Genomics data generally have larger feature sizes than its sample sizes, posing challenges for deep-learning application in this field. In this talk, I will elaborate how we get around the curse of small population size, and apply deep-learning creatively to predict disease prognosis at the population level. We have developed a tool called Cox-nnet that uses gene expression data to predict patients survival via neural network. We further developed another integration tool called DeepProg, which uses multiple types of genomics data to predict patients survival via autoencoders. We demonstrate the utility of these methods on tens of thousands of cancer samples in the cancer genome atlas (TCGA). Lastly, I will present our computational method, called DeepImpute, which uses deep-learning to impute the noisy single-cell RNA-Seq data and achieves better performance than other statistical and machine learning methods currently available. In summary, the age of AI to genomics research has arrived and is expected to transform this field to a whole new level.

Lana Garmire, Ph.D. is an Associate Professor in the Department of Computational Medicine and Bioinformatics at the University of Michigan.