GraphFLA
收藏资源简介:
GraphFLA是一个Python框架,用于构建和分析来自突变数据的不同模态(例如,DNA、RNA、蛋白质等)中的适应性景观。GraphFLA计算了20个生物学相关的特征,这些特征表征了景观地形学的4个基本方面。通过将GraphFLA应用于来自ProteinGym、RNAGym和CIS-BP的超过5,300个景观,我们展示了其在解释和比较数十个适应性预测模型性能方面的实用性。此外,我们发布了155个完整的经验适应性景观,涵盖了各种模态中超过220万个序列。
GraphFLA is a Python framework for constructing and analyzing fitness landscapes across diverse modalities (e.g., DNA, RNA, proteins, etc.) derived from mutation data. GraphFLA computes 20 biologically relevant features that characterize four fundamental aspects of landscape topography. By applying GraphFLA to over 5,300 landscapes sourced from ProteinGym, RNAGym, and CIS-BP, we demonstrate its utility in interpreting and comparing the performance of dozens of fitness prediction models. Additionally, we release 155 complete empirical fitness landscapes encompassing over 2.2 million sequences across various modalities.




