TY - JOUR A1 - Mühlberg, Eric A1 - Umstätter, Florian A1 - Domhan, Cornelius A1 - Hertlein, Tobias A1 - Ohlsen, Knut A1 - Krause, Andreas A1 - Kleist, Christian A1 - Beijer, Barbro A1 - Zimmermann, Stefan A1 - Haberkorn, Uwe A1 - Mier, Walter A1 - Uhl, Philipp T1 - Vancomycin-lipopeptide conjugates with high antimicrobial activity on vancomycin-resistant enterococci JF - Pharmaceuticals N2 - Multidrug-resistant bacteria represent one of the most important health care problems worldwide. While there are numerous drugs available for standard therapy, there are only a few compounds capable of serving as a last resort for severe infections. Therefore, approaches to control multidrug-resistant bacteria must be implemented. Here, a strategy of reactivating the established glycopeptide antibiotic vancomycin by structural modification with polycationic peptides and subsequent fatty acid conjugation to overcome the resistance of multidrug-resistant bacteria was followed. This study especially focuses on the structure–activity relationship, depending on the modification site and fatty acid chain length. The synthesized conjugates showed high antimicrobial potential on vancomycin-resistant enterococci. We were able to demonstrate that the antimicrobial activity of the vancomycin-lipopeptide conjugates depends on the chain length of the attached fatty acid. All conjugates showed good cytocompatibility in vitro and in vivo. Radiolabeling enabled the in vivo determination of pharmacokinetics in Wistar rats by molecular imaging and biodistribution studies. An improved biodistribution profile in comparison to unmodified vancomycin was observed. While vancomycin is rapidly excreted by the kidneys, the most potent conjugate shows a hepatobiliary excretion profile. In conclusion, these results demonstrate the potential of the structural modification of already established antibiotics to provide highly active compounds for tackling multidrug-resistant bacteria. KW - antibiotics KW - multidrug-resistant bacteria KW - enterococci KW - vancomycin KW - structural modification KW - fatty acids KW - polycationic peptides Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-205879 SN - 1424-8247 VL - 13 IS - 6 ER - TY - JOUR A1 - Steininger, Michael A1 - Abel, Daniel A1 - Ziegler, Katrin A1 - Krause, Anna A1 - Paeth, Heiko A1 - Hotho, Andreas T1 - ConvMOS: climate model output statistics with deep learning JF - Data Mining and Knowledge Discovery N2 - Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts. KW - Klima KW - Modell KW - Deep learning KW - Neuronales Netz KW - climate KW - neural networks KW - model output statistics Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-324213 SN - 1384-5810 VL - 37 IS - 1 ER - TY - JOUR A1 - Steininger, Michael A1 - Kobs, Konstantin A1 - Davidson, Padraig A1 - Krause, Anna A1 - Hotho, Andreas T1 - Density-based weighting for imbalanced regression JF - Machine Learning N2 - In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points. KW - supervised learning KW - imbalanced regression KW - cost-sensitive learning KW - sample weighting KW - Kerneldensity estimation Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-269177 SN - 1573-0565 VL - 110 IS - 8 ER - TY - JOUR A1 - Kim, Jin Hong A1 - Liess, Andreas A1 - Stolte, Matthias A1 - Krause, Ana-Maria A1 - Stepanenko, Vladimir A1 - Zhong, Chuwei A1 - Bialas, David A1 - Spano, Frank A1 - Würthner, Frank T1 - An Efficient Narrowband Near-Infrared at 1040 nm Organic Photodetector Realized by Intermolecular Charge Transfer Mediated Coupling Based on a Squaraine Dye JF - Advanced Materials N2 - A highly sensitive short-wave infrared (SWIR, λ > 1000 nm) organic photodiode (OPD) is described based on a well-organized nanocrystalline bulk-heterojunction (BHJ) active layer composed of a dicyanovinyl-functionalized squaraine dye (SQ-H) donor material in combination with PC\(_{61}\)BM. Through thermal annealing, dipolar SQ-H chromophores self-assemble in a nanoscale structure with intermolecular charge transfer mediated coupling, resulting in a redshifted and narrow absorption band at 1040 nm as well as enhanced charge carrier mobility. The optimized OPD exhibits an external quantum efficiency (EQE) of 12.3% and a full-width at half-maximum of only 85 nm (815 cm\(^{-1}\)) at 1050 nm under 0 V, which is the first efficient SWIR OPD based on J-type aggregates. Photoplethysmography application for heart-rate monitoring is successfully demonstrated on flexible substrates without applying reverse bias, indicating the potential of OPDs based on short-range coupled dye aggregates for low-power operating wearable applications. KW - squaraine dyes KW - crystal engineering KW - J-aggregates KW - near-infrared sensitivity KW - organic photodiodes Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-256374 VL - 33 IS - 26 ER -