AOP-helpFinder webserver: a tool for comprehensive analysis of the literature to support adverse outcome pathways development

Abstract

Motivation Adverse Outcome Pathways (AOPs) are a conceptual framework developed to support the use of alternative toxicology approaches in the risk assessment. AOPs are structured linear organizations of existing knowledge illustrating causal pathways from the initial molecular perturbation triggered by various stressors, through key events (KEs) at different levels of biology, to the ultimate health or ecotoxicological adverse outcome. Results Artificial intelligence can be used to systematically explore available toxicological data that can be parsed in the scientific literature. Recently a tool called AOP-helpFinder was developed to identify associations between stressors and KEs supporting thus documentation of AOPs. To facilitate the utilization of this advanced bioinformatics tool by the scientific and the regulatory community, a webserver was created. The proposed AOP-helpFinder webserver uses better performing version of the tool which reduces the need for manual curation of the obtained results. As an example, the server was successfully applied to explore relationships of a set of endocrine disruptors with metabolic-related events. The AOP-helpFinder webserver assists in a rapid evaluation of existing knowledge stored in the PubMed database, a global resource of scientific information, to build AOPs and Adverse Outcome Networks (AONs) supporting the chemical risk assessment. Availability and implementation AOP-helpFinder is available at http://aop-helpfinder.u-paris-sciences.fr/index.php

A Case Study on Integrating a New Key Event Into an Existing Adverse Outcome Pathway on Oxidative DNA Damage: Challenges and Approaches in a Data-Rich Area

“…In the future, machine learning tools may also be deployed to facilitate use of SR tools for more efficient and documented literature searches in AOP development. Such tools already exist but were beyond the scope of our present work (e.g., Jornod et al, 2021 ). 2) In addition, filtering for specific, reliable assays that produce quantitative data could provide an alternative strategy to both reduce the collected articles and improve the likelihood of developing a quantitative understanding with the collected articles.…”

“…In the future, machine learning tools may also be deployed to facilitate use of SR tools for more efficient and documented literature searches in AOP development. Such tools already exist but were beyond the scope of our present work (e.g., Jornod et al, 2021 ).…”

Mapping DEHP to the adverse outcome pathway network for human female reproductive toxicity

“…The literature search was conducted in two ways with the aim to capture as much information as possible to link DEHP to the HFRT-AOP network. First, an automatic search was performed using the recently developed AOP-helpFinder tool (Jornod et al 2021). This tool is a hybrid approach that combines text mining procedures and graph theory to identify the linkage between a stressor and biological events.…”

Evidenced-Based Approaches to Support the Development of Endocrine-Mediated Adverse Outcome Pathways: Challenges and Opportunities

“…Specificity and precision have the advantage of making a KER more searchable. Notably, an artificial intelligence based approach using text mining and graph theory, named AOP-helpFinder, allows to automatically identify and extract specific AOP-related terms and evidence (aop-helpfinder.u-paris-sciences.fr) (Jornod et al, 2020;Jornod et al, 2021;Zgheib et al, 2021). In "Rugard et al, 2020", AOP-helpFinder results pointed out linkages between Bisphenol-F and relevant MIEs [i.e., "PPARc inhibition" (Peroxisome proliferator-activated receptor γ)] often associated with liver steatosis and lipid accumulation (Yang et al, 2010).…”