MotivationGeneral-purpose protein structure embedding can be used for many important protein biology tasks, such as protein design, drug design and binding affinity prediction. Recent researches have shown that attention-based encoder layers are more suitable to learn high-level features. Based on this key observation, we propose a two-level general-purpose protein structure embedding neural network, called ContactLib-ATT. On local embedding level, a biologically more meaningful contact context is introduced. On global embedding level, attention-based encoder layers are employed for better global representation learning.ResultsOur general-purpose protein structure embedding framework is trained and tested on the SCOP40 2.07 dataset. As a result, ContactLib-ATT achieves a SCOP superfamily classification accuracy of 82.4% (i.e., 6.7% higher than state-of-the-art method). On the same dataset, ContactLib-ATT is used to simulate a structure-based search engine for remote homologous proteins, and our top-10 candidate list contains at least one remote homolog with a probability of 91.9%.Contactningkang@hust.edu.cn and xfcui@email.sdu.edu.cn

Background The results from the previous experiment have demonstrated that there were occurrence of bone loss and excess metabolism in Hyperthyroidism-induced rats. Thus, there was speculation that there may be an underlying relationship between metabolism and bone loss. In addition, there were past studies showing acetylation influencing metabolism in tissues and diseases. The hypothesis from this case study stated that excessive metabolism was induced upon acetylated vital metabolism enzymes. Results In the case study, a HYP-induced osteoporosis rats model was used and the glucose metabolite was tested through the acetylation of proteins by the mass spectrometer. The results showed that pivotal enzymes of Glycolysis-Tricarboxylic acid cycle-Oxidative phosphorylation were acetyled along with upregulated metabolites. All the acetyly-lysine sites of related enzymes were listed in this article.Our results showed that bone loss in HYP rats accompanied by upregulation of CREB-binding protein (Crebbp, CBP). Furthermore, our result indicated that CBP has a close relationship with enhancement of LDHa that promote glucose metabolism. Conclusions Acetylation is the key variable of energy metabolism in hyperthyroid osteoporosis rats, therein, we showed a representation relationship between CBP and LDHa.