Investigation of Protein Melting Temperature Prediction with Cross-Method Validation on Biophysical Data

Abstract Motivation Protein melting temperature ( T m ) prediction accelerates the discovery of thermostable enzymes which are crucial for industrial biotechnology often requiring harsh reaction conditions. Experimental determination of T m remains labour-intensive and varies across techniques, motivating the development of in silico predictors. Mass-spectrometry datasets such as Meltome Atlas now enable large-scale T m prediction with models based on deep learning, but model generalisation across diverse experimental datasets has not been systematically tested. Results We evaluated the generalisability of state-of-the-art deep learning approaches and explored ESM-based embeddings for T m prediction. To this end, we assembled the ProMelt training dataset (45 441 proteins) and five independent biophysics-based validation datasets. Our analysis revealed substantial differences between proteomics- and biophysics-based T m measurements, highlighting the challenge of cross-domain generalisation. Existing state-of-the-art predictors trained on large-scale proteomics datasets showed reduced performance on biophysics-based validation sets. Our fine-tuned embedding-based models, particularly LoRA-adapted ESM-2 (TmProt 1.0), outperformed state-of-the-art predictors in identifying thermostable proteins ( T m ≥ 60 °C) across heterogeneous datasets, achieving AUC scores of 0.75–0.77. We also demonstrated that the available models could be used efficiently in the sequence prioritization task. Availability The TmProt web server is available at https://loschmidt.chemi.muni.cz/tmprot/ . Source code and data are available at https://github.com/loschmidt/TmProt .