Search

In order to improve the accuracy of the corrosion fatigue life prediction model for the 7050 aluminum alloy, this study presents a corrosion fatigue life prediction model based on back-propagation (BP) neural network optimized by improved grey wolf optimization (IGWO) algorithm that takes into account different sampling orientations and stress magnitudes. The model determines the mapping relationship between corrosion fatigue life, sample direction, and stress level. It also compares the improved grey wolf optimization-backpropagation (IGWO-BP) prediction error with three other models: BP, particle swarm optimization-back propagation (PSO-BP), and genetic algorithm-backpropagation (GA-BP). The IGWO-BP model's performance measures are as follows: a determination coefficient (R2) of 0.9740, a mean absolute error (MAE) of 0.0479, a root mean square error (RMSE) of 0.0596, and a mean absolute percentage error (MAPE) of 0.9443%. For both the training and test sets, the predicted results are within an error margin of 1.5 times. When compared with the conventional BP neural network, the R2 of IGWO-BP is increased by 5.69%, and the RMSE, MAE, and MAPE of IGWO-BP are the smallest, reduced by 26.24, 26.19, and 26.72%, respectively. [ABSTRACT FROM AUTHOR]

The human genome is diploid, and knowledge of the variants on each chromosome is important for the interpretation of genomic information. Here we report the assembly of a haplotype-resolved diploid genome without using a reference genome. Our pipeline relies on fosmid pooling together with whole-genome shotgun strategies, based solely on next-generation sequencing and hierarchical assembly methods. We applied our sequencing method to the genome of an Asian individual and generated a 5.15-Gb assembled genome with a haplotype N50 of 484 kb. Our analysis identified previously undetected indels and 7.49 Mb of novel coding sequences that could not be aligned to the human reference genome, which include at least six predicted genes. This haplotype-resolved genome represents the most complete de novo human genome assembly to date. Application of our approach to identify individual haplotype differences should aid in translating genotypes to phenotypes for the development of personalized medicine. [ABSTRACT FROM AUTHOR]