Browsing by Author "Liu, Bingqiang"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Define and visualize pathological architectures of human tissues from spatially resolved transcriptomics using deep learning
    (Elsevier, 2022-08-24) Chang, Yuzhou; He, Fei; Wang, Juexin; Chen, Shuo; Li, Jingyi; Liu, Jixin; Yu, Yang; Su, Li; Ma, Anjun; Allen, Carter; Lin, Yu; Sun, Shaoli; Liu, Bingqiang; Otero, José Javier; Chung, Dongjun; Fu, Hongjun; Li, Zihai; Xu, Dong; Ma, Qin; Medical and Molecular Genetics, School of Medicine
    Spatially resolved transcriptomics provides a new way to define spatial contexts and understand the pathogenesis of complex human diseases. Although some computational frameworks can characterize spatial context via various clustering methods, the detailed spatial architectures and functional zonation often cannot be revealed and localized due to the limited capacities of associating spatial information. We present RESEPT, a deep-learning framework for characterizing and visualizing tissue architecture from spatially resolved transcriptomics. Given inputs such as gene expression or RNA velocity, RESEPT learns a three-dimensional embedding with a spatial retained graph neural network from spatial transcriptomics. The embedding is then visualized by mapping into color channels in an RGB image and segmented with a supervised convolutional neural network model. Based on a benchmark of 10x Genomics Visium spatial transcriptomics datasets on the human and mouse cortex, RESEPT infers and visualizes the tissue architecture accurately. It is noteworthy that, for the in-house AD samples, RESEPT can localize cortex layers and cell types based on pre-defined region- or cell-type-enriched genes and furthermore provide critical insights into the identification of amyloid-beta plaques in Alzheimer's disease. Interestingly, in a glioblastoma sample analysis, RESEPT distinguishes tumor-enriched, non-tumor, and regions of neuropil with infiltrating tumor cells in support of clinical and prognostic cancer applications.
  • Thumbnail Image
    Item
    IRIS3: integrated cell-type-specific regulon inference server from single-cell RNA-Seq
    (Oxford, 2020-05-18) Ma, Anjun; Wang, Cankun; Chang, Yuzhou; Brennan, Faith H; McDermaid, Adam; Liu, Bingqiang; Zhang, Chi; Popovich, Phillip G; Ma, Qin; Medical and Molecular Genetics, School of Medicine
    group of genes controlled as a unit, usually by the same repressor or activator gene, is known as a regulon. The ability to identify active regulons within a specific cell type, i.e., cell-type-specific regulons (CTSR), provides an extraordinary opportunity to pinpoint crucial regulators and target genes responsible for complex diseases. However, the identification of CTSRs from single-cell RNA-Seq (scRNA-Seq) data is computationally challenging. We introduce IRIS3, the first-of-its-kind web server for CTSR inference from scRNA-Seq data for human and mouse. IRIS3 is an easy-to-use server empowered by over 20 functionalities to support comprehensive interpretations and graphical visualizations of identified CTSRs. CTSR data can be used to reliably characterize and distinguish the corresponding cell type from others and can be combined with other computational or experimental analyses for biomedical studies. CTSRs can, therefore, aid in the discovery of major regulatory mechanisms and allow reliable constructions of global transcriptional regulation networks encoded in a specific cell type. The broader impact of IRIS3 includes, but is not limited to, investigation of complex diseases hierarchies and heterogeneity, causal gene regulatory network construction, and drug development.
  • Thumbnail Image
    Item
    Prediction of regulatory motifs from human Chip-sequencing data using a deep learning framework
    (Oxford University Press, 2019-09-05) Yang, Jinyu; Ma, Anjun; Hoppe, Adam D.; Wang, Cankun; Li, Yang; Zhang, Chi; Wang, Yan; Liu, Bingqiang; Ma, Qin; Medical and Molecular Genetics, School of Medicine
    The identification of transcription factor binding sites and cis-regulatory motifs is a frontier whereupon the rules governing protein-DNA binding are being revealed. Here, we developed a new method (DEep Sequence and Shape mOtif or DESSO) for cis-regulatory motif prediction using deep neural networks and the binomial distribution model. DESSO outperformed existing tools, including DeepBind, in predicting motifs in 690 human ENCODE ChIP-sequencing datasets. Furthermore, the deep-learning framework of DESSO expanded motif discovery beyond the state-of-the-art by allowing the identification of known and new protein-protein-DNA tethering interactions in human transcription factors (TFs). Specifically, 61 putative tethering interactions were identified among the 100 TFs expressed in the K562 cell line. In this work, the power of DESSO was further expanded by integrating the detection of DNA shape features. We found that shape information has strong predictive power for TF-DNA binding and provides new putative shape motif information for human TFs. Thus, DESSO improves in the identification and structural analysis of TF binding sites, by integrating the complexities of DNA binding into a deep-learning framework.
  • Thumbnail Image
    Item
    QUBIC2: a novel and robust biclustering algorithm for analyses and interpretation of large-scale RNA-Seq data
    (Oxford, 2020) Xie, Juan; Ma, Anjun; Zhang, Yu; Liu, Bingqiang; Cao, Sha; Wang, Cankun; Xu, Jennifer; Zhang, Chi; Ma, Qin; Medical and Molecular Genetics, School of Medicine
    Motivation The biclustering of large-scale gene expression data holds promising potential for detecting condition-specific functional gene modules (i.e. biclusters). However, existing methods do not adequately address a comprehensive detection of all significant bicluster structures and have limited power when applied to expression data generated by RNA-Sequencing (RNA-Seq), especially single-cell RNA-Seq (scRNA-Seq) data, where massive zero and low expression values are observed. Results We present a new biclustering algorithm, QUalitative BIClustering algorithm Version 2 (QUBIC2), which is empowered by: (i) a novel left-truncated mixture of Gaussian model for an accurate assessment of multimodality in zero-enriched expression data, (ii) a fast and efficient dropouts-saving expansion strategy for functional gene modules optimization using information divergency and (iii) a rigorous statistical test for the significance of all the identified biclusters in any organism, including those without substantial functional annotations. QUBIC2 demonstrated considerably improved performance in detecting biclusters compared to other five widely used algorithms on various benchmark datasets from E.coli, Human and simulated data. QUBIC2 also showcased robust and superior performance on gene expression data generated by microarray, bulk RNA-Seq and scRNA-Seq.