Xilong Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xilong Zhao has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Junwei Han
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin 150081, China
3 shared publications - Bingyue Pan
College of Bioinformatics Science and Technology Harbin Medical University Harbin 150081 P. R. China
2 shared publications - Yalan He
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin 150081, China
2 shared publications - Yongbao Zhang
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin 150081, China
2 shared publications Yujie Tang
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin 150081, China
2 shared publications- Ziyi Wang
College of Bioinformatics Science and Technology
2 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Vol. 12 (24) , eaed6373
PathTIGR: A pathway topology-informed graph representation learning framework for immunotherapy response prediction
Immunotherapy has revolutionized cancer treatment, yet substantial inter-patient response heterogeneity limits therapeutic benefit to specific patient subsets. Here, we present PathTIGR, a pathway topology-informed graph representation learning framework that systematically integrates biological pathway network topology knowledge with genome variation information for immunotherapy response prediction. PathTIGR uses a three-component design: (i) pathway graph encoder with multihead attention embeding pathway topology knowledge and cancer genomic variants to pathway representation, (ii) transformer module capturing pathway regulatory dependencies, and (iii) multilayer perceptron synthesizing pathway-level representations to predict immunotherapy response. This architecture enables PathTIGR to capture complex molecular interactions underlying immunotherapy response. Comprehensive validation across multiple independent immunotherapy cohorts demonstrates that PathTIGR achieves superior predictive performance compared to established biomarkers and state-of-the-art deep learning approaches while maintaining biological interpretability through identification of key signatures underlying response heterogeneity. PathTIGR represents an interpretable graph-based learning framework that enhances immunotherapy response prediction and elucidates molecular determinants of therapeutic efficacy, thereby facilitating the advancement of precision cancer immunotherapy.
- 10 June 2026
- Vol. 12 (24) , eaed6373
Open AccessPathTIGR: A pathway topology-informed graph representation learning framework for immunotherapy response prediction
Immunotherapy has revolutionized cancer treatment, yet substantial inter-patient response heterogeneity limits therapeutic benefit to specific patient subsets. Here, we present PathTIGR, a pathway topology-informed graph representation learning framework that systematically integrates biological pathway network topology knowledge with genome variation information for immunotherapy response prediction. PathTIGR uses a three-component design: (i) pathway graph encoder with multihead attention embeding pathway topology knowledge and cancer genomic variants to pathway representation, (ii) transformer module capturing pathway regulatory dependencies, and (iii) multilayer perceptron synthesizing pathway-level representations to predict immunotherapy response. This architecture enables PathTIGR to capture complex molecular interactions underlying immunotherapy response. Comprehensive validation across multiple independent immunotherapy cohorts demonstrates that PathTIGR achieves superior predictive performance compared to established biomarkers and state-of-the-art deep learning approaches while maintaining biological interpretability through identification of key signatures underlying response heterogeneity. PathTIGR represents an interpretable graph-based learning framework that enhances immunotherapy response prediction and elucidates molecular determinants of therapeutic efficacy, thereby facilitating the advancement of precision cancer immunotherapy.
- 26 March 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 65 (7) , 3827-3840
Knowledge-Based Artificial Intelligence System for Drug Prioritization
In silico drug prioritization may be a promising and time-saving strategy to identify potential drugs, standing as a faster and more cost-effective approach than de novo approaches. In recent years, artificial intelligence has greatly evolved the drug development process. Here, we present a novel computational framework for drug prioritization, labyrinth, designed to simulate human knowledge retrieval and inference to identify potential drug candidates for each disease. With the integration of up-to-date clinical trials, literature co-occurrences, drug-target interactions, and disease similarities, our framework achieves over 90% predictive accuracy across clinical trial phases and strong alignment with clinical practice in TCGA cohorts. We have demonstrated effectiveness across 20 different disease categories with robust ROC-AUC metrics and the balance between predictive accuracy and model interpretability. We further demonstrate its effectiveness at both the population and the individual levels. This study not only demonstrates the capacity for its drug prioritization but underscores the importance of aligning computational models with intuitive human reasoning. We have wrapped the core function into an R package named labyrinth, which is freely available on GitHub under the GPL-v2 license (https://github.com/hanjunwei-lab/labyrinth).
- 26 March 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 65 (7) , 3827-3840
Knowledge-Based Artificial Intelligence System for Drug Prioritization
In silico drug prioritization may be a promising and time-saving strategy to identify potential drugs, standing as a faster and more cost-effective approach than de novo approaches. In recent years, artificial intelligence has greatly evolved the drug development process. Here, we present a novel computational framework for drug prioritization, labyrinth, designed to simulate human knowledge retrieval and inference to identify potential drug candidates for each disease. With the integration of up-to-date clinical trials, literature co-occurrences, drug-target interactions, and disease similarities, our framework achieves over 90% predictive accuracy across clinical trial phases and strong alignment with clinical practice in TCGA cohorts. We have demonstrated effectiveness across 20 different disease categories with robust ROC-AUC metrics and the balance between predictive accuracy and model interpretability. We further demonstrate its effectiveness at both the population and the individual levels. This study not only demonstrates the capacity for its drug prioritization but underscores the importance of aligning computational models with intuitive human reasoning. We have wrapped the core function into an R package named labyrinth, which is freely available on GitHub under the GPL-v2 license (https://github.com/hanjunwei-lab/labyrinth).
- Open Access
- 2 January 2024
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 13
ssMutPA: single-sample mutation-based pathway analysis approach for cancer precision medicine
Background: Single-sample pathway enrichment analysis is an effective approach for identifying cancer subtypes and pathway biomarkers, facilitating the development of precision medicine. However, the existing approaches focused on investigating the changes in gene expression levels but neglected somatic mutations, which play a crucial role in cancer development. Findings: In this study, we proposed a novel single-sample mutation-based pathway analysis approach (ssMutPA) to infer individualized pathway activities by integrating somatic mutation data and the protein–protein interaction network. For each sample, ssMutPA first uses local and global weighted strategies to evaluate the effects of genes from mutations according to the network topology and then calculates a single-sample mutation-based pathway enrichment score (ssMutPES) to reflect the accumulated effect of mutations of each pathway. To illustrate the performance of ssMutPA, we applied it to 33 cancer cohorts from The Cancer Genome Atlas database and revealed patient stratification with significantly different prognosis in each cancer type based on the ssMutPES profiles. We also found that the identified characteristic pathways with high overlap across different cancers could be used as potential prognosis biomarkers. Moreover, we applied ssMutPA to 2 melanoma cohorts with immunotherapy and identified a subgroup of patients who may benefit from therapy. Conclusions: We provided evidence that ssMutPA could infer mutation-based individualized pathway activity profiles and complement the current individualized pathway analysis approaches focused on gene expression data, which may offer the potential for the development of precision medicine. ssMutPA is available at https://CRAN.R-project.org/package=ssMutPA.
- 2 January 2024
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 13
Open AccessssMutPA: single-sample mutation-based pathway analysis approach for cancer precision medicine
Background: Single-sample pathway enrichment analysis is an effective approach for identifying cancer subtypes and pathway biomarkers, facilitating the development of precision medicine. However, the existing approaches focused on investigating the changes in gene expression levels but neglected somatic mutations, which play a crucial role in cancer development. Findings: In this study, we proposed a novel single-sample mutation-based pathway analysis approach (ssMutPA) to infer individualized pathway activities by integrating somatic mutation data and the protein–protein interaction network. For each sample, ssMutPA first uses local and global weighted strategies to evaluate the effects of genes from mutations according to the network topology and then calculates a single-sample mutation-based pathway enrichment score (ssMutPES) to reflect the accumulated effect of mutations of each pathway. To illustrate the performance of ssMutPA, we applied it to 33 cancer cohorts from The Cancer Genome Atlas database and revealed patient stratification with significantly different prognosis in each cancer type based on the ssMutPES profiles. We also found that the identified characteristic pathways with high overlap across different cancers could be used as potential prognosis biomarkers. Moreover, we applied ssMutPA to 2 melanoma cohorts with immunotherapy and identified a subgroup of patients who may benefit from therapy. Conclusions: We provided evidence that ssMutPA could infer mutation-based individualized pathway activity profiles and complement the current individualized pathway analysis approaches focused on gene expression data, which may offer the potential for the development of precision medicine. ssMutPA is available at https://CRAN.R-project.org/package=ssMutPA.