Bowen Liu
Bowen Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chengsheng Zhang
Center for Molecular Diagnosis and Precision Medicine, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University
1 shared publication - Hao Liang
Xi'an Jiaotong University
1 shared publication - Jiadong Lin
Xi'an Jiaotong University
1 shared publication - Jianyong Sun
Xi'an Jiaotong University, Xi'an, China
1 shared publication - Kai Ye
MOE Key Lab for Intelligent Networks & Networks Security, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, China
1 shared publication - Kenta Nakai
Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
1 shared publication
Latest Publications
- Open Access
- 27 March 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (3)
HyGAnno: hybrid graph neural network–based cell type annotation for single-cell ATAC sequencing data
Reliable cell type annotations are crucial for investigating cellular heterogeneity in single-cell omics data. Although various computational approaches have been proposed for single-cell RNA sequencing (scRNA-seq) annotation, high-quality cell labels are still lacking in single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq) data, because of extreme sparsity and inconsistent chromatin accessibility between datasets. Here, we present a novel automated cell annotation method that transfers cell type information from a well-labeled scRNA-seq reference to an unlabeled scATAC-seq target, via a parallel graph neural network, in a semi-supervised manner. Unlike existing methods that utilize only gene expression or gene activity features, HyGAnno leverages genome-wide accessibility peak features to facilitate the training process. In addition, HyGAnno reconstructs a reference–target cell graph to detect cells with low prediction reliability, according to their specific graph connectivity patterns. HyGAnno was assessed across various datasets, showcasing its strengths in precise cell annotation, generating interpretable cell embeddings, robustness to noisy reference data and adaptability to tumor tissues.
- 27 March 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (3)
Open AccessHyGAnno: hybrid graph neural network–based cell type annotation for single-cell ATAC sequencing data
Reliable cell type annotations are crucial for investigating cellular heterogeneity in single-cell omics data. Although various computational approaches have been proposed for single-cell RNA sequencing (scRNA-seq) annotation, high-quality cell labels are still lacking in single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq) data, because of extreme sparsity and inconsistent chromatin accessibility between datasets. Here, we present a novel automated cell annotation method that transfers cell type information from a well-labeled scRNA-seq reference to an unlabeled scATAC-seq target, via a parallel graph neural network, in a semi-supervised manner. Unlike existing methods that utilize only gene expression or gene activity features, HyGAnno leverages genome-wide accessibility peak features to facilitate the training process. In addition, HyGAnno reconstructs a reference–target cell graph to detect cells with low prediction reliability, according to their specific graph connectivity patterns. HyGAnno was assessed across various datasets, showcasing its strengths in precise cell annotation, generating interpretable cell embeddings, robustness to noisy reference data and adaptability to tumor tissues.
- Open Access
- 9 January 2020
- Published by Cold Spring Harbor Laboratory in bioRxiv
MSIsensor-pro: fast, accurate and matched-normal-sample-free detection of microsatellite instability
We developed MSIsensor-pro (https://github.com/xjtu-omics/msisensor-pro), an open-source single sample microsatellite instability (MSI) scoring method for research and clinical applications. MSIsensor-pro introduces a multinomial distribution model to quantify polymerase slippages for each tumor sample and a discriminative sites selection method to enable MSI detection without matched normal samples. For samples of various sequencing depths and tumor purities, MSIsensor-pro significantly outperformed the current leading methods in terms of both accuracy and computational cost.
- 9 January 2020
- Published by Cold Spring Harbor Laboratory in bioRxiv
Open AccessMSIsensor-pro: fast, accurate and matched-normal-sample-free detection of microsatellite instability
We developed MSIsensor-pro (https://github.com/xjtu-omics/msisensor-pro), an open-source single sample microsatellite instability (MSI) scoring method for research and clinical applications. MSIsensor-pro introduces a multinomial distribution model to quantify polymerase slippages for each tumor sample and a discriminative sites selection method to enable MSI detection without matched normal samples. For samples of various sequencing depths and tumor purities, MSIsensor-pro significantly outperformed the current leading methods in terms of both accuracy and computational cost.