Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model
This work addresses the challenge of designing antibodies with specific chain pairing constraints for biomedical applications, representing an incremental advance by incorporating protein-protein interactions into generative models.
The authors tackled the problem of generative antibody design by developing pAbT5, an encoder-decoder model that generates complementary heavy or light chains from a pairing partner, resulting in sequences that respect conservation in framework regions and variability in hypervariable domains, with demonstrated recovery of ground-truth chain type and gene families.
Current protein language models (pLMs) predominantly focus on single-chain protein sequences and often have not accounted for constraints on generative design imposed by protein-protein interactions. To address this gap, we present paired Antibody T5 (pAbT5), an encoder-decoder model to generate complementary heavy or light chain from its pairing partner. We show that our model respects conservation in framework regions and variability in hypervariable domains, demonstrated by agreement with sequence alignment and variable-length CDR loops. We also show that our model captures chain pairing preferences through the recovery of ground-truth chain type and gene families. Our results showcase the potential of pAbT5 in generative antibody design, incorporating biological constraints from chain pairing preferences.