Along with the development of high-throughput sequencing technologies, both sample size and SNP number are increasing rapidly in genome-wide association studies (GWAS), and the associated computation is more challenging than ever. Here, we present a memory-efficient, visualization-enhanced, and parallel-accelerated R package called “rMVP” to address the need for improved GWAS computation. rMVP can 1) effectively process large GWAS data, 2) rapidly evaluate population structure, 3) efficiently estimate variance components by Efficient Mixed-Model Association eXpedited (EMMAX), Factored Spectrally Transformed Linear Mixed Models (FaST-LMM), and Haseman-Elston (HE) regression algorithms, 4) implement parallel-accelerated association tests of markers using general linear model (GLM), mixed linear model (MLM), and fixed and random model circulating probability unification (FarmCPU) methods, 5) compute fast with a globally efficient design in the GWAS processes, and 6) generate various visualizations of GWAS-related information. Accelerated by block matrix multiplication strategy and multiple threads, the association test methods embedded in rMVP are significantly faster than PLINK, GEMMA, and FarmCPU_pkg. rMVP is freely available at https://github.com/xiaolei-lab/rMVP.

Background: The broad adoption of electronic health records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models. Methods: In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions. Results: We evaluate the performance of proposed models on 3 risk prediction tasks (i.e. in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only. Conclusions: The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.

Soybean (Glycine max) serves as a major source of protein and edible oils worldwide. The genetic and genomic bases of the adaptation of soybean to tropical regions remain largely unclear. Here, we identify the novel locus Time of Flowering 16 (Tof16), which confers delay flowering and improve yield at low latitudes and determines that it harbors the soybean homolog of LATE ELONGATED HYPOCOTYL (LHY). Tof16 and the previously identified J locus genetically additively but independently control yield under short-day conditions. More than 80% accessions in low latitude harbor the mutations of tof16 and j, which suggests that loss of functions of Tof16 and J are the major genetic basis of soybean adaptation into tropics. We suggest that maturity and yield traits can be quantitatively improved by modulating the genetic complexity of various alleles of the LHY homologs, J and E1. Our findings uncover the adaptation trajectory of soybean from its temperate origin to the tropics.

Genomic Selection (GS) has been proved to be a powerful tool for estimating genetic values in plant and livestock breeding. Newly developed sequencing technologies have dramatically reduced the cost of genotyping and significantly increased the scale of genotype data that used for GS. Meanwhile, state-of-the-art statistical methods were developed to make the best use of high marker density genotype data. In this study, 14 traits from four data sets of three species (maize, cattle, and pig) and five influential factors that affect the prediction accuracy were evaluated, including marker density (from 1 to ~600 k), statistical method (GBLUP-A, GBLUP-AD, and BayesR), minor allele frequency (MAF), heritability, and genetic architecture. Results indicate that in the GBLUP method, higher marker density leads to a higher prediction accuracy. In contrast, BayesR method needs more Monte Carlo Markov Chain (MCMC) iterations to reach the convergence and get reliable prediction values. BayesR outperforms GBLUP in predicting high or medium heritability trait that affected by one or several genes with large effects, while GBLUP performs similarly or slightly better than BayesR in predicting low heritability trait that controlled by a large amount of genes with minor effects. Prediction accuracy of trait with complex genetic architecture can be improved by increasing the marker density. Interestingly, for simple traits that controlled by one or several genes with large effects, higher marker density can cause a lower prediction accuracy if the QTN is included, but leads to a higher prediction accuracy if the QTN is excluded. The quantity of genetic markers with low MAF would not significantly affect the prediction accuracy of GBLUP, but results in a bad prediction accuracy performance of BayesR method. Compared with GBLUP-A, GBLUP-AD didn't show any advantages in capturing the non-additive variance for the traits with high heritability. The factors that affected prediction accuracy are discussed in this study and indicate that a combination of either GBLUP or BayesR method with moderate marker density and favorable polymorphism single nucleotide polymorphisms (SNPs) (~25 k SNPs) would always produce a good and stable prediction accuracy with acceptable breeding and computational costs.

The analyses of multi-omics data have revealed candidate genes for objective traits. However, they are integrated poorly, especially in non-model organisms, and they pose a great challenge for prioritizing candidate genes for follow-up experimental verification. Here, we present a general convolutional neural network model that integrates multi-omics information to prioritize the candidate genes of objective traits. By applying this model to Sus scrofa, which is a non-model organism, but one of the most important livestock animals, the model precision was 72.9%, recall 73.5%, and F1-Measure 73.4%, demonstrating a good prediction performance compared with previous studies in Arabidopsis thaliana and Oryza sativa. Additionally, to facilitate the use of the model, we present ISwine (http://iswine.iomics.pro/), which is an online comprehensive knowledgebase in which we incorporated almost all the published swine multi-omics data. Overall, the results suggest that the deep learning strategy will greatly facilitate analyses of multi-omics integration in the future.