Dongxiao Zhu

Dongxiao Zhu

Auto-generated profile, based on publicly available information

Dongxiao Zhu

Wayne State University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
24 December 2012 in Nucleic Acids Research
Verified
Journal Article
Open access
PDF file
TJThair Judeh
Thair Judeh
CJCole Johnson
Cole Johnson
AKAnuj Kumar
Anuj Kumar
DZDongxiao Zhu
Dongxiao Zhu
To mine gene expression data sets effectively, analysis frameworks need to incorporate methods that identify intergenic relationships within enriched biologically relevant subpathways. For this purpose, we developed the Topology Enrichment Analysis frameworK (TEAK). TEAK employs a novel in-house algorithm and a tailor-made Clique Percolation Method to extract linear and nonlinear KEGG subpathways, respectively. TEAK scores subpathways using the Bayesian Information Criterion for context specific data and the Kullback-Leibler divergence for case–control data. In this article, we utilized TEAK with experimental studies to analyze microarray data sets profiling stress responses in the model eukaryote Saccharomyces cerevisiae. Using a public microarray data set, we identified via TEAK linear sphingolipid metabolic subpathways activated during the yeast response to nitrogen stress, and phenotypic analyses of the corresponding deletion strains indicated previously unreported fitness defects for the dpl1Δ and lag1Δ mutants under conditions of nitrogen limitation. In addition, we studied the yeast filamentous response to nitrogen stress by profiling changes in transcript levels upon deletion of two key filamentous growth transcription factors, FLO8 and MSS11. Via TEAK we identified a nonlinear glycerophospholipid metabolism subpathway involving the SLC1 gene, which we found via mutational analysis to be required for yeast filamentous growth.

1 July 2020
Verified
Conference Paper
Open access
DPDeng Pan
Deng Pan
XLXiangrui Li
Xiangrui Li
XLXin Li
Xin Li
DZDongxiao Zhu
Dongxiao Zhu
Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainable recommendation has attracted much attention from research community. However, trade-off exists between explainability and performance of the recommendation where metadata is often needed to alleviate the dilemma. We present a novel feature mapping approach that maps the uninterpretable general features onto the interpretable aspect features, achieving both satisfactory accuracy and explainability in the recommendations by simultaneous minimization of rating prediction loss and interpretation loss. To evaluate the explainability, we propose two new evaluation metrics specifically designed for aspect-level explanation using surrogate ground truth. Experimental results demonstrate a strong performance in both recommendation and explaining explanation, eliminating the need for metadata. Code is available from https://github.com/pd90506/AMCF.

2 July 2013 in PLOS ONE
Verified
Journal Article
Open access
PDF file
NDNan Deng
Nan Deng
CSCecilia G. Sanchez
Cecilia G. Sanchez
JLJoseph Lasky
Joseph Lasky
DZDongxiao Zhu
Dongxiao Zhu
Idiopathic pulmonary fibrosis (IPF) is an interstitial lung disease of unknown cause that lacks a proven therapy for altering its high mortality rate. Microarrays have been employed to investigate the pathogenesis of IPF, but are presented mostly at the gene-expression level due to technologic limitations. In as much as, alternative RNA splicing isoforms are increasingly identified as potential regulators of human diseases, including IPF, we propose a new approach with the capacity to detect splicing variants using RNA-seq data. We conducted a joint analysis of differential expression and differential splicing on annotated human genes and isoforms, and identified 122 non-differentially expressed genes with a high degree of “switch” between major and minor isoforms. Three cases with variant mechanisms for alternative splicing were validated using qRT-PCR, among the group of genes in which expression was not significantly changed at the gene level. We also identified 35 novel transcripts that were unique to the fibrotic lungs using exon-exon junction evidence, and selected a representative for qRT-PCR validation. The results of our study are likely to provide new insight into the pathogenesis of pulmonary fibrosis and may eventuate in new treatment targets.

11 May 2024
Verified
Conference Paper
Open access
WZWenqi Zheng
Wenqi Zheng
EWEmma Walquist
Emma Walquist
IDIsha Datey
Isha Datey
XZXiangyu Zhou
Xiangyu Zhou
KBKelly Berishaj
Kelly Berishaj
DZDouglas Zytko
Douglas Zytko
A majority of people experience trauma, spurring calls to incorporate trauma-informed approaches (TIA) from public health and social work into technology design. While technologies touted as trauma-informed are starting to propagate the literature, there persists a gap in knowledge around how design teams apply TIA and qualify their technology as adhering to trauma-informed principles. We address this through a 12-month development project with trauma and sexual violence experts to produce Ube, a data donation platform for collecting online dating sexual consent data to improve sexual risk detection AI. Through analysis of design documentation we retrospectively articulate a trauma-informed design process that evolved through the course of Ube’s development, comprising three elements for integrating trauma-informed principles: design goals that adapt the definition of TIA to the application domain, design activities that map to trauma-informed principles, and consequent design choices. We conclude with methodological recommendations to improve trauma-informed design processes.

1 October 2023
Verified
Book Chapter
Closed access
PDF file
CLChengyin Li
Chengyin Li
YQYao Qiang
Yao Qiang
RSRafi Ibn Sultan
Rafi Ibn Sultan
HBHassan Bagher-Ebadian
Hassan Bagher-Ebadian
PKPrashant Khanduri
Prashant Khanduri
DZDongxiao Zhu
Dongxiao Zhu

27 March 2025 in JMIR AI
Verified
Journal Article
Open access
MRMohammad Amin Roshani
Mohammad Amin Roshani
XZXiangyu Zhou
Xiangyu Zhou
YQYao Qiang
Yao Qiang
SSSrinivasan Suresh
Srinivasan Suresh
SHSteven D. Hicks
Steven D. Hicks
DZDongxiao Zhu
Dongxiao Zhu
Background: Large language models (LLMs) have demonstrated powerful capabilities in natural language tasks and are increasingly being integrated into health care for tasks like disease risk assessment. Traditional machine learning methods rely on structured data and coding, limiting their flexibility in dynamic clinical environments. This study presents a novel approach to disease risk assessment using generative LLMs through conversational artificial intelligence (AI), eliminating the need for programming. Objective: This study evaluates the use of pretrained generative LLMs, including LLaMA2-7b and Flan-T5-xl, for COVID-19 severity prediction with the goal of enabling a real-time, no-code, risk assessment solution through chatbot-based, question-answering interactions. To contextualize their performance, we compare LLMs with traditional machine learning classifiers, such as logistic regression, extreme gradient boosting (XGBoost), and random forest, which rely on tabular data. Methods: We fine-tuned LLMs using few-shot natural language examples from a dataset of 393 pediatric patients, developing a mobile app that integrates these models to provide real-time, no-code, COVID-19 severity risk assessment through clinician-patient interaction. The LLMs were compared with traditional classifiers across different experimental settings, using the area under the curve (AUC) as the primary evaluation metric. Feature importance derived from LLM attention layers was also analyzed to enhance interpretability. Results: Generative LLMs demonstrated strong performance in low-data settings. In zero-shot scenarios, the T0-3b-T model achieved an AUC of 0.75, while other LLMs, such as T0pp(8bit)-T and Flan-T5-xl-T, reached 0.67 and 0.69, respectively. At 2-shot settings, logistic regression and random forest achieved an AUC of 0.57, while Flan-T5-xl-T and T0-3b-T obtained 0.69 and 0.65, respectively. By 32-shot settings, Flan-T5-xl-T reached 0.70, similar to logistic regression (0.69) and random forest (0.68), while XGBoost improved to 0.65. These results illustrate the differences in how generative LLMs and traditional models handle the increasing data availability. LLMs perform well in low-data scenarios, whereas traditional models rely more on structured tabular data and labeled training examples. Furthermore, the mobile app provides real-time, COVID-19 severity assessments and personalized insights through attention-based feature importance, adding value to the clinical interpretation of the results. Conclusions: Generative LLMs provide a robust alternative to traditional classifiers, particularly in scenarios with limited labeled data. Their ability to handle unstructured inputs and deliver personalized, real-time assessments without coding makes them highly adaptable to clinical settings. This study underscores the potential of LLM-powered conversational artificial intelligence (AI) in health care and encourages further exploration of its use for real-time, disease risk assessment and decision-making support.