Search for: All records

Predicting the range of substrates accepted by an enzyme from its amino acid sequence is challenging. Although sequence‐ and structure‐based annotation approaches are often accurate for predicting broad categories of substrate specificity, they generally cannot predict which specific molecules will be accepted as substrates for a given enzyme, particularly within a class of closely related molecules. Combining targeted experimental activity data with structural modeling, ligand docking, and physicochemical properties of proteins and ligands with various machine learning models provides complementary information that can lead to accurate predictions of substrate scope for related enzymes. Here we describe such an approach that can predict the substrate scope of bacterial nitrilases, which catalyze the hydrolysis of nitrile compounds to the corresponding carboxylic acids and ammonia. Each of the four machine learning models (logistic regression, random forest, gradient‐boosted decision trees, and support vector machines) performed similarly (average ROC = 0.9, average accuracy = ~82%) for predicting substrate scope for this dataset, although random forest offers some advantages. This approach is intended to be highly modular with respect to physicochemical property calculations and software used for structural modeling and docking.

Plant–microbe interactions underpin processes related to soil ecology, plant function, and global carbon cycling. However, quantifying the spatial dynamics of these interactions has proven challenging in natural systems. Currently, microfluidic platforms are at the forefront of innovation for culturing, imaging, and manipulating plants in controlled environments. Using a microfluidic platform to culture plants with beneficial bacteria, visualization and quantification of the spatial dynamics of these interactions during the early stages of plant development is possible. For two plant growth–promoting bacterial isolates, the population of bacterial cells reaches a coverage density of 1–2% of the root's surface at the end of a 4 d observation period regardless of bacterial species or inoculum concentration. The two bacterial species form distinct associations with root tissue through a mechanism that appears to be independent of the presence of the other bacterial species, despite evidence for their competition. Root development changes associated with these bacterial treatments depend on the initial concentrations and species of the bacterial population present. This microfluidic approach provides context for understanding plant–microbe interactions during the early stages of plant development and can be used to generate new hypotheses about physical and biochemical exchanges between plants and their associated microbial communities.