BackgroundPersonalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of ‘big data’ and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future.ConclusionsThere is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.

BackgroundIn breast cancer, overexpression of the transmembrane tyrosine kinase ERBB2 is an adverse prognostic marker, and occurs in almost 30% of the patients. For therapeutic intervention, ERBB2 is targeted by monoclonal antibody trastuzumab in adjuvant settings; however, de novo resistance to this antibody is still a serious issue, requiring the identification of additional targets to overcome resistance. In this study, we have combined computational simulations, experimental testing of simulation results, and finally reverse engineering of a protein interaction network to define potential therapeutic strategies for de novo trastuzumab resistant breast cancer.ResultsFirst, we employed Boolean logic to model regulatory interactions and simulated single and multiple protein loss-of-functions. Then, our simulation results were tested experimentally by producing single and double knockdowns of the network components and measuring their effects on G1/S transition during cell cycle progression. Combinatorial targeting of ERBB2 and EGFR did not affect the response to trastuzumab in de novo resistant cells, which might be due to decoupling of receptor activation and cell cycle progression. Furthermore, examination of c-MYC in resistant as well as in sensitive cell lines, using a specific chemical inhibitor of c-MYC (alone or in combination with trastuzumab), demonstrated that both trastuzumab sensitive and resistant cells responded to c-MYC perturbation.ConclusionIn this study, we connected ERBB signaling with G1/S transition of the cell cycle via two major cell signaling pathways and two key transcription factors, to model an interaction network that allows for the identification of novel targets in the treatment of trastuzumab resistant breast cancer. Applying this new strategy, we found that, in contrast to trastuzumab sensitive breast cancer cells, combinatorial targeting of ERBB receptors or of key signaling intermediates does not have potential for treatment of de novo trastuzumab resistant cells. Instead, c-MYC was identified as a novel potential target protein in breast cancer cells.

Brown adipocytes are a primary site of energy expenditure and reside not only in classical brown adipose tissue but can also be found in white adipose tissue. Here we show that microRNA 155 is enriched in brown adipose tissue and is highly expressed in proliferating brown preadipocytes but declines after induction of differentiation. Interestingly, microRNA 155 and its target, the adipogenic transcription factor CCAAT/enhancer-binding protein β, form a bistable feedback loop integrating hormonal signals that regulate proliferation or differentiation. Inhibition of microRNA 155 enhances brown adipocyte differentiation and induces a brown adipocyte-like phenotype (‘browning’) in white adipocytes. Consequently, microRNA 155-deficient mice exhibit increased brown adipose tissue function and ‘browning’ of white fat tissue. In contrast, transgenic overexpression of microRNA 155 in mice causes a reduction of brown adipose tissue mass and impairment of brown adipose tissue function. These data demonstrate that the bistable loop involving microRNA 155 and CCAAT/enhancer-binding protein β regulates brown lineage commitment, thereby, controlling the development of brown and beige fat cells.

Background: With the increased availability of high throughput data, such as DNA microarray data, researchers are capable of producing large amounts of biological data. During the analysis of such data often there is the need to further explore the similarity of genes not only with respect to their expression, but also with respect to their functional annotation which can be obtained from Gene Ontology (GO).

No abstract

We propose a new kernel function for attributed molecular graphs, which is based on the idea of computing an optimal assignment from the atoms of one molecule to those of another one, including information on neighborhood, membership to a certain structural element and other characteristics for each atom. As a byproduct this leads to a new class of kernel functions. We demonstrate how the necessary computations can be carried out efficiently. Compared to marginalized graph kernels our method in some cases leads to a significant reduction of the prediction error. Further improvement can be gained, if expert knowledge is combined with our method. We also investigate a reduced graph representation of molecules by collapsing certain structural elements, like e.g. rings, into a single node of the molecular graph.

Abstract-In outdoor environments, there is a variety of different types of ground surfaces. If some of them are slippery or bumpy, for example, the ground surface itself is a possible hazard for an autonomous mobile vehicle traversing the surface. Therefore, it is beneficial if the vehicle is able to estimate, which terrain it is currently traversing. Using this estimation, the vehicle can adapt its driving style to the terrain. In this paper, we present a method for terrain classification based on vibration induced in the vehicle's body. An accelerometer mounted on the vehicle measures the vibration perpendicular to the ground surface. We experimentally compare representations of the data based on the Fast Fourier Transform (FFT) and on the Power Spectral Density (PSD). Additionally, we suggest a simpler and more compact representation based on features calculated from the raw data vectors and a combination of this representation with the PSD. We train and classify the data with a Support Vector Machine (SVM). Experiments on a large real-world dataset containing seven different terrain types evaluate our approach.

Kernel methods, like the well-known Support Vector Machine (SVM), have received growing attention in recent years for designing QSAR models that have a high predictive strength. One of the key concepts of SVMs is the usage of a so-called kernel function, which can be thought of as a special similarity measure. In this paper we consider kernels for molecular structures, which are based on a graph representation of chemical compounds. The similarity score is calculated by computing an optimal assignment of the atoms from one molecule to those of another one, including information on specific chemical properties, membership to a substructure (e.g., aromatic ring, carbonyl group, etc.) and neighborhood for each atom. We show that by using this kernel we can achieve a generalization performance comparable to a classical model with a few descriptors, which are a-priori known to be relevant for the problem, and significantly better results than with and without performing an automatic descriptor selection. For this purpose we investigate ADME classification and regression datasets for predicting bioavailability (Yoshida), Human Intestinal Absorption (HIA), Blood-Brain-Barrier (BBB) penetration and a dataset consisting of four different inhibitor classes (SOL). We further explore the effect of combining our kernel with a problem-dependent descriptor set. We also demonstrate the usefulness of an extension of our method to a reduced graph representation of molecules, in which certain structural features, like, e.g., rings, donors or acceptors, are represented as a single node in the molecular graph.