Background: European Union legislature requires replacement of animal experiments with alternative methods, whenever such methods are suitable to reach the intended scientific objective. However, searching for alternative methods in the scientific literature is a time-consuming task that requires careful screening of an enormously large number of experimental biomedical publications. The identification of potentially relevant methods, e.g. organ or cell culture models, or computer simulations, can be supported with text mining tools specifically built for this purpose. Such tools are trained (or fine tuned) on relevant data sets labeled by human experts. Methods: We developed the GoldHamster corpus, composed of 1,600 PubMed (Medline) abstracts, in which we manually identified the used experimental model according to a set of eight labels, namely: “in vivo”, “organs”, “primary cells”, “immortal cell lines”, “invertebrates”, “humans”, “in silico” and “other” (models). We recruited 13 annotators with expertise in the biomedical domain and assigned each article to two individuals. Three additional rounds of annotation aimed at improving the quality of the annotations with disagreements in the first round. Furthermore, we conducted various machine learning experiments based on supervised learning to evaluate the suitability of the corpus for our classification task. Results: We obtained more than 7,000 abstract-level annotations for the above labels. The inter-annotator agreement (kappa coefficient) varied among labels, and ranged from 0.63 (for “others”) to 0.82 (for “invertebrates”), with an overall score of 0.74. The best-performing machine learning experiment used the BioBERT pre-trained model with fine-tuning to our corpus, which gained an overall f-score of 0.82. Conclusions: We obtained a high agreement for most of the labels, and our evaluation demonstrated, that our corpus is suitable for training reliable predictive models for automatic classification of biomedical literature according to the used experimental models. Our “Smart feature-based interactive” search tool (SMAFIRA) will employ this classifier for supporting the retrieval of alternative methods to animal experiments. The corpus and the source code will be made available.
In the EU, the breeding of genetically modified laboratory animals is, by definition, an animal experiment if the offspring may experience pain, suffering, or harm. In order to determine the actual burden of genetically modified mice, established methods are available. However, the breeding of immunodeficient mice is considered an experiment requiring a permit, even if no pain, suffering or harm is observed under scientifically required defined hygienic housing conditions, as determined by established methods of severity assessment. This seems contradictory and leads to uncertainty among scientists. With this commentary, we would like to shed light on this topic from different perspectives and propose a solution in terms of individualized severity assessment and approval procedures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.