ASPECT: Alternative Splicing Event Classification with Transformers

Motivation: Alternative splicing (AS) is a fundamental regulatory mechanism that expands transcriptomic and proteomic diversity by generating multiple mRNA isoforms from a single gene. Aberrant AS has been implicated in numerous diseases through the production of dysfunctional or pathogenic protein variants. However, much of the existing AS research has focused predominantly on exon skipping and constitutive splicing, with comparatively limited attention to other biologically relevant AS event types. Moreover, many current computational approaches rely on short genomic sequence windows and conventional deep learning architectures, which may limit their ability to capture broader regulatory context associated with complex splicing decisions. Bridging these methodological and conceptual gaps is essential for advancing comprehensive AS characterization and improving our understanding of its role in human health and disease. Results: We present ASPECT, an alternative splicing event classification framework built upon DNABERT-2 with Byte Pair Encoding (BPE) tokenization. Across multiple binary alternative splicing event pair classification tasks, ASPECT achieves consistently strong performance as measured by AUC, F1-score, and accuracy, demonstrating reliable discrimination between closely related splicing event types. Importantly, ASPECT demonstrates consistent performance when applied to TCGA BRCA cancer-associated splicing events reconstructed from SpliceSeq annotations, supporting its applicability beyond the canonical splicing events used for training. Availability: The open-source code, data, and detailed documentation used in this study are available at https://github.com/OluwadareLab/ASPECT. Contact: Oluwatosin.Oluwadare@unt.edu. Supplementary information: N/A.