In recent years, obtaining RNA secondary structure information has played an important role in RNA and gene function research. Although some RNA secondary structures can be gained experimentally, in most cases, efficient, and accurate computational methods are still needed to predict RNA secondary structure. Current RNA secondary structure prediction methods are mainly based on the minimum free energy algorithm, which finds the optimal folding state of RNA in vivo using an iterative method to meet the minimum energy or other constraints. However, due to the complexity of biotic environment, a true RNA structure always keeps the balance of biological potential energy status, rather than the optimal folding status that meets the minimum energy. For short sequence RNA its equilibrium energy status for the RNA folding organism is close to the minimum free energy status; therefore, the minimum free energy algorithm for predicting RNA secondary structure has higher accuracy. Nevertheless, in a longer sequence RNA, constant folding causes its biopotential energy balance to deviate far from the minimum free energy status. This deviation is because of its complex structure and results in a serious decline in the prediction accuracy of its secondary structure. In this paper, we propose a novel RNA secondary structure prediction algorithm using a convolutional neural network model combined with a dynamic programming method to improve the accuracy with large-scale RNA sequence and structure data. We analyze current experimental RNA sequences and structure data to construct a deep convolutional network model, and then we extract implicit features of an effective classification from large-scale data to predict the pairing probability of each base in an RNA sequence. For the obtained probabilities of RNA sequence base pairing, an enhanced dynamic programming method is applied to obtain the optimal RNA secondary structure. Results indicate that our proposed method is superior to the common RNA secondary structure prediction algorithms in predicting three benchmark RNA families. Based on the characteristics of deep learning algorithm, it can be inferred that the method proposed in this paper has a 30% higher prediction success rate when compared with other algorithms, which will be needed as the amount of real RNA structure data increases in the future.

Live attenuated virus vaccines have been generated by several strategies, including cold-adapted live attenuated influenza vaccines (CAIVs), codon-deoptimized virus, premature termination codon-harboring virus, hyper-interferon-sensitive virus and viral-protein-altered virus 1-12 . However, current attenuation strategies are often accompanied by decrease or loss of safety, efficacy or productivity 1,[13][14][15][16] . In addition, immune escape due to rapid viral evolution poses a further challenge for traditional influenza vaccines 1,13 . Thus, there is an urgent need for new vaccine approaches that could enable the generation of safer and more effective live vaccines in a simpler way 2 .

BackgroundXinjiang is one of the areas with the highest incidence of cervical cancer in China. Genetic variation in Human papillomavirus type 16 (HPV16) may increase the ability of the virus to mediate carcinogenesis and immune escape, which are risk factors for the progression of cervical cancer. We investigated polymorphism in HPV16 and the distribution of its sub-lineages in the region by analyzing the E6, E7 and long control region (LCR) gene sequences from women with HPV16-positive cervical samples in Xinjiang.MethodsA total of 138 cases of cervical lesions and squamous cell carcinoma with infection of HPV16 virus were collected. The E6 and E7 genes and LCR of HPV16 virus were sequenced and compared with the HPV16 European prototype reference and other HPV16 mutants for single nucleotide polymorphisms. Neighbor-joining phylogenetic trees were constructed using E6, E7 and LCR sequences.ResultsFourteen missense mutations were found in the E6 gene; the loci with the highest mutation frequency were T350G (36/75, 48%) and T178G (19/75, 25.3%). In the E7 gene, the locus with the highest mutation frequency was A647G (18/75, 24%). A total of 33 polymorphic sites were found in the LCR, of which T7447C (39/95, 40.1%) was the most frequent.ConclusionHPV16 in Xinjiang is mainly of the European variant, followed by the Asian variant type; no Africa 1, 2 or Asia–America variant types were found.