ELITE: E3 Ligase Inference for Tissue specific Elimination: A LLM Based E3 Ligase Prediction System for Precise Targeted Protein Degradation

Targeted protein degradation (TPD) has transformed modern drug discovery by harnessing the ubiquitin-proteasome system to eliminate disease-driving proteins previously deemed undruggable. However, current approaches predominantly rely on a narrow set of ubiquitously expressed E3 ligases, such as Cereblon (CRBN) and Von Hippel-Lindau (VHL), which limits tissue specificity, increases systemic toxicity, and fosters resistance. Here, we present an AI-driven framework for the rational identification of tissue-specific E3 ligases suitable for precision-targeted degradation. Our model leverages an BERT-based protein language architecture trained on billions of sequences to generate contextual embeddings that capture structural and functional motifs relevant for E3-substrate compatibility. By integrating these embeddings with tissue-resolved protein-protein interaction data, the framework predicts ligase-target interactions that are both biologically plausible and context-restricted. This enables the prioritization of ligases capable of driving selective degradation of pathogenic proteins within disease-relevant tissues. The proposed approach offers a scalable path to expand the E3 ligase repertoire and advance TPD toward true precision medicine. The AI architecture used in this study builds upon a well-established, state-of-the-art protein language modeling framework rather than introducing a fundamentally new model design. The principal contribution instead lies in the deliberate engineering of a task-specific dataset that integrates large-scale protein sequence embeddings with tissue-resolved expression and interaction information tailored to targeted protein degradation. By curating and harmonizing these heterogeneous data modalities for the explicit purpose of identifying tissue-selective E3 ligases, we enable a generalizable foundation model to be effectively adapted to a previously unexplored application context. This data-centric advance underpins the framework's ability to generate biologically meaningful, context-aware predictions and represents a central contribution of the present work.