Xuhong Zhang

Xuhong Zhang

Auto-generated profile, based on publicly available information

Xuhong Zhang

Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington Department of Computer Science Bloomington, IN 47405

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 January 2025 in Computational and Structural Biotechnology Journal
Verified
Journal Article
Open access
ABAishwarya Budhkar
Aishwarya Budhkar
QSQianqian Song
Qianqian Song
JSJing Su
Jing Su
XZXuhong Zhang
Xuhong Zhang
The widespread adoption of Artificial Intelligence (AI) and machine learning (ML) tools across various domains has showcased their remarkable capabilities and performance. Black-box AI models raise concerns about decision transparency and user confidence. Therefore, explainable AI (XAI) and explainability techniques have rapidly emerged in recent years. This paper aims to review existing works on explainability techniques in bioinformatics, with a particular focus on omics and imaging. We seek to analyze the growing demand for XAI in bioinformatics, identify current XAI approaches, and highlight their limitations. Our survey emphasizes the specific needs of both bioinformatics applications and users when developing XAI methods and we particularly focus on omics and imaging data. Our analysis reveals a significant demand for XAI in bioinformatics, driven by the need for transparency and user confidence in decision-making processes. At the end of the survey, we provided practical guidelines for system developers.

25 July 2024 in Briefings in Bioinformatics
Verified
Journal Article
Open access
PDF file
ABAishwarya Budhkar
Aishwarya Budhkar
ZTZiyang Tang
Ziyang Tang
XLXiang Liu
Xiang Liu
XZXuhong Zhang
Xuhong Zhang
JSJing Su
Jing Su
QSQianqian Song
Qianqian Song
Recent advancements in spatial imaging technologies have revolutionized the acquisition of high-resolution multichannel images, gene expressions, and spatial locations at the single-cell level. Our study introduces xSiGra, an interpretable graph-based AI model, designed to elucidate interpretable features of identified spatial cell types, by harnessing multimodal features from spatial imaging technologies. By constructing a spatial cellular graph with immunohistology images and gene expression as node attributes, xSiGra employs hybrid graph transformer models to delineate spatial cell types. Additionally, xSiGra integrates a novel variant of gradient-weighted class activation mapping component to uncover interpretable features, including pivotal genes and cells for various cell types, thereby facilitating deeper biological insights from spatial data. Through rigorous benchmarking against existing methods, xSiGra demonstrates superior performance across diverse spatial imaging datasets. Application of xSiGra on a lung tumor slice unveils the importance score of cells, illustrating that cellular activity is not solely determined by itself but also impacted by neighboring cells. Moreover, leveraging the identified interpretable genes, xSiGra reveals endothelial cell subset interacting with tumor cells, indicating its heterogeneous underlying mechanisms within complex cellular interactions.

6 January 2020 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
JPJennifer D Portz
Jennifer D Portz
KEKira Elsbernd
Kira Elsbernd
EPEvan Plys
Evan Plys
KFKelsey Lynett Ford
Kelsey Lynett Ford
XZXuhong Zhang
Xuhong Zhang
SBSheana Bull
Sheana Bull
Background: Mobile health (mHealth) provides a unique modality for improving access to and awareness of palliative care among patients, families, and caregivers from diverse backgrounds. Some mHealth palliative care apps exist, both commercially available and established by academic researchers. However, the elements of family support and family caregiving tools offered by these early apps is unknown. Objective: The objective of this scoping review was to use social convoy theory to describe the inclusion and functionality of family, social relationships, and caregivers in palliative care mobile apps. Methods: Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Review guidelines, a systematic search of palliative care mHealth included (1) research-based mobile apps identified from academic searches published between January 1, 2010, and March 31, 2019 and (2) commercially available apps for app stores in April 2019. Two reviewers independently assessed abstracts, app titles, and descriptions against the inclusion and exclusion criteria. Abstracted data covered app name, research team or developer, palliative care element, target audience, and features for family support and caregiving functionality as defined by social convoy theory. Results: Overall, 10 articles describing 9 individual research-based apps and 22 commercially available apps were identified. Commercially available apps were most commonly designed for both patients and social convoys, whereas the majority of research apps were designed for patient use only. Conclusions: Results suggest there is an emerging presence of apps for patients and social convoys receiving palliative care; however, there are many needs for developers and researchers to address in the future. Although palliative care mHealth is a growing field, additional research is needed for apps that embrace a team approach to information sharing, target family- and caregiver-specific issues, promote access to palliative care, and are comprehensive of palliative needs.

16 September 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
MIM Pilar Ingle
M Pilar Ingle
CVCristina Valdovinos
Cristina Valdovinos
KFKelsey L Ford
Kelsey L Ford
Shuo ZhouShuo Zhou
Shuo Zhou
SBSheana Bull
Sheana Bull
JPJennifer Portz
Jennifer Portz
Background: Although patient portals are widely used for health promotion, little is known about the use of palliative care and end-of-life (PCEOL) portal tools available for patients and caregivers. Objective: This study aims to identify and assess the user perspectives of PCEOL portal tools available to patients and caregivers described and evaluated in the literature. Methods: We performed a scoping review of the academic literature directed by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) extension for Scoping Review and searched three databases. Sources were included if they reported the development or testing of a feature, resource, tool, or intervention; focused on at least one PCEOL domain defined by the National Coalition for Hospice and Palliative Care; targeted adults with serious illness or caregivers; and were offered via a patient portal tethered to an electronic medical record. We independently screened the titles and abstracts (n=796) for eligibility. Full-text (84/796, 10.6%) sources were reviewed. We abstracted descriptions of the portal tool name, content, targeted population, and reported user acceptability for each tool from included sources (n=19). Results: In total, 19 articles describing 12 tools were included, addressing the following PCEOL domains: ethical or legal (n=5), physical (n=5), and psychological or psychiatric (n=2). No tools for bereavement or hospice care were identified. Studies have reported high acceptability of tools among users; however, few sources commented on usability among older adults. Conclusions: PCEOL patient portal tools are understudied. As medical care increasingly moves toward virtual platforms, future research should investigate the usability and acceptability of PCEOL patient portal resources and evaluate their impact on health outcomes.

21 October 2023
Verified
Conference Paper
Open access
YWYang Wu
Yang Wu
XLXurui Li
Xurui Li
XZXuhong Zhang
Xuhong Zhang
YKYangyang Kang
Yangyang Kang
CSChanglong Sun
Changlong Sun
XLXiaozhong Liu
Xiaozhong Liu

6 October 2025 in bioRxiv
Verified
Preprint
Open access
ABAishwarya Budhkar
Aishwarya Budhkar
JHJuhyung Ha
Juhyung Ha
QSQianqian Song
Qianqian Song
JSJing Su
Jing Su
XZXuhong Zhang
Xuhong Zhang
Integrating transcriptome-wide single-cell gene expression data with spatial context significantly enhances our understanding of tissue biology, cellular interactions, and disease progression. Although single-cell RNA sequencing (scRNA-seq) provides high-resolution gene expression data, it lacks crucial spatial context, whereas spatial transcriptomics techniques offer spatial resolution but are limited in the transcriptomic coverage. To address these limitations, integrating scRNA-seq and spatial transcriptomics data is essential. We introduce SpaGene, a novel deep learning framework designed to integrate scRNA-seq data and spatial transcriptomics data. SpaGene consists of two encoder-decoder pairs combined with two translators and two discriminators to effectively impute missing gene expressions within spatial transcriptomics datasets. We benchmarked SpaGene against existing state-of-the-art methods across diverse datasets. Across the datasets, SpaGene achieved an average 33% higher Pearson correlation coefficient (PCC), 21% higher Structural similarity index (SSIM), and 6.6% lower Root mean squared error (RMSE) compared to the existing approaches, highlighting its capability to reliably impute missing genes and provide comprehensive transcriptomics profiles. Application of our model to lung tumor tissue revealed immune cell enrichment at tumor boundaries, restricted myeloid cell trafficking in adjacent normal regions, and microenvironmental-driven pathways linked to immune neighborhoods. These results provide novel insight into immune exclusion and tumor-immune interactions that drive tumor progression, highlighting potential avenues for therapeutic development. Thus, SpaGene extends the power of spatial transcriptomics by delivering spatially resolved, enhanced transcriptome data that enable deeper biological understanding.