Abstract: A method and system perform causal analysis on data relating to Anti-Microbial Resistant (AMR) bacteria, including receiving patient data, clinical trial data, and kinetic model of bacteria data, wherein the patient data relates to instances of AMR infections, converting the patient data, clinical trial data, and kinetic model of bacteria data into a normalized attribute form, the form being a vector format including at least a model portion for at least kinetic model data, an experiment portion for at least data describing an experiment in a clinical trial, and a data portion for at least patient data and clinical trial experimental result data, and loading the data converted into normalized attribute form into a clinical trial database.

Abstract: A causal inference engine relies on a category database and a graph database. Via a loader, a category generator, and a spatial web generator, input data is received in disparate formats and converted into a normalized attribute vector comprising a mathematical model, experiment, experimental data, and miscellaneous attributes. The normalized attribute vectors are then loaded into a category database and a graph database. Specifically, the loader makes use of a multi-formal combinatorial parser, and an ontology store to convert the different data and formats into normalized attribute vectors. The category generator reviews mathematical model attributes in the normalized attribute vectors to associate vectors into mathematical categories. The spatial web generator performs similarity scores in the attributes of the vectors to determine placement in a graph database. The data in the category database and the graph database are then utilized by the causal inference engine to perform inferences.