Accurate cancer subtype prediction is crucial for personalized medicine. Integrating multi-omics data represents a viable approach to comprehending the intricate pathophysiology of complex diseases like cancer. Conventional machine learning techniques are not ideal for analyzing the complex interrelationships among different categories of omics data. Numerous models have been suggested using graph-based learning to uncover veiled representations and network formations unique to distinct types of omics data to heighten predictions regarding cancers and characterize patients’ profiles, amongst other applications aimed at improving disease management in medical research. The existing graph-based state-of-the-art multi-omics integration approaches for cancer subtype prediction, MOGONET, and SUPREME, use a graph convolutional network (GCN), which fails to consider the level of importance of neighboring nodes on a particular node. To address this gap, we hypothesize that paying attention to each neighbor or providing appropriate weights to neighbors based on their importance might improve the cancer subtype prediction. The natural choice to determine the importance of each neighbor of a node in a graph is to explore the graph attention network (GAT). Here, we propose MOGAT, a novel multi-omics integration approach, leveraging GAT models that incorporate graph-based learning with an attention mechanism. MOGAT utilizes a multi-head attention mechanism to extract appropriate information for a specific sample by assigning unique attention coefficients to neighboring samples. Based on our knowledge, our group is the first to explore GAT in multi-omics integration for cancer subtype prediction. To evaluate the performance of MOGAT in predicting cancer subtypes, we explored two sets of breast cancer data from TCGA and METABRIC. Our proposed approach, MOGAT, outperforms MOGONET by 32% to 46% and SUPREME by 2% to 16% in cancer subtype prediction in different scenarios, supporting our hypothesis. Our results also showed that GAT embeddings provide a better prognosis in differentiating the high-risk group from the low-risk group than raw features.

Background: Lung cancer is a leading cause of cancer-related mortality, with disparities in incidence and outcomes observed across different racial and sex groups. Identifying both patient-specific and cohort-specific disparity biomarkers is critical for developing targeted treatments. The lung cancer dataset is highly imbalanced across races, leading to biased results in disparity information if classification is based on race. Method: This study developed an explainable artificial intelligence-based framework, TILDA-X, which designs classification models based on disease conditions instead of races to mitigate racial imbalance in the dataset and applies explainable AI to delineate patient-specific disparity information. A lung cancer transcriptome dataset with three disease conditions—lung adenocarcinoma, lung squamous cell carcinoma, and healthy samples—was used to develop classification models. Applying a bottom-up approach from patient-specific disparity information, the cohort-specific disparity information is discovered for different racial and sex groups, African American males, European American males, African American females, and European American females. Results: Classification based on disease conditions achieved accuracy between 88% and 100% for minority groups (African American males and females), whereas it was only between 0% and 16% for race-based classification, which underscores the significance of the proposed approach. Functional analysis of sub-cohort-specific biomarker genes revealed unique pathways associated with lung cancers in different races and sexes. Among the significant pathways identified, over ~63% overlapped with previously reported lung cancer-related studies, supporting the biological validity of our findings. Overall, combining disease conditions-based classification with explainable AI, this study provides a robust, interpretable framework for characterizing race- and sex-specific disparities in lung cancer, offering a foundation for precision oncology and equitable therapeutic development based on transcriptome profile only.

Genome-wide association and other genetic studies have identified genes involved in disease pathogenesis, and their encoded proteins have provided therapeutic targets. However, little is known about which cells are the functional home of these disease-associated genes and proteins. Single-cell technologies are enabling high-resolution profiling of cell phenotypes and revealing cellular contexts of disease, yet much of the resulting knowledge remains embedded in individual datasets and scientific literature. To address these gaps, the National Library of Medicine has developed Cell Knowledge Network (NLM-CKN, https://nlm-ckn.org ). Reproducible computational workflows have generated cell phenotype knowledge for 2,585 cell sets and 5,139 selectively expressed genes from 88 datasets covering 10 human organs. Mapping of these cell sets to cell types grounds Cell Ontology terms in experimental evidence. This experimental knowledge is integrated with external knowledge of anatomical and cell-type hierarchies, gene-disease associations, and therapeutic interventions. A semantic schema defines node types and relations, enabling knowledge to be transformed into triple assertions and loaded into an ArangoDB database with provenance and quantitative evidence. The NLM-CKN interface supports graphical exploration of the cellular constituents of healthy human tissues. Finally, topological analyses generate insights into cellular contributions to disease pathogenesis, cellular contexts for therapeutic intervention, and drug-repurposing hypotheses.

Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors. Predicting this disease early is challenging because it depends on traditional diagnostic methods that face issues of subjectivity, which commonly delay diagnosis. Several objective analyses are currently in practice to help overcome the challenges of subjectivity; however, a proper explanation of these analyses is still lacking. While machine learning (ML) has demonstrated potential in supporting PD diagnosis, existing approaches often rely on subjective reports only and lack interpretability for individualized risk estimation. This study proposes SCOPE-PD, an explainable AI-based prediction framework, by integrating subjective and objective assessments to provide personalized health decisions. Subjective and objective clinical assessment data are collected from the Parkinson's Progression Markers Initiative (PPMI) study to construct a multimodal prediction framework. Several ML techniques are applied to these data, and the best ML model is selected to interpret the results. Model interpretability is examined using SHAP-based analysis. The Random Forest algorithm achieves the highest accuracy of 98.66 percent using combined features from both subjective and objective test data. Tremor, bradykinesia, and facial expression are identified as the top three contributing features from the MDS-UPDRS test in the prediction of PD.

Lung cancer is a leading cause of cancer-related mortality, with disparities in incidence and outcomes observed across different racial and sex groups. Understanding the genetic factors of these disparities is critical for developing targeted treatment therapies. This study aims to identify both patient-specific and cohort-specific biomarker genes that contribute to lung cancer health disparities among African American males (AAMs), European American males (EAMs), African American females (AAFs), and European American females (EAFs). The real-world data is highly imbalanced with respect to race, and the lung cancer dataset is no exception. So, classification with race labels will generate highly biased results toward the larger cohort. We developed a computational framework by designing the classification problems with disease conditions instead of races and leveraging the local interpretability of explainable AI, SHAP (SHapley Additive exPlanations). This study used three disease conditions of lung cancer, including Lung Adenocarcinoma (LUAD), Lung Squamous Cell Carcinoma (LUSC), and Healthy samples (HEALTHY) to design four classification tasks: one 3-class problem (LUAD-LUSC-HEALTHY) and three 2-class problems (LUAD-LUSC, LUAD-HEALTHY, and LUSC-HEALTHY). This multiple-classification approach allows a LUAD patient to be interrogated via three classification problems, namely LUAD-LUSC-HEALTHY, LUAD-LUSC, and LUAD-HEALTHY, thus providing a robust approach of retrieving disparity information for individual patients through the local interpretation of SHAP. The proposed method successfully discovered the sets of genes and pathways related to health disparities in lung cancer between two cohorts, including AAMs vs. EAMs, AAFs vs. EAFs, AAMs vs. AAFs, and EAMs vs. EAFs. The discovered list of genes and pathways provide a short list for biological scientists to conduct wet lab experiment.