I. Introduction
To reduce the manufacturing costs of antibody drugs, it is crucial to predict physicochemical properties such as hydrophobicity and thermo-stability from antibody sequences. Recent emerging protein language models (pLMs) are beneficial for predicting antibody properties. As the pLM is pretrained on a large amount of protein sequence, the model can predict antibody properties even though it is fine-tuned using only a small amount of data regarding the target task.