Integrating RNA sequencing with deep learning-based metabolic toxicity prediction: A new perspective on screening...

Nearly 99 % of liquid crystal monomers (LCMs) toxicological data remains gaps, especially to aquatic organisms. Herein, this study proposes a rapid and high-throughput screening method for identifying priority LCMs in natural water. Using six fluorinated LCMs (LCMs^F) with significant enrichment characteristics in zebrafish as examples, RNA sequencing revealed that LCMs^F-induced metabolic disturbances are predominant, including 28 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway abnormalities attributed to 498 differentially expressed genes. Notably, the intricate sequencing process resulted in the inability to rapid identify additional 857 LCMs^F that may induce metabolic disturbances. To address this, LCMsT-MTP, a predictive deep learning model based on RNA sequencing, was developed. This model integrates a comprehensive representation of LCMs^F structures and metabolic toxicity target sequences. LCMsT-MTP improves upon traditional methods that are limited to single targets and mechanisms by facilitating the simultaneous identification of 21 metabolic toxicities induced by LCMs^F. In addition, the LCMsT-MTP model was further applied to non-fluorinated LCMs (LCMs^{None F}) that satisfy the applicability domains test. Accordingly, a metabolic toxicity priority list of LCMs was proposed, with ∼95 % of LCMs classified as high or medium risk. Priority list validation by molecular dynamics confirmed that the interactions of LCMs^F/LCMs^{None F} and metabolic toxicity targets in representative KEGG pathways were distinct.