An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters

Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.

Antibacterial activity evaluation of a novel K3-specific phage against Acinetobacter baumannii and evidence for receptor-binding domain transfer across morphologies

Acinetobacter baumannii(A.baumannii)poses a serious public health challenge due to its notorious antimicrobial resistance,particularly carbapenem-resistant A.baumannii(CRAB).In this study,we isolated a virulent phage,named P1068,from medical wastewater capable of lysing CRAB,primarily targeting the K3 capsule type.Basic characterization showed that P1068 infected the A.baumannii ZWAb014 with an optimal MOI of 1,experienced a latent period of 10 min and maintained stability over a temperature range of 4–37C and pH range of 3–10.Phylogenetic and average nucleotide identity analyses indicate that P1068 can be classified as a novel species within the genus Obolenskvirus of the Caudoviricetes class as per the most recent virus classification released by the International Committee on Taxonomy of Viruses(ICTV).Additionally,according to classical morphological classification,P1068 is identified as a T4-like phage(Myoviridae).Interestingly,we found that the tail fiber protein(TFP)of P1068 shares 74%coverage and 88.99%identity with the TFP of a T7-like phage(Podoviridae),AbKT21phiIII(NC_048142.1).This finding suggests that the TFP gene of phages may undergo horizontal transfer across different genera and morphologies.In vitro antimicrobial assays showed that P1068 exhibited antimicrobial activity against A.baumannii in both biofilm and planktonic states.In mouse models of intraperitoneal infection,P1068 phage protected mice from A.baumannii infection and significantly reduced bacterial loads in various tissues such as the brain,blood,lung,spleen,and liver compared to controls.In conclusion,this study demonstrates that phage P1068 might be a potential candidate for the treatment of carbapenem-resistant and biofilmforming A.baumannii infections,and expands the understanding of horizontal transfer of phage TFP genes.