Transcriptional profiling of Dictyostelium development reveals significant conservation of transcriptional profiles between evolutionarily divergent species.

Analysis of biomedical images requires computational expertize that are uncommon among biomedical scientists. Deep learning approaches for image analysis provide an opportunity to develop user-friendly tools for exploratory data analysis. Here, we use the visual programming toolbox Orange (http://orange.biolab.si) to simplify image analysis by integrating deep-learning embedding, machine learning procedures, and data visualization. Orange supports the construction of data analysis workflows by assembling components for data preprocessing, visualization, and modeling. We equipped Orange with components that use pre-trained deep convolutional networks to profile images with vectors of features. These vectors are used in image clustering and classification in a framework that enables mining of image sets for both novel and experienced users. We demonstrate the utility of the tool in image analysis of progenitor cells in mouse bone healing, identification of developmental competence in mouse oocytes, subcellular protein localization in yeast, and developmental morphology of social amoebae.

Long-term stability of monoclonal antibodies to be used as biologics is a key aspect in their development. Therefore, its possible early prediction from accelerated stability studies is of major interest, despite currently being regarded as not sufficiently robust. In this work, using a combination of accelerated stability studies (up to 6 months) and first order degradation kinetic model, we are able to predict the long-term stability (up to 3 years) of multiple monoclonal antibody formulations. More specifically, we can robustly predict the long-term stability behaviour of a protein at the intended storage condition (5 °C), based on up to six months of data obtained for multiple quality attributes from different temperatures, usually from intended (5 °C), accelerated (25 °C) and stress conditions (40 °C). We have performed stability studies and evaluated the stability data of several mAbs including IgG1, IgG2, and fusion proteins, and validated our model by overlaying the 95% prediction interval and experimental stability data from up to 36 months. We demonstrated improved robustness, speed and accuracy of kinetic long-term stability prediction as compared to classical linear extrapolation used today, which justifies long-term stability prediction and shelf-life extrapolation for some biologics such as monoclonal antibodies. This work aims to contribute towards further development and refinement of the regulatory landscape that could steer toward allowing extrapolation for biologics during the developmental phase, clinical phase, and also in marketing authorisation applications, as already established today for small molecules.

Supplementary data are available at Bioinformatics online.