AI and Rare Diseases ── Platforms ── 2026-11-14
Rare-disease diagnosis and drug discovery platforms and AI
- Abstract
BACKGROUND: In children, Kawasaki disease (KD) - characterized by immune dysregulation and vasculitis - represents the most common cause of acquired heart disease. Although cell adhesion molecules (CAMs) contribute significantly to the vascular inflammation observed in KD, how they act synergistically and how this knowledge might be applied clinically remain poorly understood. METHODS: Leveraging multiple public KD transcriptomic datasets, we identified differentially expressed CAM-related genes through differential expression analysis and WGCNA, then used four machine learning algorithms (Least Absolute Shrinkage and Selection Operator, eXtreme Gradient Boosting, random forest, and support vector machine recursive feature elimination) to build a six-gene diagnostic model. Immune infiltration was assessed via single sample Gene Set Enrichment Analysis, CIBERSORT, and MCP-Counter, and molecular subtyping with functional enrichment by clusterProfiler. RESULTS: This study pinpointed six core diagnostic genes. The model built from them showed excellent discriminative ability across training and several independent validation datasets. Immune profiling revealed a KD microenvironment skewed by overabundant innate immune cells (neutrophils, monocytes, macrophages) and marked deficiency of adaptive immune cells (CD8+ T cells, NK cells, B cells). Using these genes, patients split into two molecular subtypes, with subtype 2 featuring enhanced adaptive immune infiltration. CONCLUSION: A six-gene KD diagnostic model is proposed here, revealing immune imbalance, molecular subtypes, and potential drug targets, and offering novel insights into CAM-associated pathways.
Journal IF-equivalent: 2.5 (OpenAlex 2-year mean citedness, value as of 2026-11-12, retrieved 2026-11-13; not the official Clarivate IF)Reference: Shao Z, Ruan Z, Sheng F, Su C. Establishment and validation of a diagnostic model for Kawasaki disease based on cell adhesion molecule-related genes and analysis of immune-related features. Microvasc Res. 2026 Nov [Epub ahead of print]. doi:10.1016/j.mvr.2026.105036. PMID: 43014667.Checked: Abstract only - Abstract
BACKGROUND: Traditional molecular diagnosis of rare genetic diseases often struggles with complex genotype-phenotype relationships, such as pleiotropy and locus heterogeneity. Despite advances in next-generation sequencing, variant interpretation remains a major bottleneck, frequently requiring labor-intensive expert review to establish phenotypic specificity. To address this challenge, we developed GenPhenia, a deep learning-based framework designed to assist phenotype-driven gene prioritization using clinical features encoded with the Human Phenotype Ontology (HPO). RESULTS: GenPhenia leverages large-scale synthetic clinical history datasets and a graph neural network architecture with message-passing strategies combined with BERT-based phenotype embeddings to learn phenotype-gene associations. The model was validated using both ClinVar-derived datasets and real-world clinical cohorts. On the challenging MCRD benchmark dataset, GenPhenia achieved 60% Top-1 recall and 80% Top-10 recall, substantially outperforming previously reported methods, which achieved less than 30% Top-10 recall under the same conditions. Clinical case studies across endocrinology, cardiology, and immunology further demonstrate that the model effectively refines gene rankings as phenotypic specificity increases during the diagnostic process. CONCLUSIONS: GenPhenia provides a scalable and highly sensitive computational approach for phenotype-driven gene prioritization that aligns with the iterative nature of clinical phenotyping and genomic diagnosis. The framework may facilitate more efficient variant interpretation and support the integration of artificial intelligence methods into clinical genomics workflows for rare disease diagnosis.
Journal IF-equivalent: 4.6 (OpenAlex 2-year mean citedness, value as of 2026-11-12, retrieved 2026-11-13; not the official Clarivate IF)Reference: Brunello FG, Colangelo G, Rius A, Erra L, Lugones AC, Aguirre N, et al. GenPhenia: using deep neural networks to accelerate rare-disease diagnosis. Hum Genomics. 2026 Aug 14;20(1):159. doi:10.1186/s40246-026-01023-9. PMID: 43015840.Checked: Abstract only