The AKT2/SIRT5/TFEB pathway as a potential therapeutic target in atrophic AMD.

Age-related macular degeneration (AMD), the leading cause of geriatric blindness, is a multi-factorial disease with retinal-pigmented epithelial (RPE) cell dysfunction as a central pathogenic driver. With RPE degeneration, lysosomal function is a core process that is disrupted. Transcription factors EB/E3 (TFEB/E3) tightly control lysosomal function; their disruption can cause aging disorders, such as AMD. Here, we show that induced pluripotent stem cells (iPSC)-derived RPE cells with the complement factor H variant [ CFH (Y402H)] have increased AKT2, which impairs TFEB/TFE3 nuclear translocation and lysosomal function. Increased AKT2 can inhibit PGC1α, which downregulates SIRT5, an AKT2 binding partner. SIRT5 and AKT2 co-regulate each other, thereby modulating TFEB-dependent lysosomal function in the RPE. Failure of the AKT2/SIRT5/TFEB pathway in the RPE induced abnormalities in the autophagy-lysosome cellular axis by upregulating secretory autophagy, thereby releasing a plethora of factors that likely contribute to drusen formation, a hallmark of AMD. Finally, overexpressing AKT2 in RPE cells in mice led to an AMD-like phenotype. Thus, targeting the AKT2/SIRT5/TFEB pathway could be a potential therapy for atrophic AMD.

Increased LCN2 (lipocalin 2) in the RPE decreases autophagy and activates inflammasome-ferroptosis processes in a mouse model of dry AMD.

In dry age-related macular degeneration (AMD), LCN2 (lipocalin 2) is upregulated. Whereas LCN2 has been implicated in AMD pathogenesis, the mechanism remains unknown. Here, we report that in retinal pigmented epithelial (RPE) cells, LCN2 regulates macroautophagy/autophagy, in addition to maintaining iron homeostasis. LCN2 binds to ATG4B to form an LCN2-ATG4B-LC3-II complex, thereby regulating ATG4B activity and LC3-II lipidation. Thus, increased LCN2 reduced autophagy flux. Moreover, RPE cells from cryba1 KO, as well as sting1 KO and Sting1Gt mutant mice (models with abnormal iron chelation), showed decreased autophagy flux and increased LCN2, indicative of CGAS- and STING1-mediated inflammasome activation. Live cell imaging of RPE cells with elevated LCN2 also showed a correlation between inflammasome activation and increased fluorescence intensity of the Liperfluo dye, indicative of oxidative stress-induced ferroptosis. Interestingly, both in human AMD patients and in mouse models with a dry AMD-like phenotype (cryba1 cKO and KO), the LCN2 homodimer variant is increased significantly compared to the monomer. Sub-retinal injection of the LCN2 homodimer secreted by RPE cells into NOD-SCID mice leads to retinal degeneration. In addition, we generated an LCN2 monoclonal antibody that neutralizes both the monomer and homodimer variants and rescued autophagy and ferroptosis activities in cryba1 cKO mice. Furthermore, the antibody rescued retinal function in cryba1 cKO mice as assessed by electroretinography. Here, we identify a molecular pathway whereby increased LCN2 elicits pathophysiology in the RPE, cells known to drive dry AMD pathology, thus providing a possible therapeutic strategy for a disease with no current treatment options.Abbreviations: ACTB: actin, beta; Ad-GFP: adenovirus-green fluorescent protein; Ad-LCN2: adenovirus-lipocalin 2; Ad-LCN2-GFP: adenovirus-LCN2-green fluorescent protein; LCN2AKT2: AKT serine/threonine kinase 2; AMBRA1: autophagy and beclin 1 regulator 1; AMD: age-related macular degeneration; ARPE19: adult retinal pigment epithelial cell line-19; Asp278: aspartate 278; ATG4B: autophagy related 4B cysteine peptidase; ATG4C: autophagy related 4C cysteine peptidase; ATG7: autophagy related 7; ATG9B: autophagy related 9B; BLOC-1: biogenesis of lysosomal organelles complex 1; BLOC1S1: biogenesis of lysosomal organelles complex 1 subunit 1; C57BL/6J: C57 black 6J; CGAS: cyclic GMP-AMP synthase; ChQ: chloroquine; cKO: conditional knockout; Cys74: cysteine 74; Dab2: DAB adaptor protein 2; Def: deferoxamine; DHE: dihydroethidium; DMSO: dimethyl sulfoxide; ERG: electroretinography; FAC: ferric ammonium citrate; Fe2+: ferrous; FTH1: ferritin heavy chain 1; GPX: glutathione peroxidase; GST: glutathione S-transferase; H2O2: hydrogen peroxide; His280: histidine 280; IFNL/IFNλ: interferon lambda; IL1B/IL-1ß: interleukin 1 beta; IS: Inner segment; ITGB1/integrin ß1: integrin subunit beta 1; KO: knockout; LC3-GST: microtubule associated protein 1 light chain 3-GST; C-terminal fusion; MAP1LC3/LC3: microtubule associated protein 1 light chain 3; LCN2: lipocalin 2; mAb: monoclonal antibody; MDA: malondialdehyde; MMP9: matrix metallopeptidase 9; NLRP3: NLR family pyrin domain containing 3; NOD-SCID: nonobese diabetic-severe combined immunodeficiency; OS: outer segment; PBS: phosphate-buffered saline; PMEL/PMEL17: premelanosome protein; RFP: red fluorescent protein; rLCN2: recombinant LCN2; ROS: reactive oxygen species; RPE SM: retinal pigmented epithelium spent medium; RPE: retinal pigment epithelium; RSL3: RAS-selective lethal; scRNAseq: single-cell ribonucleic acid sequencing; SD-OCT: spectral domain optical coherence tomography; shRNA: small hairpin ribonucleic acid; SM: spent medium; SOD1: superoxide dismutase 1; SQSTM1/p62: sequestosome 1; STAT1: signal transducer and activator of transcription 1; STING1: stimulator of interferon response cGAMP interactor 1; TYR: tyrosinase; VCL: vinculin; WT: wild type.

The Impaired Neurodevelopment of Human Neural Rosettes in HSV-1-Infected Early Brain Organoids.

Intrauterine infections during pregnancy by herpes simplex virus (HSV) can cause significant neurodevelopmental deficits in the unborn/newborn, but clinical studies of pathogenesis are challenging, and while animal models can model some aspects of disease, in vitro studies of human neural cells provide a critical platform for more mechanistic studies. We utilized a reductionist approach to model neurodevelopmental outcomes of HSV-1 infection of neural rosettes, which represent the in vitro equivalent of differentiating neural tubes. Specifically, we employed early-stage brain organoids (ES-organoids) composed of human induced pluripotent stem cells (hiPSCs)-derived neural rosettes to investigate aspects of the potential neuropathological effects induced by the HSV-1 infections on neurodevelopment. To allow for the long-term differentiation of ES-organoids, viral infections were performed in the presence of the antiviral drug acyclovir (ACV). Despite the antiviral treatment, HSV-1 infection caused organizational changes in neural rosettes, loss of structural integrity of infected ES-organoids, and neuronal alterations. The inability of ACV to prevent neurodegeneration was associated with the generation of ACV-resistant mutants during the interaction of HSV-1 with differentiating neural precursor cells (NPCs). This study models the effects of HSV-1 infection on the neuronal differentiation of NPCs and suggests that this environment may allow for accelerated development of ACV-resistance.

Time-resolved proximity labeling of protein networks associated with ligand-activated EGFR.

Ligand binding to the EGF receptor (EGFR) triggers multiple signal-transduction processes and promotes endocytosis of the receptor. The mechanisms of EGFR endocytosis and its cross-talk with signaling are poorly understood. Here, we combine peroxidase-catalyzed proximity labeling, isobaric peptide tagging, and quantitative mass spectrometry to define the dynamics of the proximity proteome of ligand-activated EGFR. Using this approach, we identify a network of signaling proteins, which remain associated with the receptor during its internalization and trafficking through the endosomal system. We show that Trk-fused gene (TFG), a protein known to function at the endoplasmic reticulum exit sites, is enriched in the proximity proteome of EGFR in early/sorting endosomes and localized in these endosomes and demonstrate that TFG regulates endosomal sorting of EGFR. This study provides a comprehensive resource of time-dependent nanoscale environment of EGFR, thus opening avenues to discovering new regulatory mechanisms of signaling and intracellular trafficking of receptor tyrosine kinases.

Hotspot ESR1 Mutations Are Multimodal and Contextual Modulators of Breast Cancer Metastasis.

Constitutively active estrogen receptor α (ER/ESR1) mutations have been identified in approximately one-third of ER+ metastatic breast cancers. Although these mutations are known as mediators of endocrine resistance, their potential role in promoting metastatic disease has not yet been mechanistically addressed. In this study, we show the presence of ESR1 mutations exclusively in distant but not local recurrences in five independent breast cancer cohorts. In concordance with transcriptomic profiling of ESR1-mutant tumors, genome-edited ESR1 Y537S and D538G-mutant cell models exhibited a reprogrammed cell adhesive gene network via alterations in desmosome/gap junction genes and the TIMP3/MMP axis, which functionally conferred enhanced cell-cell contacts while decreasing cell-extracellular matrix adhesion. In vivo studies showed ESR1-mutant cells were associated with larger multicellular circulating tumor cell (CTC) clusters with increased compactness compared with ESR1 wild-type CTCs. These preclinical findings translated to clinical observations, where CTC clusters were enriched in patients with ESR1-mutated metastatic breast cancer. Conversely, context-dependent migratory phenotypes revealed cotargeting of Wnt and ER as a vulnerability in a D538G cell model. Mechanistically, mutant ESR1 exhibited noncanonical regulation of several metastatic pathways, including secondary transcriptional regulation and de novo FOXA1-driven chromatin remodeling. Collectively, these data provide evidence for ESR1 mutation-modulated metastasis and suggest future therapeutic strategies for targeting ESR1-mutant breast cancer. SIGNIFICANCE: Context- and allele-dependent transcriptome and cistrome reprogramming in mutant ESR1 cell models elicit diverse metastatic phenotypes related to cell adhesion and migration, which can be pharmacologically targeted in metastatic breast cancer.

Real-time imaging of asthmatic epithelial cells identifies migratory deficiencies under type-2 conditions.

BACKGROUND: The epithelium is increasingly recognized as a pathologic contributor to asthma and its phenotypes. Although delayed wound closure by asthmatic epithelial cells is consistently observed, underlying mechanisms remain poorly understood, partly due to difficulties in studying dynamic physiologic processes involving polarized multilayered cell systems. Although type-2 immunity has been suggested to play a role, the mechanisms by which repair is diminished are unclear. OBJECTIVES: This study sought to develop and utilize primary multilayered polarized epithelial cell systems, derived from patients with asthma, to evaluate cell migration in response to wounding under type-2 and untreated conditions. METHODS: A novel wounding device for multilayered polarized cells, along with time-lapse live cell/real-time confocal imaging were evaluated under IL-13 and untreated conditions. The influence of inhibition of 15 lipoxygenase (15LO1), a type-2 enzyme, on the process was also addressed. Cell migration patterns were analyzed by high-dimensional frequency modulated Möbius for statistical comparisons. RESULTS: IL-13 stimulation negatively impacts wound healing by altering the total speed, directionality, and acceleration of individual cells. Inhibition 15LO1 partially improved the wound repair through improving total speed. CONCLUSIONS: Migration abnormalities contributed to markedly slower wound closure of IL-13 treated cells, which was modestly reversed by 15LO1 inhibition, suggesting its potential as an asthma therapeutic target. These novel methodologies offer new ways to dynamically study cell movements and identify contributing pathologic processes.

Cytoplasmic CPSF6 Regulates HIV-1 Capsid Trafficking and Infection in a Cyclophilin A-Dependent Manner.

Human immunodeficiency virus type 1 (HIV-1) capsid binds host proteins during infection, including cleavage and polyadenylation specificity factor 6 (CPSF6) and cyclophilin A (CypA). We observe that HIV-1 infection induces higher-order CPSF6 formation, and capsid-CPSF6 complexes cotraffic on microtubules. CPSF6-capsid complex trafficking is impacted by capsid alterations that reduce CPSF6 binding or by excess cytoplasmic CPSF6 expression, both of which are associated with decreased HIV-1 infection. Higher-order CPSF6 complexes bind and disrupt HIV-1 capsid assemblies in vitro Disruption of HIV-1 capsid binding to CypA leads to increased CPSF6 binding and altered capsid trafficking, resulting in reduced infectivity. Our data reveal an interplay between CPSF6 and CypA that is important for cytoplasmic capsid trafficking and HIV-1 infection. We propose that CypA prevents HIV-1 capsid from prematurely engaging cytoplasmic CPSF6 and that differences in CypA cellular localization and innate immunity may explain variations in HIV-1 capsid trafficking and uncoating in CD4+ T cells and macrophages.IMPORTANCE HIV is the causative agent of AIDS, which has no cure. The protein shell that encases the viral genome, the capsid, is critical for HIV replication in cells at multiple steps. HIV capsid has been shown to interact with multiple cell proteins during movement to the cell nucleus in a poorly understood process that may differ during infection of different cell types. In this study, we show that premature or too much binding of one human protein, cleavage and polyadenylation specificity factor 6 (CPSF6), disrupts the ability of the capsid to deliver the viral genome to the cell nucleus. Another human protein, cyclophilin A (CypA), can shield HIV capsid from premature binding to CPSF6, which can differ in CD4+ T cells and macrophages. Better understanding of how HIV infects cells will allow better drugs to prevent or inhibit infection and pathogenesis.

Direct coupling of oligomerization and oligomerization-driven endocytosis of the dopamine transporter to its conformational mechanics and activity.

Dopamine transporter (DAT) mediates the reuptake of synaptically released dopamine, and thus controls the duration and intensity of dopamine neurotransmission. Mammalian DAT has been observed to form oligomers, although the mechanisms of oligomerization and its role in DAT activity and trafficking remain largely unknown. We discovered a series of small molecule compounds that stabilize trimers and induce high-order oligomers of DAT and concomitantly promote its clathrin-independent endocytosis. Using a combination of chemical cross-linking, fluorescence resonance energy transfer microscopy, antibody-uptake endocytosis assay, live-cell lattice light sheet microscopy, ligand binding and substrate transport kinetics analyses, and molecular modeling and simulations, we investigated molecular basis of DAT oligomerization and endocytosis induced by these compounds. Our study showed that small molecule-induced DAT oligomerization and endocytosis are favored by the inward-facing DAT conformation and involve interactions of four hydrophobic residues at the interface between transmembrane (TM) helices TM4 and TM9. Surprisingly, a corresponding quadruple DAT mutant displays altered dopamine transport kinetics and increased cocaine-analog binding. The latter is shown to originate from an increased preference for outward-facing conformation and inward-to-outward transition. Taken together, our results demonstrate a direct coupling between conformational dynamics of DAT, functional activity of the transporter, and its oligomerization leading to endocytosis. The high specificity of such coupling for DAT makes the TM4-9 hub a new target for pharmacological modulation of DAT activity and subcellular localization.

PLA2G6 guards placental trophoblasts against ferroptotic injury.

The recently identified ferroptotic cell death is characterized by excessive accumulation of hydroperoxy-arachidonoyl (C20:4)- or adrenoyl (C22:4)- phosphatidylethanolamine (Hp-PE). The selenium-dependent glutathione peroxidase 4 (GPX4) inhibits ferroptosis, converting unstable ferroptotic lipid hydroperoxides to nontoxic lipid alcohols in a tissue-specific manner. While placental oxidative stress and lipotoxicity are hallmarks of placental dysfunction, the possible role of ferroptosis in placental dysfunction is largely unknown. We found that spontaneous preterm birth is associated with ferroptosis and that inhibition of GPX4 causes ferroptotic injury in primary human trophoblasts and during mouse pregnancy. Importantly, we uncovered a role for the phospholipase PLA2G6 (PNPLA9, iPLA2beta), known to metabolize Hp-PE to lyso-PE and oxidized fatty acid, in mitigating ferroptosis induced by GPX4 inhibition in vitro or by hypoxia/reoxygenation injury in vivo. Together, we identified ferroptosis signaling in the human and mouse placenta, established a role for PLA2G6 in attenuating trophoblastic ferroptosis, and provided mechanistic insights into the ill-defined placental lipotoxicity that may inspire PLA2G6-targeted therapeutic strategies.

Regulation of ALT-associated homology-directed repair by polyADP-ribosylation.

The synthesis of poly(ADP-ribose) (PAR) reconfigures the local chromatin environment and recruits DNA-repair complexes to damaged chromatin. PAR degradation by poly(ADP-ribose) glycohydrolase (PARG) is essential for progression and completion of DNA repair. Here, we show that inhibition of PARG disrupts homology-directed repair (HDR) mechanisms that underpin alternative lengthening of telomeres (ALT). Proteomic analyses uncover a new role for poly(ADP-ribosyl)ation (PARylation) in regulating the chromatin-assembly factor HIRA in ALT cancer cells. We show that HIRA is enriched at telomeres during the G2 phase and is required for histone H3.3 deposition and telomere DNA synthesis. Depletion of HIRA elicits systemic death of ALT cancer cells that is mitigated by re-expression of ATRX, a protein that is frequently inactivated in ALT tumors. We propose that PARylation enables HIRA to fulfill its essential role in the adaptive response to ATRX deficiency that pervades ALT cancers.

Live-cell imaging and analysis reveal cell phenotypic transition dynamics inherently missing in snapshot data.

Recent advances in single-cell techniques catalyze an emerging field of studying how cells convert from one phenotype to another, in a step-by-step process. Two grand technical challenges, however, impede further development of the field. Fixed cell-based approaches can provide snapshots of high-dimensional expression profiles but have fundamental limits on revealing temporal information, and fluorescence-based live-cell imaging approaches provide temporal information but are technically challenging for multiplex long-term imaging. We first developed a live-cell imaging platform that tracks cellular status change through combining endogenous fluorescent labeling that minimizes perturbation to cell physiology and/or live-cell imaging of high-dimensional cell morphological and texture features. With our platform and an A549 VIM-RFP epithelial-to-mesenchymal transition (EMT) reporter cell line, live-cell trajectories reveal parallel paths of EMT missing from snapshot data due to cell-cell dynamic heterogeneity. Our results emphasize the necessity of extracting dynamical information of phenotypic transitions from multiplex live-cell imaging.

Autocrine C-peptide protects INS1 ß cells against palmitic acid-induced oxidative stress in peroxisomes by inducing catalase.

AIMS: C-peptide, produced by pancreatic ß cells and co-secreted in the bloodstream with insulin, has antioxidant properties in glucose- and hydrogen peroxide (H2O2)-exposed INS1 ß cells. Palmitic acid, the most physiologically abundant long-chain free fatty acid in humans, is metabolized in peroxisomes of ß cells accumulating H2O2 that can lead to oxidative stress. Here, we tested the hypothesis that C-peptide protects ß cells from palmitic acid-induced stress by lowering peroxisomal H2O2. MATERIALS AND METHODS: We exposed INS1 ß cells to palmitic acid and C-peptide in the setting of increasing glucose concentration and tested for changes in parameters of stress and death. To study the ability of C-peptide to lower peroxisomal H2O2, we engineered an INS1 ß cell line stably expressing the peroxisomal-targeted H2O2 sensor HyPer, whose fluorescence increases with cellular H2O2. An INS1 ß cell line stably expressing a live-cell fluorescent catalase reporter was used to detect changes in catalase gene expression. RESULTS: C-peptide protects INS1 ß cells from the combined effect of palmitic acid and glucose by reducing peroxisomal H2O2 to baseline levels and increasing expression of catalase. CONCLUSIONS: In conditions of glucolipotoxicity, C-peptide increases catalase expression and reduces peroxisomal oxidative stress and death of INS1 ß cells. Maintenance of C-peptide secretion is a pro-survival requisite for ß cells in adverse conditions. Loss of C-peptide secretion would render ß cells more vulnerable to stress and death leading to secretory dysfunction and diabetes.

Ribosome-associated vesicles: A dynamic subcompartment of the endoplasmic reticulum in secretory cells.

The endoplasmic reticulum (ER) is a highly dynamic network of membranes. Here, we combine live-cell microscopy with in situ cryo-electron tomography to directly visualize ER dynamics in several secretory cell types including pancreatic ß-cells and neurons under near-native conditions. Using these imaging approaches, we identify a novel, mobile form of ER, ribosome-associated vesicles (RAVs), found primarily in the cell periphery, which is conserved across different cell types and species. We show that RAVs exist as distinct, highly dynamic structures separate from the intact ER reticular architecture that interact with mitochondria via direct intermembrane contacts. These findings describe a new ER subcompartment within cells.

Neurokinin-1 Receptor Signaling Is Required for Efficient Ca2+ Flux in T-Cell-Receptor-Activated T Cells.

Efficient Ca2+ flux induced during cognate T cell activation requires signaling the T cell receptor (TCR) and unidentified G-protein-coupled receptors (GPCRs). T cells express the neurokinin-1 receptor (NK1R), a GPCR that mediates Ca2+ flux in excitable and non-excitable cells. However, the role of the NK1R in TCR signaling remains unknown. We show that the NK1R and its agonists, the neuropeptides substance P and hemokinin-1, co-localize within the immune synapse during cognate activation of T cells. Simultaneous TCR and NK1R stimulation is necessary for efficient Ca2+ flux and Ca2+-dependent signaling that sustains the survival of activated T cells and helper 1 (Th1) and Th17 bias. In a model of contact dermatitis, mice with T cells deficient in NK1R or its agonists exhibit impaired cellular immunity, due to high mortality of activated T cells. We demonstrate an effect of the NK1R in T cells that is relevant for immunotherapies based on pro-inflammatory neuropeptides and its receptors.

RAD51AP1 Is an Essential Mediator of Alternative Lengthening of Telomeres.

Alternative lengthening of telomeres (ALT) is a homology-directed repair (HDR) mechanism of telomere elongation that controls proliferation in aggressive cancers. We show that the disruption of RAD51-associated protein 1 (RAD51AP1) in ALT+ cancer cells leads to generational telomere shortening. This is due to RAD51AP1's involvement in RAD51-dependent homologous recombination (HR) and RAD52-POLD3-dependent break induced DNA synthesis. RAD51AP1 KO ALT+ cells exhibit telomere dysfunction and cytosolic telomeric DNA fragments that are sensed by cGAS. Intriguingly, they activate ULK1-ATG7-dependent autophagy as a survival mechanism to mitigate DNA damage and apoptosis. Importantly, RAD51AP1 protein levels are elevated in ALT+ cells due to MMS21 associated SUMOylation. Mutation of a single SUMO-targeted lysine residue perturbs telomere dynamics. These findings indicate that RAD51AP1 is an essential mediator of the ALT mechanism and is co-opted by post-translational mechanisms to maintain telomere length and ensure proliferation of ALT+ cancer cells.

The Lysophosphatidylcholine Transporter MFSD2A Is Essential for CD8+ Memory T Cell Maintenance and Secondary Response to Infection.

Access to nutrients is critical for an effective T cell immune response to infection. Although transporters for sugars and amino acids have previously been described in the context of the CD8+ T cell immune response, the active transport of exogenous fatty acids has remained enigmatic. In this study, we discovered that the sodium-dependent lysophosphatidylcholine (LPC) transporter major facilitator superfamily domain containing 2A (MFSD2A) is upregulated on activated CD8+ T cells and is required for memory T cell maintenance. MFSD2A deficiency in mice resulted in decreased import of LPC esterified to long chain fatty acids into activated CD8+ T cells, and MFSD2A-deficient cells are at a competitive disadvantage resulting in reduced memory T cell formation and maintenance and reduced response to secondary infection. Mechanistically, import of LPCs was required to maintain T cell homeostatic turnover, which when lost resulted in a decreased memory T cell pool and thus a reduced secondary response to repeat infection.

Learn to segment single cells with deep distance estimator and deep cell detector.

Single cell segmentation is a critical and challenging step in cell imaging analysis. Traditional processing methods require time and labor to manually fine-tune parameters and lack parameter transferability between different situations. Recently, deep convolutional neural networks (CNN) treat segmentation as a pixel-wise classification problem and have become a general and efficient method for image segmentation. However, cell imaging data often possesses characteristics that adversely affect segmentation accuracy: absence of established training datasets, few pixels on cell boundaries, and ubiquitous blurry features. We developed a strategy that combines strengths of CNN and traditional watershed algorithm. First, we trained a CNN to learn Euclidean distance transform (EDT) of the mask corresponding to the input images (deep distance estimator). Next, we trained a faster R-CNN (Region with CNN) to detect individual cells in the EDT image (deep cell detector). Then, the watershed algorithm performed the final segmentation using the outputs of previous two steps. Tests on a library of fluorescence, phase contrast and differential interference contrast (DIC) images showed that both the combined method and various forms of the pixel-wise classification algorithm achieved similar pixel-wise accuracy. However, the combined method achieved significantly higher cell count accuracy than the pixel-wise classification algorithm did, with the latter performing poorly when separating connected cells, especially those connected by blurry boundaries. This difference is most obvious when applied to noisy images of densely packed cells. Furthermore, both deep distance estimator and deep cell detector converge fast and are easy to train.