LAFEM: A scoring model to evaluate functional landscape of lysine acetylome

Protein lysine acetylation is a critical post-translation modification (PTM) involved in a wide range of biological processes. To date, about 20,000 acetylation sites of homo sapiens were identified through mass spectrometry-based proteomic technology but more than 95% of them have unclear functional annotations due to the lack of existing prioritization strategy to assess the functional importance of the acetylation sites in large-scale. Hence, based on machine learning of 8 critical features surrounding lysine acetylation site, we established a lysine acetylation functional evaluating model (LAFEM) to high-throughput estimate the functional importance of given acetylation sites. Random-forest model and under-sampling dataset with the best performance were selected to construct LAFEM. Global analysis demonstrated that acetylation sites with high acetylation functional scores (AFSs) were commonly located in hub proteins and their molecular environment mainly had the features of larger solvent accessible surface area (SASA), stronger hydrogen-bonding-donating abilities, higher homology and disordered degree. Importantly, LAFEM performed well in validation dataset and acetylome and showed good complementarity with differentially expressed analysis. Cellular experiment confirmed that, in Nuclear Casein Kinase and Cyclin Dependent Kinase Substrate 1 (NUCKS1), acetyl-K35 with higher AFS was more important than acetyl-K9 with lower AFS in the proliferation of A549 cells. LAFEM provides a prioritization strategy to discover large-scale functional acetylation sites, which constitutes an unprecedented resource for better understanding of functional acetylome.