Identifying Protein-Protein Interaction using Tree LSTM and Structured Attention

2018/07/27 by Ahmed, Mahtab, Islam, Jumayel, Samee, Muhammad Rifayat +1 · 1 citation
#Computation and Language (cs.CL) #FOS: Biological sciences #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM)

paper · doi:10.48550/arxiv.1808.03227

Abstract

Identifying interactions between proteins is important to understand underlying biological processes. Extracting a protein-protein interaction (PPI) from the raw text is often very difficult. Previous supervised learning methods have used handcrafted features on human-annotated data sets. In this paper, we propose a novel tree recurrent neural network with structured attention architecture for doing PPI. Our architecture achieves state of the art results (precision, recall, and F1-score) on the AIMed and BioInfer benchmark data sets. Moreover, our models achieve a significant improvement over previous best models without any explicit feature extraction. Our experimental results show that traditional recurrent networks have inferior performance compared to tree recurrent networks for the supervised PPI problem.

Cited by

• Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models

Related

• SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction
• Feature Assisted bi-directional LSTM Model for Protein-Protein Interaction Identification from Biomedical Texts
• Graph Neural Networks for Protein-Protein Interactions -- A Short Survey
• Extracting Inter-Protein Interactions Via Multitasking Graph Structure Learning
• Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction