Hongyan Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongyan Cao has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Yuehua Cui
Michigan State University
11 shared publications Ruiling Fang
Department of Health Statistics, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, School of Public Health, Shanxi Medical University , No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001
7 shared publicationsTong Wang
Department of Health Statistics, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, School of Public Health, Shanxi Medical University , No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001
7 shared publicationsGaiqin Liu
Department of Health Statistics Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment School of Public Health Shanxi Medical University Taiyuan Shanxi China
4 shared publicationsHaitao Yang
Division of Health Statistics, School of Public Health, Hebei Medical University, 050017 Shijiazhuang, China
4 shared publicationsHongmei Yu
Department of Health Statistics, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, School of Public Health, Shanxi Medical University , No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001
4 shared publications
Latest Publications
- Open Access
- 4 May 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (3)
CEDR: robust consensus cancer subtyping with multi-omics data via ensemble dimensionality reduction
Cancer is a highly heterogeneous disease underpinned by complex molecular alterations. Accurate subtyping is critical for guiding personalized treatment and improving clinical outcomes. However, multi-omics data are high-dimensional, noisy, and heterogeneous across platforms, posing major challenges for reliable subtyping. To address this, dimensionality reduction is necessary to capture underlying molecular patterns in a low-dimensional space, facilitating both computational efficiency and biological interpretation. We present Consensus subtyping method with Ensemble Dimensionality Reduction for multi-omics data integration (CEDR), a consensus subtyping framework that integrates complementary linear and nonlinear dimensionality reduction methods with robust clustering and probabilistic ensemble modeling. Different from existing dimensionality reduction techniques, our framework adopts an ensemble learning framework that integrates multiple dimensionality reduction techniques with robust clustering to achieve reliable consensus cancer subtyping. We apply Optimally Tuned Robust Improper Maximum Likelihood Estimator to the concatenated low-dimensional matrix for robust subtyping, and ensemble the result with the Mixture Model for Clustering Ensembles to identify stable subtypes. Across extensive simulations, CEDR consistently outperformed conventional dimensionality reduction-based clustering, the Cluster Of Clusters Analysis (COCA) ensemble strategy, and state-of-the-art multi-omics integration algorithms (SNF and CIMLR) in both accuracy and robustness. Application to clear cell renal cell carcinoma and lower-grade glioma revealed biologically interpretable subtypes characterized by distinctive survival outcomes, pathway activities, and immune infiltration patterns. These findings demonstrate that CEDR provides a powerful and reliable strategy for multi-omics data integration and cancer subtyping, with strong potential for broader applications in high-dimensional multimodal data analysis.
- 4 May 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (3)
Open AccessCEDR: robust consensus cancer subtyping with multi-omics data via ensemble dimensionality reduction
Cancer is a highly heterogeneous disease underpinned by complex molecular alterations. Accurate subtyping is critical for guiding personalized treatment and improving clinical outcomes. However, multi-omics data are high-dimensional, noisy, and heterogeneous across platforms, posing major challenges for reliable subtyping. To address this, dimensionality reduction is necessary to capture underlying molecular patterns in a low-dimensional space, facilitating both computational efficiency and biological interpretation. We present Consensus subtyping method with Ensemble Dimensionality Reduction for multi-omics data integration (CEDR), a consensus subtyping framework that integrates complementary linear and nonlinear dimensionality reduction methods with robust clustering and probabilistic ensemble modeling. Different from existing dimensionality reduction techniques, our framework adopts an ensemble learning framework that integrates multiple dimensionality reduction techniques with robust clustering to achieve reliable consensus cancer subtyping. We apply Optimally Tuned Robust Improper Maximum Likelihood Estimator to the concatenated low-dimensional matrix for robust subtyping, and ensemble the result with the Mixture Model for Clustering Ensembles to identify stable subtypes. Across extensive simulations, CEDR consistently outperformed conventional dimensionality reduction-based clustering, the Cluster Of Clusters Analysis (COCA) ensemble strategy, and state-of-the-art multi-omics integration algorithms (SNF and CIMLR) in both accuracy and robustness. Application to clear cell renal cell carcinoma and lower-grade glioma revealed biologically interpretable subtypes characterized by distinctive survival outcomes, pathway activities, and immune infiltration patterns. These findings demonstrate that CEDR provides a powerful and reliable strategy for multi-omics data integration and cancer subtyping, with strong potential for broader applications in high-dimensional multimodal data analysis.
- Open Access
- 1 March 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (2)
An integrative association analysis for complex diseases in underrepresented groups by leveraging the trans-ethnic genetic similarity
Genome-wide association studies (GWASs) have been conducted primarily in European (EUR) populations, limiting insights into underrepresented groups such as East Asian (EAS), but cross-ancestry GWASs have demonstrated high trans-ethnic genetic similarity between EUR and non-EUR populations. To enhance association analysis power in EAS populations, we propose tranScore, a novel summary-statistics-based transfer learning method that leverages trans-ethnic genetic similarity through hierarchical modeling. By considering EUR as auxiliary population, tranScore performs joint testing of genetic effects in auxiliary and target populations via well-established P-value combination procedures. Simulations demonstrate that tranScore maintains control of type I error rates and provides substantial power gains for diverse genetic architectures, showing robustness against various challenges including incomplete SNP overlap and effect heterogeneity. In the real-data application of eight diseases from the China Kadoorie Biobank (CKB), after incorporating the genetic information of the EUR population, tranScore identified significantly more genes than the traditional score test which ignored such information. Approximately 41.9% of discovered genes were replicated in the Biobank Japan cohort. Overall, tranScore represents a flexible and powerful statistical approach for association analysis of complex diseases and traits through transfer learning of shared genetic similarities between the auxiliary and target populations.
- 1 March 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (2)
Open AccessAn integrative association analysis for complex diseases in underrepresented groups by leveraging the trans-ethnic genetic similarity
Genome-wide association studies (GWASs) have been conducted primarily in European (EUR) populations, limiting insights into underrepresented groups such as East Asian (EAS), but cross-ancestry GWASs have demonstrated high trans-ethnic genetic similarity between EUR and non-EUR populations. To enhance association analysis power in EAS populations, we propose tranScore, a novel summary-statistics-based transfer learning method that leverages trans-ethnic genetic similarity through hierarchical modeling. By considering EUR as auxiliary population, tranScore performs joint testing of genetic effects in auxiliary and target populations via well-established P-value combination procedures. Simulations demonstrate that tranScore maintains control of type I error rates and provides substantial power gains for diverse genetic architectures, showing robustness against various challenges including incomplete SNP overlap and effect heterogeneity. In the real-data application of eight diseases from the China Kadoorie Biobank (CKB), after incorporating the genetic information of the EUR population, tranScore identified significantly more genes than the traditional score test which ignored such information. Approximately 41.9% of discovered genes were replicated in the Biobank Japan cohort. Overall, tranScore represents a flexible and powerful statistical approach for association analysis of complex diseases and traits through transfer learning of shared genetic similarities between the auxiliary and target populations.
- Open Access
- 12 February 2026
- Published by Wiley in Advanced Science
- Vol. 13 (30) , e20912
SpatialESD: Spatial Ensemble Domain Detection in Spatial Transcriptomics
Spatial transcriptomics (ST) measures gene expression while preserving spatial context within tissues. One of the key tasks in ST analysis is spatial domain detection, which remains challenging due to the complex structure of ST data and the varying performance of individual clustering methods. To address this, we propose SpatialESD, a Spatial EnSemble Domain detection method that integrates results from different spatial domain detection methods to improve spatial domain detection. SpatialESD captures both direct cooccurrence patterns and multiscale indirect relationships between clusters, improving the robustness and accuracy of spatial domain detection. We evaluated SpatialESD on simulated datasets and multiple 10x Visium spatial transcriptomics datasets, including human brain, breast cancer, and ovarian cancer samples. The results show that SpatialESD consistently outperforms individual methods and the existing EnSDD ensemble method in terms of clustering accuracy and stability. Based on the identified domains, we further detected domain‐specific differentially expressed genes and performed trajectory and cell–cell interaction analyses. These results reveal spatial patterns of gene expression and cellular communication, offering insights into tissue organization and disease mechanisms. Overall, SpatialESD provides a reliable and effective solution for spatial domain detection in ST data and facilitates downstream biological discovery.
- 12 February 2026
- Published by Wiley in Advanced Science
- Vol. 13 (30) , e20912
Open AccessSpatialESD: Spatial Ensemble Domain Detection in Spatial Transcriptomics
Spatial transcriptomics (ST) measures gene expression while preserving spatial context within tissues. One of the key tasks in ST analysis is spatial domain detection, which remains challenging due to the complex structure of ST data and the varying performance of individual clustering methods. To address this, we propose SpatialESD, a Spatial EnSemble Domain detection method that integrates results from different spatial domain detection methods to improve spatial domain detection. SpatialESD captures both direct cooccurrence patterns and multiscale indirect relationships between clusters, improving the robustness and accuracy of spatial domain detection. We evaluated SpatialESD on simulated datasets and multiple 10x Visium spatial transcriptomics datasets, including human brain, breast cancer, and ovarian cancer samples. The results show that SpatialESD consistently outperforms individual methods and the existing EnSDD ensemble method in terms of clustering accuracy and stability. Based on the identified domains, we further detected domain‐specific differentially expressed genes and performed trajectory and cell–cell interaction analyses. These results reveal spatial patterns of gene expression and cellular communication, offering insights into tissue organization and disease mechanisms. Overall, SpatialESD provides a reliable and effective solution for spatial domain detection in ST data and facilitates downstream biological discovery.
- Open Access
- 1 February 2026
- Published by Wiley in Cancer Medicine
- Vol. 15 (2) , e71572
Identification of Glioma Phenotypic Subtypes From Multimodal MRI Data Using Hierarchical Multi‐Kernel Learning
Background: Gliomas are the most common primary brain tumors, exhibiting significant phenotypic variability even within the same grade. Identifying glioma subtypes through non‐invasive methods could improve patient management. Methods: In this study, we applied hierarchical multi‐kernel learning to identify glioma phenotypic subtypes using MRI data (T1CE and T2FLAIR) from the First Hospital of Shanxi Medical University (FHSXMU) and Shanxi Provincial People's Hospital (SPPH) ( n = 246). We further validated our findings using an independent dataset of similar tumor characteristics from The Cancer Genome Atlas/The Cancer Imaging Archive (TCGA/TCIA) ( n = 144). Additionally, we analyzed pathway activity across glioma subtypes from the TCGA/TCIA dataset and employed five machine learning models, namely kernel partial least squares with the genetic algorithm (GA‐KPLS), random forest, the least absolute shrinkage and selection operator, K‐Nearest Neighbor, and Naïve Bayes, to predict isocitrate dehydrogenase (IDH) genotype from the FHSXMU/SPPH dataset. Results: We identified 2 glioma phenotypic subtypes, high‐risk and low‐risk groups. These groups showed significant differences in overall survival ( p < 0.05) and were associated with distinct signaling pathways. The JAK–STAT and TGF‐β pathways were activated in the high‐risk group, while the Hypoxia and p53 pathways were activated in the low‐risk group. Among the machine learning models, the GA‐KPLS model demonstrated the highest predictive performance for the IDH genotype, achieving an area under the curve of 0.819. Conclusion: Our study provides a non‐invasive method to identify glioma phenotypic subtypes, reveal distinct signaling pathways, and define therapeutically homogeneous patient subgroups that could guide targeted therapy.
- 1 February 2026
- Published by Wiley in Cancer Medicine
- Vol. 15 (2) , e71572
Open AccessIdentification of Glioma Phenotypic Subtypes From Multimodal MRI Data Using Hierarchical Multi‐Kernel Learning
Background: Gliomas are the most common primary brain tumors, exhibiting significant phenotypic variability even within the same grade. Identifying glioma subtypes through non‐invasive methods could improve patient management. Methods: In this study, we applied hierarchical multi‐kernel learning to identify glioma phenotypic subtypes using MRI data (T1CE and T2FLAIR) from the First Hospital of Shanxi Medical University (FHSXMU) and Shanxi Provincial People's Hospital (SPPH) ( n = 246). We further validated our findings using an independent dataset of similar tumor characteristics from The Cancer Genome Atlas/The Cancer Imaging Archive (TCGA/TCIA) ( n = 144). Additionally, we analyzed pathway activity across glioma subtypes from the TCGA/TCIA dataset and employed five machine learning models, namely kernel partial least squares with the genetic algorithm (GA‐KPLS), random forest, the least absolute shrinkage and selection operator, K‐Nearest Neighbor, and Naïve Bayes, to predict isocitrate dehydrogenase (IDH) genotype from the FHSXMU/SPPH dataset. Results: We identified 2 glioma phenotypic subtypes, high‐risk and low‐risk groups. These groups showed significant differences in overall survival ( p < 0.05) and were associated with distinct signaling pathways. The JAK–STAT and TGF‐β pathways were activated in the high‐risk group, while the Hypoxia and p53 pathways were activated in the low‐risk group. Among the machine learning models, the GA‐KPLS model demonstrated the highest predictive performance for the IDH genotype, achieving an area under the curve of 0.819. Conclusion: Our study provides a non‐invasive method to identify glioma phenotypic subtypes, reveal distinct signaling pathways, and define therapeutically homogeneous patient subgroups that could guide targeted therapy.
- Open Access
- 4 November 2025
- Published by Springer Nature in BMC Neurology
- Vol. 25 (1) , 1-15
Phenotypic stratification of Low-grade Glioma using multimodal MRI via outcome-weighted integrative clustering
Background: Low-grade glioma (LGG) is a diverse group of primary brain tumors, whose molecular heterogeneity hinders classification by traditional pathological methods. Accurate phenotypic subtyping of LGG is essential for capturing tumor characteristics and optimizing clinical management. We intend to identify LGG phenotypic subtypes based on multimodal magnetic resonance imaging (MRI) data, enhancing prognosis evaluation and optimizing treatment strategy. Methods: This was a retrospective multicenter study, and data were drawn from the First Hospital of Shanxi Medical University (FHSXMU) and Shanxi Provincial People’s Hospital (SPPH) (FHSXMU/SPPH cohort, n = 162), and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (TCGA/TCIA cohort, n = 118). In the FHSXMU/SPPH cohort, LGG phenotypic subtypes were identified using the outcome-weighted integrative clustering method (survClust) based on multimodal MRI data (CE-T1 and T2FLAIR). A multivariate Cox proportional hazards model was applied to evaluate survival differences between subtypes. Statistical comparisons between subtypes were performed, and the statistically significant MRI features were utilized to predict clinically relevant biomarkers – isocitrate dehydrogenase (IDH) mutation combined with O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation. Five models were constructed, including fused kernel partial least squares with the genetic algorithm (GA-fKPLS), logistic regression, random forest, support vector machine, and k -nearest neighbor. In the TCGA/TCIA cohort, we validated the identified phenotypic subtypes and further explored their biological characteristics by analyzing pathway activity and immune infiltration levels using mRNA expression data. Results: Two distinct LGG phenotypic subtypes were identified in the FHSXMU/SPPH cohort, and validated in the TCGA/TCIA cohort. In the FHSXMU/SPPH cohort, significant differences in pathological grade, MGMT promoter status, IDH genotype, survival status, tumor volume, and survival outcome ( HR : 2.553, 95% CI : [1.226–5.315]) between the two subtypes ( P < 0.05). Compared to other four models, the GA-fKPLS model exhibited superior predictive performance (AUC: 0.809). In the TCGA/TCIA cohort, two LGG phenotypic subtypes showed significant differences in pathway activities (JAK-STAT, TNF-α, p53) and immune cell infiltration (M2 macrophages, T cell regulatory, Monocytes) ( P adj < 0.05). Conclusion: This study identified two LGG phenotypic subtypes and potential biomarkers, offering supplementary information for clinical evaluation and treatment decision-making. Graphical
- 4 November 2025
- Published by Springer Nature in BMC Neurology
- Vol. 25 (1) , 1-15
Open AccessPhenotypic stratification of Low-grade Glioma using multimodal MRI via outcome-weighted integrative clustering
Background: Low-grade glioma (LGG) is a diverse group of primary brain tumors, whose molecular heterogeneity hinders classification by traditional pathological methods. Accurate phenotypic subtyping of LGG is essential for capturing tumor characteristics and optimizing clinical management. We intend to identify LGG phenotypic subtypes based on multimodal magnetic resonance imaging (MRI) data, enhancing prognosis evaluation and optimizing treatment strategy. Methods: This was a retrospective multicenter study, and data were drawn from the First Hospital of Shanxi Medical University (FHSXMU) and Shanxi Provincial People’s Hospital (SPPH) (FHSXMU/SPPH cohort, n = 162), and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (TCGA/TCIA cohort, n = 118). In the FHSXMU/SPPH cohort, LGG phenotypic subtypes were identified using the outcome-weighted integrative clustering method (survClust) based on multimodal MRI data (CE-T1 and T2FLAIR). A multivariate Cox proportional hazards model was applied to evaluate survival differences between subtypes. Statistical comparisons between subtypes were performed, and the statistically significant MRI features were utilized to predict clinically relevant biomarkers – isocitrate dehydrogenase (IDH) mutation combined with O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation. Five models were constructed, including fused kernel partial least squares with the genetic algorithm (GA-fKPLS), logistic regression, random forest, support vector machine, and k -nearest neighbor. In the TCGA/TCIA cohort, we validated the identified phenotypic subtypes and further explored their biological characteristics by analyzing pathway activity and immune infiltration levels using mRNA expression data. Results: Two distinct LGG phenotypic subtypes were identified in the FHSXMU/SPPH cohort, and validated in the TCGA/TCIA cohort. In the FHSXMU/SPPH cohort, significant differences in pathological grade, MGMT promoter status, IDH genotype, survival status, tumor volume, and survival outcome ( HR : 2.553, 95% CI : [1.226–5.315]) between the two subtypes ( P < 0.05). Compared to other four models, the GA-fKPLS model exhibited superior predictive performance (AUC: 0.809). In the TCGA/TCIA cohort, two LGG phenotypic subtypes showed significant differences in pathway activities (JAK-STAT, TNF-α, p53) and immune cell infiltration (M2 macrophages, T cell regulatory, Monocytes) ( P adj < 0.05). Conclusion: This study identified two LGG phenotypic subtypes and potential biomarkers, offering supplementary information for clinical evaluation and treatment decision-making. Graphical
- Open Access
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Multi-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning
Cancer is a highly heterogeneous disease characterized by complex molecular changes. Subtypes identified through multi-omics data hold significant promise for improving prognosis and facilitating personalized precision treatment. Recent multi-omics integration methods have mostly focused on capturing complementary information from different data types, often overlooking potential interactions between omics data. Here we develop a novel method named interactive multi-kernel learning (iMKL), which incorporates omics-omics interactions alongside heterogeneous data types under the unsupervised multi-kernel learning framework, to improve subtype identification. Using the sample-similarity kernel for each dataset, we propose a joint Hadamard product strategy to capture higher-order interactive effects from different omics data types. We applied iMKL to two renal cell carcinoma (RCC) datasets—clear renal cell carcinoma (ccRCC) and type II papillary renal cell carcinoma (type II pRCC)—both including miRNA expression, mRNA expression, and DNA methylation data. Stability analysis through random sampling of patients or features demonstrated that iMKL exhibits strong robustness and accuracy in identifying patient subtypes. The identified subtypes revealed dramatic differences in patient survival, with both ccRCC and type II pRCC classified into three distinct subtypes. The findings in the real application highlight potential biomarkers associated with adverse patient outcomes and demonstrate substantial advancement in cancer subtype identification. The iMKL method effectively identifies tumor molecular subtypes that are strongly associated with clinical features and survival rates, providing valuable insights for accurate cancer subtyping, clinical decision-making, and the realization of personalized treatment strategies.
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Open AccessMulti-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning
Cancer is a highly heterogeneous disease characterized by complex molecular changes. Subtypes identified through multi-omics data hold significant promise for improving prognosis and facilitating personalized precision treatment. Recent multi-omics integration methods have mostly focused on capturing complementary information from different data types, often overlooking potential interactions between omics data. Here we develop a novel method named interactive multi-kernel learning (iMKL), which incorporates omics-omics interactions alongside heterogeneous data types under the unsupervised multi-kernel learning framework, to improve subtype identification. Using the sample-similarity kernel for each dataset, we propose a joint Hadamard product strategy to capture higher-order interactive effects from different omics data types. We applied iMKL to two renal cell carcinoma (RCC) datasets—clear renal cell carcinoma (ccRCC) and type II papillary renal cell carcinoma (type II pRCC)—both including miRNA expression, mRNA expression, and DNA methylation data. Stability analysis through random sampling of patients or features demonstrated that iMKL exhibits strong robustness and accuracy in identifying patient subtypes. The identified subtypes revealed dramatic differences in patient survival, with both ccRCC and type II pRCC classified into three distinct subtypes. The findings in the real application highlight potential biomarkers associated with adverse patient outcomes and demonstrate substantial advancement in cancer subtype identification. The iMKL method effectively identifies tumor molecular subtypes that are strongly associated with clinical features and survival rates, providing valuable insights for accurate cancer subtyping, clinical decision-making, and the realization of personalized treatment strategies.
- Open Access
Multi-Omics Data Integration for Improved Cancer Subtyping via Denoising Autoencoder-Based Multi-Kernel Learning
Objectives: Cancer, characterized by its profound complexity and heterogeneity, arises from a multitude of molecular disruptions. The pursuit of identifying distinct cancer subtypes is driven by the need to stratify patients into clinically coherent subgroups, each exhibiting unique prognostic outcomes. The integration of multi-omics datasets enhances the precision of subtyping and advances precision medicine. Methods: Considering the high-dimensional nature inherent to various multi-omics data types, we introduce an innovative deep learning framework, DAE-MKL, which integrates denoising autoencoders with multi-kernel learning for identifying cancer subtypes. Leveraging the capabilities of DAE, we extract non-linearly transformed features that retain pertinent information while mitigating noise and redundancy. These refined data representations are then funneled into the MKL framework, thereby enhancing the accuracy of subtype identification. We applied the DAE-MKL framework to both simulated studies and empirical datasets derived from two distinct cancer types, low-grade glioma (LGG, = 86) and kidney renal clear cell carcinoma (KIRC, = 285), thereby validating its utility and feasibility. Results: In simulations, DAE-MKL achieved superior performance with NMI gains up to 0.78 compared to other state-of-the-art methods. For real datasets, DAE-MKL identified three LGG subtypes and three KIRC subtypes, showing significant survival differences (KIRC log-rank = 3.33 × 10−8, LGG log-rank = 3.99 × 10−8). Additionally, we explored potential cancer-related biomarkers. Conclusions: The DAE-MKL effectively identifies molecular subtypes, reduces data dimensionality, and improves prognostic stratification in multi-omics cancer datasets, providing an effective tool for precision oncology.Open AccessMulti-Omics Data Integration for Improved Cancer Subtyping via Denoising Autoencoder-Based Multi-Kernel Learning
Objectives: Cancer, characterized by its profound complexity and heterogeneity, arises from a multitude of molecular disruptions. The pursuit of identifying distinct cancer subtypes is driven by the need to stratify patients into clinically coherent subgroups, each exhibiting unique prognostic outcomes. The integration of multi-omics datasets enhances the precision of subtyping and advances precision medicine. Methods: Considering the high-dimensional nature inherent to various multi-omics data types, we introduce an innovative deep learning framework, DAE-MKL, which integrates denoising autoencoders with multi-kernel learning for identifying cancer subtypes. Leveraging the capabilities of DAE, we extract non-linearly transformed features that retain pertinent information while mitigating noise and redundancy. These refined data representations are then funneled into the MKL framework, thereby enhancing the accuracy of subtype identification. We applied the DAE-MKL framework to both simulated studies and empirical datasets derived from two distinct cancer types, low-grade glioma (LGG, = 86) and kidney renal clear cell carcinoma (KIRC, = 285), thereby validating its utility and feasibility. Results: In simulations, DAE-MKL achieved superior performance with NMI gains up to 0.78 compared to other state-of-the-art methods. For real datasets, DAE-MKL identified three LGG subtypes and three KIRC subtypes, showing significant survival differences (KIRC log-rank = 3.33 × 10−8, LGG log-rank = 3.99 × 10−8). Additionally, we explored potential cancer-related biomarkers. Conclusions: The DAE-MKL effectively identifies molecular subtypes, reduces data dimensionality, and improves prognostic stratification in multi-omics cancer datasets, providing an effective tool for precision oncology. - 6 September 2025
- Published by Elsevier in Journal of Affective Disorders
- Vol. 393 (Pt A) , 120197
Construction of diagnostic model and identification of key genes of bipolar disorder based on GA-KPLS
- 6 September 2025
- Published by Elsevier in Journal of Affective Disorders
- Vol. 393 (Pt A) , 120197
Construction of diagnostic model and identification of key genes of bipolar disorder based on GA-KPLS
- Open Access
- 19 May 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (5) , e70263
Characterizing bidirectional transitions in mild cognitive impairment and post‐reversion based on longitudinal neuroimaging and cognitive assessments
INTRODUCTION: Characterizing transitions of cognitive state, including reversion from mild cognitive impairment (MCI) to normal cognition (NC) and subsequent cognitive stability or deterioration for post‐reversion, has so far remained limited.METHODS: Using a retrospective cohort of subjects with an MCI diagnosis at study entry and at least two follow‐up visits between 2005 and December 2022, we developed a functional multistate model framework to estimate longitudinal patterns of transition probabilities between different cognitive states.RESULTS: The probability of reversion increased from 2% at baseline to a maximum of 8% by year 10 before gradual decline thereafter. For post‐reversion, the probability of progression to MCI rose from 8% to 35.71% at Year 10 and subsequently stabilized.DISCUSSION: The instantaneous risk of MCI progressing was similar to the risk of re‐progression to MCI for post‐reversion. Post‐reversion subjects remained at an increased risk of cognitive deterioration.Highlights: The instantaneous risk of MCI progressing to AD is similar to the risk of re‐progression to MCI for post‐reversion. The FMSM we developed effectively utilizes multiple longitudinal markers to reveal variable transition patterns between different cognitive states. Considering both spatiotemporal dimensions and sparse irregularities from longitudinal neuroimaging and neuropsychological scales, fMLFPCA and MVFPCA help to extract variation patterns, to capture detailed changes characterizing the multidimensional evolution patterns of MCI.
- 19 May 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (5) , e70263
Open AccessCharacterizing bidirectional transitions in mild cognitive impairment and post‐reversion based on longitudinal neuroimaging and cognitive assessments
INTRODUCTION: Characterizing transitions of cognitive state, including reversion from mild cognitive impairment (MCI) to normal cognition (NC) and subsequent cognitive stability or deterioration for post‐reversion, has so far remained limited.METHODS: Using a retrospective cohort of subjects with an MCI diagnosis at study entry and at least two follow‐up visits between 2005 and December 2022, we developed a functional multistate model framework to estimate longitudinal patterns of transition probabilities between different cognitive states.RESULTS: The probability of reversion increased from 2% at baseline to a maximum of 8% by year 10 before gradual decline thereafter. For post‐reversion, the probability of progression to MCI rose from 8% to 35.71% at Year 10 and subsequently stabilized.DISCUSSION: The instantaneous risk of MCI progressing was similar to the risk of re‐progression to MCI for post‐reversion. Post‐reversion subjects remained at an increased risk of cognitive deterioration.Highlights: The instantaneous risk of MCI progressing to AD is similar to the risk of re‐progression to MCI for post‐reversion. The FMSM we developed effectively utilizes multiple longitudinal markers to reveal variable transition patterns between different cognitive states. Considering both spatiotemporal dimensions and sparse irregularities from longitudinal neuroimaging and neuropsychological scales, fMLFPCA and MVFPCA help to extract variation patterns, to capture detailed changes characterizing the multidimensional evolution patterns of MCI.
- Open Access
- 23 September 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (6)
A metagene based similarity network fusion approach for multi-omics data integration identified novel subtypes in renal cell carcinoma
Renal cell carcinoma (RCC) ranks among the most prevalent cancers worldwide, with both incidence and mortality rates increasing annually. The heterogeneity among RCC patients presents considerable challenges for developing universally effective treatment strategies, emphasizing the necessity of in-depth research into RCC’s molecular mechanisms, understanding the variations among RCC patients and further identifying distinct molecular subtypes for precise treatment. We proposed a metagene-based similarity network fusion (Meta-SNF) method for RCC subtype identification with multi-omics data, using a non-negative matrix factorization technique to capture alternative structures inherent in the dataset as metagenes. These latent metagenes were then integrated to construct a fused network under the Similarity Network Fusion (SNF) framework for more precise subtyping. We conducted simulation studies and analyzed real-world data from two RCC datasets, namely kidney renal clear cell carcinoma (KIRC) and kidney renal papillary cell carcinoma (KIRP) to demonstrate the utility of Meta-SNF. The simulation studies indicated that Meta-SNF achieved higher accuracy in subtype identification compared with the original SNF and other state-of-the-art methods. In analyses of real data, Meta-SNF produced more distinct and well-separated clusters, classifying both KIRC and KIRP into four subtypes with significant differences in survival outcomes. Subsequently, we performed comprehensive bioinformatics analyses focused on subtypes with poor prognoses in KIRC and KIRP and identified several potential biomarkers. Meta-SNF offers a novel strategy for subtype identification using multi-omics data, and its application to RCC datasets has yielded diverse biological insights which are highly valuable for informing clinical decision-making processes in the treatment of RCC.
- 23 September 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (6)
Open AccessA metagene based similarity network fusion approach for multi-omics data integration identified novel subtypes in renal cell carcinoma
Renal cell carcinoma (RCC) ranks among the most prevalent cancers worldwide, with both incidence and mortality rates increasing annually. The heterogeneity among RCC patients presents considerable challenges for developing universally effective treatment strategies, emphasizing the necessity of in-depth research into RCC’s molecular mechanisms, understanding the variations among RCC patients and further identifying distinct molecular subtypes for precise treatment. We proposed a metagene-based similarity network fusion (Meta-SNF) method for RCC subtype identification with multi-omics data, using a non-negative matrix factorization technique to capture alternative structures inherent in the dataset as metagenes. These latent metagenes were then integrated to construct a fused network under the Similarity Network Fusion (SNF) framework for more precise subtyping. We conducted simulation studies and analyzed real-world data from two RCC datasets, namely kidney renal clear cell carcinoma (KIRC) and kidney renal papillary cell carcinoma (KIRP) to demonstrate the utility of Meta-SNF. The simulation studies indicated that Meta-SNF achieved higher accuracy in subtype identification compared with the original SNF and other state-of-the-art methods. In analyses of real data, Meta-SNF produced more distinct and well-separated clusters, classifying both KIRC and KIRP into four subtypes with significant differences in survival outcomes. Subsequently, we performed comprehensive bioinformatics analyses focused on subtypes with poor prognoses in KIRC and KIRP and identified several potential biomarkers. Meta-SNF offers a novel strategy for subtype identification using multi-omics data, and its application to RCC datasets has yielded diverse biological insights which are highly valuable for informing clinical decision-making processes in the treatment of RCC.