Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

Abstract

IntroductionCausal feature selection entails identifying confounders that eliminate confounding bias when estimating effects from observational data. Traditionally, researchers employ expertise and literature review to identify confounders. Uncontrolled confounding from unidentified confounders threatens validity while conditioning on intermediate variables (mediators) weakens estimates, and conditioning on common effects (colliders) induces bias. Additionally, erroneously conditioning on variables playing multiple roles introduces bias. In a use case studying depression as a potential independent risk factor for Alzheimer’s disease (AD), we introduce a novel knowledge graph application enabling causal feature selection from computable literature-derived knowledge and biomedical ontologies to address these challenges.MethodsUsing the output from three machine reading systems, we harmonized the computable knowledge extracted from a scoped literature corpus. Next, we applied logical closure operations to infer missing knowledge and mapped the outputs to target terminologies. We then combined the outputs with ontology-grounded resources using a robust KG framework developed by computational biologists. Next, we translated epidemiological definitions of confounder, collider, and mediator into queries for searching the KG and summarized the roles played by the variables identified. Finally, we analyzed a selection of variables and reasoning paths in the search results.ResultsConfounder search yielded 128 confounders, including 58 phenotypes, 47 drugs, and 35 genes. Search also identified 23 collider and 16 mediator phenotypes. Only 31 of the 58 confounder phenotypes were found to behave exclusively as confounders. The remaining 27 phenotypes also play other roles, and 7 of the 21 confounders identified by both the KG and the literature were identified as being exclusively confounders. Stroke was an example of a variable playing all three roles.DiscussionOur findings suggest that our KG application could augment human expertise while confirming the complexity of selecting potential confounders for depression with AD. Imperfect concept mapping introduced errors, and the small literature corpus limited the scope of search results.ConclusionOur results suggest that our method may widely apply to causal feature selection. However, the search results need to be reviewed by human experts and tested empirically, and further work is required to optimize KG output for human consumption.Highlights•Knowledge of causal variables and their roles is essential for causal inference.•We show how to search a knowledge graph (KG) for causal variables and their roles.•The KG combines literature-derived knowledge with ontology-grounded knowledge.•We design queries to search the KG for confounder, collider, and mediator roles.•KG search reveals variables in these roles for depression and Alzheimer’s disease.Graphical abstract

An open source knowledge graph ecosystem for the life sciences

“…PheKnowLator benchmark KGs have been used in applications of toxicogenomic mechanistic inference 43 , to enable the exploration of large-scale biomedical hypergraphs 44 , and to facilitate deeper sub-phenotyping of pediatric rare disease patients 45 . Recently, PheKnowLator was used to create a disease-specific KG that combined ontology-grounded resources with literature-derived computable knowledge from machine reading 46 . The resulting KG was then used to identify causal features suitable for addressing confounding bias.…”

Trends and Insights on Tools Used for the Development of Expert Systems: A Systematic Review of Research Articles (2018-2022)

“…Through the interface the python language has utilized CLIPS functionalities in optimizing security compliance activities (Ghanem et al, 2023), automating decision making for aircraft navigation , refining computer networks security policies (Basile et al, 2022) and deploying AI-based radiology in veterinary practice (Fitzke etal., 2021). Python and ClipsPy have also incorporated other tools key among them SemRep -a natural language processing tool and INDRA -an assembler for dynamic reasoning (Malec et al, 2022;Taneja et al, 2022).…”

Utilizing LLMs to Evaluate the Argument Quality of Triples in SemMedDB for Enhanced Understanding of Disease Mechanisms

“…For example, the Semantic MEDLINE Database (SemMedDB) is a representative repository of subject-predicate-object triples extracted from the entire set of PubMed titles and abstracts (2). SemMedDB has been utilized by manually selecting causal predicates such as CAUSES, PREVENTS, and DISRUPTS to identify intermediates (3)(4)(5) and common causes, i.e., confounders (6,7) between the investigated exposure-and-outcome variables. While widely used for constructing biomedical knowledge graphs, it demonstrated limited performance with precision of 0.69, recall of 0.42, and an F1 score of 0.52 in a relaxed evaluation (8).…”