Protein Language Models (PLMs) have emerged as performant and scalable tools
for predicting the functional impact and clinical significance of
protein-coding variants, but they still lag experimental accuracy. Here, we
present a novel fine-tuning approach to improve the performance of PLMs with
experimental maps of variant effects from Deep Mutational Scanning (DMS) assays
using a Normalised Log-odds Ratio (NLR) head. We find consistent improvements
in a held-out protein test set, and on independent DMS and clinical variant
annotation benchmarks from ProteinGym and ClinVar. These findings demonstrate
that DMS is a promising source of sequence diversity and supervised training
data for improving the performance of PLMs for variant effect prediction.

通过深度突变扫描（DMS）试验的实验性映射，使用归一化的对数比率（NLR）头部，提出了一种改进蛋白质语言模型（PLMs）性能的微调方法，以改善变异效应预测的性能。

用深入突变扫描对蛋白质语言模型进行微调，提高变体效应预测

Fine-tuning Protein Language Models with Deep Mutational Scanning  improves Variant Effect Prediction

Reliable prediction of variant effects in proteins has seen considerable
progress in recent years. The increasing availability of data in this regime
has improved both the prediction performance and our ability to track progress
in the field, measured in terms of prediction accuracy averaged over many
datasets. For practical use in protein engineering, it is important that we can
also provide reliable uncertainty estimates for our predictions, but such
metrics are rarely reported. We here provide a Gaussian process regression
model, Kermut, which obtains state-of-the-art performance for protein property
prediction while also offering estimates of uncertainty through its posterior.
We proceed by assessing the quality of these uncertainty estimates. Our results
show that the model provides meaningful overall calibration, but that accurate
instance-specific uncertainty quantification remains challenging. We hope that
this will encourage future work in this promising direction.

在蛋白质领域，可靠的变异影响预测取得了显著进展，通过提供具备不确定性估计的高斯过程回归模型 Kermut，能够在蛋白质属性预测中获得最先进的性能，并展示了对预测的可靠性定量估计的质量评估结果。