Shuhui Liu

Dr. Shuhui Liu

Northwestern Polytechnical University, Xi'an, China
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2021 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
YZYupei Zhang
Yupei Zhang
RARui An
Rui An
SLShuhui Liu
Shuhui Liu
JCJiaqi Cui
Jiaqi Cui
XSXuequn Shang
Xuequn Shang
Predicting and understanding student learning performance has been a long-standing task in learning science, which can benefit personalized teaching and learning. This study shows that the progress towards this task can be accelerated by using learning record data to feed a deep learning model that considers the intrinsic course association and the structured features. We proposed a multi-source sparse attention convolutional neural network (MsaCNN) to predict the course grades in a general formulation. MsaCNN adopts multi-scale convolution kernels on student grade records to capture structured features, a global attention strategy to discover the relationship between courses, and multiple input-heads to integrate multi-source features. All achieved features are then poured into a softmax classifier towards an end-to-end supervised deep learning model. Conducting insights into higher education on real-world university datasets, the results show that MsaCNN achieves better performance than traditional methods and delivers an interpretation of student performance by virtue of the resulted course relationships. Inspired by this interpretation, we created an association map for all mentioned courses, followed by evaluating the map with a questionnaire survey. This study provides computer-aided system tools and discovers the course-space map from the educational data, potentially facilitating the personalized learning progress.

27 October 2022 in Frontiers in Immunology
Verified
Journal Article
Open access
SLShuhui Liu
Shuhui Liu
RYRuiying Yin
Ruiying Yin
ZYZiwei Yang
Ziwei Yang
FWFeili Wei
Feili Wei
JHJianhua Hu
Jianhua Hu
Background: Rhubarb is an important traditional Chinese medicine, and rhein is one of its most important active ingredients. Studies have found that rhein can improve ulcerative colitis by regulating gut microbes, but there are few reports on its effects on liver diseases. Therefore, this study aims to investigate these effects and underlying mechanisms.Methods: Mice were given rhein (100 mg/kg), with both a normal control group and a model group receiving the same amount of normal saline for one week. Acute liver injury was induced in mice by intraperitoneal injection of D-GalN (800 mg/kg)/LPS (10 ug/kg). Samples (blood, liver, and stool) were then collected and assessed for histological lesions and used for 16S rRNA gene sequencing, high-performance liquid chromatography-mass spectrometry (LC-MS) and RNA-seq analysis.Results: The levels of ALT and AST in the Model group were abnormal higher compared to the normal control group, and the levels of ALT and AST were significantly relieved in the rhein group. Hepatic HE staining showed that the degree of liver injury in the rhein group was lighter than that in the model group, and microbiological results showed that norank_o:Clostridia_UCG-014, Lachnoclostridium, and Roseburia were more abundant in the model group compared to the normal control group. Notably, the rhein treatment group showed reshaped disturbance of intestinal microbial community by D-GalN/LPS and these mice also had higher levels of Verrucomicrobia, Akkermansiaceae and Bacteroidetes. Additionally, There were multiple metabolites that were significantly different between the normal control group and the model group, such as L-α-amino acid, ofloxacin-N-oxide, 1-hydroxy-1,3-diphenylpropan-2-one,and L-4-hydroxyglutamate semialdehyde, but that returned to normal levels after rhein treatment. The gene expression level in the model group also changed significantly, various genes such as Cxcl2, S100a9, Tnf, Ereg, and IL-10 were up-regulated, while Mfsd2a and Bhlhe41 were down-regulated, which were recovered after rhein treatment.Conclusion: Overall, our results show that rhein alleviated D-GalN/LPS-induced acute liver injury in mice. It may help modulate gut microbiota in mice, thereby changing metabolism in the intestine. Meanwhile, rhein also may help regulate genes expression level to alleviate D-GalN/LPS-induced acute liver injury.

1 October 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YZYupei Zhang
Yupei Zhang
SWShuangshuang Wei
Shuangshuang Wei
SLShuhui Liu
Shuhui Liu
YWYifei Wang
Yifei Wang
YXYunan Xu
Yunan Xu
XSXuequn Shang
Xuequn Shang

12 July 2022 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
YZYupei Zhang
Yupei Zhang
SLShuhui Liu
Shuhui Liu
XQXiran Qu
Xiran Qu
XSXuequn Shang
Xuequn Shang

1 November 2017
Verified
Conference Paper
Closed access
YGYang Guo
Yang Guo
SLShuhui Liu
Shuhui Liu
ZLZhanhuai Li
Zhanhuai Li
XSXuequn Shang
Xuequn Shang
The classification of cancer subtypes is of great importance in cancer disease diagnosis and therapy. Many supervised learning methods have been applied to classification of cancer subtypes in the past few years, especially of deep learning based methods. Recently, a deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees, and it has been proved that deep forest model has competitive or even better performance than deep neural networks. However, the original deep forest may face under-fitting and ensemble diversity problems when dealing with small sample size, and high-dimension biology data. It is important to improve the deep forest model to work better on small-scale biology data. In this paper, we propose a deep learning model to follow the mission of cancer subtype classification on small-scale biology data sets, which can be viewed as modification of original deep forest model. Our model distinguishes from the original deep forest model with two main contributions: First, a named multi-class-scanning method is proposed to train multiple simple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representations learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests of representations learning, thus to propagate the benefits of discriminative features among layers to improve the overall classification performance. Systematical experiments on both microarray and RNA-seq data sets demonstrate that our method consistently outperforms the most state-of-the-art classification methods in application of cancer subtype classifications.

8 May 2021 in Briefings in Bioinformatics
Verified
Journal Article
Closed access
PDF file
SLShuhui Liu
Shuhui Liu
YZYupei Zhang
Yupei Zhang
XSXuequn Shang
Xuequn Shang
ZZZhaolei Zhang
Zhaolei Zhang
Different subtypes of the same cancer often show distinct genomic signatures and require targeted treatments. The differences at the cellular and molecular levels of tumor microenvironment in different cancer subtypes have significant effects on tumor pathogenesis and prognostic outcomes. Although there have been significant researches on the prognostic association of tumor infiltrating lymphocytes in selected histological subtypes, few investigations have systemically reported the prognostic impacts of immune cells in molecular subtypes, as quantified by machine learning approaches on multi-omics datasets. This paper describes a new computational framework, ProTICS, to quantify the differences in the proportion of immune cells in tumor microenvironment and estimate their prognostic effects in different subtypes. First, we stratified patients into molecular subtypes based on gene expression and methylation profiles by applying nonnegative tensor factorization technique. Then we quantified the proportion of cell types in each specimen using an mRNA-based deconvolution method. For tumors in each subtype, we estimated the prognostic effects of immune cell types by applying Cox proportional hazard regression. At the molecular level, we also predicted the prognosis of signature genes for each subtype. Finally, we benchmarked the performance of ProTICS on three TCGA datasets and another independent METABRIC dataset. ProTICS successfully stratified tumors into different molecular subtypes manifested by distinct overall survival. Furthermore, the different immune cell types showed distinct prognostic patterns with respect to molecular subtypes. This study provides new insights into the prognostic association between immune cells and molecular subtypes, showing the utility of immune cells as potential prognostic markers. Availability: R code is available at https://github.com/liu-shuhui/ProTICS