Application of Text Mining in Risk Assessment of Chemical Mixtures: A Case Study of Polycyclic Aromatic Hydrocarbons (PAHs)

Abstract

BACKGROUND: Cancer risk assessment of complex exposures, such as exposure to mixtures of polycyclic aromatic hydrocarbons (PAHs), is challenging due to the diverse biological activities of these compounds. With the help of text mining (TM), we have developed TM tools-the latest iteration of the Cancer Risk Assessment using Biomedical literature tool (CRAB3) and a Cancer Hallmarks Analytics Tool (CHAT)-that could be useful for automatic literature analyses in cancer risk assessment and research. Although CRAB3 analyses are based on carcinogenic modes of action (MOAs) and cover almost all the key characteristics of carcinogens, CHAT evaluates literature according to the hallmarks of cancer referring to the alterations in cellular behavior that characterize the cancer cell. OBJECTIVES: The objective was to evaluate the usefulness of these tools to support cancer risk assessment by performing a case study of 22 European Union and U.S. Environmental Protection Agency priority PAHs and diesel exhaust and a case study of PAH interactions with silica. METHODS: We analyzed PubMed literature, comprising 57,498 references concerning priority PAHs and complex PAH mixtures, using CRAB3 and CHAT. RESULTS: CRAB3 analyses correctly identified similarities and differences in genotoxic and nongenotoxic MOAs of the 22 priority PAHs and grouped them according to their known carcinogenic potential. CHAT had the same capacity and complemented the CRAB output when comparing, for example, benzo[a]pyrene and dibenzo [a,l]pyrene. Both CRAB3 and CHAT analyses highlighted potentially interacting mechanisms within and across complex PAH mixtures and mechanisms of possible importance for interactions with silica. CONCLUSION: These data suggest that our TM approach can be useful in the hazard identification of PAHs and mixtures including PAHs. The tools can assist in grouping chemicals and identifying similarities and differences in carcinogenic MOAs and their interactions.

Developing human biomonitoring as a 21st century toolbox within the European exposure science strategy 2020–2030

“…Automatic and reliable classification of large amounts of textual data could potentially be useful in future decision-making. In particular, big data can be used for identifying and prioritising problems, gathering and analysis of information, facilitating expert evaluation/judgement and cognitive models (Ali et al 2021;Brandon et al 2020;Ciallella and Zhu 2019).…”