bioRxiv Science⌕ Search

Biology subjects

Geng, L.

Publications and source records attributed to Geng, L..

16 recordsLinked to original sources

Gasdermin E couples mitochondrial damage to pyroptotic neurodegeneration in Parkinson disease

Parkinsons disease (PD) features progressive loss of nigrostriatal dopamine neurons, but how mitochondrial damage engages programmed cell death pathways remains unresolved. Here, we identify gasdermin E (GSDME), the caspase-3-activated executor of pyroptosis, as a critical mediator of neurodegeneration in toxin-based PD models. In primary neurons and SH-SY5Y cells, the mitochondrial complex I inhibitor MPTP/MPP triggered caspase-3 activation, GSDME cleavage, and lytic membrane rupture. Genetic silencing of Gsdme or its transcriptional regulator SP1 reduced neuronal death. In vivo, Gsdme deficiency preserved substantia nigra pars compacta dopaminergic neurons, improved motor performance, and mitigated anxiety- and depression-like behaviors after MPTP administration. Loss of Gsdme also dampened microglial and astrocytic activation and lowered proinflammatory cytokines in striatum and substantia nigra. Mechanistically, cleaved GSDME localized to mitochondria, disrupted membrane potential, increased reactive oxygen species, and precipitated organelle injury, thereby coupling mitochondrial dysfunction to pyroptotic cell death. These findings identify GSDME-mediated pyroptosis as a mechanistic link between mitochondrial toxicity and neuroinflammation in PD and nominate GSDME as a therapeutic entry point to slow disease progression. SignificanceHow mitochondrial injury kills dopamine neurons in Parkinsons disease is a central unresolved question. We show that the pyroptosis executor GSDME is required for neurodegeneration and neuroinflammation in MPTP models, mechanistically linking caspase-3 activation and mitochondrial damage to lytic cell death. Targeting GSDME may provide a strategy to protect vulnerable neurons in PD. Graphic Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=191 SRC="FIGDIR/small/694264v1_ufig1.gif" ALT="Figure 1"> View larger version (47K): org.highwire.dtl.DTLVardef@15364e7org.highwire.dtl.DTLVardef@57b65org.highwire.dtl.DTLVardef@1e85108org.highwire.dtl.DTLVardef@1200d34_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsGSDME drives PD-linked neuronal loss. Silencing GSDME (or its transcriptional factor Sp1) ameliorates MPTP-triggered neuronal cell death. Genetic ablation of Gsdme is protective in the MPTP-induced PD mouse model. Gsdme-/-mice retain nigrostriatal DA neurons, show improved motor and affective behaviors, and exhibit reduced microglial and astrocytic activation and cytokines release upon MPTP treatment. Cleaved GSDME accumulates on mitochondria, collapses {Delta}{Psi}m, raises ROS, and links mitochondrial toxicity to pyroptosis, thus positioning GSDME as a tractable target to slow PD progression.

neuroscience↗

BCKDK, a novel hypoxia-responsive kinase that exacerbates cerebral ischemia injury

Alterations of circulating amino acid profile have been observed in patients with ischemic stroke. However, whether ischemia disrupts amino acid metabolism in the brain tissue and subsequently potentiates cellular stress and cerebral injury have never been explored. Employing a metabolomics approach combined with metabolic flux analysis, impaired catabolism and significant enrichment of branched-chain amino acids (BCAAs) were identified in mouse primary neuron cells upon oxygen-glucose deprivation. Consistently, BCAA catabolism was also damaged in the brain of mouse with acute ischemic stroke, accompanied with suppressed activity of branched-chain alpha-keto acid dehydrogenase (BCKDH) and upregulation of BCKDH kinase (BCKDK). Furthermore, restoration of BCAA catabolism by suppressing BCKDK via pharmacological inhibitor or silencing RNA dramatically alleviated cerebral ischemia injury in mice. Mechanistically, ischemia induces the expression of BCKDK via hypoxia-inducible factor 1-mediated transcriptional activation and inhibits BCAA conversion into substrates for tricarboxylic acid cycle, contributing to potentiated energy deficiency, glutamate excitotoxicity, and neuronal injury. Collectively, this study identified BCKDK as a novel hypoxia-responsive factor and a promising therapeutic target for cerebral ischemia injury.

molecular biology↗

Peptides alleviate cognitive impairment by inhibiting and disassembling amyloid-beta aggregates in Alzheimer disease

Alzheimers disease (AD) is a devasting neurodegenerative disorder characterized by {beta}-amyloid formation, further exacerbated by RIPK1/RIPK3 necrosome-induced programmed necrosis (necroptosis). We previously showed that the RIPK1/RIPK3 necrosome forms a functional amyloid complex using its RIP homotypic interaction motifs (RHIMs). Here, we discovered that the core RIPK1/RIPK3 necrosome shares strikingly structural similarity to the C-terminal region of {beta}-amyloid (A{beta}42), and the RHIM-derived tetrapeptides (IQIG or VQVG) directly inhibit A{beta} aggregation, disassemble preformed A{beta} fibrils (PFFs), and reduce RIPK1 polymerization. Also, the peptides exhibit effective membrane permeability and could reduce A{beta}40 or A{beta}42-induced neural death and TNF-induced necroptosis in SH-SY5Y cells. IQIG and VQVG injected by ICV increase learning and memory abilities by reducing A{beta} plaques and hyperphosphorylated tau in the cortex and hippocampus of APP/PS1 double-transgenic mice. Mechanistically, the peptides directly interact with A{beta} to block A{beta} aggregation and alleviate microglia-mediated neuroinflammation. Strikingly, single-cell RNA sequencing revealed that the peptides-treated AD transgenic mice restored neuronal homeostasis with increased GABAergic neurons and decreased glutamatergic neurons. Furthermore, total cell-cell interaction strength increased while the AD risk gene Apoe expression decreased in the specific oligodendrocyte subtype of peptides-treated AD mice. Thus, our findings revealed that the peptides could improve cognition and memory capabilities and serve as promising structural templates for potential drugs against AD.

neuroscience↗

Proteomic analysis of exosomes from lymphatic affluents reveals their implications in developing premetastatic niche in melanoma.

Melanoma is an aggressive form of skin cancer that often spreads via lymphatic pathways to regional and distant sites. Melanoma-derived lymphatic exosomes play a crucial role in forming a tumor-supportive environment for metastasis, or premetastatic niche, within the first tumor draining lymph node, also known as the sentinel lymph node (SLN). Therefore, analyzing the proteomic content of tumor-draining lymphatic exosomes that deliver oncogenic molecules to the SLN is important in understanding the premetastatic niche. To reveal the proteomic landscape of lymphatic exosomes, we performed multidimension liquid chromatography-tandem mass spectrometry with multiplexing (18-samples) using tandem mass tag (TMT) labeling to profile the lymphatic exosomal proteomes obtained from afferent lymphatic channels leading to the SLN of patients with melanoma (n=6), control afferent lymphatic channels from prophylactic mastectomy (n=3) and non-cancer post-operative lymphatic fluid (n=9). Lymphatic fluid from postoperative lymphadenectomy drains served as another control to filter out non-melanoma alteration in lymph that may be related to the procedure of surgical resection and wound healing process. Our proteomic analysis identified 3929 proteins in the lymphatic exosomes, of which 968 were unique proteins absent from the current exosomal database. Interestingly, melanoma lymphatic exosomes possess distinctive proteomic cargo, which is significantly associated with cancer-associated and cellular structural remodeling pathways (FDR <0.05). Moreover, proinflammatory wound healing pathways are predominantly present in melanoma and postoperative lymph fluid compared to normal control afferent lymphatic channels. We identified a total of 17 uniquely modulated proteins in melanoma compared to control and postoperative lymph, which are critically involved in the process of melanoma tumorigenesis. At least ten upregulated proteins strongly correlate with each other at the gene expression levels in melanoma tumors compared to controls and may serve as a signature panel for melanoma (p = 2.13 x 10-58). In summary, this study represents the first comparative analysis of the lymphatic exosomal proteome and highlights distinct exosomal proteins that may support premetastatic niche formation in the SLN.

cancer biology↗

The Mycobacterium tuberculosis ESX effector promotes pyroptosis-dependent pathogenicity and dissemination

O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=126 SRC="FIGDIR/small/653593v1_ufig1.gif" ALT="Figure 1"> View larger version (43K): org.highwire.dtl.DTLVardef@8cd5e5org.highwire.dtl.DTLVardef@2ec22forg.highwire.dtl.DTLVardef@1ceb773org.highwire.dtl.DTLVardef@6dfba4_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOGraphic AbstractC_FLOATNO C_FIG Mycobacterium tuberculosis (Mtb) remains a major global health threat, partly due to the extensive cytotoxicity induced during infection. Although GSDMD-mediated excessive pyroptosis promotes pathogen dissemination and tissue damage in tuberculosis, the mechanism remains poorly understood. Here, we identify the effector EccB5, a component of the Mtb ESX-5 secretion system, as a key driver of pyroptosis and hyperinflammatory responses. EccB5 enhances Mtb virulence by inducing pyroptosis of macrophages, promoting bacterial dissemination and exacerbating lung pathology. Conditional knockdown EccB5 increases host cell viability. Mechanistically, EccB5 directly interacts with GSDMD, strengthens its association with caspase-1, and facilitates caspase-1-mediated cleavage of GSDMD both in vitro and in vivo. In summary, our findings uncover a precise mechanism by which Mtb modulates host responses and advances its pathogenicity.

microbiology↗

Simultaneous, real-time tracking of many neuromodulatory signals with Multiplexed Optical Recording of Sensors on a micro-Endoscope

Dozens of extracellular molecules jointly impact a given neuron, yet we lack methods to simultaneously record many such signals in real time. We developed a probe to track ten or more neuropeptides and neuromodulators using spatial multiplexing of genetically encoded fluorescent sensors. Cultured cells expressing one sensor at a time are immobilized at the front of a gradient refractive index (GRIN) lens for 3D two-photon imaging in vitro and in vivo. The sensor identity and detection sensitivity of each cell are determined via robotic dipping of the probe into wells containing various ligands and concentrations. Using this probe, we detected stimulation-evoked release of multiple neuromodulators in acute brain slices. We also tracked endogenous and drug-evoked changes in cerebrospinal fluid composition in the awake mouse lateral ventricle, which triggered downstream activation of the choroid plexus epithelium. Our approach offers a first step towards quantitative, real-time, high-dimensional tracking of brain fluid composition.

neuroscience↗

Mitoxantrone inhibits and downregulates ERα through binding at the DBD-LBD interface

Targeting the estrogen receptor (ER or ER) through competitive antagonists, receptor downregulators, or estrogen synthesis inhibition remains the primary therapeutic strategy for luminal breast cancer. We have identified a novel mechanism of ER inhibition by targeting the critical interface between its DNA-binding domain (DBD) and ligand-binding domain (LBD). We demonstrate that mitoxantrone (MTO), a topoisomerase II inhibitor, binds at this previously unexplored DBD-LBD interface. Using comprehensive computational, biophysical, biochemical, and cellular analyses, we show that independent of its DNA damage response activity, MTO binding induces distinct conformational changes in ER, leading to its cytoplasmic redistribution and subsequent proteasomal degradation. Notably, MTO effectively inhibits clinically relevant ER mutations (Y537S and D538G) that confer resistance to current endocrine therapies, outperforming fulvestrant in both in vitro and in vivo assays. Our findings establish domain-domain interaction targeting as a viable therapeutic strategy for ER, with translational implications for other nuclear receptors.

cancer biology↗

Red-shifted GRAB acetylcholine sensors for multiplex imaging in vivo

The neurotransmitter acetylcholine (ACh) is essential in both the central and peripheral nervous systems. Recent studies highlight the significance of interactions between ACh and various neuromodulators in regulating complex behaviors. The ability to simultaneously image ACh and other neuromodulators can provide valuable information regarding the mechanisms underlying these behaviors. Here, we developed a series of red fluorescent G protein-coupled receptor activation-based (GRAB) ACh sensors, with a wide detection range and expanded spectral profile. The high-affinity sensor, rACh1h, reliably detects ACh release in various brain regions, including the nucleus accumbens, amygdala, hippocampus, and cortex. Moreover, rACh1h can be co-expressed with green fluorescent sensors in order to record ACh release together with other neurochemicals in various behavioral contexts using fiber photometry and two-photon imaging, with high spatiotemporal resolution. These new ACh sensors can therefore provide valuable new insights regarding the functional role of the cholinergic system under both physiological and pathological conditions.

neuroscience↗

RING1 dictates GSDMD-mediated inflammatory response and host susceptibility to pathogen infection

RING1 is an E3 ligase component of the polycomb repressive complex 1 (PRC1) with known roles in chromatin regulation and cellular processes such as apoptosis and autophagy. However, its involvement in inflammation and pyroptosis needs to be better characterized. Here, we found that human RING1, but not RING2, promoted K48-linked ubiquitination of Gasdermin D (GSDMD) and acted as a negative regulator of pyroptosis and bacterial infection. Ring1 knockout mice increased the bacterial loads and mortality rate by treatment of S. typhimurium. Upon infection by M. tuberculosis (Mtb) H37Rv strain, RING1 deletion initially reduced bacterial loads but later increased lung inflammation and impaired immune defense responses in mice. Also, Ring1 knockout exacerbated acute sepsis induced by lipopolysaccharide (LPS). Mechanistically, RING1 directly interacts with GSDMD and ubiquitinates the K51 and K168 sites of GSDMD for K48-linked proteasomal degradation, thereby inhibiting pyroptosis. Inhibition of RING1 E3 ligase activity by mutation or small molecular compound increased GSDMD level and cell death during pyroptosis. Our findings reveal that RING1 dictates GSDMD-mediated inflammatory response and host susceptibility to pathogen infection, highlighting RING1 as a potential therapeutic target for combating infectious diseases. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=115 SRC="FIGDIR/small/622030v1_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@e6d4a6org.highwire.dtl.DTLVardef@92f137org.highwire.dtl.DTLVardef@11a69c4org.highwire.dtl.DTLVardef@115dc0b_HPS_FORMAT_FIGEXP M_FIG Graphic Abstract C_FIG HighlightsO_LIE3 ubiquitin ligase RING1 targets GSDMD for proteasomal degradation. C_LIO_LIMice lacking RING1 are more vulnerable to S. typhimurium infection and LPS- induced sepsis. C_LIO_LIIn the early stages of M. tuberculosis (Mtb) infection, Ring1-/- mice exhibit efficient bacterial clearance. C_LIO_LIChronic inflammation in Ring1-/- mice impairs the ability to control Mtb in the late stages of infection. C_LI

cell biology↗

Functional Activity, Functional Connectivity and Complex Network Biomarkers of Progressive Hyposmia Parkinson's Disease with No Cognitive Impairment: Evidences from Resting-state fMRI Study

BackgroundOlfactory dysfunction stands as one of the most prevalent non-motor symptoms in the initial stage of Parkinsons disease (PD). Nevertheless, the intricate mechanisms underlying olfactory deficits in Parkinsons disease still remain elusive. MethodsThis study collected rs-fMRI data from 30 PD patients (15 with severe hyposmia (PD-SH) and 15 with no/mild hyposmia (PD-N/MH)) and 15 healthy controls (HC). To investigate functional segregation, the amplitude of low-frequency fluctuation (ALFF) and regional homogeneity (ReHo) were utilized. Functional connectivity (FC) analysis was performed to explore the functional integration across diverse brain regions. Additionally, the graph theory-based network analysis was employed to assess functional networks in PD patients. Furthermore, Pearson correlation analysis was conducted to delve deeper into the relationship between the severity of olfactory dysfunction and various functional metrics. ResultsFirstly, PD patients showed significantly higher ALFF values in the superior temporal gyrus compared to HC, especially in the PD-SH group versus PD-N/MH. Meanwhile, ALFF values in this region negatively correlated with olfactory testing scores. Secondly, PD patients had higher ReHo in middle temporal gyrus and superior frontal gyrus than HC, especially PD-SH. Meanwhile, olfactory scores negatively correlated with these ReHo values. Thirdly, we observed a negative correlation between superior cerebellar-insula connectivity and olfactory scores, suggesting a neural circuit link to olfactory dysfunction. Lastly, the PD patients brain networks consistently showed small-world attributes, with the PD-N/MH group having significantly higher nodal betweenness in the superior cerebellum than the PD-SH group. Theres also a positive link between superior cerebellums betweenness and olfactory scores. Additionally, there is a notable difference in the node degree of the superior temporal gyrus when comparing the PD-SH group to the PD-N/MH group. ConclusionUsing fMRI, our study analyzed brain function in PD-SH, PD-N/MH, and HC groups, revealing impaired segregation and integration in PD-SH and PD-N/MH. We hypothesize that changes in temporal, frontal, occipital, and cerebellar activities, along with aberrant cerebellum-insula connectivity and node degree and betweenness disparities, may be linked to olfactory dysfunction in PD patients.

neuroscience↗

APLNR marks a cardiac progenitor derived with human induced pluripotent stem cells

Cardiomyocytes can be readily derived from human induced pluripotent stem cell (hiPSC) lines, yet its efficacy varies across different batches of the same and different hiPSC lines. To unravel the inconsistencies of in vitro cardiac differentiation, we utilized single cell transcriptomics on hiPSCs undergoing cardiac differentiation and identified cardiac and extra-cardiac lineages throughout differentiation. We further identified APLNR as a surface marker for in vitro cardiac progenitors and immunomagnetically isolated them. Differentiation of isolated in vitro APLNR+ cardiac progenitors derived from multiple hiPSC lines resulted in predominantly cardiomyocytes accompanied with cardiac mesenchyme. Transcriptomic analysis of differentiating in vitro APLNR+ cardiac progenitors revealed transient expression of cardiac progenitor markers before further commitment into cardiomyocyte and cardiac mesenchyme. Analysis of in vivo human and mouse embryo single cell transcriptomic datasets have identified APLNR expression in early cardiac progenitors of multiple lineages. This platform enables generation of in vitro cardiac progenitors from multiple hiPSC lines without genetic manipulation, which has potential applications in studying cardiac development, disease modelling and cardiac regeneration.

cell biology↗

Protective effect of plasma neutralization from prior SARS-CoV-2 Omicron infection against BA.5 subvariant symptomatic reinfection

From December 2022 to January 2023, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections caused by BA.5 and BF.7 subvariants of B.1.1.529 (Omicron) swept across mainland China. It is crucial to estimate the protective effect of the neutralizing antibodies generated by such mass infections against the next potential SARS-CoV-2 reinfection wave, especially if driven by CH.1.1 or XBB.1.5. Previously, we recruited and continuously followed a cohort of individuals that experienced Omicron BA.1, BA.2, and BA.5 breakthrough infections, as well as a control cohort with no history of SARS-CoV-2 infection. In the previously uninfected cohort, the total symptomatic infection rate surveyed during the outbreak was 91.6%, while the symptomatic reinfection rate was 32.9%, 10.5%, and 2.8% among individuals with prior Omicron BA.1, BA.2 and BA.5 infection, respectively, with median intervals between infections of 335, 225 and 94 days. Pseudovirus neutralization assays were performed in plasma samples collected from previously Omicron BA.1-infected individuals approximately 3 months before the outbreak. Results indicate a robust correlation between the plasma neutralizing antibody titers and the protective effect against symptomatic reinfection. The geometric mean of the 50% neutralizing titers (NT50) against D614G, BA.5, and BF.7 were 2.0, 2.5, and 2.3-fold higher in individuals without symptomatic reinfection than in those with symptomatic reinfection (p < 0.01). Low plasma neutralizing antibody titer (below the geometric mean of NT50) was associated with an enhanced cumulative risk of symptomatic reinfection, with a hazard ratio (HR) of 23.55 (95% CI: 9.23-60.06) against BF.7 subvariant. Importantly, neutralizing antibodies titers post one month after BF.7/BA.5 breakthrough infections against CH.1.1 and XBB.1.5 are similar to that against BF.7 from individuals with prior BA.1 infection while not experiencing a symptomatic BF.7/BA.5 reinfection (plasma collected 3 months before the outbreak), suggesting that the humoral immunity generated by the current BF.7/BA.5 breakthrough infection may provide protection against CH.1.1 and XBB.1.5 symptomatic reinfection wave for 4 months. Of note, the higher hACE2 binding of XBB.1.5 may reduce the protection period since the potential increase of infectivity.

immunology↗

A toolkit of highly selective and sensitive genetically encoded neuropeptide sensors

Neuropeptides are key signaling molecules in the endocrine and nervous systems that regulate many critical physiological processes, including energy balance, sleep and circadian rhythms, stress, and social behaviors. Understanding the functions of neuropeptides in vivo requires the ability to monitor their dynamics with high specificity, sensitivity, and spatiotemporal resolution; however, this has been hindered by the lack of direct, sensitive and non-invasive tools. Here, we developed a series of GRAB (G protein-coupled receptor activation-based) sensors for detecting somatostatin (SST), cholecystokinin (CCK), corticotropin-releasing factor (CRF), neuropeptide Y (NPY), neurotensin (NTS), and vasoactive intestinal peptide (VIP). These fluorescent sensors utilize the corresponding GPCRs as the neuropeptide-sensing module with the insertion of a circular-permutated GFP as the optical reporter. This design detects the binding of specific neuropeptides at nanomolar concentration with a robust increase in fluorescence. We used these GRAB neuropeptide sensors to measure the spatiotemporal dynamics of endogenous SST release in isolated pancreatic islets and to detect the release of both CCK and CRF in acute brain slices. Moreover, we detect endogenous CRF release induced by stressful experiences in vivo using fiber photometry and 2-photon imaging in mice. Together, these new sensors establish a robust toolkit for studying the release, function, and regulation of neuropeptides under both physiological and pathophysiological conditions.

neuroscience↗

Compartmental Neuropeptide Release Measured Using a New Oxytocin Sensor

As a peptide hormone and neuromodulator, oxytocin (OT) plays a critical role in a variety of physiological and pathophysiological processes in both the central nervous system and the periphery. However, the processes that regulate spatial OT release in the brain remain enigmatic. Here, we developed a genetically encoded GPCR activation-based (GRAB) OT sensor called GRABOT1.0. Using this sensor, we directly visualized stimulation-induced OT release from specific compartments of OT neurons in acute brain slices, and discovered that N-type calcium channels predominantly mediate axonal OT release, while L-type calcium channels mediate somatodendritic OT release. In addition, we found that components in the fusion machinery of OT release differ between axon terminals versus somata and dendrites. Finally, we demonstrated the sensor responses to the activation of OT neurons in various brain regions in vivo and revealed region specific OT release during male courtship behavior. Taken together, these results provide key insights regarding the role of compartmental OT release in the control of physiological and behavioral functions.

neuroscience↗

Circularly permuted LOV domain as an engineering module for optogenetic tools

We re-engineered a commonly-used light-sensing protein, LOV domain, using a circular permutation strategy to allow photoswitchable control of the C-terminus of a peptide. We demonstrate that the use of circularly permuted LOV domain on its own or together with the original LOV could expand the engineering capabilities of optogenetic tools.

synthetic biology↗

Morphologic Classification and Automatic Nugent Scoring of Bacterial Vaginosis by Deep Neural Networks

BackgroundBacterial vaginosis (BV) was the most common condition for womens health caused by the disruption of normal vaginal flora and an overgrowth of certain disease-causing bacteria, affecting 30-50% of women at some time in their lives. Gram stain followed by Nugent scoring (NS) based on bacterial morphotypes under the microscope was long considered golden standard for BV diagnosis. This conventional manual method was often considered labor intensive, time consuming, and variable results from person to person. MethodsWe developed four convolutional neural networks (CNN) models, and evaluated their ability to automatic identify vaginal bacteria and classify Nugent scores from microscope images. All the CNN models were first trained with 23280 microscopic images labeled with Nugent scores from top experts. A separate set of 5815 images were evaluated by the CNN models. The best CNN model was selected to generalize its application on an independent sets of 1082 images collecting from three teaching hospitals. Different hardwares were used to take images in hospitals. ResultsOur model could classify three Nugent Scores from images with high three classification accuracy of 89.3% (with 82.4% sensitivity and 96.6% specificity) on the 5815 test images, which was better diagnostic yield than the top-level technologists and obstetricians in China. The ability of generalization for our model was strong that it obtained 75.1%, which was 6.6% higher than the average of technologists. ConclusionThe CNN model over performed human healthcare practitioners on accuracy, efficiency and stability for BV diagnosis using microscopic image-based Nugent scores. The deep learning model may offer translational application in automating diagnosis of bacterial vaginosis with proper supporting hardware.

microbiology↗