SummaryAPS1/APECED patients are defined by defects in the autoimmune regulator (AIRE) that mediates central T cell tolerance to many self-antigens. AIRE deficiency also affects B cell tolerance, but this is incompletely understood. Here we show that most APS1/APECED patients displayed B cell autoreactivity toward unique sets of approximately 100 self-proteins. Thereby, autoantibodies from 81 patients collectively detected many thousands of human proteins. The loss of B cell tolerance seemingly occurred during antibody affinity maturation, an obligatorily T cell-dependent step. Consistent with this, many APS1/APECED patients harbored extremely high-affinity, neutralizing autoantibodies, particularly against specific cytokines. Such antibodies were biologically active in vitro and in vivo, and those neutralizing type I interferons (IFNs) showed a striking inverse correlation with type I diabetes, not shown by other anti-cytokine antibodies. Thus, naturally occurring human autoantibodies may actively limit disease and be of therapeutic utility.

Modern biology frequently relies on machine learning to provide predictions and improve decision processes. There have been recent calls for more scrutiny on machine learning performance and possible limitations. Here we present a set of community-wide recommendations aiming to help establish standards of machine learning validation in biology. Adopting a structured methods description for machine learning based on DOME (data, optimization, model, evaluation) will allow both reviewers and readers to better understand and assess the performance and limitations of a method or outcome. The recommendations are complemented by a machine learning summary table which can be easily included in the supplementary material of published papers. Redundancy between data splitsMaximum pairwise identity within and between training and test set is 25% enforced with UniqueProt tool. Availability of dataYes, URL: http://protein.bio.unipd.it/espritz/ Optimization Algorithm BRNN (Bi-directional recurrent neural network) with ensemble averaging. Meta-predictionsNo. Data encodingSliding window of length 23 residues on input sequence with "one hot" encoding (i.e. 20 inputs per residue).

No abstract

The majority of studies on psoriasis have focused on explaining the genetic background and its associations with the immune system’s response. The aim of this study was to identify the low-molecular weight compounds contributing to the metabolomic profile of psoriasis and to provide computational models that help with the classification and monitoring of the severity of the disease. We compared the results from targeted and untargeted analyses of patients’ serums with plaque psoriasis to controls. The main differences were found in the concentrations of acylcarnitines, phosphatidylcholines, amino acids, urea, phytol, and 1,11-undecanedicarboxylic acid. The data from the targeted analysis were used to build classification models for psoriasis. The results from this study provide an overview of the metabolomic serum profile of psoriasis along with promising statistical models for the monitoring of the disease.Electronic supplementary materialThe online version of this article (doi:10.1007/s00403-017-1760-1) contains supplementary material, which is available to authorized users.

Deep learning is the trendiest tool in a computational biologist's toolbox. This exciting class of methods, based on artificial neural networks, quickly became popular due to its competitive performance in prediction problems. In pioneering early work, applying simple network architectures to abundant data already provided gains over traditional counterparts in functional genomics, image analysis, and medical diagnostics. Now, ideas for constructing and training networks and even off-the-shelf models have been adapted from the rapidly developing machine learning subfield to improve performance in a range of computational biology tasks. Here, we review some of these advances in the last 2 years.

High titer autoantibodies produced by B lymphocytes are clinically important features of many common autoimmune diseases. APECED patients with deficient autoimmune regulator (AIRE) gene collectively display a broad repertoire of high titer autoantibodies, including some which are pathognomonic for major autoimmune diseases. AIRE deficiency severely reduces thymic expression of gene-products ordinarily restricted to discrete peripheral tissues, and developing T cells reactive to those gene-products are not inactivated during their development. However, the extent of the autoantibody repertoire in APECED and its relation to thymic expression of self-antigens are unclear. We here undertook a broad protein array approach to assess autoantibody repertoire in APECED patients. Our results show that in addition to shared autoantigen reactivities, APECED patients display high inter-individual variation in their autoantigen profiles, which collectively are enriched in evolutionarily conserved, cytosolic and nuclear phosphoproteins. The APECED autoantigens have two major origins; proteins expressed in thymic medullary epithelial cells and proteins expressed in lymphoid cells. These findings support the hypothesis that specific protein properties strongly contribute to the etiology of B cell autoimmunity.

Atopic dermatitis is a chronic inflammatory disease which usually starts in the early childhood and ends before adulthood. However up to 3% of adults remain affected by the disease. The onset and course of the disease is influenced by various genetic and environmental factors. Although the immune system has a great effect on the outcome of the disease, metabolic markers can also try to explain the background of atopic dermatitis. In this study we analyzed the serum of patients with atopic dermatitis using both targeted and untargeted metabolomics approaches. We found the most significant changes to be related to phosphatidylcholines, acylcarnitines and their ratios and a cleavage peptide of Fibrinogen A-α. These findings that have not been reported before will further help to understand this complex disease.

Identifying nuclei is a standard first step to analysing cells in microscopy images. The traditional approach relies on signal from a DNA stain, or fluorescent transgene expression localised to the nucleus. However, imaging techniques that do not use fluorescence can also carry useful information. Here, we demonstrate that it is possible to accurately segment nuclei directly from brightfield images using deep learning. We confirmed that three convolutional neural network architectures can be adapted for this task, with U-Net achieving the best overall performance, Mask R-CNN providing an additional benefit of instance segmentation, and DeepCell proving too slow for practical application. We found that accurate segmentation is possible using as few as 16 training images and that models trained on images from similar cell lines can extrapolate well. Acquiring data from multiple focal planes further helps distinguish nuclei in the samples. Overall, our work liberates a fluorescence channel reserved for nuclear staining, thus providing more information from the specimen, and reducing reagents and time required for preparing imaging experiments.