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.

The ability to computationally predict whether a compound treats a disease would improve the economy and success rate of drug approval. This study describes Project Rephetio to systematically model drug efficacy based on 755 existing treatments. First, we constructed Hetionet (neo4j.het.io), an integrative network encoding knowledge from millions of biomedical studies. Hetionet v1.0 consists of 47,031 nodes of 11 types and 2,250,197 relationships of 24 types. Data were integrated from 29 public resources to connect compounds, diseases, genes, anatomies, pathways, biological processes, molecular functions, cellular components, pharmacologic classes, side effects, and symptoms. Next, we identified network patterns that distinguish treatments from non-treatments. Then, we predicted the probability of treatment for 209,168 compound–disease pairs (het.io/repurpose). Our predictions validated on two external sets of treatment and provided pharmacological insights on epilepsy, suggesting they will help prioritize drug repurposing candidates. This study was entirely open and received realtime feedback from 40 community members.

The first decade of Genome Wide Association Studies (GWAS) has uncovered a wealth of disease-associated variants. Two important derivations will be the translation of this information into a multiscale understanding of pathogenic variants and leveraging existing data to increase the power of existing and future studies through prioritization. We explore edge prediction on heterogeneous networks—graphs with multiple node and edge types—for accomplishing both tasks. First we constructed a network with 18 node types—genes, diseases, tissues, pathophysiologies, and 14 MSigDB (molecular signatures database) collections—and 19 edge types from high-throughput publicly-available resources. From this network composed of 40,343 nodes and 1,608,168 edges, we extracted features that describe the topology between specific genes and diseases. Next, we trained a model from GWAS associations and predicted the probability of association between each protein-coding gene and each of 29 well-studied complex diseases. The model, which achieved 132-fold enrichment in precision at 10% recall, outperformed any individual domain, highlighting the benefit of integrative approaches. We identified pleiotropy, transcriptional signatures of perturbations, pathways, and protein interactions as influential mechanisms explaining pathogenesis. Our method successfully predicted the results (with AUROC = 0.79) from a withheld multiple sclerosis (MS) GWAS despite starting with only 13 previously associated genes. Finally, we combined our network predictions with statistical evidence of association to propose four novel MS genes, three of which (JAK2, REL, RUNX3) validated on the masked GWAS. Furthermore, our predictions provide biological support highlighting REL as the causal gene within its gene-rich locus. Users can browse all predictions online (http://het.io). Heterogeneous network edge prediction effectively prioritized genetic associations and provides a powerful new approach for data integration across multiple domains. For complex human diseases, identifying the genes harboring susceptibility variants has taken on medical importance. Disease-associated genes provide clues for elucidating disease etiology, predicting disease risk, and highlighting therapeutic targets. Here, we develop a method to predict whether a given gene and disease are associated. To capture the multitude of biological entities underlying pathogenesis, we constructed a heterogeneous network, containing multiple node and edge types. We built on a technique developed for social network analysis, which embraces disparate sources of data to make predictions from heterogeneous networks. Using the compendium of associations from genome-wide studies, we learned the influential mechanisms underlying pathogenesis. Our findings provide a novel perspective about the existence of pervasive pleiotropy across complex diseases. Furthermore, we suggest transcriptional signatures of perturbations are an underutilized resource amongst prioritization approaches. For multiple sclerosis, we demonstrated our ability to prioritize future studies and discover novel susceptibility genes. Researchers can use these predictions to increase the statistical power of their studies, to suggest the causal genes from a set of candidates, or to generate evidence-based experimental hypothesis.

The website Sci-Hub enables users to download PDF versions of scholarly articles, including many articles that are paywalled at their journal’s site. Sci-Hub has grown rapidly since its creation in 2011, but the extent of its coverage has been unclear. Here we report that, as of March 2017, Sci-Hub’s database contains 68.9% of the 81.6 million scholarly articles registered with Crossref and 85.1% of articles published in toll access journals. We find that coverage varies by discipline and publisher, and that Sci-Hub preferentially covers popular, paywalled content. For toll access articles, we find that Sci-Hub provides greater coverage than the University of Pennsylvania, a major research university in the United States. Green open access to toll access articles via licit services, on the other hand, remains quite limited. Our interactive browser at https://greenelab.github.io/scihub allows users to explore these findings in more detail. For the first time, nearly all scholarly literature is available gratis to anyone with an Internet connection, suggesting the toll access business model may become unsustainable.

Motivation: Novel machine learning and statistical modeling studies rely on standardized comparisons to existing methods using well-studied benchmark datasets. Few tools exist that provide rapid access to many of these datasets through a standardized, user-friendly interface that integrates well with popular data science workflows. Results: This release of PMLB (Penn Machine Learning Benchmarks) provides the largest collection of diverse, public benchmark datasets for evaluating new machine learning and data science methods aggregated in one location. v1.0 introduces a number of critical improvements developed following discussions with the open-source community. Availability and implementation: PMLB is available at https://github.com/EpistasisLab/pmlb. Python and R interfaces for PMLB can be installed through the Python Package Index and Comprehensive R Archive Network, respectively.

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system and, in countries populated by northern Europeans and their descendants, a leading cause of progressive neurologic dysfunction in young adults.¹ A large body of data confirms a multifactorial source, and a decade of large-scale genomic screens identified more than 100 genomic regions in which variants are associated with increased susceptibility.² The strongest genome-wide susceptibility locus maps to the major histocompatibility complex (MHC) (6p21.3) accounting for approximately 10.5% of the genetic variance underlying the risk for MS. This pivotal association also reflects the complexity of MS risk inheritance by harboring multiple statistically independent allelic and haplotypic effects^3,4 including 2 specific interactions involving pairs of class II alleles: DQA1*01:01-DRB1*15:01 and DQB1*03:01-DQB1*03:02.⁵