Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2022 Jul 18;23(4):bbac268.
doi: 10.1093/bib/bbac268.

Contexts and contradictions: a roadmap for computational drug repurposing with knowledge inference

Daniel N Sosa  1 , Russ B Altman  2
Affiliations
Review

Contexts and contradictions: a roadmap for computational drug repurposing with knowledge inference

Daniel N Sosa et al. Brief Bioinform. .

Abstract

The cost of drug development continues to rise and may be prohibitive in cases of unmet clinical need, particularly for rare diseases. Artificial intelligence-based methods are promising in their potential to discover new treatment options. The task of drug repurposing hypothesis generation is well-posed as a link prediction problem in a knowledge graph (KG) of interacting of drugs, proteins, genes and disease phenotypes. KGs derived from biomedical literature are semantically rich and up-to-date representations of scientific knowledge. Inference methods on scientific KGs can be confounded by unspecified contexts and contradictions. Extracting context enables incorporation of relevant pharmacokinetic and pharmacodynamic detail, such as tissue specificity of interactions. Contradictions in biomedical KGs may arise when contexts are omitted or due to contradicting research claims. In this review, we describe challenges to creating literature-scale representations of pharmacological knowledge and survey current approaches toward incorporating context and resolving contradictions.

Keywords: drug repurposing; knowledge graphs; metascience; natural language processing.

PubMed Disclaimer

Figures

Figure 1
Figure 1
A LBD pipeline for drug repurposing with knowledge inference. Challenges present in scientific text, knowledge extraction and knowledge representation include: NLP quality, incorporation of key contextual information and representation and adjudication of contradictory information.
Figure 2
Figure 2
An example of two extracted sentence-level predications suggesting contradictory information about a PPI.
Figure 3
Figure 3
Incorporating contextual information such as tissue specificity of PPIs may help adjudicate apparent contradictions in KGs.
Figure 4
Figure 4
Quantitative representations of the confidence of knowledge, as in the case of contradictory GWAS gene–disease associations, can be used in frameworks for reasoning under uncertainty including soft logic and Bayesian methods.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. DiMasi JA, Grabowski HG, Hansen RW. Innovation in the pharmaceutical industry: new estimates of R&D costs. J Health Econ 2016;47:20–33. - PubMed
    1. Kantarjian HM, Prat F, Steensma DP, et al. Cancer research in the United States: a critical review of current status and proposal for alternative models. Cancer 2018;124(14):2881–9. - PubMed
    1. Milsted RAV. Cancer drug approval in the United States, Europe, and Japan. Adv Cancer Res 2006;96:371–91. - PubMed
    1. Harrison RK. Phase ii and phase iii failures: 2013-2015. Nat Rev Drug Discov 2016;15(12):817–8. - PubMed
    1. Doench JG. Am I ready for CRISPR? A user’s guide to genetic screens. Nat Rev Genet 2018;19(2):67–80. - PubMed

Publication types