EnviGraph generates synthetic data to improve biodegradation prediction
Synthetic reaction data from transformation rules for graph-to-sequence pretraining in biodegradation pathway prediction
Machine Learning
Summary
Predicting how chemicals break down in the environment requires lots of reaction data, but real examples are often scarce. The authors created enviGraph, a tool that makes large amounts of synthetic reaction data based on known transformation rules. This synthetic data helps train computer models to better predict chemical breakdown pathways. Their method improved prediction accuracy compared to using existing reaction datasets alone, especially for specific biodegradation scenarios.
What this means in practice
- •For environmental engineers: Use improved biodegradation pathway predictions to assess chemical fate in soil and sludge treatment processes.
- •For chemical safety assessors: Incorporate synthetic data pretrained models for better product and pathway predictions in regulatory evaluations of pesticide biodegradation.
Authors
Irsyaad Rijwan, Liam Brydon, Aidan Jared, Jörg Simon Wicker
Abstract
The scarcity of observed biodegradation reactions constrains the training of product and pathway predictors. We present enviGraph, a framework that generates and curates synthetic reaction data, uses these data to pretrain a graph-to-sequence predictor, and fine-tunes the predictor on observed environmental reactions for product and recursive pathway prediction. Applying inherited environmental transformation rules to structures from PubChem, NORMAN SusDat and EPA DSSTox, followed by curation, produces 776,851 canonical parent-product pairs for pretraining. We compare this dataset with three United States Patent and Trademark Office (USPTO) reaction datasets: USPTO-50K, USPTO-MIT and USPTO-Stereo. We evaluate enviGraph and the sequence-based enviFormer using ten folds split by pathway on the EAWAG Biocatalysis/Biodegradation Database (BBD), regulatory pesticide biodegradation data (Soil) and activated-sludge biodegradation data (Sludge). For both predictors, synthetic pretraining gives the highest BBD mean precision-recall area under the curve (PR-AUC) among the evaluated pretraining datasets for single-generation and multi-generation prediction. enviGraph achieves BBD single-generation PR-AUC of $0.202 \pm 0.050$ with synthetic pretraining, compared with $0.169 \pm 0.065$ for the retrospectively selected strongest USPTO condition, USPTO-Stereo (mean $\pm$ sample standard deviation across folds). Its exact BBD top-1 and top-5 accuracies with synthetic pretraining are 0.355 and 0.594. The strongest USPTO conditions give higher PR-AUC means than synthetic pretraining in most Soil and Sludge comparisons. enviGraph has higher Soil multi-generation PR-AUC means than enviFormer under each of the four main pretraining datasets, and with synthetic pretraining it also leads enviFormer on BBD single-generation PR-AUC and exact top-1 and top-5 accuracy.