Drug-induced gene expression profiles are rich information sources that can help to measure the effect of a drug on the transcriptional state of cells. However, the available experimental data only covers a limited set of conditions such as treatment time, dosages, and cell lines. This poses a challenge for neural network models to learn embeddings that can be generalized to new experimental conditions. In this project, we focus on the cell line as the confounder variable and train an Adversarial Neural Network to extract transcriptional effects that are conserved across multiple cell lines, and can thus be more confidently generalized to the biological setting of interest. Additionally, we investigate several methods to test whether our approach can simultaneously learn biologically valid embeddings and deconfound the effect of cell lines on the data distribution

Supervised learning methods require vast amounts of annotated images to successfully train an image classifier. Acquiring the necessary annotated images is costly. The increased availability of photorealistic computer generated images that are annotated automatically begs the question under which conditions it is possible to leverage this synthetic data during training. We investigate the conditions that make it possible to leverage computer generated renders of car models for fine-grained car model classification. / Övervakade inlärningsmetoder kräver stora mängder kommenterade bilder för att framgångsrikt träna en bildklassificator. Det är kostsamt att skaffa de nödvändiga bilderna med kommentarer. Den ökade tillgången till fotorealistiska datorgenererade bilder som kommenteras automatiskt väcker frågan om under vilka förhållanden det är möjligt att utnyttja dessa syntetiska data vid träning. Vi undersöker vilka villkor som gör det möjligt att utnyttja datorgenererade renderingar av bilmodeller för finkornig klassificering av bilmodeller.