8/11 - Fridolin Gross: Predicting microRNA targets using a biochemical model combined with machine learning

microRNAs are important post-transcriptional regulators of gene expression, but identifying functionally relevant targets remains a challenge. Recent research has shown that prediction of microRNA-mediated repression can be improved by using a biochemical model combined with affinity predictions from a convolutional neuronal network. We have translated this approach into a flexible Bioconductor package that can also be used via a user-friendly web interface. In addition to presenting the package itself, I will discuss the underlying strategy from a philosophical perspective, as an example of how machine learning can be integrated with more conventional modeling methods.