In this study, we expand upon the FLIP benchmark-designed for evaluating protein fitness prediction models in small, specialized prediction tasks-by assessing the performance of state-of-the-art large protein language models, including ESM-2 and SaProt on the FLIP dataset. Unlike larger, more diverse benchmarks such as ProteinGym, which cover a broad spectrum of tasks, FLIP focuses on constrained settings where data availability is limited. This makes it an ideal framework to evaluate model performance in scenarios with scarce task-specific data. We investigate whether recent advances in protein language models lead to significant improvements in such settings. Our findings provide valuable insights into the performance of large-scale models in specialized protein prediction tasks.
@article{arxiv.2501.18223,
title = {Exploring Large Protein Language Models in Constrained Evaluation Scenarios within the FLIP Benchmark},
author = {Manuel F. Mollon and Joaquin Gonzalez-Rodriguez and Alicia Lozano-Diez and Daniel Ramos and Doroteo T. Toledano},
journal= {arXiv preprint arXiv:2501.18223},
year = {2025}
}