TY - JOUR A1 - Loeffler-Wirth, Henry A1 - Kreuz, Markus A1 - Hopp, Lydia A1 - Arakelyan, Arsen A1 - Haake, Andrea A1 - Cogliatti, Sergio B. A1 - Feller, Alfred C. A1 - Hansmann, Martin-Leo A1 - Lenze, Dido A1 - Möller, Peter A1 - Müller-Hermelink, Hans Konrad A1 - Fortenbacher, Erik A1 - Willscher, Edith A1 - Ott, German A1 - Rosenwald, Andreas A1 - Pott, Christiane A1 - Schwaenen, Carsten A1 - Trautmann, Heiko A1 - Wessendorf, Swen A1 - Stein, Harald A1 - Szczepanowski, Monika A1 - Trümper, Lorenz A1 - Hummel, Michael A1 - Klapper, Wolfram A1 - Siebert, Reiner A1 - Loeffler, Markus A1 - Binder, Hans T1 - A modular transcriptome map of mature B cell lymphomas JF - Genome Medicine N2 - Background Germinal center-derived B cell lymphomas are tumors of the lymphoid tissues representing one of the most heterogeneous malignancies. Here we characterize the variety of transcriptomic phenotypes of this disease based on 873 biopsy specimens collected in the German Cancer Aid MMML (Molecular Mechanisms in Malignant Lymphoma) consortium. They include diffuse large B cell lymphoma (DLBCL), follicular lymphoma (FL), Burkitt’s lymphoma, mixed FL/DLBCL lymphomas, primary mediastinal large B cell lymphoma, multiple myeloma, IRF4-rearranged large cell lymphoma, MYC-negative Burkitt-like lymphoma with chr. 11q aberration and mantle cell lymphoma. Methods We apply self-organizing map (SOM) machine learning to microarray-derived expression data to generate a holistic view on the transcriptome landscape of lymphomas, to describe the multidimensional nature of gene regulation and to pursue a modular view on co-expression. Expression data were complemented by pathological, genetic and clinical characteristics. Results We present a transcriptome map of B cell lymphomas that allows visual comparison between the SOM portraits of different lymphoma strata and individual cases. It decomposes into one dozen modules of co-expressed genes related to different functional categories, to genetic defects and to the pathogenesis of lymphomas. On a molecular level, this disease rather forms a continuum of expression states than clearly separated phenotypes. We introduced the concept of combinatorial pattern types (PATs) that stratifies the lymphomas into nine PAT groups and, on a coarser level, into five prominent cancer hallmark types with proliferation, inflammation and stroma signatures. Inflammation signatures in combination with healthy B cell and tonsil characteristics associate with better overall survival rates, while proliferation in combination with inflammation and plasma cell characteristics worsens it. A phenotypic similarity tree is presented that reveals possible progression paths along the transcriptional dimensions. Our analysis provided a novel look on the transition range between FL and DLBCL, on DLBCL with poor prognosis showing expression patterns resembling that of Burkitt’s lymphoma and particularly on ‘double-hit’ MYC and BCL2 transformed lymphomas. Conclusions The transcriptome map provides a tool that aggregates, refines and visualizes the data collected in the MMML study and interprets them in the light of previous knowledge to provide orientation and support in current and future studies on lymphomas and on other cancer entities. KW - tumor heterogeneity KW - B cell malignancies KW - gene regulation KW - molecular subtypes KW - machine learning Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-237262 VL - 11 ER - TY - JOUR A1 - Vey, Johannes A1 - Kapsner, Lorenz A. A1 - Fuchs, Maximilian A1 - Unberath, Philipp A1 - Veronesi, Giulia A1 - Kunz, Meik T1 - A toolbox for functional analysis and the systematic identification of diagnostic and prognostic gene expression signatures combining meta-analysis and machine learning JF - Cancers N2 - The identification of biomarker signatures is important for cancer diagnosis and prognosis. However, the detection of clinical reliable signatures is influenced by limited data availability, which may restrict statistical power. Moreover, methods for integration of large sample cohorts and signature identification are limited. We present a step-by-step computational protocol for functional gene expression analysis and the identification of diagnostic and prognostic signatures by combining meta-analysis with machine learning and survival analysis. The novelty of the toolbox lies in its all-in-one functionality, generic design, and modularity. It is exemplified for lung cancer, including a comprehensive evaluation using different validation strategies. However, the protocol is not restricted to specific disease types and can therefore be used by a broad community. The accompanying R package vignette runs in ~1 h and describes the workflow in detail for use by researchers with limited bioinformatics training. KW - bioinformatics tool KW - R package KW - machine learning KW - meta-analysis KW - biomarker signature KW - gene expression analysis KW - survival analysis KW - functional analysis Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-193240 SN - 2072-6694 VL - 11 IS - 10 ER - TY - JOUR A1 - Kammerer, Klaus A1 - Hoppenstedt, Burkhard A1 - Pryss, Rüdiger A1 - Stökler, Steffen A1 - Allgaier, Johannes A1 - Reichert, Manfred T1 - Anomaly Detections for Manufacturing Systems Based on Sensor Data—Insights into Two Challenging Real-World Production Settings JF - Sensors N2 - o build, run, and maintain reliable manufacturing machines, the condition of their components has to be continuously monitored. When following a fine-grained monitoring of these machines, challenges emerge pertaining to the (1) feeding procedure of large amounts of sensor data to downstream processing components and the (2) meaningful analysis of the produced data. Regarding the latter aspect, manifold purposes are addressed by practitioners and researchers. Two analyses of real-world datasets that were generated in production settings are discussed in this paper. More specifically, the analyses had the goals (1) to detect sensor data anomalies for further analyses of a pharma packaging scenario and (2) to predict unfavorable temperature values of a 3D printing machine environment. Based on the results of the analyses, it will be shown that a proper management of machines and their components in industrial manufacturing environments can be efficiently supported by the detection of anomalies. The latter shall help to support the technical evangelists of the production companies more properly. KW - anomaly detection KW - sensor data KW - machine learning KW - production machines Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-193885 SN - 1424-8220 VL - 19 IS - 24 ER -