If you are a Union College student interested in doing research, browse some of current projects below and reach out to me via emaill (doingg@union.edu) with any overlapping interests. Always feel free to come by my office as well (Steinmetz 108B) during office hours (Wed 2:00 - 3:30, Thurs 4:00 - 5:30).
While strides have been made toward increasingly audited machine learning models, it remains unknown if the model-interpretation and model-explanation algorithms developed for image processing and other domains will prove successful when used on biological data. We are testing the application of common xAI methods on compendia of micobial gene expression data, including assessing models I begun experimentally validating in the Hogan Lab (Tan and Doing et al 2018) and building new compendia (Doing et al 2023).
We are exploring the utility of using large compendia of gene expression data from well-studied microbes to boost the performance of machine learning models trained to study microbes with fewer publicly available gene expression datasets. Several compendia of gene expression data have been constructed for model microbes including E. coli, P. aeruginosa, S. aureus and S. cerevisiae (reviewed by the Greene Lab in Lee et al 2023 ). For each of these species there are also gene expression datasets for less often profiled, but equally intriguing, phylogenetically related species. Transfer learning-based neural network architectures are promising approaches for bridging these related, but hetergenous, datasets.