Personalized, 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. There 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.

In 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. First, 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. In 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.

The problem of feature selection is a difficult combinatorial task in machine learning and of high practical relevance, e.g. in bioinformatics. genetic algorithms (GAs) offer a natural way to solve this problem. In this paper, we present a special genetic algorithm, which especially takes into account the existing bounds on the generalization error for support vector machines (SVMs). This new approach is compared to the traditional method of performing cross-validation and to other existing algorithms for feature selection.

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). We present the freely available software package GOSim, which allows to calculate the functional similarity of genes based on various information theoretic similarity concepts for GO terms. GOSim extends existing tools by providing additional lately developed functional similarity measures for genes. These can e.g. be used to cluster genes according to their biological function. Vice versa, they can also be used to evaluate the homogeneity of a given grouping of genes with respect to their GO annotation. GOSim hence provides the researcher with a flexible and powerful tool to combine knowledge stored in GO with experimental data. It can be seen as complementary to other tools that, for instance, search for significantly overrepresented GO terms within a given group of genes. GOSim is implemented as a package for the statistical computing environment R and is distributed under GPL within the CRAN project.

Brown adipose tissue (BAT) dissipates energy and its activity correlates with leanness in human adults. ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography coupled with computer tomography (PET/CT) is still the standard for measuring BAT activity, but exposes subjects to ionizing radiation. To study BAT function in large human cohorts, novel diagnostic tools are needed. Here we show that brown adipocytes release exosomes and that BAT activation increases exosome release. Profiling miRNAs in exosomes released from brown adipocytes, and in exosomes isolated from mouse serum, we show that levels of miRNAs change after BAT activation in vitro and in vivo. One of these exosomal miRNAs, miR-92a, is also present in human serum exosomes. Importantly, serum concentrations of exosomal miR-92a inversely correlate with human BAT activity measured by ¹⁸F-FDG PET/CT in two unique and independent cohorts comprising 41 healthy individuals. Thus, exosomal miR-92a represents a potential serum biomarker for BAT activity in mice and humans.