Deep semi-supervised learning ensemble framework for classifying co-mentions of human proteins and phenotypes

• Main Authors: Kahanda, I. (Author), Pourreza Shahri, M. (Author)
• Format: Article
• Language: English
• Published: BioMed Central Ltd 2021
• Subjects: Biomedical relationship extraction; data mining; Data Mining; Deep learning; Deep neural networks; Ensemble learning; Extraction; human; Human phenotype ontology; Human proteins; Humans; Learning algorithms; Natural language processing systems; Neural Networks, Computer; Ontology's; phenotype; Phenotype; Protein phenotype relationship; Protein phenotype relationships; Proteins; Recurrent neural networks; Relationship extraction; Semi-supervised; Semi-supervised learning; supervised machine learning; Supervised Machine Learning
• Online Access: View Fulltext in Publisher

 Background: Identifying human protein-phenotype relationships has attracted researchers in bioinformatics and biomedical natural language processing due to its importance in uncovering rare and complex diseases. Since experimental validation of protein-phenotype associations is prohibitive, automated tools capable of accurately extracting these associations from the biomedical text are in high demand. However, while the manual annotation of protein-phenotype co-mentions required for training such models is highly resource-consuming, extracting millions of unlabeled co-mentions is straightforward. Results: In this study, we propose a novel deep semi-supervised ensemble framework that combines deep neural networks, semi-supervised, and ensemble learning for classifying human protein-phenotype co-mentions with the help of unlabeled data. This framework allows the ability to incorporate an extensive collection of unlabeled sentence-level co-mentions of human proteins and phenotypes with a small labeled dataset to enhance overall performance. We develop PPPredSS, a prototype of our proposed semi-supervised framework that combines sophisticated language models, convolutional networks, and recurrent networks. Our experimental results demonstrate that the proposed approach provides a new state-of-the-art performance in classifying human protein-phenotype co-mentions by outperforming other supervised and semi-supervised counterparts. Furthermore, we highlight the utility of PPPredSS in powering a curation assistant system through case studies involving a group of biologists. Conclusions: This article presents a novel approach for human protein-phenotype co-mention classification based on deep, semi-supervised, and ensemble learning. The insights and findings from this work have implications for biomedical researchers, biocurators, and the text mining community working on biomedical relationship extraction. © 2021, The Author(s).