Zero/Few-Shot Dark Kinase-Phosphosite Associatıon Predictıon With Biologically Grounded Data Augmentation

Protein phosphorylation, a fundamental cellular process mediated by kinases, iscrucial for signaling, and its dysregulation is implicated in numerous human diseases.A significant challenge persists in identifying substrate phosphosites for the vastnumber of understudied ’dark’ kinases, for which conventional supervised machinelearning methods are ineffective due to data scarcity. To address this gap, thisthesis develops a zero- and few-shot learning framework and introduces biologicallygrounded data augmentation strategies, all evaluated on the DARKIN benchmark.We introduce two novel deep learning architectures: DARKIN-FT, a compatibilitybasedmodel that enhances performance through end-to-end fine-tuning of phosphositeencoder, and DARKIN-Interact, a binary classification model that directlycaptures kinase–substrate interactions via joint attention over sequence pairs. Thecentral contribution is a systematic investigation into biologically grounded dataaugmentation, evaluating three distinct strategies: (i) kinase-conditional phosphositegeneration via a fine-tuned ProGen2 model, (ii) weak supervision using predictionsfrom the Kinase Substrate Specificity Atlas (KSSA), and (iii) augmentationwith homologous sequences. Our results demonstrate that DARKIN-FT and DARKIN-Interact significantly outperformexisting baselines on the DARKIN benchmark. The investigation intodata augmentation yielded mixed results: while kinase conditional generation withProGen2 and weak labeling with KSSA degraded the performance, augmentationwith homologous sequences improved the Macro Average Precision of the DARKINInteractmodel. While the results are promising, challenges persist in disambiguatingkinases with high sequence similarity.Overall, this thesis establishes a framework for kinase–phosphosite interaction predictionin low-data regimes and provides valuable insights into the strengths andlimitations of data augmentation in the dark kinase-phosphosite association task.