Hui Xiong

To facilitate precision medicine and whole-genome annotation, we developed a machine-learning technique that scores how strongly genetic variants affect RNA splicing, whose alteration contributes to many diseases. Analysis of more than 650,000 intronic and exonic variants revealed widespread patterns of mutation-driven aberrant splicing. Intronic disease mutations that are more than 30 nucleotides from any splice site alter splicing nine times as often as common variants, and missense exonic disease mutations that have the least impact on protein function are five times as likely as others to alter splicing. We detected tens of thousands of disease-causing mutations, including those involved in cancers and spinal muscular atrophy. Examination of intronic and exonic variants found using whole-genome sequencing of individuals with autism revealed misspliced genes with neurodevelopmental phenotypes. Our approach provides evidence for causal variants and should enable new discoveries in precision medicine.

How species with similar repertoires of protein-coding genes differ so markedly at the phenotypic level is poorly understood. By comparing organ transcriptomes from vertebrate species spanning ~350 million years of evolution, we observed significant differences in alternative splicing complexity between vertebrate lineages, with the highest complexity in primates. Within 6 million years, the splicing profiles of physiologically equivalent organs diverged such that they are more strongly related to the identity of a species than they are to organ type. Most vertebrate species-specific splicing patterns are cis-directed. However, a subset of pronounced splicing changes are predicted to remodel protein interactions involving trans-acting regulators. These events likely further contributed to the diversification of splicing and other transcriptomic changes that underlie phenotypic differences among vertebrate species.

Leptospirosis is a widely spread disease of global concern. Infection causes flu-like episodes with frequent severe renal and hepatic damage, such as haemorrhage and jaundice. In more severe cases, massive pulmonary haemorrhages, including fatal sudden haemoptysis, can occur. Here we report the complete genomic sequence of a representative virulent serovar type strain (Lai) of Leptospira interrogans serogroup Icterohaemorrhagiae consisting of a 4.33-megabase large chromosome and a 359-kilobase small chromosome, with a total of 4,768 predicted genes. In terms of the genetic determinants of physiological characteristics, the facultatively parasitic L. interrogans differs extensively from two other strictly parasitic pathogenic spirochaetes, Treponema pallidum and Borrelia burgdorferi, although similarities exist in the genes that govern their unique morphological features. A comprehensive analysis of the L. interrogans genes for chemotaxis/motility and lipopolysaccharide synthesis provides a basis for in-depth studies of virulence and pathogenesis. The discovery of a series of genes possibly related to adhesion, invasion and the haematological changes that characterize leptospirosis has provided clues about how an environmental organism might evolve into an important human pathogen.

MOTIVATION: Alternative splicing (AS) is a regulated process that directs the generation of different transcripts from single genes. A computational model that can accurately predict splicing patterns based on genomic features and cellular context is highly desirable, both in understanding this widespread phenomenon, and in exploring the effects of genetic variations on AS. METHODS: Using a deep neural network, we developed a model inferred from mouse RNA-Seq data that can predict splicing patterns in individual tissues and differences in splicing patterns across tissues. Our architecture uses hidden variables that jointly represent features in genomic sequences and tissue types when making predictions. A graphics processing unit was used to greatly reduce the training time of our models with millions of parameters. RESULTS: We show that the deep architecture surpasses the performance of the previous Bayesian method for predicting AS patterns. With the proper optimization procedure and selection of hyperparameters, we demonstrate that deep architectures can be beneficial, even with a moderately sparse dataset. An analysis of what the model has learned in terms of the genomic features is presented.