Systematic integration of biomedical knowledge prioritizes drugs for repurposing.
Himmelstein DS, Lizee A, Hessler C, Brueggeman L, Chen SL, Hadley D, Green A, Khankhanian P, Baranzini SE. · 2017
Read Systematic integration of biomedical knowledge prioritizes drugs for repurposing. by Himmelstein DS, Lizee A, Hessler C, Brueggeman L, Chen SL, Hadley D, Green A, Khankhanian P, Baranzini SE. (2017) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc5640425.txt.
Introduction
Himmelstein and co-authors built a knowledge network to rank drugs for new uses. Their research article appeared in eLife. The project is called Project Rephetio. It models drug effects from 755 known treatments. Their network, Hetionet, links many data types. It joins compounds, diseases, genes, and pathways. Data came from 29 public resources.
The network holds about 47,000 nodes. It holds over two million relationships. The team found patterns that mark real treatments. They then scored about 209,000 compound and disease pairs. External checks supported the predictions. The scores gave fresh leads for epilepsy drugs. The whole study ran in the open. Community members gave feedback during the work.
Catalog record
| CREATOR | Himmelstein DS, Lizee A, Hessler C, Brueggeman L, Chen SL, Hadley D, Green A, Khankhanian P, Baranzini SE. |
|---|---|
| YEAR | 2017 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 81 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |
Browse the full library · About the Tower of Babel
Full text
The opening of the work, from the library's hosted text:
Systematic integration of biomedical knowledge prioritizes drugs for repurposing By Daniel Scott Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, Sergio E Baranzini, Alfonso Valencia Published in: eLife DOI: 10.7554/eLife.26726 ABSTRACT 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. INTRODUCTION The cost of developing a new therapeutic drug has been estimated at 1.4 billion dollars (DiMasi et al., 2016), the process typically takes 15 years from lead compound to market (Reichert, 2003), and the likelihood of success is stunningly low (Hay et al., 2014). Strikingly, the costs have been doubling every 9 years since 1970, a sort of inverse Moore’s law, which is far from an optimal strategy from both a business and public health perspective (Scannell et al., 2012). Drug repurposing — identifying novel uses for existing therapeutics — can drastically reduce the duration, failure rates, and costs of approval (Ashburn and Thor, 2004). These benefits stem from the rich preexisting information on approved drugs, including extensive toxicology profiling performed during development, preclinical models, clinical trials, and postmarketing surveillance. Drug repurposing is poised to become more efficient as mining of electronic health records (EHRs) to retrospectively assess the effect of drugs gains feasibility (Wang et al., 2015; Xu et al., 2015; Brilliant et al., 2016; Tatonetti et al., 2012). However, systematic approaches to repurpose drugs based on mining EHRs alone will likely lack power due to multiple testing. Similar to the approach followed to increase the power of genome-wide association studies (GWAS) (Stephens and Balding, 2009; Sawcer, 2008), integration of biological knowledge to prioritize drug repurposing will help overcome limited EHR sample size and data quality. In addition to repurposing, several other paradigm shifts in drug development have been proposed to improve efficiency. Since small molecules tend to bind to many targets, polypharmacology aims to find synergy in the multiple effects of a drug (Roth et al., 2004). Network pharmacology assumes diseases consist of a multitude of molecular alterations resulting in a robust disease state. Network pharmacology seeks to uncover multiple points of intervention into a specific pathophysiological state that together rehabilitate an otherwise resilient disease process (Hopkins, 2008; Hopkins, 2007). Although target-centric drug discovery has dominated the field for decades, phenotypic screens have more recently resulted in a comparatively higher number of first-in-class small molecules (Swinney and Anthony, 2011). Recent technological advances have enabled a new paradigm in which mid- to high-throughput assessment of intermediate phenotypes, such as the molecular response to drugs, is replacing the classic target discovery approach (Iskar et al., 2012; Lamb, 2007; Qu and Rajpal, 2012). Furthermore, integration of multiple channels of evidence, particularly diverse types of data, can overcome the limitations and weak performance inherent to data of a single domain (Hodos et al., 2016). Modern computational approaches offer a convenient platform to tie these developments together as the reduced cost and increased velocity of in silico experimentation massively lowers the barriers to entry and price of failure (Hurle et al., 2013; Liu et al., 2013). Hetnets (short for heterogeneous networks) are networks with multiple types of nodes and relationships. They offer an intuitive, versatile, and powerful structure for data integration by aggregating graphs for each relationship type onto common nodes. In this study, we developed a hetnet (Hetionet v1.0) by integrating knowledge and experimental findings from decades of biomedical research spanning millions of publications. We adapted an algorithm originally developed for social network analysis and applied it to Hetionet v1.0 to identify patterns of efficacy and predict new uses for drugs. The algorithm performs edge prediction through a machine learning framework that accommodates the breadth and depth of information contained in Hetionet v1.0 (Himmelstein and Baranzini, 2015a; Sun et al., 2011). Our approach represents an in silico implementation of network pharmacology that natively incorporates polypharmacology and high-throughput phenotypic screening. One fundamental characteristic of our method is that it learns and evaluates itself on existing medical indications (i.e. a 'gold standard’). Next, we introduce previous approaches that also performed comprehensive evaluation on existing treatments. A 2011 study, named PREDICT, compiled 1933 treatments between 593 drugs and 313 diseases (Gottlieb et al., 2011). Starting from the premise that similar drugs treat similar diseases, PREDICT trained a classifier that incorporates five types of drug-drug and two types of disease-disease similarity. A 2014 study compiled 890 treatments between 152 drugs and 145 diseases with transcriptional signatures (Cheng et al., 2014). The authors found that compounds triggering an opposing transcriptional response to the disease were more likely to be treatments, although this effect was weak and limited to cancers. A 2016 study compiled 402 treatments between 238 drugs and 78 diseases and used a single proximity score — the average shortest path distance between a drug’s targets and disease’s associated proteins on the interactome — as a classifier (Guney et al., 2016). We build on these successes by creating a framework for incorporating the effects of any biological relationship into the prediction of whether a drug treats a disease. By doing this, we were able to capture a multitude of effects that have been suggested as influential for drug repurposing including drug-drug similarity (Gottlieb et al., 2011; Li and Lu, 2012), disease-disease similarity (Gottlieb et al., 2011; Chiang and Butte, 2009), transcriptional signatures (Lamb, 2007; Qu and Rajpal, 2012; Cheng et al., 2014; Lamb et al., 2006; Iorio et al., 2013), protein interactions (Guney et al., 2016), genetic association (Nelson et al., 2015; Sanseau et al., 2012), drug side effects (Campillos et al., 2008; Nugent et al., 2016), disease symptoms (Zhou et al., 2014), and molecular pathways (Pratanwanich and Lió, 2014). Our ability to create such an integrative model of drug efficacy relies on the hetnet data structure to unite diverse information. On Hetionet v1.0, our algorithm learns which types of compound–disease paths discriminate treatments from non-treatments in order to predict the probability that a compound treats a disease. We refer to this study as Project Rephetio (pronounced as rep-het-ee-oh). Both Rephetio and Hetionet are portmanteaus combining the words repurpose, heterogeneous, and network with the URL het.io. RESULTS Hetionet v1.0 We obtained and integrated data from 29 publicly available resources to create Hetionet v1.0 (Figure 1). The hetnet contains 47,031 nodes of 11 types (Table 1) and 2,250,197 relationships of 24 types (Table 2). The nodes consist of 1552 small molecule compounds and 137 complex diseases, as