Residual network improves the prediction accuracy of genomic selection.

Genetic improvement of complex traits in animal and plant breeding depends on the efficient and accurate estimation of breeding values. Deep learning methods have been shown to be not superior over traditional genomic selection (GS) methods, partially due to the degradation problem (i.e. with the increase of the model depth, the performance of the deeper model deteriorates). Since the deep learning method residual network (ResNet) is designed to solve gradient degradation, we examined its performance and factors related to its prediction accuracy in GS. Here we compared the prediction accuracy of conventional genomic best linear unbiased prediction, Bayesian methods (BayesA, BayesB, BayesC, and Bayesian Lasso), and two deep learning methods, convolutional neural network and ResNet, on three datasets (wheat, simulated and real pig data). ResNet outperformed other methods in both Pearson's correlation coefficient (PCC) and mean squared error (MSE) on the wheat and simulated data. For the pig backfat depth trait, ResNet still had the lowest MSE, whereas Bayesian Lasso had the highest PCC. We further clustered the pig data into four groups and, on one separated group, ResNet had the highest prediction accuracy (both PCC and MSE). Transfer learning was adopted and capable of enhancing the performance of both convolutional neural network and ResNet. Taken together, our findings indicate that ResNet could improve GS prediction accuracy, affected potentially by factors such as the genetic architecture of complex traits, data volume, and heterogeneity.

GWLD: an R package for genome-wide linkage disequilibrium analysis.

Linkage disequilibrium (LD) analysis is fundamental to the investigation of the genetic architecture of complex traits (e.g. human disease, animal and plant breeding) and population structure and evolution dynamics. However, until now, studies primarily focus on LD status between genetic variants located on the same chromosome. Moreover, genome (re)sequencing produces unprecedented numbers of genetic variants, and fast LD computation becomes a challenge. Here, we have developed GWLD, a parallelized and generalized tool designed for the rapid genome-wide calculation of LD values, including conventional D/D', r2, and (reduced) mutual information (MI and RMI) measures. LD between genetic variants within and across chromosomes can be rapidly computed and visualized in either an R package or a standalone C++ software package. To evaluate the accuracy and speed of LD calculation, we conducted comparisons using 4 real datasets. Interchromosomal LD patterns observed potentially reflect levels of selection intensity across different species. Both versions of GWLD, the R package (https://github.com/Rong-Zh/GWLD/GWLD-R) and the standalone C++ software (https://github.com/Rong-Zh/GWLD/GWLD-C++), are freely available on GitHub.

An improved Deeplabv3+ semantic segmentation algorithm with multiple loss constraints.

Aiming at the problems of low segmentation accuracy and inaccurate object boundary segmentation in current semantic segmentation algorithms, a semantic segmentation algorithm using multiple loss function constraints and multi-level cascading residual structure is proposed. The multi-layer cascaded residual unit was used to increase the range of the network layer receptive field. A parallel network was constructed to extract different depth feature information, then different depth feature information and encoder output features are fused to obtain multiple outputs feature which build multiple losses with the label, thereby constraining the model to optimize the network. The proposed network was evaluated on Cityscapes and CamVid datasets. The experimental results show that the mean Intersection over Union ratio (MIoU) of the proposed algorithm is 3.07% and 3.59% higher than the original Deeplabv3+ algorithm, respectively.

Detection of plane in remote sensing images using super-resolution.

The object detection of remote sensing image often has low accuracy and high missed or false detection rate due to the large number of small objects, instance level noise and cloud occlusion. In this paper, a new object detection model based on SRGAN and YOLOV3 is proposed, which is called SR-YOLO. It solves the problems of SRGAN network sensitivity to hyper-parameters and modal collapse. Meanwhile, The FPN network in YOLOv3 is replaced by PANet, shortened the distance between the lowest and the highest layers, and the SR-YOLO model has strong robustness and high detection ability by using the enhanced path to enrich the characteristics of each layer. The experimental results on the UCAS-High Resolution Aerial Object Detection Dataset showed SR-YOLO has achieved excellent performance. Compared with YOLOv3, the average precision (AP) of SR-YOLO increased from 92.35% to 96.13%, the log-average miss rate (MR-2) decreased from 22% to 14%, and the Recall rate increased from 91.36% to 95.12%.