A Data-driven Integrative Platform for Computational Prediction of Toxin Biotransformation



Please select a search method.

Supported search methods:


Text Query Structure Fragment Similarity MCS Toxin Biotransformation

In recent years, biogenic toxins have received increasing attention because of their high contamination levels in feeds, foods, and environments. However, there is a lack of an integrative platform for seamless linking of data-driven computational methods with ‘wet’ experimental validations. To this end, we built a novel platform that integrates the technical aspects of toxin biotransformation methods. First, a biogenic toxin database termed ToxinDB, containing multifaceted data on more than 4,836 toxins, was built. More than 8,000 biotransformation reaction rules were extracted from over 300,000 biochemical reactions extracted from ~580,000 literature reports that have been curated by more than 100 people in the past decade. Based on these reaction rules, a toxin biotransformation prediction model was constructed. Finally, the global chemical space of biogenic toxins was constructed, comprising ~550,000 toxins and putative toxin metabolites, of which 94.7% of the metabolites have not been previously reported. This unique integrative platform will assist exploration of the ‘dark matter’ of a toxin’s metabolome and promote the discovery of detoxification enzymes.