The study was carried out in collaboration of researchers from the University of Birmingham together with scientists at the Research Centre for Eco-Environmental Sciences (RCEES) in China and the Helmholtz Centre of Environmental Research (UFZ) in Germany.
Water fleas as test organisms
Chemically analysing surface water for individual substances is time-consuming and labour-intensive. Indicator organisms are therefore also used to determine the toxicity of water pollutants. This includes measuring the bioactivity of water fleas (Daphnia).
„Our innovative approach leverages Daphnia as the sentinel species to uncover potential toxic substances in the environment,“ explains Dr Xiaojing Li, of the University of Birmingham (UoB) and the lead author of this study. „By using AI methods, we can identify which subsets of chemicals might be particularly harmful to aquatic life, even at low concentrations that wouldn’t normally raise concerns.“
Chemical fingerprints from chemically complex river water samples
The study was carried out with a total of 30 water samples from the Chaobai river region in China. The river system receives pollutants from agricultural runoffs, domestic and industrial wastewater effluents. Chemical fingerprints were derived from each of the sample and waterfleas (Daphnia magna) were exposed to the water samples. There bioactivity profiles were collected and all organisms that have survived the dwell time in their water sample were used for RNA-sequencing.
Using a multiblock correlation analysis, the scientists established correlations between chemical mixtures identified in the water samples with gene expression patterns induced by these chemical mixtures. In doing so, they identified 80 metabolic pathways putatively activated by mixtures of inorganic ions, heavy metals, polycyclic aromatic hydrocarbons, industrial chemicals, and a set of biocides, pesticides, and pharmacologically active substances.
Dr Jiarui Zhou, also at the University of Birmingham, who led the development of the AI algorithms, said: “Our approach demonstrates how advanced computational methods can help solve pressing environmental challenges. By analysing vast amounts of biological and chemical data simultaneously, we can better understand and predict environmental risks.“
“However, this study breaks new ground by allowing us to identify key classes of chemicals that affect living organisms within a genuine environmental mixture at relatively low concentration while simultaneously characterising the biomolecular changes elicited.”, says Dr. Timothy Williams of University of Birmingham.
The research was funded by the Royal Society International Collaboration Award, the European Union’s Horizon 2020 research and innovation programme, and the Natural Environmental Research Council Innovation People programme.
The study is published here.