A Temporal Graph Model to Predict Chemical Transformations in Complex Dissolved Organic Matter

Abstract

Dissolved organic matter (DOM) is a complex mixture of thousands of natural molecules that undergo constant transformation in the environment, such as sunlight induced photochemical reactions. Despite molecular level resolution from ultrahigh resolution mass spectrometry (UHRMS), trends of mass peak intensities are currently the only way to follow photochemically induced molecular changes in DOM. Many real-world relationships and temporal processes can be intuitively modeled using graph data structures (networks). Graphs enhance the potential and value of AI applications by adding context and interconnections allowing the uncovering of hidden or unknown relationships in data sets. We use a temporal graph model and link prediction to identify transformations of DOM molecules in a photo-oxidation experiment. Our link prediction algorithm simultaneously considers educt removal and product formation for molecules linked by predefined transformation units (oxidation, decarboxylation, etc.). The transformations are further weighted by the extent of intensity change and clustered on the graph structure to identify groups of similar reactivity. The temporal graph is capable of identifying relevant molecules subject to similar reactions and enabling to study their time course. Our approach overcomes previous data evaluation limitations for mechanistic studies of DOM and leverages the potential of temporal graphs to study DOM reactivity by UHRMS.

Exometabolomic exploration of culturable airborne microorganisms from an urban atmosphere

“…The transformation networks are frequently used to analyze the metabolic state of organisms since the underlying biochemical reactions are well-known (Plamper et al, 2023). The main organic molecules involved in transforming the pigments of Penicillium aurantiogriseum and Talaromyces sp.…”

Machine Learning Models for Evaluating Biological Reactivity Within Molecular Fingerprints of Dissolved Organic Matter Over Time

“…As an emerging artificial intelligence domain, ML can learn from large, complex, and multi‐dimensional data to develop predictive models and has proven to be a promising tool for handling non‐linear correlations between the learnable features and target labels (Bergen et al., 2019). As such, ML models have been established and well applied to FT‐ICR MS data analysis to gain an in‐depth understanding of both the bulk (Yi et al., 2023) and molecular level (Plamper et al., 2023; Zhao et al., 2023). In previous work, we constructed ML models to study the photochemical reactivity of estuarine DOM worldwide (Zhao et al., 2023).…”

“…The recent development of data‐driven toolboxes has enhanced our understanding of DOM cycling across aquatic systems, including approaches such as molecular network analysis (Yu & Petrick, 2020), inter‐sample ranking (Herzsprung et al., 2012), key formula search (Herzsprung et al., 2023), as well as manifold machine learning (ML) methodologies (Herzsprung et al., 2020; Plamper et al., 2023). As an emerging artificial intelligence domain, ML can learn from large, complex, and multi‐dimensional data to develop predictive models and has proven to be a promising tool for handling non‐linear correlations between the learnable features and target labels (Bergen et al., 2019).…”

Deciphering Microbe-Mediated Dissolved Organic Matter Reactome in Wastewater Treatment Plants Using Directed Paired Mass Distance

“…A potential solution is inspired by a chemical proportionality approach, which incorporates sequential data to explore the change direction of linked compounds within feature-based molecular networks . Based on the principle, a temporal graph model was also built to investigate the directions of predefined transformation units (e.g., oxidation, decarboxylation) of DOM under irradiation . Hence, coupling the direction inference strategy and the PMD method provides an opportunity to comprehensively profile the reactome of wastewater DOM.…”