About

Xiaojing Liao is an Associate Professor at the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. Her research interests include Security and Privacy. She teaches courses such as CS 463 (ECE 424) - Computer Security II and CS 562 - Advanced Topics in Security, Privacy, and Machine Learning. Her work focuses on issues related to security and privacy within computing systems, contributing to the academic and practical understanding of these critical areas in computer science.

Research topics

• Computer Science
• Data Mining
• Medicine
• Biology
• Internal medicine
• Oncology
• Database
• Data science
• World Wide Web

Selected publications

• Ensemble Learning-Based Quantitative Diagnosis of Battery Internal Short Circuit with Short-term Charging Segments

  Journal of Physics Conference Series · 2026-04-01

  articleOpen access

  Abstract Internal short circuit (ISC) of lithium-ion batteries can lead to rapid performance degradation and pose severe safety hazards, such as thermal runaway. Therefore, accurate diagnosis and quantification of ISC faults are crucial to ensuring the safety of battery systems. In this study, we propose an ensemble learning-based ISC quantitative diagnosis method using short-term charging segments. First, multi-dimensional physical and statistical features are extracted from short constant-current charging windows. Then the boosted decision tree ensemble method is employed to enhance accuracy and robustness of ISC severity evaluation. Furthermore, Shapley value analysis is employed to interpret the ensemble model and quantify the contribution of each feature to the ISC severity diagnosis. Experimental validation on a multi-cell dataset with various ISC resistance levels ranging from 6 Ω to 100 Ω demonstrates that the proposed method can accurately estimate the short-circuit resistance. This capability enables reliable and high-accuracy ISC diagnosis, thereby enhancing the safety of electric vehicles and energy storage systems.

  PublisherDOI

• Unsupervised Anomaly Detection in Ev Batteries Using Real-World Charging Data: A Multi-Scale Random Subspace Mapping Framework

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• The Glabridin from Huangqin Decoction Prevents the Development of Ulcerative Colitis into Colitis-Associated Colorectal Cancer by Modulating MMP1/MMP3 Activity

  International Immunopharmacology · 2024-05-27 · 11 citations

  articleOpen access

  BACKGROUND AND AIM: Huangqin decoction (HQD) is a Chinese medicine used to treat colitis and colorectal cancer (CRC). However, the specific compounds and mechanisms of HQD remain unclear despite its good curative clinical results. Through bioinformatics, network pharmacology, and experiments, this study aims to explore the progressive mechanisms of colitis-associated colorectal cancer (CAC) from ulcerative colitis (UC) while examining the protective effects of HQD and its compounds against this. METHODS: Bioinformatics was utilized to identify the hub genes between UC and CRC, and their clinical predictive significance, function, and expression were validated. Employing network pharmacology in combination with hub genes, key targets of HQD for preventing the development of UC into CAC were identified. Molecular docking and molecular dynamics (MD) were utilized to procure compounds that effectively bind to these targets and their transcription factors (TFs). Finally, the expression and mechanism of key targets were demonstrated in mice with UC or CAC. RESULTS: (1) Joint analysis of UC and CRC gene sets resulted in 14 hub genes, mainly related to extracellular matrix receptor binding, biological processes in the extracellular matrix, focal adhesion and neutrophil migration; (2) Network pharmacology results show HQD has 133 core targets for treating UC and CRC, acting on extracellular matrix, inflammatory bowel disease, chemical carcinogen receptor activation and other pathways; (3) The intersection of hub genes and core targets yielded two key targets, MMP1 and MMP3; (4) STAT3 is a shared TF of MMP1 and MMP3. (5) Molecular docking and MD verified that the dockings between Glabridin and STAT3/MMP1/MMP3 are stable and reliable; (6) In murine vivo experiments verified that Glabridin reduces inflammation, extracellular matrix degradation, and the occurrence of epithelial-mesenchymal transition to prevent UC transforming into CAC by inhibiting the phosphorylation of STAT3 and regulating the activity of MMP1/3.

  PublisherDOI

• Supercontinuum intrinsic fluorescence imaging heralds free view of living systems

  bioRxiv (Cold Spring Harbor Laboratory) · 2024-01-26 · 3 citations

  preprintOpen access

  Optimal imaging strategies remain underdeveloped to maximize information for fluorescence microscopy while minimizing the harm to fragile living systems. Taking hint from the supercontinuum generation in ultrafast laser physics, we generated supercontinuum fluorescence from untreated unlabeled live samples before nonlinear photodamage onset. Our imaging achieved high-content cell phenotyping and tissue histology, identified bovine embryo polarization, quantified aging-related stress across cell types and species, demystified embryogenesis before and after implantation, sensed drug cytotoxicity in real-time, scanned brain area for targeted patching, optimized machine learning to track small moving organisms, induced two-photon phototropism of leaf chloroplasts under two-photon photosynthesis, unraveled microscopic origin of autumn colors, and interrogated intestinal microbiome. The results enable a facility-type microscope to freely explore vital molecular biology across life sciences.

  PublisherOA PDFDOI

• [Mechanism of Huangqin Decoction in repairing intestinal barrier of ulcerative colitis by regulating tryptophan metabolism and activating AhR].

  PubMed · 2024-10-01 · 1 citations

  article

  This study aims to elucidate the mechanism of Huangqin Decoction(HQD) in treating ulcerative colitis(UC) by investigating the relationship between tryptophan metabolism and intestinal barriers. In the in vivo experiments, 3% dextran sulfate sodium(DSS) was used to induce a mouse model of acute colitis, with mesalazine as a positive control. The therapeutic effect of HQD on mice with UC was evaluated according to body weight, disease activity index(DAI), colon length, and pathological changes. Targeted metabolomics was used to detect the concentration of tryptophan and its metabolites in mouse feces. Western blot and RT-qPCR techniques were used to assess the expression levels of colonic aryl hydrocarbon receptor(AhR), myosin light chain kinase(MLCK), myo-sin light chain(MLC), and p-MLC. Serum FITC-dextran concentration, bacterial culture of mesenteric lymph nodes and spleen, as well as fluorescence probe in situ hybridization technique were used to evaluate intestinal epithelial permeability. Alcian blue and nuclear fast red staining, Western blot, and RT-qPCR techniques were used to detect the expression of mucin secreted by the mouse's intestinal epithelial goblet cells. Transmission electron microscopy was utilized to observe the connections of the mouse's intestinal epithelial cells. Immunofluorescence, Western blot, and RT-qPCR techniques were used to assess the expression of tight junction proteins in the mouse's intestinal epithelium. In the in vitro experiments, lipopolysaccharide(LPS) was used to induce intestinal epithelial barrier injury model in Caco2 cells, and AhR siRNA was used to further clarify the mechanism of HQD in activating AhR to improve intestinal barrier function. The results demonstrated that HQD effectively alleviated symptoms and pathological changes in the colon of DSS-induced mice with colitis. Treatment with HQD could regulate tryptophan metabolism in the feces of mice with colitis, activate AhR, and improve the intestinal epithelial barrier. Additionally, the results of the in vitro experiments confirmed that HQD could restore the expression of tight junction proteins in the intestinal epithelium of colitis cells by activating AhR to regulate the MLCK/p-MLC signaling pathway.

  PublisherDOI

• Intratumor Graph Neural Network of Tumor-Associated Collagen Signatures from Multiphoton Microscopy Empowers Prognosis of 995 Breast Cancer Patients

  2022-01-01

  article

  We perform cancer prognosis based on 8 collagen signatures obtained by sampling a histological section with multiphoton microscopy. The model with intratumor graph neural network (IGNN) significantly outperforms that without IGNN for breast cancer patients.

  PublisherDOI

• Intratumor graph neural network recovers hidden prognostic value of multi-biomarker spatial heterogeneity

  Nature Communications · 2022-07-22 · 37 citations

  articleOpen access

  Biomarkers are indispensable for precision medicine. However, focused single-biomarker development using human tissue has been complicated by sample spatial heterogeneity. To address this challenge, we tested a representation of primary tumor that synergistically integrated multiple in situ biomarkers of extracellular matrix from multiple sampling regions into an intratumor graph neural network. Surprisingly, the differential prognostic value of this computational model over its conventional non-graph counterpart approximated that of combined routine prognostic biomarkers (tumor size, nodal status, histologic grade, molecular subtype, etc.) for 995 breast cancer patients under a retrospective study. This large prognostic value, originated from implicit but interpretable regional interactions among the graphically integrated in situ biomarkers, would otherwise be lost if they were separately developed into single conventional (spatially homogenized) biomarkers. Our study demonstrates an alternative route to cancer prognosis by taping the regional interactions among existing biomarkers rather than developing novel biomarkers.

  PublisherOA PDFDOI

• Large-scale tumor-associated collagen signatures identify high-risk breast cancer patients

  Theranostics · 2021 · 126 citations

  • Medicine
  • Internal medicine
  • Oncology

  = 264) collected from a different clinical center. Results: TACS1-8 model alone competed favorably with all reported models in predicting disease-free survival (AUC: 0.838, [0.800-0.872]; 0.827, [0.779-0.868]; 0.807, [0.754-0.853] in the three cohorts) and stratifying low- and high-risk patients (HR 7.032, [4.869-10.158]; 6.846, [4.370-10.726], 4.423, [2.917-6.708]). The combination of these factors with the TACS-score into a nomogram model further improved the prognosis (AUC: 0.865, [0.829-0.896]; 0.861, [0.816-0.898]; 0.854, [0.805-0.894]; HR 7.882, [5.487-11.323]; 9.176, [5.683-14.816], and 5.548, [3.705-8.307]). The nomogram identified 72 of 357 (~20%) patients with unsuccessful 5-year disease-free survival that might have been undertreated postoperatively. Conclusions: The risk prediction model based on TACS1-8 considerably outperforms the contextual clinical model and may thus convince pathologists to pursue a TACS-based breast cancer prognosis. Our methodology identifies a significant portion of patients susceptible to undertreatment (high-risk patients), in contrast to the multigene assays that often strive to mitigate overtreatment. The compatibility of our methodology with standard histology using traditional (non-tissue-microarray) formalin-fixed paraffin-embedded (FFPE) tissue sections could simplify subsequent clinical translation.

  PublisherDOI

• Wound-like tumor periphery in human breast cancer predicts a convergent drug nonresponse

  bioRxiv (Cold Spring Harbor Laboratory) · 2021-11-04 · 1 citations

  preprintOpen access

  Abstract A significant portion of breast cancer patients are nonresponsive to well-established drugs and destined for a poor outcome regardless of molecular subtype. Although several (multiparameter) molecular markers have predicted their resistance to some of these drugs, profound uniparameter markers predictive of a convergent nonresponse to all these drugs remain elusive. We employ co-registered standard-multiphoton histology to representatively sample a few peripheral niches of the primary tumor, so that hundreds of patients can be stratified with either a wound-like or non-wound tumor periphery. With no fitting variable, this simple uniparameter morphological marker is: (a) highly sensitive and specific to predict a multidrug-nonresponsive phenotype that accounts for the majority of recurrence or death, independent of the molecular subtype or related adjuvant drug selection, clinical endpoint (disease-free versus overall survival), and hosting medical center; (b) robust against intratumor heterogeneity and valid at the earliest clinicopathological stage; and (c) dominant in predicting prognosis in the context of routine clinicopathological markers. Considering the mechanistic link between a wound-like extracellular matrix and a microenvironment supporting migratory or mesenchymal tumor cells, we attribute these unusual capabilities to an epithelial-mesenchymal transition nature of the morphological marker long sought after by pathologists.

  PublisherOA PDFDOI

• Knowledge-guided analysis of "omics" data using the KnowEnG cloud platform

  PLoS Biology · 2020 · 49 citations

  • Computer Science
  • Data Mining
  • Computer Science

  We present Knowledge Engine for Genomics (KnowEnG), a free-to-use computational system for analysis of genomics data sets, designed to accelerate biomedical discovery. It includes tools for popular bioinformatics tasks such as gene prioritization, sample clustering, gene set analysis, and expression signature analysis. The system specializes in "knowledge-guided" data mining and machine learning algorithms, in which user-provided data are analyzed in light of prior information about genes, aggregated from numerous knowledge bases and encoded in a massive "Knowledge Network." KnowEnG adheres to "FAIR" principles (findable, accessible, interoperable, and reuseable): its tools are easily portable to diverse computing environments, run on the cloud for scalable and cost-effective execution, and are interoperable with other computing platforms. The analysis tools are made available through multiple access modes, including a web portal with specialized visualization modules. We demonstrate the KnowEnG system's potential value in democratization of advanced tools for the modern genomics era through several case studies that use its tools to recreate and expand upon the published analysis of cancer data sets.

  PublisherDOI

Frequent coauthors

• Deyong Kang

  Union Hospital

  16 shared

• Wenhui Guo

  Beijing Tian Tan Hospital

  16 shared

• Lida Qiu

  Minjiang University

  14 shared

• Haohua Tu

  12 shared

• Fangmeng Fu

  Fujian Medical University

  12 shared

• Lianhuang Li

  Fujian Normal University

  10 shared

• Jianxin Chen

  Fujian Normal University

  8 shared

• Jiajia He

  Jimei University

  8 shared

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2005

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  2001

• B.S., Computer Science

  University of Science and Technology of China

  1998