Beyond the canonical: The role of post-transcriptional regulation in drug-target interaction prediction

Protein isoforms produced from the same gene through post-transcriptional regulatory mechanisms, such as alternative splicing, can substantially alter protein structure and function, including drug-binding properties. However, most existing drug-target interaction (DTI) and drug-target affinity (DTA) prediction models rely exclusively on a single representative protein sequence per gene, typically the canonical or longest isoform, thereby overlooking the functional diversity introduced by alternative isoforms. This assumption can introduce bias, limit generalizability, and compromise the biological validity of model predictions. In this study, we systematically investigate the impact of protein isoform variation on DTI prediction accuracy. Our results show that substituting the canonical sequence with an alternative isoform often leads to substantial declines in predictive performance. Structural and binding affinity analyses further reveal that these discrepancies are frequently associated with changes in predicted binding-site configurations, which we further examine through controlled perturbations of binding-site residues. These experiments suggest that even subtle alterations in binding regions can lead to inconsistent DTI predictions. Overall, our findings uncover a critical limitation in current DTI modeling frameworks and underscore the importance of incorporating isoform-specific information to better reflect biological reality and improve therapeutic relevance. The codes and datasets are available at https://github.com/compbiolabucf/DTIVariant.Author summary: Computational drug–target interaction models have become central tools in modern drug discovery, yet they typically represent each gene with a single canonical protein sequence, overlooking the fact that most human genes produce multiple isoforms through alternative splicing. These isoforms can differ in structure and drug-binding properties, raising the question of whether current prediction models are robust to such biologically realistic variation. Here, we systematically evaluate how replacing canonical sequences with alternative isoforms from the same gene affects both drug–target interaction and drug–target affinity predictions. We find that even when interaction labels are kept unchanged, isoform substitution often leads to substantial performance declines. Structural comparisons suggest that prediction consistency is closely linked to preservation of binding-site geometry, and controlled removal of binding-site residues progressively disrupts both interaction classification and affinity estimation. Together, our findings expose a fundamental limitation of gene-level modeling assumptions and highlight the need for isoform-aware datasets and prediction strategies to better reflect the functional complexity of the human proteome.