Browsing by Author "Kramer, Frank"

In this chapter, we describe an approach to reconstruct cellular signaling networks based on measurements of protein activation after different stimulation experiments. As experimental platform reverse-phase protein arrays (RPPA) are used. RPPA allow the measurement of proteins and phosphoproteins across many samples in parallel with minimal sample consumption using a panel of highly target protein-specific antibodies. Functional interactions of proteins are modeled using a Boolean network. We describe the Boolean network reconstruction approach ddepn (dynamic deterministic effects propagation networks), which uses time course data to derive protein interactions based on perturbation experiments. We explain how the method works, give a practical application example, and describe how the results can be interpreted. Furthermore prior knowledge on signaling pathways is essential for network reconstruction. Here we describe the use of our software rBiopaxParser to integrate prior knowledge on protein signaling available in public databases. All applied methods are freely available as open-source R software packages. We describe the preparation of RPPA data as well as all relevant programming steps to format the RPPA data, to infer the prior knowledge, and to reconstruct and analyze the protein signaling networks.

Gene expression data is commonly available in cancer research and provides a snapshot of the molecular status of a specific tumor tissue. This high-dimensional data can be analyzed for diagnoses, prognoses, and to suggest treatment options. Machine learning based methods are widely used for such analysis. Recently, a set of deep learning techniques was successfully applied in different domains including bioinformatics. One of these prominent techniques are convolutional neural networks (CNN). Currently, CNNs are extending to non-Euclidean domains like graphs. Molecular networks are commonly represented as graphs detailing interactions between molecules. Gene expression data can be assigned to the vertices of these graphs, and the edges can depict interactions, regulations and signal flow. In other words, gene expression data can be structured by utilizing molecular network information as prior knowledge. Here, we applied graph CNN to gene expression data of breast cancer patients to predict the occurrence of metastatic events. To structure the data we utilized a protein-protein interaction network. We show that the graph CNN exploiting the prior knowledge is able to provide classification improvements for the prediction of metastatic events compared to existing methods.