Prediction of Adverse Biological Effects of Chemicals Using Knowledge Graph Embeddings

TL;DR

This paper constructs a knowledge graph from ecotoxicological data and demonstrates that applying various knowledge graph embedding models improves the accuracy of predicting adverse biological effects of chemicals, especially with fine-tuning techniques.

Contribution

It introduces a novel knowledge graph for ecotoxicology and evaluates multiple embedding models, showing enhanced prediction accuracy through fine-tuning.

Findings

Knowledge graph embeddings improve effect prediction accuracy

Fine-tuning embeddings enhances model performance

Evaluation of nine diverse embedding models

Abstract

We have created a knowledge graph based on major data sources used in ecotoxicological risk assessment. We have applied this knowledge graph to an important task in risk assessment, namely chemical effect prediction. We have evaluated nine knowledge graph embedding models from a selection of geometric, decomposition, and convolutional models on this prediction task. We show that using knowledge graph embeddings can increase the accuracy of effect prediction with neural networks. Furthermore, we have implemented a fine-tuning architecture that adapts the knowledge graph embeddings to the effect prediction task and leads to better performance. Finally, we evaluate certain characteristics of the knowledge graph embedding models to shed light on the individual model performance.