Dr McGeachie’s primary scientific interest is to apply new and innovative analysis techniques to complex genomic datasets, where those results can be applied to translational medicine in asthma, allergy, and related fields. He has focused particularly on network analyses, most notably the robust prediction of outcomes using Bayesian networks from a variety of clinical, demographic and genomic inputs. He has also been interested in integrative genomic techniques combining genome-wide eQTL, mRNA and SNP data. Since completing his doctorate in Artificial Intelligence at MIT, where he studied decision making and machine learning, he has conducted several projects that successfully employed predictive network models in atherosclerosis, leukemia eQTLs, inhaled corticosteroid response, metabolomics of asthma and ICU mortality, and the developing infant gut microbiome. These applications are examples of using his public Bayesian Network software package, CGBayesNets, which is designed to support all phases of predictive analysis in genomic applications. He has been recently most active in asthma metabolomics, gut microbiome, and steroid treatment response in asthmatics. |