Abstract
The BioCreative VI Track IV (mining protein interactions and mutations for precision medicine) challenge was organized in 2017 with the goal of applying biomedical text mining methods to support advancements in precision medicine approaches. As part of the challenge, a new dataset was introduced for the purpose of building a supervised relation extraction model capable of taking a test article and returning a list of interacting protein pairs identified by their Entrez Gene IDs. Specifically, such pairs represent proteins participating in a binary protein–protein interaction relation where the interaction is additionally affected by a genetic mutation—referred to as a PPIm relation. In this study, we explore an end-to-end approach for PPIm relation extraction by deploying a three-component pipeline involving deep learning-based named-entity recognition and relation classification models along with a knowledge-based approach for gene normalization. We propose several recall-focused improvements to our original challenge entry that placed second when matching on Entrez Gene ID (exact matching) and on HomoloGene ID. On exact matching, the improved system achieved new competitive test results of 37.78% micro-F1 with a precision of 38.22% and recall of 37.34% that corresponds to an improvement from the prior best system by approximately three micro-F1 points. When matching on HomoloGene IDs, we report similarly competitive test results at 46.17% micro-F1 with a precision and recall of 46.67 and 45.59%, respectively, corresponding to an improvement of more than eight micro-F1 points over the prior best result. The code for our deep learning system is made publicly available at https://github.com/bionlproc/biocppi_extraction.
Highlights
Precision medicine is an emerging disease treatment paradigm in which healthcare is customized to each individual patient
In this paper we exclusively focus on the PPIm extraction task and propose a pipeline of the following three modular components: named entity recognition (NER), gene mention normalization (GN) and relation classification (RC)
We propose the use of a deep neural network system based on a Convolutional neural networks (CNNs)–long short-term memory’ (LSTM) hybrid model initially proposed by Chiu et al [6] for NER
Summary
Precision medicine is an emerging disease treatment paradigm in which healthcare is customized to each individual patient. We refer to this particular type of relation, where the participants of a PPI are affected by a mutation, as a PPIm relation This challenge is important as there has been a lack of tools that allows for the extraction of such interactions from biomedical literature despite its potential to support approaches in precision medicine. Convolutional neural networks (CNNs) in particular were originally developed for image recognition tasks [18] and have been successfully applied to the text domain by exploiting so-called neural word embeddings [17, 33]. These word embeddings represent words as vectors and can be pre-trained using unsupervised methods and further trained when learning on a specific task. Using CNNs along with neural word embeddings has been shown to be effective in many natural language tasks (including text classification and relation extraction) since they naturally capture syntactic and semantic information [3, 7, 24]
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
