MAAPE: A Modular Approach to Evolutionary Analysis of Protein Embeddings

Abstract

We present MAPPE, a novel algorithm integrating a k-nearest neighbor (KNN) similarity network with co-occurrence matrix analysis to extract evolutionary insights from protein language model (PLM) embeddings. The KNN network captures diverse evolutionary relationships and events, while the co-occurrence matrix identifies directional evolutionary paths and potential signals of gene transfer. MAPPE overcomes the limitations of traditional sequence alignment methods in detecting structural homology and functional associations in low-similarity protein sequences. By employing sliding windows of varying sizes, it analyzes embeddings to uncover both local and global evolutionary signals encoded by PLMs. We have benchmarked MAAPE approach on two well-characterized protein family datasets: the Als regulatory system (AlsS/AlsR) and the Rad DNA repair protein families. In both cases, MAAPE successfully reconstructed evolutionary networks that align with established phylogenetic relationships. This approach offers a deeper understanding of evolutionary relationships and holds significant potential for applications in protein evolution research, functional prediction, and the rational design of novel proteins.