Application of text mining to develop AOP-based mucus hypersecretion genesets and confirmation with in vitro and clinical samples

Abstract

Mucus hypersecretion contributes to lung function impairment observed in COPD (chronic obstructive pulmonary disease), a tobacco smoking-related disease. A detailed mucus hypersecretion adverse outcome pathway (AOP) has been constructed from literature reviews, experimental and clinical data, mapping key events (KEs) across biological organisational hierarchy leading to an adverse outcome. AOPs can guide the development of biomarkers that are potentially predictive of diseases and support the assessment frameworks of nicotine products including electronic cigarettes. Here, we describe a method employing manual literature curation supported by a focused automated text mining approach to identify genes involved in 5 KEs contributing to decreased lung function observed in tobacco-related COPD. KE genesets were subsequently confirmed by unsupervised clustering against 3 different transcriptomic datasets including (1) in vitro acute cigarette smoke and e-cigarette aerosol exposure, (2) in vitro repeated incubation with IL-13, and (3) lung biopsies from COPD and healthy patients. The 5 KE genesets were demonstrated to be predictive of cigarette smoke exposure and mucus hypersecretion in vitro, and less conclusively predict the COPD status of lung biopsies. In conclusion, using a focused automated text mining and curation approach with experimental and clinical data supports the development of risk assessment strategies utilising AOPs.

Clinical Application of Early Warning Scoring Based on BiLSTM-Attention in Emergency Obstetric Preexamination and Triage

“…The classification, particularly for the abovementioned literature for equipment failure defects, is only focused on post hoc analysis and data lean control, while the real-time diagnosis of the upper window alarm information has the ability to provide auxiliary decision making and risk warning for obstetric emergency prescreening defect troubleshooting by healthcare providers [ 11 ].…”

A Narrative Literature Review of Natural Language Processing Applied to the Occupational Exposome

“…The authors of [ 15 ] propose to use scientific literature on PubMed to assess the impact of environmental exposures from early life using different unsupervised learning methods (e.g., LDA (Latent Dirichlet Allocation)) to gain insight into the different topics. The work by [ 29 ] models the impact of COPD (chronic obstructive pulmonary) from smoking using Adverse Outcome Pathways generated from the scientific literature. The is collected and filtered from PubMed to create a corpus and then clustered using the text mining approach proposed by [ 50 ].…”

“…Tool used NLTK [9][10][11][12][13], [14] Other [9,[15][16][17][18], [19][20][21], [13,[22][23][24], [25][26][27] Not declared [15,[28][29][30][31][32], [33][34][35][36][37], [38][39][40] Resources Scientific literature [12,15,28,29,41,42], [14,22,23,31], [24,43,44], [19][20][21]33,…”

Natural language processing in toxicology: Delineating adverse outcome pathways and guiding the application of new approach methodologies

“…More recently, Minet et al. [35] built ad-hoc gene sets from the mucus hypersecretion AOP developed by Luettich et al. [36] .…”

“…For example, highlighting causal relationships between upstream (molecular) key events and downstream (cellular) key events will considerably facilitate the review process by AOP developers. The automation of literature search will also highlight data gaps more efficiently than manual review, which could be filled in by the development of new testing methods (NAMs) as evidenced earlier [35] .…”