Design of Peptide-Based Protein Degraders via Contrastive Deep Learning
Palepu, K.; Ponnapati, M.; Bhat, S.; Tysinger, E.; Stan, T.; Brixi, G.; Koseki, S. R. T.; Chatterjee, P.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWTherapeutic modalities targeting pathogenic proteins are the gold standard of treatment for multiple disease indications. Unfortunately, a significant portion of these proteins are considered "undruggable" by standard small molecule-based approaches, largely due to their disordered nature and instability. Designing functional peptides to undruggable targets, either as standalone binders or fusions to effector domains, thus presents a unique opportunity for therapeutic intervention. In this work, we adapt recent models for contrastive language-image pre-training (CLIP) to devise a unified, sequence-based framework to design target-specific peptides. Furthermore, by leveraging known experimental binding proteins as scaffolds, we create a streamlined inference pipeline, termed Cut&CLIP, that efficiently selects peptides for downstream screening. Finally, we experimentally fuse candidate peptides to E3 ubiquitin ligase domains and demonstrate robust intracellular degradation of pathogenic protein targets in human cells, motivating further development of our technology for future clinical translation.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Accelerating protein engineering with fitness landscape modeling and reinforcement learning 95%
- PepFlow: direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion 95%
- Evaluating generalizability of artificial intelligence models for molecular datasets 93%
Similar papers in this journal
Similar papers in this journal
- biocentral: embedding-based protein predictions 92%
- Assembly of Protein Complexes In and On the Membrane with Predicted Spatial Arrangement Constraints 92%
- Identification of Iron-Sulfur (Fe-S) and Zn-binding Sites Within Proteomes Predicted by DeepMind's AlphaFold2 Program Dramatically Expands the Metalloproteome 91%
Similar papers in this journal
- Sequence-based prediction of protein-protein interactions: a structure-aware interpretable deep learning model 94%
- Meta Learning Improves Robustness and Performance in Machine Learning-Guided Protein Engineering 94%
- DynamicGT: a dynamic-aware geometric transformer model to predict protein binding interfaces in flexible and disordered regions 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.