Gliosis-dependent expression of complement factor H truncated variants attenuates retinal neurodegeneration following ischemic injury.

Inherited, age-related, and acute retinal diseases are often exacerbated by an aberrant or excessive activity of the complement system. Consequently, cells not directly affected by an acute event or genetic variants may degenerate, resulting in enhanced visual impairment. The therapeutic potential of supplementation of complement factor H (FH), a key regulator of the complement cascade, is therefore particularly promising in the context of retinal diseases caused by complement activation. In this study, we engineered adeno-associated viruses (AAVs) containing sequences of two truncated human FH variants. The expression of these variants was regulated by the glial fibrillary acidic protein (GFAP) promoter, which is selectively active in gliotic Müller cells. Both FH variants consisted of FH domains 19-20, which were connected to domains 1-4 and 1-7, respectively, by a polyglycine linker. These AAVs were intravitreally injected following ischemic injury of C57BL/6J mouse retinas. We observed transgene expression in gliotic Müller cells and to some extent in astrocytes. The expression correlated directly with damage severity. Interventions resulted in decreased complement activation, accelerated normalization of microglia activity and morphological improvements. Reduced levels of C3 transcripts and C3d protein in conjunction with higher transcript levels of inhibitory regulators like Cfi and Cfh, hinted at attenuated complement activity. This study demonstrates the great potential of complement regulatory gene addition therapy. With further in vivo testing it could be applied to treat a wide range of retinal diseases where no causative therapies are available.

Triple-fusion protein (TriFu): A potent, targeted, enzyme-like inhibitor of all three complement activation pathways.

The introduction of a therapeutic anti-C5 antibody into clinical practice in 2007 inspired a surge into the development of complement-targeted therapies. This has led to the recent approval of a C3 inhibitory peptide, an antibody directed against C1s and a full pipeline of several complement inhibitors in preclinical and clinical development. However, no inhibitor is available that efficiently inhibits all three complement initiation pathways and targets host cell surface markers as well as complement opsonins. To overcome this, we engineered a novel fusion protein combining selected domains of the three natural complement regulatory proteins decay accelerating factor, factor H and complement receptor 1. Such a triple fusion complement inhibitor (TriFu) was recombinantly expressed and purified alongside multiple variants and its building blocks. We analyzed these proteins for ligand binding affinity and decay acceleration activity by surface plasmon resonance. Additionally, we tested complement inhibition in several in vitro/ex vivo assays using standard classical and alternative pathway restricted hemolysis assays next to hemolysis assays with paroxysmal nocturnal hemoglobinuria erythrocytes. A novel in vitro model of the alternative pathway disease C3 glomerulopathy was established to evaluate the potential of the inhibitors to stop C3 deposition on endothelial cells. Next to the novel engineered triple fusion variants which inactivate complement convertases in an enzyme-like fashion, stoichiometric complement inhibitors targeting C3, C5, factor B, and factor D were tested as comparators. The triple fusion approach yielded a potent complement inhibitor that efficiently inhibits all three complement initiation pathways while targeting to surface markers.

Validation of a methylation-based signature for subventricular zone involvement in glioblastoma.

PURPOSE: Glioblastomas (GBM) with subventricular zone (SVZ) contact have previously been associated with a specific epigenetic fingerprint. We aim to validate a reported bulk methylation signature to determine SVZ contact. METHODS: Methylation array analysis was performed on IDHwt GBM patients treated at our institution. The v11b4 classifier was used to ensure the inclusion of only receptor tyrosine kinase (RTK) I, II, and mesenchymal (MES) subtypes. Methylation-based assignment (SVZM ±) was performed using hierarchical cluster analysis. Magnetic resonance imaging (MRI) (T1ce) was independently reviewed for SVZ contact by three experienced readers. RESULTS: Sixty-five of 70 samples were classified as RTK I, II, and MES. Full T1ce MRI-based rater consensus was observed in 54 cases, which were retained for further analysis. Epigenetic SVZM classification and SVZ were strongly associated (OR: 15.0, p = 0.003). Thirteen of fourteen differential CpGs were located in the previously described differentially methylated LRBA/MAB21L2 locus. SVZ + tumors were linked to shorter OS (hazard ratio (HR): 3.80, p = 0.02) than SVZM + at earlier time points (time-dependency of SVZM, p < 0.05). Considering the SVZ consensus as the ground truth, SVZM classification yields a sensitivity of 96.6%, specificity of 36.0%, positive predictive value (PPV) of 63.6%, and negative predictive value (NPV) of 90.0%. CONCLUSION: Herein, we validated the specific epigenetic signature in GBM in the vicinity of the SVZ and highlighted the importance of methylation of a part of the LRBA/MAB21L2 gene locus. Whether SVZM can replace MRI-based SVZ assignment as a prognostic and diagnostic tool will require prospective studies of large, homogeneous cohorts.

Nucleotide-free structures of KIF20A illuminate atypical mechanochemistry in this kinesin-6.

KIF20A is a critical kinesin for cell division and a promising anti-cancer drug target. The mechanisms underlying its cellular roles remain elusive. Interestingly, unusual coupling between the nucleotide- and microtubule-binding sites of this kinesin-6 has been reported, but little is known about how its divergent sequence leads to atypical motility properties. We present here the first high-resolution structure of its motor domain that delineates the highly unusual structural features of this motor, including a long L6 insertion that integrates into the core of the motor domain and that drastically affects allostery and ATPase activity. Together with the high-resolution cryo-electron microscopy microtubule-bound KIF20A structure that reveals the microtubule-binding interface, we dissect the peculiarities of the KIF20A sequence that influence its mechanochemistry, leading to low motility compared to other kinesins. Structural and functional insights from the KIF20A pre-power stroke conformation highlight the role of extended insertions in shaping the motor's mechanochemical cycle. Essential for force production and processivity is the length of the neck linker in kinesins. We highlight here the role of the sequence preceding the neck linker in controlling its backward docking and show that a neck linker four times longer than that in kinesin-1 is required for the activity of this motor.

Complement inhibition can decrease the haemostatic response in a microvascular bleeding model at multiple levels.

Background: Haemostasis is a crucial process by which the body stops bleeding. It is achieved by the formation of a platelet plug, which is strengthened by formation of a fibrin mesh mediated by the coagulation cascade. In proinflammatory and prothrombotic conditions, multiple interactions of the complement system and the coagulation cascade are known to aggravate thromboinflammatory processes and increase the risk of arterial and venous thrombosis. Whether those interactions also play a relevant role during the physiological process of haemostasis is not yet completely understood. The aim of this study was to investigate the potential role of complement components and activation during the haemostatic response to mechanical vessel injury. Methods: We used a microvascular bleeding model that simulates a blood vessel, featuring human endothelial cells, perfusion with fresh human whole blood, and an inducible mechanical injury to the vessel. We studied the effects of complement inhibitors against components of the lectin (MASP-1, MASP-2), classical (C1s), alternative (FD) and common pathways (C3, C5), as well as a novel triple fusion inhibitor of all three complement pathways (TriFu). Effects on clot formation were analysed by recording of fibrin deposition and the platelet activation marker CD62P at the injury site in real time using a confocal microscope. Results: With the inhibitors targeting MASP-2 or C1s, no significant reduction of fibrin formation was observed, while platelet activation was significantly reduced in the presence of the FD inhibitor. Both common pathway inhibitors targeting C3 or C5, respectively, were associated with a substantial reduction of fibrin formation, and platelet activation was also reduced in the presence of the C3 inhibitor. Triple inhibition of all three activation pathways at the C3-convertase level by TriFu reduced both fibrin formation and platelet activation. When several complement inhibitors were directly compared in two individual donors, TriFu and the inhibitors of MASP-1 and C3 had the strongest effects on clot formation. Conclusion: The observed impact of complement inhibition on reducing fibrin clot formation and platelet activation suggests a role of the complement system in haemostasis, with modulators of complement initiation, amplification or effector functions showing distinct profiles. While the interactions between complement and coagulation might have evolved to support haemostasis and protect against bleeding in case of vessel injury, they can turn harmful in pathological conditions when aggravating thromboinflammation and promoting thrombosis.

Human lysozyme inhibits the fibrillation of serum amyloid a protein from systemic AA amyloidosis.

BACKGROUND: Systemic AA amyloidosis is a world-wide occurring protein misfolding disease in humans and animals that arises from the formation of amyloid fibrils from serum amyloid A (SAA) protein and their deposition in multiple organs. OBJECTIVE: To identify new agents that prevent fibril formation from SAA protein and to determine their mode of action. MATERIALS AND METHODS: We used a cell model for the formation of amyloid deposits from SAA protein to screen a library of peptides and small proteins, which were purified from human hemofiltrate. To clarify the inhibitory mechanism the obtained inhibitors were characterised in cell-free fibril formation assays and other biochemical methods. RESULTS: We identified lysozyme as an inhibitor of SAA fibril formation. Lysozyme antagonised fibril formation both in the cell model as well as in cell-free fibril formation assays. The protein binds SAA with a dissociation constant of 16.5 ± 0.6 µM, while the binding site on SAA is formed by segments of positively charged amino acids. CONCLUSION: Our data imply that lysozyme acts in a chaperone-like fashion and prevents the aggregation of SAA protein through direct, physical interactions.

Complement and platelets: prothrombotic cell activation requires membrane attack complex-induced release of danger signals.

Complement activation in the diseases paroxysmal nocturnal hemoglobinuria (PNH) and atypical hemolytic uremic syndrome (aHUS) results in cytolysis and fatal thrombotic events, which are largely refractory to anticoagulation and/or antiplatelet therapy. Anticomplement therapy, however, efficiently prevents thrombotic events in PNH and aHUS, but the underlying mechanisms remain unresolved. We show that complement-mediated hemolysis in whole blood induces platelet activation similarly to activation by adenosine 5'-diphosphate (ADP). Blockage of C3 or C5 abolished platelet activation. We found that human platelets failed to respond functionally to the anaphylatoxins C3a and C5a. Instead, complement activation did lead to prothrombotic cell activation in the whole blood when membrane attack complex (MAC)-mediated cytolysis occurred. Consequently, we demonstrate that ADP receptor antagonists efficiently inhibited platelet activation, although full complement activation, which causes hemolysis, occurred. By using an established model of mismatched erythrocyte transfusions in rats, we crossvalidated these findings in vivo using the complement inhibitor OmCI and cobra venom factor. Consumptive complement activation in this animal model only led to a thrombotic phenotype when MAC-mediated cytolysis occurred. In conclusion, complement activation only induces substantial prothrombotic cell activation if terminal pathway activation culminates in MAC-mediated release of intracellular ADP. These results explain why anticomplement therapy efficiently prevents thromboembolisms without interfering negatively with hemostasis.

The Complement-Targeted Inhibitor Mini-FH Protects against Experimental Periodontitis via Both C3-Dependent and C3-Independent Mechanisms.

A minimized version of complement factor H (FH), designated mini-FH, was previously engineered combining the N-terminal regulatory domains (short consensus repeat [SCR]1-4) and C-terminal host-surface recognition domains (SCR19-20) of the parent molecule. Mini-FH conferred enhanced protection, as compared with FH, in an ex vivo model of paroxysmal nocturnal hemoglobinuria driven by alternative pathway dysregulation. In the current study, we tested whether and how mini-FH could block another complement-mediated disease, namely periodontitis. In a mouse model of ligature-induced periodontitis (LIP), mini-FH inhibited periodontal inflammation and bone loss in wild-type mice. Although LIP-subjected C3-deficient mice are protected relative to wild-type littermates and exhibit only modest bone loss, mini-FH strikingly inhibited bone loss even in C3-deficient mice. However, mini-FH failed to inhibit ligature-induced bone loss in mice doubly deficient in C3 and CD11b. These findings indicate that mini-FH can inhibit experimental periodontitis even in a manner that is independent of its complement regulatory activity and is mediated by complement receptor 3 (CD11b/CD18). Consistent with this notion, a complement receptor 3-interacting recombinant FH segment that lacks complement regulatory activity (specifically encompassing SCRs 19 and 20; FH19-20) was also able to suppress bone loss in LIP-subjected C3-deficient mice. In conclusion, mini-FH appears to be a promising candidate therapeutic for periodontitis by virtue of its ability to suppress bone loss via mechanisms that both include and go beyond its complement regulatory activity.

Combined Heterozygous Genetic Variations in Complement C2 and C8B: An Explanation for Multidimensional Immune Imbalance?

The complement system plays a crucial role in host defense, homeostasis, and tissue regeneration and bridges the innate and the adaptive immune systems. Although the genetic variants in complement C2 (c.839_849+17del; p.(Met280Asnfs*5)) and C8B (c.1625C>T; p.(Thr542Ile)) are known individually, here, we report on a patient carrying their combination in a heterozygous form. The patient presented with a reduced general condition and suffers from a wide variety of autoimmune diseases. While no autoimmune disease-specific autoantibodies could be detected, genetic analysis revealed abnormalities in the two complement genes C2 and C8B. Therefore, we performed a comprehensive investigation of the innate immune system on a cellular and humoral level to define the functional consequences. We found slightly impaired functionality of neutrophils and monocytes regarding phagocytosis and reactive oxygen species generation and a diminished expression of the C5aR1. An extensive complement analysis revealed a declined activation potential for the alternative and classical pathway. Reconstitution with purified C2 and C8 into patient serum failed to normalize the dysfunction, whereas the addition of C3 improved the hemolytic activity. In clinical transfer, in vitro supplementation of the patient's plasma with FFP as a complement source could fully restore full complement functionality. This study describes for the first time a combined heterozygous genetic variation in complement C2 and C8B which, however, cannot fully explain the overall dysfunctions and calls for further complement deficiency research and corresponding therapies.

Preferential production and secretion of the complement regulator factor H-like protein 1 (FHL-1) by human myeloid cells.

Factor H is a pivotal complement regulatory protein that is preferentially produced by the liver and circulates in high concentrations in serum. There has been an increasing interest in the extrahepatic production of complement factors, including by cells of the immune system, since this contributes to non-canonical functions of local complement activation and regulation. Here we investigated the production and regulation of factor H and its splice variant factor H-like protein 1 (FHL-1) by human myeloid cells. As validation, we confirmed the predominant presence of intact factor H in serum, despite a strong but comparable mRNA expression of CFH and FHL1 in liver. Comparable levels of CFH and FHL1 were also observed in renal tissue, although a dominant staining for FHL-1 was shown within the proximal tubules. Human in vitro generated pro- and anti-inflammatory macrophages both expressed and produced factor H/FHL-1, but this was strongest in pro-inflammatory macrophages. Production was not affected by LPS activation, but was increased upon stimulation with IFN-γ or CD40L. Importantly, in both macrophage subsets mRNA expression of FHL1 was significantly higher than CFH. Moreover, production of FHL-1 protein could be confirmed using precipitation and immunoblotting of culture supernatants. These data identify macrophages as producers of factor H and FHL-1, thereby potentially contributing to local complement regulation at sites of inflammation.

Firms' responses to the COVID-19 pandemic.

The COVID-19 pandemic requires firms to adequately respond. In this study, we first explore in our empirical data how firms responded to the COVID-19 crisis and identify five tactical response types, operational, digitalization, financial, supportive, and organizational responses. Furthermore, our findings indicate that responses vary in scope; Some firms act on their own, while others engage in collaborations. Finally, we find that the response angle is different across firms, as some firms leverage potential and others primarily mitigate risk. Second, we follow an event study design to measure the financial implications of these responses. We find that responses to the COVID-19 pandemic generally entail a positive stock market reaction. Financial and digitalization responses, as well as risk mitigation responses, are consistently evaluated positively. We discuss our findings in context of different theoretical lenses, substantiating the emerging literature on the COVID-19 crisis, and the established literature on crisis response management.

Bi-allelic loss-of-function variants in KIF21A cause severe fetal akinesia with arthrogryposis multiplex.

BACKGROUND: Fetal akinesia (FA) results in variable clinical presentations and has been associated with more than 166 different disease loci. However, the underlying molecular cause remains unclear in many individuals. We aimed to further define the set of genes involved. METHODS: We performed in-depth clinical characterisation and exome sequencing on a cohort of 23 FA index cases sharing arthrogryposis as a common feature. RESULTS: We identified likely pathogenic or pathogenic variants in 12 different established disease genes explaining the disease phenotype in 13 index cases and report 12 novel variants. In the unsolved families, a search for recessive-type variants affecting the same gene was performed; and in five affected fetuses of two unrelated families, a homozygous loss-of-function variant in the kinesin family member 21A gene (KIF21A) was found. CONCLUSION: Our study underlines the broad locus heterogeneity of FA with well-established and atypical genotype-phenotype associations. We describe KIF21A as a new factor implicated in the pathogenesis of severe neurogenic FA sequence with arthrogryposis of multiple joints, pulmonary hypoplasia and facial dysmorphisms. This hypothesis is further corroborated by a recent report on overlapping phenotypes observed in Kif21a null piglets.

Protein therapeutics and their lessons: Expect the unexpected when inhibiting the multi-protein cascade of the complement system.

Over a century after the discovery of the complement system, the first complement therapeutic was approved for the treatment of paroxysmal nocturnal hemoglobinuria (PNH). It was a long-acting monoclonal antibody (aka 5G1-1, 5G1.1, h5G1.1, and now known as eculizumab) that targets C5, specifically preventing the generation of C5a, a potent anaphylatoxin, and C5b, the first step in the eventual formation of membrane attack complex. The enormous clinical and financial success of eculizumab across four diseases (PNH, atypical hemolytic uremic syndrome (aHUS), myasthenia gravis (MG), and anti-aquaporin-4 (AQP4) antibody-positive neuromyelitis optica spectrum disorder (NMOSD)) has fueled a surge in complement therapeutics, especially targeting diseases with an underlying complement pathophysiology for which anti-C5 therapy is ineffective. Intensive research has also uncovered challenges that arise from C5 blockade. For example, PNH patients can still face extravascular hemolysis or pharmacodynamic breakthrough of complement suppression during complement-amplifying conditions. These "side" effects of a stoichiometric inhibitor like eculizumab were unexpected and are incompatible with some of our accepted knowledge of the complement cascade. And they are not unique to C5 inhibition. Indeed, "exceptions" to the rules of complement biology abound and have led to unprecedented and surprising insights. In this review, we will describe initial, present and future aspects of protein inhibitors of the complement cascade, highlighting unexpected findings that are redefining some of the mechanistic foundations upon which the complement cascade is organized.

Complement-regulatory biomaterial coatings: Activity and selectivity profile of the factor H-binding peptide 5C6.

The use of biomaterials in modern medicine has enabled advanced drug delivery strategies and led to reduced morbidity and mortality in a variety of interventions such as transplantation or hemodialysis. However, immune-mediated reactions still present a serious complication of these applications. One of the drivers of such reactions is the complement system, a central part of humoral innate immunity that acts as a first-in-line defense system in its own right but also coordinates other host defense responses. A major regulator of the complement system is the abundant plasma protein factor H (FH), which impairs the amplification of complement responses. Previously, we could show that it is possible to recruit FH to biomedical surfaces using the phage display-derived cyclic peptide 5C6 and, consequently, reduce deposition of C3b, an activation product of the complement system. However, the optimal orientation of 5C6 on surfaces, structural determinants within the peptide for the binding, and the exact binding region on FH remained unknown. Here, we show that the cyclic core and C-terminal region of 5C6 are essential for its interaction with FH and that coating through its N-terminus strongly increases FH recruitment and reduces C3-mediated opsonization in a microparticle-based assay. Furthermore, we could demonstrate that 5C6 selectively binds to FH but not to related proteins. The observation that 5C6 also binds murine FH raises the potential for translational evaluation in animal models. This work provides important insight for the future development of 5C6 as a probe or therapeutic entity to reduce complement activation on biomaterials. STATEMENT OF SIGNIFICANCE: Biomaterials have evolved into core technologies critical to biomedical and drug delivery applications alike, yet their safe and efficient use may be adversely impacted by immune responses to the foreign materials. Taking inspiration from microbial immune evasion strategies, our group developed a peptide-based surface coating that recruits factor H (FH), a host regulator of the complement system, from plasma to the material surface and prevents unwanted activation of this innate immunity pathway. In this study, we identified the molecular determinants that define the interaction between FH and the coated peptide, developed tethering strategies with largely enhanced binding capacity and provided important insight into the target selectivity and species specificity of the FH-binding peptide, thereby paving the way for preclinical development steps.

Minimal vertex model explains how the amnioserosa avoids fluidization during Drosophila dorsal closure.

Dorsal closure is a process that occurs during embryogenesis of Drosophila melanogaster . During dorsal closure, the amnioserosa (AS), a one-cell thick epithelial tissue that fills the dorsal opening, shrinks as the lateral epidermis sheets converge and eventually merge. During this process, the aspect ratio of amnioserosa cells increases markedly. The standard 2-dimensional vertex model, which successfully describes tissue sheet mechanics in multiple contexts, would in this case predict that the tissue should fluidize via cell neighbor changes. Surprisingly, however, the amnioserosa remains an elastic solid with no such events. We here present a minimal extension to the vertex model that explains how the amnioserosa can achieve this unexpected behavior. We show that continuous shrinkage of the preferred cell perimeter and cell perimeter polydispersity lead to the retention of the solid state of the amnioserosa. Our model accurately captures measured cell shape and orientation changes and predicts non-monotonic junction tension that we confirm with laser ablation experiments. Significance Statement: During embryogenesis, cells in tissues can undergo significant shape changes. Many epithelial tissues fluidize, i.e. cells exchange neighbors, when the average cell aspect ratio increases above a threshold value, consistent with the standard vertex model. During dorsal closure in Drosophila melanogaster , however, the amnioserosa tissue remains solid even as the average cell aspect ratio increases well above threshold. We introduce perimeter polydispersity and allow the preferred cell perimeters, usually held fixed in vertex models, to decrease linearly with time as seen experimentally. With these extensions to the standard vertex model, we capture experimental observations quantitatively. Our results demonstrate that vertex models can describe the behavior of the amnioserosa in dorsal closure by allowing normally fixed parameters to vary with time.

Minimal vertex model explains how the amnioserosa avoids fluidization during Drosophila dorsal closure.

Dorsal closure is a process that occurs during embryogenesis of Drosophila melanogaster. During dorsal closure, the amnioserosa (AS), a one-cell thick epithelial tissue that fills the dorsal opening, shrinks as the lateral epidermis sheets converge and eventually merge. During this process, the aspect ratio of amnioserosa cells increases markedly. The standard 2-dimensional vertex model, which successfully describes tissue sheet mechanics in multiple contexts, would in this case predict that the tissue should fluidize via cell neighbor changes. Surprisingly, however, the amnioserosa remains an elastic solid with no such events. We here present a minimal extension to the vertex model that explains how the amnioserosa can achieve this unexpected behavior. We show that continuous shrink-age of the preferred cell perimeter and cell perimeter polydispersity lead to the retention of the solid state of the amnioserosa. Our model accurately captures measured cell shape and orientation changes and predicts non-monotonic junction tension that we confirm with laser ablation experiments.

Modulation of Neutrophil Activity by Soluble Complement Cleavage Products-An In-Depth Analysis.

The cellular and fluid phase-innate immune responses of many diseases predominantly involve activated neutrophil granulocytes and complement factors. However, a comparative systematic analysis of the early impact of key soluble complement cleavage products, including anaphylatoxins, on neutrophil granulocyte function is lacking. Neutrophil activity was monitored by flow cytometry regarding cellular (electro-)physiology, cellular activity, and changes in the surface expression of activation markers. The study revealed no major effects induced by C3a or C4a on neutrophil functions. By contrast, exposure to C5a or C5a des-Arg stimulated neutrophil activity as reflected in changes in membrane potential, intracellular pH, glucose uptake, and cellular size. Similarly, C5a and C5a des-Arg but no other monitored complement cleavage product enhanced phagocytosis and reactive oxygen species generation. C5a and C5a des-Arg also altered the neutrophil surface expression of several complement receptors and neutrophil activation markers, including C5aR1, CD62L, CD10, and CD11b, among others. In addition, a detailed characterization of the C5a-induced effects was performed with a time resolution of seconds. The multiparametric response of neutrophils was further analyzed by a principal component analysis, revealing CD11b, CD10, and CD16 to be key surrogates of the C5a-induced effects. Overall, we provide a comprehensive insight into the very early interactions of neutrophil granulocytes with activated complement split products and the resulting neutrophil activity. The results provide a basis for a better and, importantly, time-resolved and multiparametric understanding of neutrophil-related (patho-)physiologies.

DeepProjection: specific and robust projection of curved 2D tissue sheets from 3D microscopy using deep learning.

The efficient extraction of image data from curved tissue sheets embedded in volumetric imaging data remains a serious and unsolved problem in quantitative studies of embryogenesis. Here, we present DeepProjection (DP), a trainable projection algorithm based on deep learning. This algorithm is trained on user-generated training data to locally classify 3D stack content, and to rapidly and robustly predict binary masks containing the target content, e.g. tissue boundaries, while masking highly fluorescent out-of-plane artifacts. A projection of the masked 3D stack then yields background-free 2D images with undistorted fluorescence intensity values. The binary masks can further be applied to other fluorescent channels or to extract local tissue curvature. DP is designed as a first processing step than can be followed, for example, by segmentation to track cell fate. We apply DP to follow the dynamic movements of 2D-tissue sheets during dorsal closure in Drosophila embryos and of the periderm layer in the elongating Danio embryo. DeepProjection is available as a fully documented Python package.