subtype and disease duration and help explain variation in cutaneous severity.
- 17 November 2026
- Published by Oxford University Press (OUP) in British Journal of Dermatology
Immune microenvironment types provide additional insight into clinical heterogeneity in systemic sclerosis
In systemic sclerosis, current clinical descriptors do not fully explain why patients with similar serological profiles can have very different degrees of skin involvement. We identified 14 immune microenvironment types (IMTs) by integrating newly generated peripheral-blood scRNA-seq data with curated publicly available scRNA-seq datasets, and subsequently evaluated their spatial and clinical relevance using publicly available spatial and bulk transcriptomic datasets. The most clinically meaningful associations were observed in skin. These tissue states provide additional clinical resolution beyond serological subtype and disease duration and help explain variation in cutaneous severity.
- Top Cited Papers
- 17 July 2024
- Published by Springer Nature in Nature Protocols
- Vol. 19 (11) , 3292-3320
Using clusterProfiler to characterize multiomics data
With the advent of multiomics, software capable of multidimensional enrichment analysis has become increasingly crucial for uncovering gene set variations in biological processes and disease pathways. This is essential for elucidating disease mechanisms and identifying potential therapeutic targets. clusterProfiler stands out for its comprehensive utilization of databases and advanced visualization features. Importantly, clusterProfiler supports various biological knowledge, including Gene Ontology and Kyoto Encyclopedia of Genes and Genomes, through performing over-representation and gene set enrichment analyses. A key feature is that clusterProfiler allows users to choose from various graphical outputs to visualize results, enhancing interpretability. This protocol describes innovative ways in which clusterProfiler has been used for integrating metabolomics and metagenomics analyses, identifying and characterizing transcription factors under stress conditions, and annotating cells in single-cell studies. In all cases, the computational steps can be completed within ~2 min. clusterProfiler is released through the Bioconductor project and can be accessed via https://bioconductor.org/packages/clusterProfiler/.
- 17 July 2024
- Published by Springer Nature in Nature Protocols
- Vol. 19 (11) , 3292-3320
Top Cited PapersUsing clusterProfiler to characterize multiomics data
With the advent of multiomics, software capable of multidimensional enrichment analysis has become increasingly crucial for uncovering gene set variations in biological processes and disease pathways. This is essential for elucidating disease mechanisms and identifying potential therapeutic targets. clusterProfiler stands out for its comprehensive utilization of databases and advanced visualization features. Importantly, clusterProfiler supports various biological knowledge, including Gene Ontology and Kyoto Encyclopedia of Genes and Genomes, through performing over-representation and gene set enrichment analyses. A key feature is that clusterProfiler allows users to choose from various graphical outputs to visualize results, enhancing interpretability. This protocol describes innovative ways in which clusterProfiler has been used for integrating metabolomics and metagenomics analyses, identifying and characterizing transcription factors under stress conditions, and annotating cells in single-cell studies. In all cases, the computational steps can be completed within ~2 min. clusterProfiler is released through the Bioconductor project and can be accessed via https://bioconductor.org/packages/clusterProfiler/.
- Open Access
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characterize anisotropic areas induced by the cone-casting procedure. This paper introduces a Ripmap-Encoded Platonic Solid representation to precisely and efficiently featurize 3D anisotropic areas, achieving high-fidelity anti-aliased renderings. Central to our approach are two key components: Platonic Solid Projection and Ripmap encoding. The Platonic Solid Projection factorizes the 3D space onto the unparalleled faces of a certain Platonic solid, such that the anisotropic 3D areas can be projected onto planes with distinguishable characterization. Meanwhile, each face of the Platonic solid is encoded by the Ripmap encoding, which is constructed by anisotropically pre-filtering a learnable feature grid, to enable featurzing the projected anisotropic areas both precisely and efficiently by the anisotropic area-sampling. Extensive experiments on both well-established synthetic datasets and a newly captured real-world dataset demonstrate that our Rip-NeRF attains state-of-the-art rendering quality, particularly excelling in the fine details of repetitive structures and textures, while maintaining relatively swift training times, as shown in Fig. 1. The source code and data for this paper are at https://github.com/JunchenLiu77/Rip-NeRF.
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessRip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characterize anisotropic areas induced by the cone-casting procedure. This paper introduces a Ripmap-Encoded Platonic Solid representation to precisely and efficiently featurize 3D anisotropic areas, achieving high-fidelity anti-aliased renderings. Central to our approach are two key components: Platonic Solid Projection and Ripmap encoding. The Platonic Solid Projection factorizes the 3D space onto the unparalleled faces of a certain Platonic solid, such that the anisotropic 3D areas can be projected onto planes with distinguishable characterization. Meanwhile, each face of the Platonic solid is encoded by the Ripmap encoding, which is constructed by anisotropically pre-filtering a learnable feature grid, to enable featurzing the projected anisotropic areas both precisely and efficiently by the anisotropic area-sampling. Extensive experiments on both well-established synthetic datasets and a newly captured real-world dataset demonstrate that our Rip-NeRF attains state-of-the-art rendering quality, particularly excelling in the fine details of repetitive structures and textures, while maintaining relatively swift training times, as shown in Fig. 1. The source code and data for this paper are at https://github.com/JunchenLiu77/Rip-NeRF.
- Open Access
- 19 April 2024
- Published by Elsevier in The Innovation
- Vol. 5 (3) , 100627
Encoding biological metaverse: Advancements and challenges in neural fields from macroscopic to microscopic
- 19 April 2024
- Published by Elsevier in The Innovation
- Vol. 5 (3) , 100627
Open AccessEncoding biological metaverse: Advancements and challenges in neural fields from macroscopic to microscopic
- Open Access
- 22 January 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (2)
Deqformer: high-definition and scalable deep learning probe design method
Target enrichment sequencing techniques are gaining widespread use in the field of genomics, prized for their economic efficiency and swift processing times. However, their success depends on the performance of probes and the evenness of sequencing depth among each probe. To accurately predict probe coverage depth, a model called Deqformer is proposed in this study. Deqformer utilizes the oligonucleotides sequence of each probe, drawing inspiration from Watson–Crick base pairing and incorporating two BERT encoders to capture the underlying information from the forward and reverse probe strands, respectively. The encoded data are combined with a feed-forward network to make precise predictions of sequencing depth. The performance of Deqformer is evaluated on four different datasets: SNP panel with 38 200 probes, lncRNA panel with 2000 probes, synthetic panel with 5899 probes and HD-Marker panel for Yesso scallop with 11 000 probes. The SNP and synthetic panels achieve impressive factor 3 of accuracy (F3acc) of 96.24% and 99.66% in 5-fold cross-validation. F3acc rates of over 87.33% and 72.56% are obtained when training on the SNP panel and evaluating performance on the lncRNA and HD-Marker datasets, respectively. Our analysis reveals that Deqformer effectively captures hybridization patterns, making it robust for accurate predictions in various scenarios. Deqformer leads to a novel perspective for probe design pipeline, aiming to enhance efficiency and effectiveness in probe design tasks.
- 22 January 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (2)
Open AccessDeqformer: high-definition and scalable deep learning probe design method
Target enrichment sequencing techniques are gaining widespread use in the field of genomics, prized for their economic efficiency and swift processing times. However, their success depends on the performance of probes and the evenness of sequencing depth among each probe. To accurately predict probe coverage depth, a model called Deqformer is proposed in this study. Deqformer utilizes the oligonucleotides sequence of each probe, drawing inspiration from Watson–Crick base pairing and incorporating two BERT encoders to capture the underlying information from the forward and reverse probe strands, respectively. The encoded data are combined with a feed-forward network to make precise predictions of sequencing depth. The performance of Deqformer is evaluated on four different datasets: SNP panel with 38 200 probes, lncRNA panel with 2000 probes, synthetic panel with 5899 probes and HD-Marker panel for Yesso scallop with 11 000 probes. The SNP and synthetic panels achieve impressive factor 3 of accuracy (F3acc) of 96.24% and 99.66% in 5-fold cross-validation. F3acc rates of over 87.33% and 72.56% are obtained when training on the SNP panel and evaluating performance on the lncRNA and HD-Marker datasets, respectively. Our analysis reveals that Deqformer effectively captures hybridization patterns, making it robust for accurate predictions in various scenarios. Deqformer leads to a novel perspective for probe design pipeline, aiming to enhance efficiency and effectiveness in probe design tasks.