Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Extracting Protein-Protein Interactions (PPIs) from Biomedical Literature using Attention-based Relational Context Information

Gilchan Park, Sean McCorkle, Carlos Soto, Ian Blaby, Shinjae Yoo

TL;DR

This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels and a Transformer-based deep learning method that exploits entities’ relational context information for relation representation to improve relation classification performance.

Abstract

Because protein-protein interactions (PPIs) are crucial to understand living systems, harvesting these data is essential to probe disease development and discern gene/protein functions and biological processes. Some curated datasets contain PPI data derived from the literature and other sources (e.g., IntAct, BioGrid, DIP, and HPRD). However, they are far from exhaustive, and their maintenance is a labor-intensive process. On the other hand, machine learning methods to automate PPI knowledge extraction from the scientific literature have been limited by a shortage of appropriate annotated data. This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels and a Transformer-based deep learning method that exploits entities' relational context information for relation representation to improve relation classification performance. The model's performance is evaluated on four widely studied biomedical relation extraction datasets, as well as this work's target PPI datasets, to observe the effectiveness of the representation to relation extraction tasks in various data. Results show the model outperforms prior state-of-the-art models. The code and data are available at: https://github.com/BNLNLP/PPI-Relation-Extraction

Extracting Protein-Protein Interactions (PPIs) from Biomedical Literature using Attention-based Relational Context Information

TL;DR

This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels and a Transformer-based deep learning method that exploits entities’ relational context information for relation representation to improve relation classification performance.

Abstract

Because protein-protein interactions (PPIs) are crucial to understand living systems, harvesting these data is essential to probe disease development and discern gene/protein functions and biological processes. Some curated datasets contain PPI data derived from the literature and other sources (e.g., IntAct, BioGrid, DIP, and HPRD). However, they are far from exhaustive, and their maintenance is a labor-intensive process. On the other hand, machine learning methods to automate PPI knowledge extraction from the scientific literature have been limited by a shortage of appropriate annotated data. This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels and a Transformer-based deep learning method that exploits entities' relational context information for relation representation to improve relation classification performance. The model's performance is evaluated on four widely studied biomedical relation extraction datasets, as well as this work's target PPI datasets, to observe the effectiveness of the representation to relation extraction tasks in various data. Results show the model outperforms prior state-of-the-art models. The code and data are available at: https://github.com/BNLNLP/PPI-Relation-Extraction
Paper Structure (25 sections, 3 equations, 3 figures, 8 tables, 1 algorithm)

This paper contains 25 sections, 3 equations, 3 figures, 8 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. PPI corpora
  4. PPI extraction methods
  5. Additional PPI curation
  6. Problems discovered during curation
  7. Bias due to restricted biological focus for each set
  8. Differences in notion of the definition of an interaction
  9. Confusion over PPI-negative annotations
  10. Interaction Type Annotation
  11. Methodology
  12. Relation Representation augmented with Attention-based Context Information
  13. Model Architecture
  14. Experimental Setup
  15. Datasets
  16. ...and 10 more sections

Figures (3)

  • Figure 1: The relation representation consists of entity start markers and the max-pooled of relational context, which is a series of tokens chosen by attention probability of the entities. The relation representation based on mention pooling is depicted in Appendix \ref{['sec:appendix_rel_rep_mention_pooling']}. $\oplus$ denotes element-wise addition. The example sentence is Absence of alpha-syntrophin leads to structurally aberrant neuromuscular synapses deficient in utrophin. (Source: BioInfer corpus).
  • Figure 2: The relation representation consists of the max-pooled of two entity contextualized embeddings and the max-pooled of relational context, which is a series of tokens chosen by attention probability of the entities. $\oplus$ denotes element-wise addition. The example sentence is Absence of alpha-syntrophin leads to structurally aberrant neuromuscular synapses deficient in utrophin. (Source: BioInfer corpus).
  • Figure :