Search

Important tasks in biomedical discovery such as predicting gene functions, gene–disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree , can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network's specific connections using network permutation to generate features that depend only on degree. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Researchers seeking to predict new or missing edges in biological networks should use our permutation approach to obtain a baseline for performance that may be nonspecific because of degree. We released our methods as an open-source Python package (https://github.com/hetio/xswap/). [ABSTRACT FROM AUTHOR]

Background Hetnets, short for "heterogeneous networks," contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes—including genes, diseases, drugs, pathways, and anatomical structures—with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. Findings We developed a new procedure, termed hetnet connectivity search , that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. Conclusion We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy. [ABSTRACT FROM AUTHOR]

Complex disease genetics is a key area of research for reducing disease and improving human health. Genome-wide association studies (GWAS) help in this research by identifying regions of the genome that contribute to complex disease risk. However, GWAS are computationally intensive and require access to individual-level genetic and health information, which presents concerns about privacy and imposes costs on researchers seeking to study complex diseases. Publicly released pan-biobank GWAS summary statistics provide immediate access to results for a subset of phenotypes, but they do not inform about all phenotypes or hand-crafted phenotype definitions, which are often more relevant to study. Here, we present WebGWAS, a new tool that allows researchers to obtain GWAS summary statistics for a phenotype of interest without needing access to individual-level genetic and phenotypic data. Our public web app can be used to study custom phenotype definitions, including inclusion and exclusion criteria, and to produce approximate GWAS summary statistics for that phenotype. WebGWAS computes approximate GWAS summary statistics very quickly (<10 seconds), and it does not store private health information. We also show how the statistical approximation underlying WebGWAS can be used to accelerate the computation of multi-phenotype GWAS among correlated phenotypes. Our tool provides a faster approach to GWAS for researchers interested in complex disease, providing approximate summary statistics in short order, without the need to collect, process, and produce GWAS results. Overall, this method advances complex disease research by facilitating more accessible and cost-effective genetic studies using large observational data.

A major obstacle hindering the broad adoption of polygenic scores (PGS) is their lack of "portability" to people that differ-in genetic ancestry or other characteristics-from the GWAS samples in which genetic effects were estimated. Here, we use the UK Biobank to measure the change in PGS prediction accuracy as a continuous function of individuals' genome-wide genetic dissimilarity to the GWAS sample ("genetic distance"). Our results highlight three gaps in our understanding of PGS portability. First, prediction accuracy is extremely noisy at the individual level and not well predicted by genetic distance. In fact, variance in prediction accuracy is explained comparably well by socioeconomic measures. Second, trends of portability vary across traits. For several immunity-related traits, prediction accuracy drops near zero quickly even at intermediate levels of genetic distance. This quick drop may reflect GWAS associations being more ancestry-specific in immunity-related traits than in other traits. Third, we show that even qualitative trends of portability can depend on the measure of prediction accuracy used. For instance, for white blood cell count, a measure of prediction accuracy at the individual level (reduction in mean squared error) increases with genetic distance. Together, our results show that portability cannot be understood through global ancestry groupings alone. There are other, understudied factors influencing portability, such as the specifics of the evolution of the trait and its genetic architecture, social context, and the construction of the polygenic score. Addressing these gaps can aid in the development and application of PGS and inform more equitable genomic research.

Hetnets, short for "heterogeneous networks", contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes - including genes, diseases, drugs, pathways, and anatomical structures - with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .

Important tasks in biomedical discovery such as predicting gene functions, gene-disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree, can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network's specific connections. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Degree's predictive performance diminishes when the networks used for training and testing-despite measuring the same biological relationships-were generated using distinct techniques and hence have large differences in degree distribution. We introduce the permutation-derived edge prior as the probability that an edge exists based only on degree. The edge prior shows excellent discrimination and calibration for 20 biomedical networks (16 bipartite, 3 undirected, 1 directed), with AUROCs frequently exceeding 0.85. Researchers seeking to predict new or missing edges in biological networks should use the edge prior as a baseline to identify the fraction of performance that is nonspecific because of degree. We released our methods as an open-source Python package (https://github.com/hetio/xswap/).

The rapid global spread of the novel coronavirus SARS-CoV-2 has strained healthcare and testing resources, making the identification and prioritization of individuals most at-risk a critical challenge. Recent evidence suggests blood type may affect risk of severe COVID-19. We used observational healthcare data on 14,112 individuals tested for SARS-CoV-2 with known blood type in the New York Presbyterian (NYP) hospital system to assess the association between ABO and Rh blood types and infection, intubation, and death. We found slightly increased infection prevalence among non-O types. Risk of intubation was decreased among A and increased among AB and B types, compared with type O, while risk of death was increased for type AB and decreased for types A and B. We estimated Rh-negative blood type to have a protective effect for all three outcomes. Our results add to the growing body of evidence suggesting blood type may play a role in COVID-19., Competing Interests: Competing interests The authors have no competing interests to disclose.

The Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has caused thousands of deaths worldwide, including >18,000 in New York City (NYC) alone. The sudden emergence of this pandemic has highlighted a pressing clinical need for rapid, scalable diagnostics that can detect infection, interrogate strain evolution, and identify novel patient biomarkers. To address these challenges, we designed a fast (30-minute) colorimetric test (LAMP) for SARS-CoV-2 infection from naso/oropharyngeal swabs, plus a large-scale shotgun metatranscriptomics platform (total-RNA-seq) for host, bacterial, and viral profiling. We applied both technologies across 857 SARS-CoV-2 clinical specimens and 86 NYC subway samples, providing a broad molecular portrait of the COVID-19 NYC outbreak. Our results define new features of SARS-CoV-2 evolution, nominate a novel, NYC-enriched viral subclade, reveal specific host responses in interferon, ACE, hematological, and olfaction pathways, and examine risks associated with use of ACE inhibitors and angiotensin receptor blockers. Together, these findings have immediate applications to SARS-CoV-2 diagnostics, public health, and new therapeutic targets., Competing Interests: Conflicts of Interest Nathan Tanner and Bradley W. Langhorst are employees at New England Biolabs.

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine., (© 2018 The Authors.)