Haoran Luo

Multi-omics integration has demonstrated promising performance in complex disease prediction. However, existing research typically focuses on maximizing prediction accuracy, while often neglecting the essential task of discovering meaningful biomarkers. This issue is particularly important in biomedicine, as molecules often interact rather than function individually to influence disease outcomes. To this end, we propose a two-phase framework named GREMI to assist multi-omics classification and explanation. In the prediction phase, we propose to improve prediction performance by employing a graph attention architecture on sample-wise co-functional networks to incorporate biomolecular interaction information for enhanced feature representation, followed by the integration of a joint-late mixed strategy and the true-class-probability block to adaptively evaluate classification confidence at both feature and omics levels. In the interpretation phase, we propose a multi-view approach to explain disease outcomes from the interaction module perspective, providing a more intuitive understanding and biomedical rationale. We incorporate Monte Carlo tree search (MCTS) to explore local-view subgraphs and pinpoint modules that highly contribute to disease characterization from the global-view. Extensive experiments demonstrate that the proposed framework outperforms state-of-the-art methods in seven different classification tasks, and our model effectively addresses data mutual interference when the number of omics types increases. We further illustrate the functional- and disease-relevance of the identified modules, as well as validate the classification performance of discovered modules using an independent cohort. Code and data are available at https://github.com/Yaolab-fantastic/GREMI .

Advancing the domain of biomedical investigation, integrated multi-omics data have shown exceptional performance in elucidating complex human diseases. However, as the variety of omics information expands, precisely perceiving the informativeness of intra- and inter-omics becomes challenging due to the intricate interrelations, thus presenting significant challenges in the integration of multi-omics data. To address this, we introduce a novel multi-omics integration approach, referred to as TEMINET. This approach enhances diagnostic prediction by leveraging an intra-omics co-informative representation module and a trustworthy learning strategy used to address inter-omics fusion. Considering the multifactorial nature of complex diseases, TEMINET utilizes intra-omics features to construct disease-specific networks; then, it applies graph attention networks and a multi-level framework to capture more collective informativeness than pairwise relations. To perceive the contribution of co-informative representations within intra-omics, we designed a trustworthy learning strategy to identify the reliability of each omics in integration. To integrate inter-omics information, a combined-beliefs fusion approach is deployed to harmonize the trustworthy representations of different omics types effectively. Our experiments across four different diseases using mRNA, methylation, and miRNA data demonstrate that TEMINET achieves advanced performance and robustness in classification tasks.

Background: Integrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable of managing high-dimensional and heterogeneous datasets are required to unlock the full potential of such rich and diverse data. Methods: We propose a Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT), for comprehensive utilization of both intra- and inter-omics information. Additionally, attention mechanisms with confidence learning are incorporated for enhanced feature representation and trustworthy prediction. Results: Extensive experiments were conducted on four benchmark datasets to evaluate the effectiveness of our proposed model, including BRCA, ROSMAP, LGG, and KIPAN. Our model significantly improved most evaluation measurements and consistently surpassed the state-of-the-art methods. Ablation studies showed that the auxiliary classifiers significantly boosted classification accuracy in both the ROSMAP and LGG datasets. Moreover, the attention mechanisms and confidence evaluation block contributed to improvements in the predictive accuracy and generalizability of our model. Conclusions: The proposed framework exhibits superior performance in disease classification and biomarker discovery, establishing itself as a robust and versatile tool for analyzing multi-layer biological data. This study highlights the significance of elaborated designed deep learning methodologies in dissecting complex disease phenotypes and improving the accuracy of disease predictions.

Alzheimer’s disease (AD) is the main cause of dementia worldwide, and the genetic mechanism of which is not yet fully understood. Much evidence has accumulated over the past decade to suggest that after the first large-scale genome-wide association studies (GWAS) were conducted, the problem of “missing heritability” in AD is still a great challenge. Epistasis has been considered as one of the main causes of “missing heritability” in AD, which has been largely ignored in human genetics. The focus of current genome-wide epistasis studies is usually on single nucleotide polymorphisms (SNPs) that have significant individual effects, and the amount of heritability explained by which was very low. Moreover, AD is characterized by progressive cognitive decline and neuronal damage, and some studies have suggested that hyperphosphorylated tau (P-tau) mediates neuronal death by inducing necroptosis and inflammation in AD. Therefore, this study focused on identifying epistasis between two-marker interactions at marginal main effects across the whole genome using cerebrospinal fluid (CSF) P-tau as quantitative trait (QT). We sought to detect interactions between SNPs in a multi-GPU based linear regression method by using age, gender, and clinical diagnostic status (cds) as covariates. We then used the STRING online tool to perform the PPI network and identify two-marker epistasis at the level of gene–gene interaction. A total of 758 SNP pairs were found to be statistically significant. Particularly, between the marginal main effect SNP pairs, highly significant SNP–SNP interactions were identified, which explained a relatively high variance at the P-tau level. In addition, 331 AD-related genes were identified, 10 gene–gene interaction pairs were replicated in the PPI network. The identified gene-gene interactions and genes showed associations with AD in terms of neuroinflammation and neurodegeneration, neuronal cells activation and brain development, thereby leading to cognitive decline in AD, which is indirectly associated with the P-tau pathological feature of AD and in turn supports the results of this study. Thus, the results of our study might be beneficial for explaining part of the “missing heritability” of AD.