GPS-PBS: A Deep Learning Framework to Predict Phosphorylation Sites that Specifically Interact with Phosphoprotein-Binding Domains

Protein phosphorylation is essential for regulating cellular activities by modifying substrates at specific residues, which frequently interact with proteins containing phosphoprotein-binding domains (PPBDs) to propagate the phosphorylation signaling into downstream pathways. Although massive phosphorylation sites (p-sites) have been reported, most of their interacting PPBDs are unknown. Here, we collected 4458 known PPBD-specific binding p-sites (PBSs), considerably improved our previously developed group-based prediction system (GPS) algorithm, and implemented a deep learning plus transfer learning strategy for model training. Then, we developed a new online service named GPS-PBS, which can hierarchically predict PBSs of 122 single PPBD clusters belonging to two groups and 16 families. By comparison, GPS-PBS achieved a highly competitive accuracy against other existing tools. Using GPS-PBS, we predicted 371,018 mammalian p-sites that potentially interact with at least one PPBD, and revealed that various PPBD-containing proteins (PPCPs) and protein kinases (PKs) can simultaneously regulate the same p-sites to orchestrate important pathways, such as the PI3K-Akt signaling pathway. Taken together, we anticipate GPS-PBS can be a great help for further dissecting phosphorylation signaling networks.

Human genome-wide analysis and identification of the hyperphosphorylation-elicited interactions between subarachnoid tau protein and phosphoprotein-binding domains

Abnormally hyperphosphorylated tau can be recognized by a variety of phosphoprotein-binding domains (PBDs) to elicit downstream tau signaling in neuropathology, which has been found to have a potential association with subarachnoid hemorrhage. In this study, the genome-wide binding behavior of tau phosphorylation sites (p-sites) to PBDs involved in subarachnoid hyperphosphorylation events was systematically profiled at molecular level by integrating peptide docking, structural minimization, affinity scoring, and binding assay, from which a number of potent PBD-p-site interaction pairs were identified. It was revealed that the PBD domains exhibit distinct binding preferences for phosphotyrosine, phosphoserine, and phosphothreonine p-sites; the PBD-recognition specificity of different tau p-sites is not overlapped with each other, and their phosphorylations would therefore regulate varying biological functions in tau signaling. A number of PBD-p-site pairs were identified to have potent binding potency as compared to others. The KCIP-pS[393-399] pair was found as a strong binder, which was further optimized with a rational peptide design protocol to derive a number of affinity-improved phosphopeptides. Structural analysis revealed diverse noncovalent chemical forces across the complex interface of KCIP domain with a designed high-affinity pS[393-399]-d4, which confers both stability and specificity to the domain-peptide complex system, with affinity improved by 10.9-fold relative to the native pS[393-399].