Abstract
Automated machine-reading biocuration systems typically use sentence-by-sentence information extraction to construct meaning representations for use by curators. This does not directly reflect the typical discourse structure used by scientists to construct an argument from the experimental data available within a article, and is therefore less likely to correspond to representations typically used in biomedical informatics systems (let alone to the mental models that scientists have). In this study, we develop Natural Language Processing methods to locate, extract, and classify the individual passages of text from articles’ Results sections that refer to experimental data. In our domain of interest (molecular biology studies of cancer signal transduction pathways), individual articles may contain as many as 30 small-scale individual experiments describing a variety of findings, upon which authors base their overall research conclusions. Our system automatically classifies discourse segments in these texts into seven categories (fact, hypothesis, problem, goal, method, result, implication) with an F-score of 0.68. These segments describe the essential building blocks of scientific discourse to (i) provide context for each experiment, (ii) report experimental details and (iii) explain the data’s meaning in context. We evaluate our system on text passages from articles that were curated in molecular biology databases (the Pathway Logic Datum repository, the Molecular Interaction MINT and INTACT databases) linking individual experiments in articles to the type of assay used (coprecipitation, phosphorylation, translocation etc.). We use supervised machine learning techniques on text passages containing unambiguous references to experiments to obtain baseline F1 scores of 0.59 for MINT, 0.71 for INTACT and 0.63 for Pathway Logic. Although preliminary, these results support the notion that targeting information extraction methods to experimental results could provide accurate, automated methods for biocuration. We also suggest the need for finer-grained curation of experimental methods used when constructing molecular biology databases
Highlights
We suggest the need for finer-grained curation of experimental methods used when constructing molecular biology databases
We used a training set based on 258 passages and evaluated performance based on mean accuracy and weighted F1 measures from 5-fold cross validation with 24 different target classes. We repeated this process for articles from the MINT database and of the 359 passages we found from experimental text referring to figures, 136 of these passages were discarded due to referring to multiple types of experiments
A key element of this work is the linkage between individual subfigures and their underlying experiments. This linkage arises from core design decisions in both the Pathway Logic (PL) and MINT data sets, and we performed a small-scale manual evaluation as a part of this study
Summary
High-level descriptive languages such as the ‘Systems-Biology Markup Language’ [2], BioPax [3] or the ‘Biological Expression Language’ [4] provide a semantic representation of pathways, reactions and reactants (with encodings for additional information such as genetic details, post-translational modifications, reaction kinetics etc.) These languages provide interpretable summaries of pathway mechanisms that can be read by humans and/or reasoned about by computational knowledge representation and reasoning methods. At a deeper level of description, executable languages such as Pathway Logic (PL) [6], Kappa [7], and PySB [8] provide simulation/reasoning frameworks that can make theoretical predictions about aspects of the state of the system under different hypothesized conditions [9] These types of formulations act as the target for reading systems and for the practice of biocuration generally
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Database : the journal of biological databases and curation
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
