AIRE-Deficient Patients Harbor Unique High-Affinity Disease-Ameliorating Autoantibodies.

APS1/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.

Practical segmentation of nuclei in brightfield cell images with neural networks trained on fluorescently labelled samples.

Identifying nuclei is a standard first step when 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 used brightfield and fluorescence images of fixed cells with fluorescently labelled DNA, and confirmed that three convolutional neural network architectures can be adapted to segment nuclei from the brightfield channel, relying on fluorescence signal to extract the ground truth for training. We found that U-Net achieved the best overall performance, Mask R-CNN provided an additional benefit of instance segmentation, and that DeepCell proved too slow for practical application. We trained the U-Net architecture on over 200 dataset variations, established 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 helps to liberate a fluorescence channel reserved for nuclear staining, thus providing more information from the specimen, and reducing reagents and time required for preparing imaging experiments.

PAWER: protein array web exploreR.

BACKGROUND: Protein microarray is a well-established approach for characterizing activity levels of thousands of proteins in a parallel manner. Analysis of protein microarray data is complex and time-consuming, while existing solutions are either outdated or challenging to use without programming skills. The typical data analysis pipeline consists of a data preprocessing step, followed by differential expression analysis, which is then put into context via functional enrichment. Normally, biologists would need to assemble their own workflow by combining a set of unrelated tools to analyze experimental data. Provided that most of these tools are developed independently by various bioinformatics groups, making them work together could be a real challenge. RESULTS: Here we present PAWER, the online web tool dedicated solely to protein microarray analysis. PAWER enables biologists to carry out all the necessary analysis steps in one go. PAWER provides access to state-of-the-art computational methods through the user-friendly interface, resulting in publication-ready illustrations. We also provide an R package for more advanced use cases, such as bespoke analysis workflows. CONCLUSIONS: PAWER is freely available at https://biit.cs.ut.ee/pawer .

Endometrial cancer diagnostic and prognostic algorithms based on proteomics, metabolomics, and clinical data: a systematic review.

Endometrial cancer is the most common gynaecological malignancy in developed countries. Over 382,000 new cases were diagnosed worldwide in 2018, and its incidence and mortality are constantly rising due to longer life expectancy and life style factors including obesity. Two major improvements are needed in the management of patients with endometrial cancer, i.e., the development of non/minimally invasive tools for diagnostics and prognostics, which are currently missing. Diagnostic tools are needed to manage the increasing number of women at risk of developing the disease. Prognostic tools are necessary to stratify patients according to their risk of recurrence pre-preoperatively, to advise and plan the most appropriate treatment and avoid over/under-treatment. Biomarkers derived from proteomics and metabolomics, especially when derived from non/minimally-invasively collected body fluids, can serve to develop such prognostic and diagnostic tools, and the purpose of the present review is to explore the current research in this topic. We first provide a brief description of the technologies, the computational pipelines for data analyses and then we provide a systematic review of all published studies using proteomics and/or metabolomics for diagnostic and prognostic biomarker discovery in endometrial cancer. Finally, conclusions and recommendations for future studies are also given.

Single-cell imaging of protein dynamics of paralogs reveals mechanisms of gene retention.

Gene duplication is common across the tree of life, including yeast and humans, and contributes to genomic robustness. In this study, we examined changes in the subcellular localization and abundance of proteins in response to the deletion of their paralogs originating from the whole-genome duplication event, which is a largely unexplored mechanism of functional divergence. We performed a systematic single-cell imaging analysis of protein dynamics and screened subcellular redistribution of proteins, capturing their localization and abundance changes, providing insight into forces determining paralog retention. Paralogs showed dependency, whereby proteins required their paralog to maintain their native abundance or localization, more often than compensation. Network feature analysis suggested the importance of functional redundancy and rewiring of protein and genetic interactions underlying redistribution response of paralogs. Translation of non-canonical protein isoform emerged as a novel compensatory mechanism. This study provides new insights into paralog retention and evolutionary forces that shape genomes.

Untargeted metabolomics profiling in pediatric patients and adult populations indicates a connection between lipid imbalance and epilepsy.

Introduction: Epilepsy is a common central nervous system disorder characterized by abnormal brain electrical activity. We aimed to compare the metabolic profiles of plasma from patients with epilepsy across different etiologies, seizure frequency, seizure type, and patient age to try to identify common disrupted pathways. Material and methods: We used data from three separate cohorts. The first cohort (PED-C) consisted of 31 pediatric patients with suspicion of a genetic disorder with unclear etiology; the second cohort (AD-C) consisted of 250 adults from the Estonian Biobank (EstBB), and the third cohort consisted of 583 adults ≥ 69 years of age from the EstBB (ELD-C). We compared untargeted metabolomics and lipidomics data between individuals with and without epilepsy in each cohort. Results: In the PED-C, significant alterations (p-value <0.05) were detected in sixteen different glycerophosphatidylcholines (GPC), dimethylglycine and eicosanedioate (C20-DC). In the AD-C, nine significantly altered metabolites were found, mainly triacylglycerides (TAG), which are also precursors in the GPC synthesis pathway. In the ELD-C, significant changes in twenty metabolites including multiple TAGs were observed in the metabolic profile of participants with previously diagnosed epilepsy. Pathway analysis revealed that among the metabolites that differ significantly between epilepsy-positive and epilepsy-negative patients in the PED-C, the lipid superpathway (p = 3.2*10-4) and phosphatidylcholine (p = 9.3*10-8) and lysophospholipid (p = 5.9*10-3) subpathways are statistically overrepresented. Analogously, in the AD-C, the triacylglyceride subclass turned out to be statistically overrepresented (p = 8.5*10-5) with the lipid superpathway (p = 1.4*10-2). The presented p-values are FDR-corrected. Conclusion: Our results suggest that cell membrane fluidity may have a significant role in the mechanism of epilepsy, and changes in lipid balance may indicate epilepsy. However, further studies are needed to evaluate whether untargeted metabolomics analysis could prove helpful in diagnosing epilepsy earlier.

A Survey of End-to-End Driving: Architectures and Training Methods.

Autonomous driving is of great interest to industry and academia alike. The use of machine learning approaches for autonomous driving has long been studied, but mostly in the context of perception. In this article, we take a deeper look on the so-called end-to-end approaches for autonomous driving, where the entire driving pipeline is replaced with a single neural network. We review the learning methods, input and output modalities, network architectures, and evaluation schemes in end-to-end driving literature. Interpretability and safety are discussed separately, as they remain challenging for this approach. Beyond providing a comprehensive overview of existing methods, we conclude the review with an architecture that combines the most promising elements of the end-to-end autonomous driving systems.

ArtSeg-Artifact segmentation and removal in brightfield cell microscopy images without manual pixel-level annotations.

Brightfield cell microscopy is a foundational tool in life sciences. The acquired images are prone to contain visual artifacts that hinder downstream analysis, and automatically removing them is therefore of great practical interest. Deep convolutional neural networks are state-of-the-art for image segmentation, but require pixel-level annotations, which are time-consuming to produce. Here, we propose ScoreCAM-U-Net, a pipeline to segment artifactual regions in brightfield images with limited user input. The model is trained using only image-level labels, so the process is faster by orders of magnitude compared to pixel-level annotation, but without substantially sacrificing the segmentation performance. We confirm that artifacts indeed exist with different shapes and sizes in three different brightfield microscopy image datasets, and distort downstream analyses such as nuclei segmentation, morphometry and fluorescence intensity quantification. We then demonstrate that our automated artifact removal ameliorates this problem. Such rapid cleaning of acquired images using the power of deep learning models is likely to become a standard step for all large scale microscopy experiments.

Live-cell microscopy or fluorescence anisotropy with budded baculoviruses-which way to go with measuring ligand binding to M4 muscarinic receptors?

M4 muscarinic acetylcholine receptor is a G protein-coupled receptor (GPCR) that has been associated with alcohol and cocaine abuse, Alzheimer's disease, and schizophrenia which makes it an interesting drug target. For many GPCRs, the high-affinity fluorescence ligands have expanded the options for high-throughput screening of drug candidates and serve as useful tools in fundamental receptor research. Here, we explored two TAMRA-labelled fluorescence ligands, UR-MK342 and UR-CG072, for development of assays for studying ligand-binding properties to M4 receptor. Using budded baculovirus particles as M4 receptor preparation and fluorescence anisotropy method, we measured the affinities and binding kinetics of both fluorescence ligands. Using the fluorescence ligands as reporter probes, the binding affinities of unlabelled ligands could be determined. Based on these results, we took a step towards a more natural system and developed a method using live CHO-K1-hM4R cells and automated fluorescence microscopy suitable for the routine determination of unlabelled ligand affinities. For quantitative image analysis, we developed random forest and deep learning-based pipelines for cell segmentation. The pipelines were integrated into the user-friendly open-source Aparecium software. Both image analysis methods were suitable for measuring fluorescence ligand saturation binding and kinetics as well as for screening binding affinities of unlabelled ligands.

Evaluating Very Deep Convolutional Neural Networks for Nucleus Segmentation from Brightfield Cell Microscopy Images.

Advances in microscopy have increased output data volumes, and powerful image analysis methods are required to match. In particular, finding and characterizing nuclei from microscopy images, a core cytometry task, remains difficult to automate. While deep learning models have given encouraging results on this problem, the most powerful approaches have not yet been tested for attacking it. Here, we review and evaluate state-of-the-art very deep convolutional neural network architectures and training strategies for segmenting nuclei from brightfield cell images. We tested U-Net as a baseline model; considered U-Net++, Tiramisu, and DeepLabv3+ as latest instances of advanced families of segmentation models; and propose PPU-Net, a novel light-weight alternative. The deeper architectures outperformed standard U-Net and results from previous studies on the challenging brightfield images, with balanced pixel-wise accuracies of up to 86%. PPU-Net achieved this performance with 20-fold fewer parameters than the comparably accurate methods. All models perform better on larger nuclei and in sparser images. We further confirmed that in the absence of plentiful training data, augmentation and pretraining on other data improve performance. In particular, using only 16 images with data augmentation is enough to achieve a pixel-wise F1 score that is within 5% of the one achieved with a full data set for all models. The remaining segmentation errors are mainly due to missed nuclei in dense regions, overlapping cells, and imaging artifacts, indicating the major outstanding challenges.

Multiplex analysis of 40 cytokines do not allow separation between endometriosis patients and controls.

Endometriosis is a common gynaecological condition characterized by severe pelvic pain and/or infertility. The combination of nonspecific symptoms and invasive laparoscopic diagnostics have prompted researchers to evaluate potential biomarkers that would enable a non-invasive diagnosis of endometriosis. Endometriosis is an inflammatory disease thus different cytokines represent potential diagnostic biomarkers. As panels of biomarkers are expected to enable better separation between patients and controls we evaluated 40 different cytokines in plasma samples of 210 patients (116 patients with endometriosis; 94 controls) from two medical centres (Slovenian, Austrian). Results of the univariate statistical analysis showed no differences in concentrations of the measured cytokines between patients and controls, confirmed by principal component analysis showing no clear separation amongst these two groups. In order to validate the hypothesis of a more profound (non-linear) differentiating dependency between features, machine learning methods were used. We trained four common machine learning algorithms (decision tree, linear model, k-nearest neighbour, random forest) on data from plasma levels of proteins and patients' clinical data. The constructed models, however, did not separate patients with endometriosis from the controls with sufficient sensitivity and specificity. This study thus indicates that plasma levels of the selected cytokines have limited potential for diagnosis of endometriosis.

Response to comment on 'AIRE-deficient patients harbor unique high-affinity disease-ameliorating autoantibodies'.

In 2016, we reported four substantial observations of APECED/APS1 patients, who are deficient in AIRE, a major regulator of central T cell tolerance (Meyer et al., 2016). Two of those observations have been challenged. Specifically, 'private' autoantibody reactivities shared by only a few patients but collectively targeting >1000 autoantigens have been attributed to false positives (Landegren, 2019). While acknowledging this risk, our study-design included follow-up validation, permitting us to adopt statistical approaches to also limit false negatives. Importantly, many such private specificities have now been validated by multiple, independent means including the autoantibodies' molecular cloning and expression. Second, a significant correlation of antibody-mediated IFNα neutralization with an absence of disease in patients highly disposed to Type I diabetes has been challenged because of a claimed failure to replicate our findings (Landegren, 2019). However, flaws in design and implementation invalidate this challenge. Thus, our results present robust, insightful, independently validated depictions of APECED/APS1, that have spawned productive follow-up studies.

Computational biology: deep learning.

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.

The metabolic analysis of psoriasis identifies the associated metabolites while providing computational models for the monitoring of the disease.

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.

Blood serum metabolome of atopic dermatitis: Altered energy cycle and the markers of systemic inflammation.

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.

Autoantibody Repertoire in APECED Patients Targets Two Distinct Subgroups of Proteins.

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.