Predicting Splicing from Primary Sequence with Deep Learning.

The splicing of pre-mRNAs into mature transcripts is remarkable for its precision, but the mechanisms by which the cellular machinery achieves such specificity are incompletely understood. Here, we describe a deep neural network that accurately predicts splice junctions from an arbitrary pre-mRNA transcript sequence, enabling precise prediction of noncoding genetic variants that cause cryptic splicing. Synonymous and intronic mutations with predicted splice-altering consequence validate at a high rate on RNA-seq and are strongly deleterious in the human population. De novo mutations with predicted splice-altering consequence are significantly enriched in patients with autism and intellectual disability compared to healthy controls and validate against RNA-seq in 21 out of 28 of these patients. We estimate that 9%-11% of pathogenic mutations in patients with rare genetic disorders are caused by this previously underappreciated class of disease variation.

Improved genome sequencing using an engineered transposase.

BACKGROUND: Next-generation sequencing (NGS) has transformed genomic research by reducing turnaround time and cost. However, no major breakthrough has been made in the upstream library preparation methods until the transposase-based Nextera method was invented. Nextera combines DNA fragmentation and barcoding in a single tube reaction and therefore enables a very fast workflow to sequencing-ready DNA libraries within a couple of hours. When compared to the traditional ligation-based methods, transposed-based Nextera has a slight insertion bias. RESULTS: Here we present the discovery of a mutant transposase (Tn5-059) with a lowered GC insertion bias through protein engineering. We demonstrate Tn5-059 reduces AT dropout and increases uniformity of genome coverage in both bacterial genomes and human genome. We also observe higher library diversity generated by Tn5-059 when compared to Nextera v2 for human exomes, which leads to less sequencing and lower cost per genome. In addition, when used for human exomes, Tn5-059 delivers consistent library insert size over a range of input DNA, allowing up to a tenfold variance from the 50 ng input recommendation. CONCLUSIONS: Enhanced DNA input tolerance of Tn5-059 can translate to flexibility and robustness of workflow. DNA input tolerance together with superior uniformity of coverage and lower AT dropouts extend the applications of transposase based library preps. We discuss possible mechanisms of improvements in Tn5-059, and potential advantages of using the new mutant in varieties of applications including microbiome sequencing and chromatin profiling.

Computing generalized Langevin equations and generalized Fokker-Planck equations.

The Mori-Zwanzig formalism is an effective tool to derive differential equations describing the evolution of a small number of resolved variables. In this paper we present its application to the derivation of generalized Langevin equations and generalized non-Markovian Fokker-Planck equations. We show how long time scales rates and metastable basins can be extracted from these equations. Numerical algorithms are proposed to discretize these equations. An important aspect is the numerical solution of the orthogonal dynamics equation which is a partial differential equation in a high dimensional space. We propose efficient numerical methods to solve this orthogonal dynamics equation. In addition, we present a projection formalism of the Mori-Zwanzig type that is applicable to discrete maps. Numerical applications are presented from the field of Hamiltonian systems.

Circulating transcripts in maternal blood reflect a molecular signature of early-onset preeclampsia.

Circulating RNA (C-RNA) is continually released into the bloodstream from tissues throughout the body, offering an opportunity to noninvasively monitor all aspects of pregnancy health from conception to birth. We asked whether C-RNA analysis could robustly detect aberrations in patients diagnosed with preeclampsia (PE), a prevalent and potentially fatal pregnancy complication. As an initial examination, we sequenced the circulating transcriptome from 40 pregnancies at the time of severe, early-onset PE diagnosis and 73 gestational age-matched controls. Differential expression analysis identified 30 transcripts with gene ontology annotations and tissue expression patterns consistent with the placental dysfunction, impaired fetal development, and maternal immune and cardiovascular system dysregulation characteristic of PE. Furthermore, machine learning identified combinations of 49 C-RNA transcripts that classified an independent cohort of patients (early-onset PE, n = 12; control, n = 12) with 85 to 89% accuracy. C-RNA may thus hold promise for improving the diagnosis and identification of at-risk pregnancies.

Characterization of chromatin accessibility with a transposome hypersensitive sites sequencing (THS-seq) assay.

Chromatin accessibility captures in vivo protein-chromosome binding status, and is considered an informative proxy for protein-DNA interactions. DNase I and Tn5 transposase assays require thousands to millions of fresh cells for comprehensive chromatin mapping. Applying Tn5 tagmentation to hundreds of cells results in sparse chromatin maps. We present a transposome hypersensitive sites sequencing assay for highly sensitive characterization of chromatin accessibility. Linear amplification of accessible DNA ends with in vitro transcription, coupled with an engineered Tn5 super-mutant, demonstrates improved sensitivity on limited input materials, and accessibility of small regions near distal enhancers, compared with ATAC-seq.

DNA sequencing using polymerase substrate-binding kinetics.

Next-generation sequencing (NGS) has transformed genomic research by decreasing the cost of sequencing. However, whole-genome sequencing is still costly and complex for diagnostics purposes. In the clinical space, targeted sequencing has the advantage of allowing researchers to focus on specific genes of interest. Routine clinical use of targeted NGS mandates inexpensive instruments, fast turnaround time and an integrated and robust workflow. Here we demonstrate a version of the Sequencing by Synthesis (SBS) chemistry that potentially can become a preferred targeted sequencing method in the clinical space. This sequencing chemistry uses natural nucleotides and is based on real-time recording of the differential polymerase/DNA-binding kinetics in the presence of correct or mismatch nucleotides. This ensemble SBS chemistry has been implemented on an existing Illumina sequencing platform with integrated cluster amplification. We discuss the advantages of this sequencing chemistry for targeted sequencing as well as its limitations for other applications.