Accurate ΔT _m Prediction Without Protein Structure Inputs for Biomolecular Stability

Predicting protein stability, like changes in melting temperature ( ΔT _m ) caused by mutations, is a critical task in therapeutic protein engineering and drug discovery. This is reflected by a growing solution space, including both AI-based sequence and structure based methods. This paper demonstrates that accurate ΔT _m prediction does not require structural input features, but can achieve state-of-the-art results with a careful training design for large sequence-based protein language models. We combine an autoresearch-inspired setup search with controlled ablation studies and show that a well-tuned sequence-only ESM2-650M model [6] outperforms structure-informed methods in our benchmark, achieving the lowest error (MAE/RMSE) and competitive Pearson correlation without pH or structural inputs. We further show that choices such as loss function, pooling strategy, auxiliary supervision, and finetuning regime materially affect performance.