Developed timelapse image analysis methods for oncology applications, enabling multi-cell tracking and analysis over many days
Automated quantification of yeast cell aging using convolutional neural networks
Built an automated targeting system for laser ablation microscopy with sub-millisecond timing
Developed a cell type identification method for single cell RNA-seq data using deep neural networks
University of California San Francisco, San Francisco, CA, 2015 - 2018 PhD Candidate Principal Investigators: Wallace Marshall, Andrew Brack Thesis: Inferring stem cell state from cell behavior
Developed Heteromotility biological motion analysis package, including feature extraction, unsupervised clustering, and time-series analysis tools to quantify dynamic state transitions in cellular systems
Quantified rates of muscle stem cell activation with single cell resolution for the first time using Heteromotility
Developed Lanternfish deep learning package to enable discrimination of cell states from cell motility measurements and prediction of cell motility behaviors
Demonstrated classification of stem cell differentiation states and cancerous transformation detection using Lanternfish
Kimmel JC, Brack AS, Marshall WF. Deep convolutional and recurrent neural networks for cell motility discrimination and prediction. 2019. In press, IEEE Transactions on Computational Biology and Bioinformatics., doi: 10.1109/TCBB.2019.2919307. Preprint featured in Company of Biologists: the Node.
Constant C, Kimmel JC, Sugaya K, Dogariu A. Optically Controlled Subcellular Diffusion. 2015. Frontiers in Optics & Laser Science.
Kimmel JC, Hwang A, Brack AS, Marshall WF. Inferring cell state dynamics with machine learning models. Invited presentation to the Machine Learning in Cell Biology Group meeting at ASCB-EMBO 2018. San Diego, CA. 2018.
Kimmel JC, Chang AY, Brack AS, Marshall WF. Inferring stem cell states from cell motility behavior reveals a dynamic state system and broken detailed balance. Selected presentation to the Quantitative Biology meeting. Honolulu, HI. 2018.
Kimmel JC, Brack AS, Marshall WF. Deep neural networks for cell motility analysis. Presentation to Nvidia Deep Learning in Biomedicine Workshop. San Francisco, CA. 2018. (Nvidia Most Innovative Use of Deep Learning in Biomedicine Award).
Kimmel JC, Chang AY, Brack AS, Marshall WF. Inferring stem cell states from cell motility behavior reveals a dynamic state system and broken detailed balance. Selected oral presentation to the Northern California Computational Biology Society. UC Santa Cruz, Santa Cruz, CA. 2017.
Kimmel JC, Chang AY, Brack AS, Marshall WF. Inferring cell state from cell motility behavior. Selected oral presentation to the NSF Quantitative Cell Biology Network Workshop. Allen Institute for Cell Science, Seattle, WA. 2016.
IEEE Journal of Biomedical and Health Informatics
PLoS Computational Biology
Honors and Awards
Nvidia Best Presentation Award, Nvidia Deep Learning in Biomedicine, 2018