Recent advances in deep learning have enabled the development of large-scale multimodal models for virtual screening and de novo molecular design. The human kinome with its abundant sequence and inhibitor data presents an attractive opportunity to develop proteochemometric models that exploit the size and internal diversity of this family of targets. Here we challenge a standard practice in sequence-based affinity prediction models: instead of leveraging the full primary structure of proteins, each target is represented by a sequence of 29 residues defining the ATP binding site. In kinase-ligand binding affinity prediction, our results show that the reduced active site sequence representation is not only computationally more efficient but consistently yields significantly higher performance than the full primary structure. This trend persists across different models, datasets, performance metrics and holds true when predicting affinity for both unseen ligands and kinases. Our interpretability analysis further demonstrates that, even without supervision, the full sequence model can learn to focus on the active site residues to a higher extent. We then investigate a de novo molecular design task and find that the active site provides benefits in the computational efficiency, but otherwise, both kinase representations yield similar optimized affinities (for both SMILES and SELFIES-based molecular generators). Our work challenges the assumption that full primary structure is indispensable for modelling human kinases. We hope that these results will inspire additional investigation into hybrid mechanistic-DL modeling approaches to support the identification and optimization of kinase inhibitors’ candidates.