Circulating cell-free DNA (cfDNA) is a powerful diagnostics tool that is widely studied in the context of liquid biopsy in oncology and other fields. In obstetrics, maternal plasma cfDNA have already proven its utility, enabling noninvasive prenatal testing (NIPT), which has become a standard for detecting chromosomal aberrations. However, identification of point mutations responsible for monogenic diseases (NIPT-M) remains limited, even when accounting to fragment specific characteristics (i.e. fragmentomics). While genotyping of individual genomes is performed today using deep learning (DL) algorithms, cfDNA-based noninvasive fetal genotyping is performed only using traditional statistical and machine-learning methods. This study introduces the first DL-based framework for cfDNA based genotyping, heralding a significant stride toward genome-wide NIPT-M. Using unique ultra-deep whole genome sequencing (WGS) data, we were motivated to develop an efficient model, especially when compared with current DL methods for WGS. This facilitates the integration of previously overlooked levels of information, encompassing DNA nucleotides, fragments, mutation regions, samples, and familial traits. Employing this novel approach, we surpass the performance of existing methodologies, successfully detecting three deleterious mutations, and allowing for NIPT-M as early as the 7th week of gestation. Our proposed approach brings genome-wide NIPT for all mutation types closer to clinical feasibility, enabling families and healthcare providers to make well-informed decisions and alleviating the anxieties and uncertainties associated with pregnancy.

Keeping track of scientific challenges, advances and emerging directions is a fundamental part of research. However, researchers face a flood of papers that hinders discovery of important knowledge. In biomedicine, this directly impacts human lives. To address this problem, we present a novel task of extraction and search of scientific challenges and directions, to facilitate rapid knowledge discovery. We construct and release an expert-annotated corpus of texts sampled from full-length papers, labeled with novel semantic categories that generalize across many types of challenges and directions. We focus on a large corpus of interdisciplinary work relating to the COVID-19 pandemic, ranging from biomedicine to areas such as AI and economics. We apply a model trained on our data to identify challenges and directions across the corpus and build a dedicated search engine. In experiments with 19 researchers and clinicians using our system, we outperform a popular scientific search engine in assisting knowledge discovery. Finally, we show that models trained on our resource generalize to the wider biomedical domain and to AI papers, highlighting its broad utility. We make our data, model and search engine publicly available.

Nanopore sequencing is an emerging technology that reads DNA by utilizing a unique method of detecting nucleic acid sequences and identifies the various chemical modifications they carry. Deep learning has increased in popularity as a useful technique to solve many complex computational tasks. 'Adaptive sequencing' is an implementation of selective sequencing, intended for use on the nanopore sequencing platform. In this study, we demonstrated an alternative method of software-based selective sequencing that is performed in real time by combining nanopore sequencing and deep learning. Our results showed the feasibility of using deep learning for classifying signals from only the first 200 nucleotides in a raw nanopore sequencing signal format. This was further demonstrated by comparing the accuracy of our deep learning classification model across data from several human cell lines and other eukaryotic organisms. We used custom deep learning models and a script that utilizes a 'Read Until' framework to target mitochondrial molecules in real time from a human cell line sample. This achieved a significant separation and enrichment ability of 2.3-fold. In a series of very short sequencing experiments (10, 30 and 120 min), we identified genomic and mitochondrial reads with accuracy above 90%, although mitochondrial DNA comprised only 0.1% of the total input material. The uniqueness of our method is the ability to distinguish two groups of DNA even without a labeled reference. This contrasts with studies that required a well-defined reference, whether of a DNA sequence or of another type of representation. Additionally, our method showed higher correlation to the theoretically possible enrichment factor, compared with other published methods. We believe that our results will lay the foundation for rapid and selective sequencing using nanopore technology and will pave the approach for clinical applications that use nanopore sequencing data.

In recent years, methods were proposed for assigning feature importance scores to measure the contribution of individual features. While in some cases the goal is to understand a specific model, in many cases the goal is to understand the contribution of certain properties (features) to a real-world phenomenon. Thus, a distinction has been made between feature importance scores that explain a model and scores that explain the data. When explaining the data, machine learning models are used as proxies in settings where conducting many real-world experiments is expensive or prohibited. While existing feature importance scores show great success in explaining models, we demonstrate their limitations when explaining the data, especially in the presence of correlations between features. Therefore, we develop a set of axioms to capture properties expected from a feature importance score when explaining data and prove that there exists only one score that satisfies all of them, the Marginal Contribution Feature Importance (MCI). We analyze the theoretical properties of this score function and demonstrate its merits empirically.

MOTIVATION: The study of RNA virus populations is a challenging task. Each population of RNA virus is composed of a collection of different, yet related genomes often referred to as mutant spectra or quasispecies. Virologists using deep sequencing technologies face major obstacles when studying virus population dynamics, both experimentally and in natural settings due to the relatively high error rates of these technologies and the lack of high performance pipelines. In order to overcome these hurdles we developed a computational pipeline, termed ViVan (Viral Variance Analysis). ViVan is a complete pipeline facilitating the identification, characterization and comparison of sequence variance in deep sequenced virus populations. RESULTS: Applying ViVan on deep sequenced data obtained from samples that were previously characterized by more classical approaches, we uncovered novel and potentially crucial aspects of virus populations. With our experimental work, we illustrate how ViVan can be used for studies ranging from the more practical, detection of resistant mutations and effects of antiviral treatments, to the more theoretical temporal characterization of the population in evolutionary studies. AVAILABILITY AND IMPLEMENTATION: Freely available on the web at http://www.vivanbioinfo.org CONTACT: : [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MicroRNAs (miRNAs) are short regulatory RNAs that down-regulate gene expression. They are essential for cell homeostasis and active in many disease states. A major discovery is the ability of miRNAs to determine the efficacy of drugs, which has given rise to the field of 'miRNA pharmacogenomics' through 'Pharmaco-miRs'. miRNAs play a significant role in pharmacogenomics by down-regulating genes that are important for drug function. These interactions can be described as triplet sets consisting of a miRNA, a target gene and a drug associated with the gene. We have developed a web server which links miRNA expression and drug function by combining data on miRNA targeting and protein-drug interactions. miRNA targeting information derive from both experimental data and computational predictions, and protein-drug interactions are annotated by the Pharmacogenomics Knowledge base (PharmGKB). Pharmaco-miR's input consists of miRNAs, genes and/or drug names and the output consists of miRNA pharmacogenomic sets or a list of unique associated miRNAs, genes and drugs. We have furthermore built a database, named Pharmaco-miR Verified Sets (VerSe), which contains miRNA pharmacogenomic data manually curated from the literature, can be searched and downloaded via Pharmaco-miR and informs on trends and generalities published in the field. Overall, we present examples of how Pharmaco-miR provides possible explanations for previously published observations, including how the cisplatin and 5-fluorouracil resistance induced by miR-148a may be caused by miR-148a targeting of the gene KIT. The information is available at www.Pharmaco-miR.org.

Insertion and deletion (indel) mutations, the most common type of structural variance in the human genome, affect a multitude of human traits and diseases. New sequencing technologies, such as deep sequencing, allow massive throughput of sequence data and greatly contribute to the field of disease causing mutation detection, in general, and indel detection, specifically. In order to infer indel presence (indel calling), the deep-sequencing data have to undergo comprehensive computational analysis. Selecting which indel calling software to use can often skew the results and inherent tool limitations may affect downstream analysis. In order to better understand these inter-software differences, we evaluated the performance of several indel calling software for short indel (1-10 nt) detection. We compared the software's sensitivity and predictive values in the presence of varying parameters such as read depth (coverage), read length, indel size and frequency. We pinpoint several key features that assist successful experimental design and appropriate tool selection. Our study may also serve as a basis for future evaluation of additional indel calling methods.

MOTIVATION: Early and accurate detection of human pathogen infection is critical for treatment and therapeutics. Here we describe pathogen identification using short RNA subtraction and assembly (SRSA), a detection method that overcomes the requirement of prior knowledge and culturing of pathogens, by using degraded small RNA and deep sequencing technology. We prove our approach's efficiency through identification of a combined viral and bacterial infection in human cells.

MOTIVATION: MicroRNAs (miRNAs) are involved in an abundant class of post-transcriptional regulation activated through binding to the 3(') -untranslated region (UTR) of mRNAs. The current wealth of mammalian miRNA genes results mostly from genomic duplication events. Many of these events are located within introns of transcriptional units. In order to better understand the genomic expansion of miRNA genes, we investigated the distribution of intronic miRNAs. RESULTS: We observe that miRNA genes are hosted within introns of short genes much larger than expected by chance. IMPLEMENTATION: We explore several explanations for this phenomenon and conclude that miRNA integration into short genes might be evolutionary favorable due to interaction with the pre-mRNA splicing mechanism.

MOTIVATION: MicroRNAs (miRNAs) are short abundant non-coding RNAs critical for many cellular processes. Deep sequencing (next-generation sequencing) technologies are being readily used to receive a more accurate depiction of miRNA expression profiles in living cells. This type of analysis is a key step towards improving our understanding of the complexity and mode of miRNA regulation. RESULTS: miRNAkey is a software package designed to be used as a base-station for the analysis of miRNA deep sequencing data. The package implements common steps taken in the analysis of such data, as well as adds unique features, such as data statistics and multiple read determination, generating a novel platform for the analysis of miRNA expression. A user-friendly graphical interface is applied to determine the analysis steps. The tabular and graphical output contains general and detailed reports on the sequence reads and provides an accurate picture of the differentially expressed miRNAs in paired samples. AVAILABILITY AND IMPLEMENTATION: See http://ibis.tau.ac.il/miRNAkey CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: MicroRNAs (miRNAs), present in most metazoans, are small non-coding RNAs that control gene expression by negatively regulating translation through binding to the 3'UTR of mRNA transcripts. Previously, experimental and computational methods were used to construct miRNA gene repositories agreeing with careful submission guidelines. RESULTS: An algorithm we developed - miRNAminer - is used for homologous conserved miRNA gene search in several animal species. Given a search query, candidate homologs from different species are tested for their known miRNA properties, such as secondary structure, energy and alignment and conservation, in order to asses their fidelity. When applying miRNAminer on seven mammalian species we identified several hundreds of high-confidence homologous miRNAs increasing the total collection of (miRbase) miRNAs, in these species, by more than 50%. miRNAminer uses stringent criteria and exhibits high sensitivity and specificity. CONCLUSION: We present - miRNAminer - the first web-server for homologous miRNA gene search in animals. miRNAminer can be used to identify conserved homolog miRNA genes and can also be used prior to depositing miRNAs in public databases. miRNAminer is available at http://pag.csail.mit.edu/mirnaminer.

The split structure of most mammalian protein-coding genes allows for the potential to produce multiple different mRNA and protein isoforms from a single gene locus through the process of alternative splicing (AS). We propose a computational approach called UNCOVER based on a pair hidden Markov model to discover conserved coding exonic sequences subject to AS that have so far gone undetected. Applying UNCOVER to orthologous introns of known human and mouse genes predicts skipped exons or retained introns present in both species, while discriminating them from conserved noncoding sequences. The accuracy of the model is evaluated on a curated set of genes with known conserved AS events. The prediction of skipped exons in the approximately 1% of the human genome represented by the ENCODE regions leads to more than 50 new exon candidates. Five novel predicted AS exons were validated by RT-PCR and sequencing analysis of 15 introns with strong UNCOVER predictions and lacking EST evidence. These results imply that a considerable number of conserved exonic sequences and associated isoforms are still completely missing from the current annotation of known genes. UNCOVER also identifies a small number of candidates for conserved intron retention.