↓ Skip to main content

Oxford University Press

Article Metrics

Modeling polypharmacy side effects with graph convolutional networks

Overview of attention for article published in Bioinformatics, June 2018
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • One of the highest-scoring outputs from this source (#6 of 8,118)
  • High Attention Score compared to outputs of the same age (98th percentile)
  • High Attention Score compared to outputs of the same age and source (99th percentile)

Mentioned by

10 news outlets
5 blogs
137 tweeters
2 Facebook pages


1 Dimensions

Readers on

135 Mendeley
1 CiteULike
Modeling polypharmacy side effects with graph convolutional networks
Published in
Bioinformatics, June 2018
DOI 10.1093/bioinformatics/bty294
Pubmed ID

Marinka Zitnik, Monica Agrawal, Jure Leskovec


The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases or co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change, favorably or unfavorably, if taken with another drug. The knowledge of drug interactions is often limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality and morbidity. Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Unlike approaches limited to predicting simple drug-drug interaction values, Decagon can predict the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well polypharmacy side effects that have a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon opens up opportunities to use large pharmacogenomic and patient population data to flag and prioritize polypharmacy side effects for follow-up analysis via formal pharmacological studies. Source code and preprocessed datasets are at: http://snap.stanford.edu/decagon.

Twitter Demographics

The data shown below were collected from the profiles of 137 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 135 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 135 100%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 44 33%
Researcher 24 18%
Student > Master 20 15%
Unspecified 16 12%
Student > Bachelor 13 10%
Other 18 13%
Readers by discipline Count As %
Computer Science 51 38%
Unspecified 19 14%
Agricultural and Biological Sciences 15 11%
Biochemistry, Genetics and Molecular Biology 15 11%
Medicine and Dentistry 7 5%
Other 28 21%

Attention Score in Context

This research output has an Altmetric Attention Score of 207. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 12 November 2018.
All research outputs
of 12,266,834 outputs
Outputs from Bioinformatics
of 8,118 outputs
Outputs of similar age
of 257,834 outputs
Outputs of similar age from Bioinformatics
of 401 outputs
Altmetric has tracked 12,266,834 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 99th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 8,118 research outputs from this source. They typically receive a little more attention than average, with a mean Attention Score of 6.8. This one has done particularly well, scoring higher than 99% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 257,834 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 98% of its contemporaries.
We're also able to compare this research output to 401 others from the same source and published within six weeks on either side of this one. This one has done particularly well, scoring higher than 99% of its contemporaries.