Systematic exploration of transcriptional responses of interspecies interaction between Karenia mikimotoi and Prorocentrum shikokuense.

Karenia mikimotoi and Prorocentrum shikokuense (also identified as P. donghaiense Lu and P. obtusidens Schiller) are two important harmful algal species which often form blooms in the coasts of China. Studies have shown that the allelopathy of K. mikimotoi and P. shikokuense plays an important role in inter-algal competition, though the underlying mechanisms remain largely unclear. Here, we observed reciprocal inhibitory effects between K. mikimotoi and P. shikokuense under co-cultures. Based on the reference sequences, we isolated RNA sequencing reads of K. mikimotoi and P. shikokuense from co-culture metatranscriptome, respectively. We found the genes involved in photosynthesis, carbon fixation, energy metabolism, nutrients absorption and assimilation were significantly up-regulated in K. mikimotoi after co-cultured with P. shikokuense. However, genes involved in DNA replication and cell cycle were significantly down-regulated. These results suggested that co-culture with P. shikokuense stimulated cell metabolism and nutrients competition activity of K. mikimotoi, and inhibited cell cycle. In contrast, genes involved in energy metabolism, cell cycle and nutrients uptake and assimilation were dramatically down-regulated in P. shikokuense under co-culture with K. mikimotoi, indicating that K. mikimotoi could highly affect the cellular activity of P. shikokuense. In addition, the expression of PLA2G12 (Group XII secretory phospholipase A2) that can catalyze the accumulation of linoleic acid or linolenic acid, and nitrate reductase that may be involved in nitric oxide production were significantly increased in K. mikimotoi, suggesting that PLA2G12 and nitrate reductase may play important roles in the allelopathy of K. mikimotoi. Our findings shed new light on the interspecies competition between K. mikimotoi and P. shikokuense, and provide a novel strategy for studying interspecific competition in complex systems.

Application Research for Fusion Model of Pseudolabel and Cross Network.

Datasets usually suffer from supervised information missing and weak generalization ability in deep convolution neural network. In this paper, pseudolabel (PL) of Weakly Supervised Learning (WSL) was used to address the problem of supervised information missing, while Cross Network (CN) of Multitask Learning (MTL) was used to solve the problem of weak generalization ability in deep convolution neural network. In PL, the data of supervised information missing was predicted; thus, PL of the corresponding data was generated. In CN, PL data and labeled data were taken as two tasks to train together. Firstly, the labeled data was divided into training dataset and testing dataset, respectively, and image preprocessing was carried out. Secondly, the network was initialized and trained, and the model with high accuracy and good generalization was selected as the optimal model. Then, the optimal model was used to predict the unlabeled data and generate PL. Finally, the steps above were repeated several times to find a better optimal model. In the experiments of the fusion model of PL and CN, Facial Beauty Prediction was regarded as main task and the others as auxiliary tasks. Experimental results show that the model was suitable for multitask training of different tasks in different or similar datasets, and the accuracy of the main task of Facial Beauty Prediction reaches 64.76%, higher than the highest accuracy by conventional methods.