Document Type


Publication Date




Publication Title

Communications Biology






870 (1-14)


Adverse Drug Reactions (ADRs) have a direct impact on human health. As continuous pharmacovigilance and drug monitoring prove to be costly and time-consuming, computational methods have emerged as promising alternatives. However, most existing computational methods primarily focus on predicting whether or not the drug is associated with an adverse reaction and do not consider the core issue of drug benefit-risk assessment-whether the treatment outcome is serious when adverse drug reactions occur. To this end, we categorize serious clinical outcomes caused by adverse reactions to drugs into seven distinct classes and present a deep learning framework, so-called GCAP, for predicting the seriousness of clinical outcomes of adverse reactions to drugs. GCAP has two tasks: one is to predict whether adverse reactions to drugs cause serious clinical outcomes, and the other is to infer the corresponding classes of serious clinical outcomes. Experimental results demonstrate that our method is a powerful and robust framework with high extendibility. GCAP can serve as a useful tool to successfully address the challenge of predicting the seriousness of clinical outcomes stemming from adverse reactions to drugs.


© The Authors, 2023.

This article is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original authors and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

Data Availability

Article states: Data availability are as follows: All raw known drug–ADR interactions are collected from ADReCS database version v3.1 ( All raw adverse event reports are collected from the united states Food and drug administration Adverse Event Reporting System (FAERS, drug–ADR interactions in the benchmark dataset (Supplementary Data 1), classes of serious clinical outcomes caused by drug–ADR interaction in the benchmark dataset (Supplementary Data 2), the SMILES sequences of drugs in the benchmark dataset (Supplementary Data 3), the semantic descriptions of ADRs in the benchmark dataset (Supplementary Data 4), and two independent test datasets (Supplementary Data 5 and 6). Source data for figures can be found in Any other relevant data are available from the authors upon reasonable request.

Code availability: The code of our deep learning model is provided in and Zendo.

Original Publication Citation

Zhao, H., Ni, P., Zhao, Q., Liang, X., Ai, D., Erhardt, S., Wang, J., Li, Y., & Wang, J. (2023). Identifying the serious clinical outcomes of adverse reactions to drugs by a multi-task deep learning framework. Communications Biology, 6(1), 1-14, Article 870.

SupplementaryInfoLi2023-1.pdf (309 kB)
Supplementary Information

SupplementaryInfoLi2023-2.pdf (87 kB)
Description of Additional Supplementary Files

SupplementaryData1.docx (1 kB)
Supplementary Data 1

SupplementaryData2.docx (1574 kB)
Supplementary Data 2

SupplementaryData3.xlsx (52 kB)
Supplementary Data 3

SupplementaryData4.xlsx (34 kB)
Supplementary Data 4

SupplementaryData5.xlsx (166 kB)
Supplementary Data 5

SupplementaryData6.xlsx (579 kB)
Supplementary Data 6

ReportingSummaryLi2023.pdf (1523 kB)
Reporting Summary