FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction.

The prediction of drug-target affinity (DTA) plays an increasingly important role in drug discovery. Nowadays, lots of prediction methods focus on feature encoding of drugs and proteins, but ignore the importance of feature aggregation. However, the increasingly complex encoder networks lead to the loss of implicit information and excessive model size. To this end, we propose a deep-learning-based approach namely FusionDTA. For the loss of implicit information, a novel muti-head linear attention mechanism was utilized to replace the rough pooling method. This allows FusionDTA aggregates global information based on attention weights, instead of selecting the largest one as max-pooling does. To solve the redundancy issue of parameters, we applied knowledge distillation in FusionDTA by transfering learnable information from teacher model to student. Results show that FusionDTA performs better than existing models for the test domain on all evaluation metrics. We obtained concordance index (CI) index of 0.913 and 0.906 in Davis and KIBA dataset respectively, compared with 0.893 and 0.891 of previous state-of-art model. Under the cold-start constrain, our model proved to be more robust and more effective with unseen inputs than baseline methods. In addition, the knowledge distillation did save half of the parameters of the model, with only 0.006 reduction in CI index. Even FusionDTA with half the parameters could easily exceed the baseline on all metrics. In general, our model has superior performance and improves the effect of drug-target interaction (DTI) prediction. The visualization of DTI can effectively help predict the binding region of proteins during structure-based drug design.

The Impact of Ultraviolet-B Radiation on the Sugar Contents and Protective Enzymes in Acyrthosiphon pisum.

Natural and anthropogenic changes have been altering many environmental factors. These include the amount of solar radiation reaching the Earth's surface. However, the effects of solar radiation on insect physiology have received little attention. As a pest for agriculture and horticulture, aphids are one of the most difficult pest groups to control due to their small size, high fecundity, and non-sexual reproduction. Study of the effects of UV-B radiation on aphid physiology may provide alternative control strategies in pest management. In this study, we examined the effects of UV-B radiation on protein and sugar contents, as well as the activities of protective enzymes, of the red and green morphs of the pea aphid over eight generations. The results indicated a significant interaction between UV-B radiation and aphid generations. Exposure of the pea aphids to UV-B radiation caused a significant decrease in the protein content and a significant increase in the glycogen and trehalose contents at each generation as measured in whole aphid bioassays. The enzyme activity of superoxide dismutase (SOD), peroxidase (POD), and catalase (CAT) of the pea aphids changed significantly at each generation with UV-B treatments. The SOD activity increased over eight generations to the highest level at G7 generation. However, the enzyme activity of CAT first increased and then decreased with UV-B treatments, and POD mostly gradually decreased over the eight generations. Therefore, UV-B radiation is an environmental factor that could result in physiological changes of the pea aphid. Moreover, our study discovered that red and green aphids did not display a significant consistent difference in the response to the UV-B treatments. These results may prove useful in future studies especially for assessing their significance in the adaptation and management against UV-B radiation.

Contribution of phenoloxidase activation mechanism to Bt insecticidal protein resistance in Asian corn borer.

Phenoloxidase (PO) is a crucial enzyme in the Arthropods melanization process, in which synthesized melanin rapidly acts at the site of injury and infection. In this study, we observed significant changes in humoral and cellular responses after exposing susceptible and resistant strains to a sub-lethal concentration of Cry1Ah toxin. Based on STRING v 11.0 computational protein-protein interaction analysis, we selected seven immune genes namely Prophenoloxidase PPO1b, PP03, Serpin-3, Serpin-5, Beta-1,3-glucan recognition protein, Immulectin-3 and Serine protease SP105 reported in Asian corn borer. Quantitative real-time PCR gene expression studies showed Cry1Ah resistant strain had higher expression of PPO1b, PP03, Serpin-3, Beta-1,3-glucan recognition protein, Immulectin-3 and Serine protease SP105 genes in midgut and hemocyte samples. This study also investigated and found that the level of prophenoloxidation (proPO) activity in Cry1Ah resistant strains was significantly higher than susceptible strains. Cry1Ah toxin significantly increased the resistant strain's immune responses, the difference was observed through assays of bacterial agglutination and phagocytosis. Additionally, immune response induced by Cry1Ah toxin influences the microbiome composition associated with the host system. These parameters seem to explain the contribution of PO/PO regulating proteins render the host to resist the Cry1Ah toxin.