用于拓扑特征数据驱动学习的流程及其在蛋白质稳定性预测中的应用
A Pipeline for Data-Driven Learning of Topological Features with Applications to Protein Stability Prediction
AI总结：
提出数据驱动学习蛋白质结构可解释拓扑特征的流程，证明其性能接近专家生物物理特征，并可通过特征融合提升蛋白质稳定性预测。
摘要：
本文提出一种数据驱动方法，用于学习生物分子数据的可解释拓扑特征，并展示了基于拓扑特征训练的简约模型在预测合成微型蛋白质稳定性方面的有效性。我们将利用自动学习结构特征的模型，与基于由领域专家（SME）确定的大量生物物理特征训练的模型进行比较。仅基于蛋白质结构拓扑特征的模型，在平均精确率分数方面达到了基于SME模型性能的92%至99%。通过考察模型性能和特征重要性指标，我们提取了大量洞见，揭示了拓扑特征与SME特征之间的高度相关性。我们进一步展示了，相比单独使用任一特征集，结合拓扑特征与SME特征如何带来更好的模型性能；这表明在某些情形下，拓扑特征可能提供现有SME特征未捕捉到的、对蛋白质稳定性预测有用的新判别信息。
英文摘要：
In this paper, we propose a data-driven method to learn interpretable topological features of biomolecular data and demonstrate the efficacy of parsimonious models trained on topological features in predicting the stability of synthetic mini proteins. We compare models that leverage automatically-learned structural features against models trained on a large set of biophysical features determined by subject-matter experts (SME). Our models, based only on topological features of the protein structures, achieved 92%-99% of the performance of SME-based models in terms of the average precision score. By interrogating model performance and feature importance metrics, we extract numerous insights that uncover high correlations between topological features and SME features. We further showcase how combining topological features and SME features can lead to improved model performance over either feature set used in isolation, suggesting that, in some settings, topological features may provide new discriminating information not captured in existing SME features that are useful for protein stability prediction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
