Motivation: The clustering of biomedical images according to their phenotype is an important step in early drug discovery. Modern highcontent-screening devices easily produce thousands of cell images, but the resulting data is usually unlabelled and it requires extra effort to construct a visual representation that supports the grouping according to the presented morphological characteristics. Results:We introduce a novel approach to visual representation learning that is guided by metadata. In high-content-screening, metadata can typically be derived from the experimental layout, which links each cell image of a particular assay to the tested chemical compound and corresponding compound concentration. In general, there exists a one-to-many relationship between phenotype and compound, since various molecules and different dosage can lead to one and the same alterations in biological cells. Our empirical results show that metadata-guided visual representation learning is an effective approach for clustering biomedical images. We have evaluated our proposed approach on both benchmark and realworld biological data. Furthermore, we have juxtaposed implicit and explicit learning techniques, where both loss function and batch construction differ. Our experiments demonstrate that metadata-guided visual representation learning is able to identify commonalities and distinguish differences in visual appearance that lead to meaningful clusters, even without image-level annotations.Note: Please refer to the supplementary material for implementation details on metadata-guided visual representation learning strategies.
Over the last decades, deep learning models have rapidly gained popularity for their ability to achieve state-of-the-art performances in different inference settings. Deep neural networks have been applied to an increasing number of problems spanning different domains of application. Novel applications define a new set of requirements that transcend accurate predictions and depend on uncertainty measures. The aims of this study are to implement Bayesian neural networks and use the corresponding uncertainty estimates to perform predictions and dataset analysis. We identify two main advantages in modeling the predictive uncertainty of deep neural networks performing classification tasks. The first is the possibility to discard highly uncertain predictions to be able to guarantee a higher accuracy of the remaining predictions. The second is the identification of unfamiliar patterns in the data that correspond to outliers in the model representation of the training data distribution. Such outliers can be further characterized as either corrupted observations or data belonging to different domains. Both advantages are well demonstrated with the benchmark datasets. Furthermore we apply the Bayesian approach to a biomedical imaging dataset where cancer cells are treated with diverse drugs, and show how one can increase classification accuracy and identify noise in the ground truth labels with uncertainty analysis.
Building environmental simulation workflows is typically a slow process involving multiple proprietary desktop tools that do not interoperate well. In this work, we demonstrate building flexible, lightweight workflows entirely in Jupyter notebooks. We demonstrate these capabilities through examples in hydrology and hydrodynamics using the AdH (Adaptive Hydraulics) and GSSHA (Gridded Surface Subsurface Hydrologic Analysis) simulators. The goal of this work is to provide a set of tools that work well together and with the existing scientific python ecosystem, that can be used in browser based environments and that can easily be reconfigured and repurposed as needed to rapidly solve specific emerging issues such as hurricanes or dam failures. As part of this work, extensive improvements were made to several generalpurpose open source packages, including support for annotating and editing plots and maps in Bokeh and HoloViews, rendering large triangular meshes and regridding large raster data in HoloViews, GeoViews, and Datashader, and widget libraries for Param. In addition, two new open source projects are being released, one for triangular mesh generation (Filigree) and one for environmental data access (Quest).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.