Applying knowledge-driven mechanistic inference to toxicogenomics. (August 2020)

• Record Type: Journal Article
• Authors: Tripodi, Ignacio J.; Callahan, Tiffany J.; Westfall, Jessica T.; Meitzer, Nayland S.; Dowell, Robin D.; Hunter, Lawrence E.
• Is Part Of: Toxicology in vitro. Volume 66(2020)
• Publication Date: 2020-08
• Subjects: Computational toxicology -- Mechanistic inference -- Artificial intelligence -- Mechanistic toxicology -- Adverse outcome pathways; Toxicity testing -- In vitro -- Periodicals; Toxicology -- Periodicals; 615.9
• DOI: 10.1016/j.tiv.2020.104877
• Languages: English
• ISSNs: 0887-2333

Abstract

Abstract: When considering toxic chemicals in the environment, a mechanistic, causal explanation of toxicity may be preferred over a statistical or machine learning-based prediction by itself. Elucidating a mechanism of toxicity is, however, a costly and time-consuming process that requires the participation of specialists from a variety of fields, often relying on animal models. We present an innovative mechanistic inference framework (MechSpy), which can be used as a hypothesis generation aid to narrow the scope of mechanistic toxicology analysis. MechSpy generates hypotheses of the most likely mechanisms of toxicity, by combining a semantically-interconnected knowledge representation of human biology, toxicology and biochemistry with gene expression time series on human tissue. Using vector representations of biological entities, MechSpy seeks enrichment in a manually curated list of high-level mechanisms of toxicity, represented as biochemically- and causally-linked ontology concepts. Besides predicting the canonical mechanism of toxicity for many well-studied compounds, we experimentally validated some of our predictions for other chemicals without an established mechanism of toxicity. This mechanistic inference framework is an advantageous tool for predictive toxicology, and the first of its kind to produce a mechanistic explanation for each prediction. MechSpy can be modified to include additional mechanisms of toxicity, and is generalizable to other types of mechanisms of human biology. Highlights: Several mechanisms of cellular toxicity can be predicted using a vector representation of semantic knowledge graph concepts. We produce putative mechanistic explanations as an ordered list of gene expression changes related to each mechanism step. Mechanisms of toxicity can be represented using ontology concepts, and enriched accounting for the sequential order of events.