1. De Novo Design of RBX1 Protein Binders Using PXDesign RBX1 (RING-box protein 1) is the catalytic subunit of Cullin-RING E3 ubiquitin ligase complexes, enabling substrate ubiquitination and proteasomal degradation. Its dysregulation is associated with tumorigenesis, making it an important target for protein binder design with applications in functional modulation and targeted protein degradation. Designing binders against RBX1 is challenging due to complex protein–protein interfaces and the vast combinatorial sequence space. To address this, we developed a fully computational, de novo pipeline based on PXDesign. All designs were generated from scratch without motif scaffolding or lead optimization, ensuring compliance with competition constraints .

2. Overall Approach The workflow integrates backbone generation, sequence design, and multi-stage filtering. PXDesign generates binder backbones targeting the RBX1 surface, followed by sequence generation using ProteinMPNN. The resulting sequences undergo sequence-level filtering, novelty enforcement, diversity selection, and structure-based validation. This staged pipeline ensures that only high-confidence and experimentally viable candidates are retained.

3. Backbone Generation and Sequence Design De novo binder backbones were generated using PXDesign across multiple length ranges (64–200 amino acids), enabling exploration of diverse binding geometries and epitope accessibility. PXDesign uses a learned generative model to produce backbone conformations compatible with the target interface without relying on natural templates . Each backbone was processed using ProteinMPNN for inverse folding. Multiple sequences were generated per backbone, and top-scoring sequences based on model likelihood were retained, ensuring structural compatibility and energetic favorability.

4. Sequence-Level Filtering Generated sequences were filtered to remove candidates with poor developability before structural evaluation. This included checks for sequence validity, duplication, and length constraints (≤250 amino acids). Physicochemical properties such as hydrophobicity, charge balance, and amino acid diversity were evaluated alongside stability indicators like aromaticity and instability index. Sequences were also screened for liabilities including N-glycosylation, deamidation, isomerization motifs, aggregation propensity, and unpaired cysteine risk . Sequences failing strict thresholds were removed, while borderline candidates were ranked, with only the strongest progressing further.

5. Novelty and Diversity Constraints To ensure de novo design compliance, sequences were screened against UniRef50 using MMseqs2. Candidates with less than 25% edit distance from known proteins were excluded, ensuring novelty . Subsequently, sequences were clustered based on similarity, and representatives were selected to maintain diversity and avoid redundancy in the final candidate set.

6. Structure-Based Validation Final candidates were evaluated through structure prediction of binder–RBX1 complexes using a GPU-accelerated framework. Binding confidence was assessed using ipTM and pDockQ2, while interface accuracy was measured using ipSAE. Additional metrics included overall structural confidence (pTM), predicted binding affinity (ΔG) using PRODIGY, buried surface area, and interface error (PAE) . Candidates with poor interface formation, low confidence scores, or structural inconsistencies were discarded.

7. Ranking and Final Selection Final binders were ranked using a composite score prioritizing ipSAE and ipTM, followed by pDockQ2, predicted affinity, and interface properties . The top candidates were selected for submission, ensuring compliance with all competition constraints.

Conclusion This PXDesign-based pipeline provides a robust framework for de novo RBX1 binder design by integrating generative modeling, sequence optimization, and rigorous filtering. The approach efficiently reduces a large design space into a small set of high-confidence, novel, and experimentally viable candidates, improving the likelihood of successful expression and binding.