Mass spectrometry (MS)-based phosphoproteomics enables the quantification of proteome-wide phosphorylation in cells and tissues. A major challenge in MS-based phosphoproteomics lies in identifying the substrates of kinases, as currently only a small fraction of substrates identified can be confidently linked with a known kinase. By leveraging large-scale phosphoproteomics data, machine learning has become an increasingly popular approach for computationally predicting substrates of kinases. However, the small number of high-quality experimentally validated kinase substrates (true positive) and the high data noise in many phosphoproteomics datasets together impact the performance of existing approaches. Here, we aim to develop advanced kinase-substrate prediction methods to address these challenges. Using a collection of seven large phosphoproteomics datasets, including six published datasets and a new muscle differentiation dataset, and both traditional and deep learning models, we first demonstrate that a 'pseudo-positive' learning strategy for alleviating small sample size is effective at improving model predictive performance. We next show that a data re-sampling based ensemble learning strategy is useful for improving model stability while further enhancing prediction. Lastly, we introduce an ensemble deep learning model ('SnapKin') incorporating the above two learning strategies into a 'snapshot' ensemble learning algorithm. We demonstrate that the SnapKin model achieves overall the best performance in kinase-substrate prediction. Together, we propose SnapKin as a promising approach for predicting substrates of kinases from large-scale phosphoproteomics data. SnapKin is freely available at https://github.com/PYangLab/SnapKin.

Cells respond to alterations in their nutrient environment by adjusting the abundance of surface nutrient transporters and receptors. This can be achieved through modulation of ubiquitin-dependent endocytosis, which in part is regulated by the NEDD4 family of E3 ligases. Here we report four novel modes by which Pub1, a fission yeast Schizosaccharomyces pombe member of the NEDD4-family of E3 ligases, is regulated. Phosphorylation of the conserved serine 188 (an analogous site in human NEDD4L is phosphorylated but uncharacterized) provides resistance to extracellular canavanine, a toxic arginine analog, indicating S188 phosphorylation enhances Pub1 function to reduce canavanine uptake. Both Pub1 serine 188 phosphorylation and proteasomal turnover of Pub1 are inhibited by Gsk3 kinase. Thus, whilst Gsk3 kinase protects Pub1 protein levels it restrains Pub1 E3 ligase function by reducing serine 188 phosphorylation. Nitrogen stress stimulates Pub1 protein turnover by the proteasome, reducing protein levels by 60% and thereby increasing abundance of the amino acid transporter Aat1 at the plasma membrane. TOR complex 2 and Gad8 (AKT) signaling negatively regulates Pub1 protein levels, and the increased proteasomal Pub1 turnover upon nitrogen stress requires TORC2 signaling. In summary, environmental control of Pub1 protein levels to modulate the abundance of nutrient transporters is regulated by the major TORC2 nutrient-sensing signaling network and proteasomal dependent control of Pub1 protein levels.