Variant-resolved prediction of context-specific isoform variation with a graph-based attention model
Clinical Snapshot
PICO Framework
| P — Population | Human genomic sequences and long-read transcriptomes across 30 tissue types and brain regions, with application to autism cohort datasets |
| I — Intervention | Otari graph neural network framework for predicting tissue-specific differential isoform abundance |
| C — Comparator | Gene-level analysis approaches and existing isoform prediction methods |
| O — Outcomes | Tissue-specific isoform abundance predictions, variant effect interpretation, detection of isoform dysregulation patterns in autism |
Bottom Line
Otari represents a significant advancement in computational genomics by providing the first framework capable of predicting how genetic variants affect specific transcript isoforms across different tissues. This tool addresses a critical gap in genetic variant interpretation, moving beyond gene-level analysis to capture the complexity of alternative splicing and isoform regulation. The validation in autism cohorts demonstrates clinical relevance, potentially identifying pathogenic mechanisms missed by conventional approaches. For Australian clinicians, this could enhance genetic counselling and diagnostic precision, particularly in neurodevelopmental disorders. However, the clinical utility will depend on validation studies demonstrating improved diagnostic accuracy and patient outcomes. The framework's availability as a research resource should accelerate isoform-focused studies, though implementation in routine clinical practice will require further validation and integration with existing genomic analysis pipelines.
Key Findings
P Value: Not reported
Effect Size: Not specified in abstract
Primary Outcome: Successful prediction of tissue-specific differential isoform abundance and detection of variant-driven isoform dysregulation
Nnt Or Sensitivity: Sensitivity and specificity for isoform prediction not reported
Confidence Interval: Not reported
Clinical Application
Requires computational infrastructure and bioinformatics expertise for implementation Could enhance genetic testing services through Medicare and support precision medicine initiatives, particularly relevant for autism diagnosis and research in Australian healthcare settings Patients undergoing genetic testing for autism spectrum disorders and other conditions where isoform variation may be clinically relevant
Abstract
In eukaryotes, most genes produce multiple transcript isoforms that diversify the transcriptome and proteome, serving as a key mechanism of functional regulation. Genetic variation can disrupt the RNA processing signals that shape isoform structure and abundance, yet modeling these effects at full-length isoform resolution remains challenging due to the complexity of transcript regulation. Here, we introduce Otari, an attention-based graph neural network framework trained on the human genomic sequence and long-read transcriptomes across 30 tissue types and brain regions. Otari predicts tissue-specific differential isoform abundance by integrating sequence-derived epigenetic and post-transcriptional signals, enabling isoform-resolved variant effect interpretation. Applied to large-scale variant datasets, including an autism cohort, Otari uncovers patterns of isoform dysregulation undetectable at the gene level, such as variant-driven perturbations in isoform abundance and microexon usage implicated in autism pathophysiology. We provide Otari as a resource for powering isoform-level analyses across tissues at scale.
References
- 1.Litman, A., Pan, Z., Sokolova, K., Fang, J., Marvin, T., Sauerwald, N., Park, C. Y., Theesfeld, C. L., & Troyanskaya, O. G. (2025). Variant-resolved prediction of context-specific isoform variation with a graph-based attention model. Cell Genomics, 101126. https://doi.org/10.1016/j.xgen.2025.101126
Related Research
PloS one
Fundus image analysis of retinitis pigmentosa using artificial intelligence
25 July 2026
Journal of medical Internet research
Initial-Visit Specialty Triage in Rare Diseases Using Large Language Models: Retrospective Benchmarking Study
24 July 2026
Nucleic acids research
SNPnexus: an enhanced web platform for large-scale and multi-sample variant analysis (2025 update)
13 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service