Cellular microscopy images contain rich insights about biology. To extract this information, researchers use features, or measurements of the patterns of interest in the images. Here, we introduce a convolutional neural network (CNN) to automatically design features for fluorescence microscopy. We use a self-supervised method to learn feature representations of single cells in microscopy images without labelled training data. We train CNNs on a simple task that leverages the inherent structure of microscopy images and controls for variation in cell morphology and imaging: given one cell from an image, the CNN is asked to predict the fluorescence pattern in a second different cell from the same image. We show that our method learns high-quality features that describe protein expression patterns in single cells both yeast and human microscopy datasets. Moreover, we demonstrate that our features are useful for exploratory biological analysis, by capturing high-resolution cellular components in a proteome-wide cluster analysis of human proteins, and by quantifying multi-localized proteins and single-cell variability. We believe paired cell inpainting is a generalizable method to obtain feature representations of single cells in multichannel microscopy images.

SummaryWe introduce YeastSpotter, a web application for the segmentation of yeast microscopy images into single cells. YeastSpotter is user-friendly and generalizable, reducing the computational expertise required for this critical preprocessing step in many image analysis pipelines.Availability and implementationYeastSpotter is available at http://yeastspotter.csb.utoronto.ca/. Code is available at https://github.com/alexxijielu/yeast_segmentation.Supplementary information Supplementary data are available at Bioinformatics online.

Pretrained protein sequence language models largely rely on the transformer architecture. However, transformer run-time and memory requirements scale quadrat-ically with sequence length. We investigate the potential of a convolution-based architecture for protein sequence masked language model pretraining and subsequent finetuning. CNNs are competitive on the pretraining task with transformers across several orders of magnitude in parameter size while scaling linearly with sequence length. More importantly, CNNs are competitive with and occasionally superior to transformers across an extensive set of downstream evaluations, including structure prediction, zero-shot mutation effect prediction, and out-of-domain generalization. We also demonstrate strong performance on sequences longer than the positional embeddings allowed in the current state-of-the-art transformer protein masked language models. Finally, we close with a call to disentangle the effects of pretraining task and model architecture when studying pretrained protein sequence models.

ObjectiveClinical studies have suggested an association between dyslipidemia and tendon injuries or chronic tendon pain; the mechanisms underlying this association are not yet known. The objectives of this study were (1) to evaluate the impact of a high fat diet on the function of load-bearing tendons and on the distribution in tendons of oxidized low density lipoprotein (oxLDL), and (2) to examine the effect of oxLDL on tendon fibroblast proliferation and gene expression.MethodsGene expression (Mmp2, Tgfb1, Col1a1, Col3a1), fat content (Oil Red O staining), oxLDL levels (immunohistochemistry) and tendon biomechanical properties were examined in mice (C57Bl/6 or ApoE -/-) receiving a standard or a high fat diet. Human tendon fibroblast proliferation and gene expression (COL1A1, COL3A1, MMP2) were examined following oxLDL exposure.ResultsIn both types of mice (C57Bl/6 or ApoE -/-), consumption of a high fat diet led to a marked increase in oxLDL deposition in the load-bearing extracellular matrix of the tendon. The consumption of a high fat diet also reduced the failure stress and load of the patellar tendon in both mouse types, and increased Mmp2 expression. ApoE -/- mice exhibited more pronounced reductions in tendon function than wild-type mice, and decreased expression of Col1a1 compared to wild type mice. Human tendon fibroblasts responded to oxLDL by increasing their proliferation and their mRNA levels of MMP2, while decreasing their mRNA levels for COL1A1 and COL3A1.ConclusionThe consumption of a high fat diet resulted in deleterious changes in tendon function, and these changes may be explained in part by the effects of oxLDL, which induced a proliferative, matrix-degrading phenotype in human tenocytes.