Chronic Inflammation Permanently Reshapes Tissue-Resident Immunity in Celiac Disease.

Tissue-resident lymphocytes play a key role in immune surveillance, but it remains unclear how these inherently stable cell populations respond to chronic inflammation. In the setting of celiac disease (CeD), where exposure to dietary antigen can be controlled, gluten-induced inflammation triggered a profound depletion of naturally occurring Vγ4+/Vδ1+ intraepithelial lymphocytes (IELs) with innate cytolytic properties and specificity for the butyrophilin-like (BTNL) molecules BTNL3/BTNL8. Creation of a new niche with reduced expression of BTNL8 and loss of Vγ4+/Vδ1+ IELs was accompanied by the expansion of gluten-sensitive, interferon-γ-producing Vδ1+ IELs bearing T cell receptors (TCRs) with a shared non-germline-encoded motif that failed to recognize BTNL3/BTNL8. Exclusion of dietary gluten restored BTNL8 expression but was insufficient to reconstitute the physiological Vγ4+/Vδ1+ subset among TCRγδ+ IELs. Collectively, these data show that chronic inflammation permanently reconfigures the tissue-resident TCRγδ+ IEL compartment in CeD. VIDEO ABSTRACT.

Cab45 deficiency leads to the mistargeting of progranulin and prosaposin and aberrant lysosomal positioning.

The trans-Golgi Network (TGN) sorts molecular "addresses" and sends newly synthesized proteins to their destination via vesicular transport carriers. Despite the functional significance of packaging processes at the TGN, the sorting of soluble proteins remains poorly understood. Recent research has shown that the Golgi resident protein Cab45 is a significant regulator of secretory cargo sorting at the TGN. Cab45 oligomerizes upon transient Ca2+ influx, recruits soluble cargo molecules (clients), and packs them in sphingomyelin-rich transport carriers. However, the identity of client molecules packed into Cab45 vesicles is scarce. Therefore, we used a precise and highly efficient secretome analysis technology called hiSPECs. Intriguingly, we observed that Cab45 deficient cells manifest hypersecretion of lysosomal hydrolases. Specifically, Cab45 deficient cells secrete the unprocessed precursors of prosaposin (PSAP) and progranulin (PGRN). In addition, lysosomes in these cells show an aberrant perinuclear accumulation suggesting a new role of Cab45 in lysosomal positioning. This work uncovers a yet unknown function of Cab45 in regulating lysosomal function.

A study of genetic variants associated with skin traits in the Vietnamese population.

BACKGROUND: Most skin-related traits have been studied in Caucasian genetic backgrounds. A comprehensive study on skin-associated genetic effects on underrepresented populations such as Vietnam is needed to fill the gaps in the field. OBJECTIVES: We aimed to develop a computational pipeline to predict the effect of genetic factors on skin traits using public data (GWAS catalogs and whole-genome sequencing (WGS) data from the 1000 Genomes Project-1KGP) and in-house Vietnamese data (WGS and genotyping by SNP array). Also, we compared the genetic predispositions of 25 skin-related traits of Vietnamese population to others to acquire population-specific insights regarding skin health. METHODS: Vietnamese cohorts of whole-genome sequencing (WGS) of 1008 healthy individuals for the reference and 96 genotyping samples (which do not have any skin cutaneous issues) by Infinium Asian Screening Array-24 v1.0 BeadChip were employed to predict skin-associated genetic variants of 25 skin-related and micronutrient requirement traits in population analysis and correlation analysis. Simultaneously, we compared the landscape of cutaneous issues of Vietnamese people with other populations by assessing their genetic profiles. RESULTS: The skin-related genetic profile of Vietnamese cohorts was similar at most to East Asian cohorts (JPT: Fst = 0.036, CHB: Fst = 0.031, CHS: Fst = 0.027, CDX: Fst = 0.025) in the population study. In addition, we identified pairs of skin traits at high risk of frequent co-occurrence (such as skin aging and wrinkles (r = 0.45, p = 1.50e-5) or collagen degradation and moisturizing (r = 0.35, p = 1.1e-3)). CONCLUSION: This is the first investigation in Vietnam to explore genetic variants of facial skin. These findings could improve inadequate skin-related genetic diversity in the currently published database.

Seizure protein 6 controls glycosylation and trafficking of kainate receptor subunits GluK2 and GluK3.

Seizure protein 6 (SEZ6) is required for the development and maintenance of the nervous system, is a major substrate of the protease BACE1 and is linked to Alzheimer's disease (AD) and psychiatric disorders, but its molecular functions are not well understood. Here, we demonstrate that SEZ6 controls glycosylation and cell surface localization of kainate receptors composed of GluK2/3 subunits. Loss of SEZ6 reduced surface levels of GluK2/3 in primary neurons and reduced kainate-evoked currents in CA1 pyramidal neurons in acute hippocampal slices. Mechanistically, loss of SEZ6 in vitro and in vivo prevented modification of GluK2/3 with the human natural killer-1 (HNK-1) glycan, a modulator of GluK2/3 function. SEZ6 interacted with GluK2 through its ectodomain and promoted post-endoplasmic reticulum transport of GluK2 in the secretory pathway in heterologous cells and primary neurons. Taken together, SEZ6 acts as a new trafficking factor for GluK2/3. This novel function may help to better understand the role of SEZ6 in neurologic and psychiatric diseases.

Conveying the pathogenesis of type 1 diabetes to the blind, low-vision and diverse needs communities through sensory stimulation.

To educate members of the blind, low-vision and diverse needs communities on the pathogenesis of the chronic autoimmune disease, type 1 diabetes, members of our team with research expertise in immune-mediated diseases, participated in the 2023 Monash Sensory Science (MSS) Exhibition. Using QR code linked audio commentary, participants were guided through tactile displays demonstrating normal insulin action in the regulation of blood glucose levels and its vital role in providing energy to tissues, followed by displays describing the various stages of the immune system's aberrant attack and the eventual complete destruction of the insulin producing beta-cells of the pancreatic islets in type 1 diabetes. These models conveyed to the participants the huge effect that this autoimmune-mediated disease has on the quality of life of affected individuals including the subsequent lifelong reliance on insulin injections to maintain glucose homeostasis. This MSS Exhibition provided a unique opportunity for our researchers to engage with under-represented members of the community and to raise awareness about such a debilitating and common autoimmune disease.

Assessing polygenic risk score models for applications in populations with under-represented genomics data: an example of Vietnam.

Most polygenic risk score (PRS)models have been based on data from populations of European origins (accounting for the majority of the large genomics datasets, e.g. >78% in the UK Biobank and >85% in the GTEx project). Although several large-scale Asian biobanks were initiated (e.g. Japanese, Korean, Han Chinese biobanks), most other Asian countries have little or near-zero genomics data. To implement PRS models for under-represented populations, we explored transfer learning approaches, assuming that information from existing large datasets can compensate for the small sample size that can be feasibly obtained in developing countries, like Vietnam. Here, we benchmark 13 common PRS methods in meta-population strategy (combining individual genotype data from multiple populations) and multi-population strategy (combining summary statistics from multiple populations). Our results highlight the complementarity of different populations and the choice of methods should depend on the target population. Based on these results, we discussed a set of guidelines to help users select the best method for their datasets. We developed a robust and comprehensive software to allow for benchmarking comparisons between methods and proposed a computational framework for improving PRS performance in a dataset with a small sample size. This work is expected to inform the development of genomics applications in under-represented populations. PRSUP framework is available at: https://github.com/BiomedicalMachineLearning/VGP.

Gene expression differences associated with intrinsic hindfoot muscle loss in the jerboa, Jaculus jaculus.

Vertebrate animals that run or jump across sparsely vegetated habitats, such as horses and jerboas, have reduced the number of distal limb bones, and many have lost most or all distal limb muscle. We previously showed that nascent muscles are present in the jerboa hindfoot at birth and that these myofibers are rapidly and completely lost soon after by a process that shares features with pathological skeletal muscle atrophy. Here, we apply an intra- and interspecies differential RNA-Seq approach, comparing jerboa and mouse muscles, to identify gene expression differences associated with the initiation and progression of jerboa hindfoot muscle loss. We show evidence for reduced hepatocyte growth factor and fibroblast growth factor signaling and an imbalance in nitric oxide signaling; all are pathways that are necessary for skeletal muscle development and regeneration. We also find evidence for phagosome formation, which hints at how myofibers may be removed by autophagy or by nonprofessional phagocytes without evidence for cell death or immune cell activation. Last, we show significant overlap between genes associated with jerboa hindfoot muscle loss and genes that are differentially expressed in a variety of human muscle pathologies and rodent models of muscle loss disorders. All together, these data provide molecular insight into the process of evolutionary and developmental muscle loss in jerboa hindfeet.

Linearity assessment: deviation from linearity and residual of linear regression approaches.

In this computer simulation study, we examine four different statistical approaches of linearity assessment, including two variants of deviation from linearity (individual (IDL) and averaged (AD)), along with detection capabilities of residuals of linear regression (individual and averaged). From the results of the simulation, the following broad suggestions are provided to laboratory practitioners when performing linearity assessment. A high imprecision can challenge linearity investigations by producing a high false positive rate or low power of detection. Therefore, the imprecision of the measurement procedure should be considered when interpreting linearity assessment results. In the presence of high imprecision, the results of linearity assessment should be interpreted with caution. Different linearity assessment approaches examined in this study performed well under different analytical scenarios. For optimal outcomes, a considered and tailored study design should be implemented. With the exception of specific scenarios, both ADL and IDL methods were suboptimal for the assessment of linearity compared. When imprecision is low (3 %), averaged residual of linear regression with triplicate measurements and a non-linearity acceptance limit of 5 % produces <5 % false positive rates and a high power for detection of non-linearity of >70 % across different types and degrees of non-linearity. Detection of departures from linearity are difficult to identify in practice and enhanced methods of detection need development.

MiRNA research-The potential for understanding the multiple facets of anorexia nervosa.

Anorexia nervosa (AN) has a multifaceted and complex pathology, yet major gaps remain in our understanding of factors involved in AN pathology. MicroRNAs (miRNAs) play a regulatory role in translating genes into proteins and help understand and treat diseases. An extensive literature review on miRNAs with AN and comorbidities has uncovered a significant lack in miRNA research. To demonstrate the importance of understanding miRNA deregulation, we surveyed the literature on depression and obesity providing examples of relevant miRNAs. For AN, no miRNA sequencing or array studies have been found, unlike other psychiatric disorders. For depression and obesity, screenings and mechanistic studies were conducted, leading to clinical studies to improve understanding of their regulatory influences. MiRNAs are promising targets for studying AN due to their role as signaling molecules, involvement in psychiatric-metabolic axes, and potential as biomarkers. These characteristics offer valuable insights into the disease's etiology and potential new treatment options. The first miRNA-based treatment for rare metabolic disorders has been approved by the FDA and it is expected that these advancements will increase in the next decade. MiRNA research in AN is essential to examine its role in the development, manifestation, and progression of the disease. PUBLIC SIGNIFICANCE: The current understanding of the development and treatment of AN is insufficient. miRNAs are short regulatory sequences that influence the translation of genes into proteins. They are the subject of research in various diseases, including both metabolic and psychiatric disorders. Studying miRNAs in AN may elucidate their causal and regulatory role, uncover potential biomarkers, and allow for future targeted treatments.

Amphiphiles Formed from Synthetic DNA-Nanomotifs Mimic the Stepwise Dispersal of Transcriptional Clusters in the Cell Nucleus.

Stem cells exhibit prominent clusters controlling the transcription of genes into RNA. These clusters form by a phase-separation mechanism, and their size and shape are controlled via an amphiphilic effect of transcribed genes. Here, we construct amphiphile-nanomotifs purely from DNA, and we achieve similar size and shape control for phase-separated droplets formed from fully synthetic, self-interacting DNA-nanomotifs. Increasing amphiphile concentrations induce rounding of droplets, prevent droplet fusion, and, at high concentrations, cause full dispersal of droplets. Super-resolution microscopy data obtained from zebrafish embryo stem cells reveal a comparable transition for transcriptional clusters with increasing transcription levels. Brownian dynamics and lattice simulations further confirm that the addition of amphiphilic particles is sufficient to explain the observed changes in shape and size. Our work reproduces key aspects of transcriptional cluster formation in biological cells using relatively simple DNA sequence-programmable nanostructures, opening novel ways to control the mesoscopic organization of synthetic nanomaterials.

Trapping of a Polyketide Synthase Module after C-C Bond Formation Reveals Transient Acyl Carrier Domain Interactions.

Modular polyketide synthases (PKSs) are giant assembly lines that produce an impressive range of biologically active compounds. However, our understanding of the structural dynamics of these megasynthases, specifically the delivery of acyl carrier protein (ACP)-bound building blocks to the catalytic site of the ketosynthase (KS) domain, remains severely limited. Using a multipronged structural approach, we report details of the inter-domain interactions after C-C bond formation in a chain-branching module of the rhizoxin PKS. Mechanism-based crosslinking of an engineered module was achieved using a synthetic substrate surrogate that serves as a Michael acceptor. The crosslinked protein allowed us to identify an asymmetric state of the dimeric protein complex upon C-C bond formation by cryo-electron microscopy (cryo-EM). The possible existence of two ACP binding sites, one of them a potential "parking position" for substrate loading, was also indicated by AlphaFold2 predictions. NMR spectroscopy showed that a transient complex is formed in solution, independent of the linker domains, and photochemical crosslinking/mass spectrometry of the standalone domains allowed us to pinpoint the interdomain interaction sites. The structural insights into a branching PKS module arrested after C-C bond formation allows a better understanding of domain dynamics and provides valuable information for the rational design of modular assembly lines.

Crystal structures of pertussis toxin with NAD+ and analogs provide structural insights into the mechanism of its cytosolic ADP-ribosylation activity.

Bordetella pertussis is the causative agent of whooping cough, a highly contagious respiratory disease. Pertussis toxin (PT), a major virulence factor secreted by B. pertussis, is an AB5-type protein complex topologically related to cholera toxin. The PT protein complex is internalized by host cells and follows a retrograde trafficking route to the endoplasmic reticulum, where it subsequently dissociates. The released enzymatic S1 subunit is then translocated from the endoplasmic reticulum into the cytosol and subsequently ADP-ribosylates the inhibitory alpha-subunits (Gαi) of heterotrimeric G proteins, thus promoting dysregulation of G protein-coupled receptor signaling. However, the mechanistic details of the ADP-ribosylation activity of PT are not well understood. Here, we describe crystal structures of the S1 subunit in complex with nicotinamide adenine dinucleotide (NAD+), with NAD+ hydrolysis products ADP-ribose and nicotinamide, with NAD+ analog PJ34, and with a novel NAD+ analog formed upon S1 subunit crystallization with 3-amino benzamide and NAD+, which we name benzamide amino adenine dinucleotide. These crystal structures provide unprecedented insights into pre- and post-NAD+ hydrolysis steps of the ADP-ribosyltransferase activity of PT. We propose that these data may aid in rational drug design approaches and further development of PT-specific small-molecule inhibitors.

A DNA Segregation Module for Synthetic Cells.

The bottom-up construction of an artificial cell requires the realization of synthetic cell division. Significant progress has been made toward reliable compartment division, yet mechanisms to segregate the DNA-encoded informational content are still in their infancy. Herein, droplets of DNA Y-motifs are formed by liquid-liquid phase separation. DNA droplet segregation is obtained by cleaving the linking component between two populations of DNA Y-motifs. In addition to enzymatic cleavage, photolabile sites are introduced for spatio-temporally controlled DNA segregation in bulk as well as in cell-sized water-in-oil droplets and giant unilamellar lipid vesicles (GUVs). Notably, the segregation process is slower in confinement than in bulk. The ionic strength of the solution and the nucleobase sequences are employed to regulate the segregation dynamics. The experimental results are corroborated in a lattice-based theoretical model which mimics the interactions between the DNA Y-motif populations. Altogether, engineered DNA droplets, reconstituted in GUVs, can represent a strategy toward a DNA segregation module within bottom-up assembled synthetic cells.

Analysis of hyperforin (St. John's wort) action at TRPC6 channel leads to the development of a new class of antidepressant drugs.

St. John's wort is an herb, long used in folk medicine for the treatment of mild depression. Its antidepressant constituent, hyperforin, has properties such as chemical instability and induction of drug-drug interactions that preclude its use for individual pharmacotherapies. Here we identify the transient receptor potential canonical 6 channel (TRPC6) as a druggable target to control anxious and depressive behavior and as a requirement for hyperforin antidepressant action. We demonstrate that TRPC6 deficiency in mice not only results in anxious and depressive behavior, but also reduces excitability of hippocampal CA1 pyramidal neurons and dentate gyrus granule cells. Using electrophysiology and targeted mutagenesis, we show that hyperforin activates the channel via a specific binding motif at TRPC6. We performed an analysis of hyperforin action to develop a new antidepressant drug that uses the same TRPC6 target mechanism for its antidepressant action. We synthesized the hyperforin analog Hyp13, which shows similar binding to TRPC6 and recapitulates TRPC6-dependent anxiolytic and antidepressant effects in mice. Hyp13 does not activate pregnan-X-receptor (PXR) and thereby loses the potential to induce drug-drug interactions. This may provide a new approach to develop better treatments for depression, since depression remains one of the most treatment-resistant mental disorders, warranting the development of effective drugs based on naturally occurring compounds.

Impact of clinical pharmacist-led interventions on switching from intravenous-to-oral antibiotics in patients with infectious diseases at a Vietnamese hospital.

OBJECTIVES: To evaluate the impact of clinical pharmacist-led interventions on the switch from intravenous (IV) to oral (PO) antibiotics among inpatients with infectious diseases. METHODS: A before-and-after study was conducted among inpatients aged 18 or older who were diagnosed with infectious diseases and received IV antibiotics for at least 24 h at the Thong Nhat Hospital during the pre-intervention (between January 2021 and June 2021) and intervention (between January 2022 and June 2022) periods. Information on patient characteristics, antibiotic usage, length of hospital stay and treatment outcomes was obtained from medical records. The interventions included introducing IV-to-PO switch guidelines to physicians and clinical pharmacists' feedback on eligible cases. The impact of the pharmacists' interventions was evaluated by comparing primary outcomes (switch rate and appropriateness of switching) and secondary outcomes (duration of IV therapy, length of hospital stay and treatment outcomes) between the two study periods. RESULTS: We included 99 patients in the pre-intervention and 80 patients in the intervention period. The proportion of patients who switched from IV-to-PO antibiotics increased from 44.4% in the pre-intervention period to 67.8% in the intervention period (p = 0.008). The overall rate of appropriate conversion increased significantly from 43.8% to 67.5% (p = 0.043). There were no statistically significant differences between the two periods with respect to the median duration of IV therapy (9 days vs. 8 days), length of hospital stay (10 days vs. 9 days) and treatment outcomes. Logistic regression analysis showed that the interventions resulted in a higher switch rate, whereas age was negatively associated with the switching rate. CONCLUSIONS: The implementation of clinical pharmacist-led interventions was effective in promoting IV-to-PO antibiotic conversion.

Lot-to-lot variation and verification.

Lot-to-lot verification is an integral component for monitoring the long-term stability of a measurement procedure. The practice is challenged by the resource requirements as well as uncertainty surrounding experimental design and statistical analysis that is optimal for individual laboratories, although guidance is becoming increasingly available. Collaborative verification efforts as well as application of patient-based monitoring are likely to further improve identification of any differences in performance in a relatively timely manner. Appropriate follow up actions of failed lot-to-lot verification is required and must balance potential disruptions to clinical services provided by the laboratory. Manufacturers need to increase transparency surrounding release criteria and work closer with laboratory professionals to ensure acceptable reagent lots are released to end users. A tripartite collaboration between regulatory bodies, manufacturers, and laboratory medicine professional bodies is key to developing a balanced system where regulatory, manufacturing, and clinical requirements of laboratory testing are met, to minimize differences between reagent lots and ensure patient safety. Clinical Chemistry and Laboratory Medicine has served as a fertile platform for advancing the discussion and practice of lot-to-lot verification in the past 60 years and will continue to be an advocate of this important topic for many more years to come.

Method evaluation in the clinical laboratory.

Method evaluation is one of the critical components of the quality system that ensures the ongoing quality of a clinical laboratory. As part of implementing new methods or reviewing best practices, the peer-reviewed published literature is often searched for guidance. From the outset, Clinical Chemistry and Laboratory Medicine (CCLM) has a rich history of publishing methods relevant to clinical laboratory medicine. An insight into submissions, from editors' and reviewers' experiences, shows that authors still struggle with method evaluation, particularly the appropriate requirements for validation in clinical laboratory medicine. Here, we consider through a series of discussion points an overview of the status, challenges, and needs of method evaluation from the perspective of clinical laboratory medicine. We identify six key high-level aspects of clinical laboratory method evaluation that potentially lead to inconsistency. 1. Standardisation of terminology, 2. Selection of analytical performance specifications, 3. Experimental design of method evaluation, 4. Sample requirements of method evaluation, 5. Statistical assessment and interpretation of method evaluation data, and 6. Reporting of method evaluation data. Each of these areas requires considerable work to harmonise the practice of method evaluation in laboratory medicine, including more empirical studies to be incorporated into guidance documents that are relevant to clinical laboratories and are freely and widely available. To further close the loop, educational activities and fostering professional collaborations are essential to promote and improve the practice of method evaluation procedures.

Mutual association between family history of gastric and colorectal cancer and risk of gastric and colorectal cancer.

BACKGROUND AND AIM: We evaluated the associations between gastric cancer (GC) family history (FH) and colorectal cancer (CRC) risk and between CRC FH and GC/gastric adenoma risk. METHODS: We used data of participants who underwent national cancer screening between 2013 and 2014. Participants with GC or CRC FH in first-degree relatives (n = 1 172 750) and those without cancer FH (n = 3 518 250) were matched 1:3 by age and gender. RESULTS: Of the 1 172 750 participants with a FH, 871 104, 264 040, and 37 606 had FHs of only GC, only CRC, and both GC and CRC, respectively. The median follow-up time was 4.8 years. GC and CRC FHs were associated with increased GC and CRC risks, respectively. GC FH was associated with CRC risk (adjusted hazard ratio 1.05; 95% confidence interval [CI] 1.01-1.10), whereas CRC FH was not associated with the risk of GC or gastric adenoma. However, gastric adenoma risk increased 1.62-fold (95% CI 1.40-1.87) in participants with FHs of both GC and CRC, demonstrating a significant difference with the 1.39-fold (95% CI 1.34-1.44) increase in participants with only GC FH. Furthermore, GC risk increased by 5.32 times (95% CI 1.74-16.24) in participants with FHs of both GC and CRC in both parents and siblings. CONCLUSIONS: GC FH was significantly associated with a 5% increase in CRC risk. Although CRC FH did not increase GC risk, FH of both GC and CRC further increased the risk of gastric adenoma. FHs of GC and CRC may affect each other's neoplastic lesion risk.

Reprogramming of the heavy-chain CDR3 regions of a human antibody repertoire.

B cells have been engineered ex vivo to express an HIV-1 broadly neutralizing antibody (bNAb). B cell reprograming may be scientifically and therapeutically useful, but current approaches limit B cell repertoire diversity and disrupt the organization of the heavy-chain locus. A more diverse and physiologic B cell repertoire targeting a key HIV-1 epitope could facilitate evaluation of vaccines designed to elicit bNAbs, help identify more potent and bioavailable bNAb variants, or directly enhance viral control in vivo. Here we address the challenges of generating such a repertoire by replacing the heavy-chain CDR3 (HCDR3) regions of primary human B cells. To do so, we identified and utilized an uncharacterized Cas12a ortholog that recognizes PAM motifs present in human JH genes. We also optimized the design of 200 nucleotide homology-directed repair templates (HDRT) by minimizing the required 3'-5' deletion of the HDRT-complementary strand. Using these techniques, we edited primary human B cells to express a hemagglutinin epitope tag and the HCDR3 regions of the bNAbs PG9 and PG16. Those edited with bNAb HCDR3 efficiently bound trimeric HIV-1 antigens, implying they could affinity mature in vivo in response to the same antigens. This approach generates diverse B cell repertoires recognizing a key HIV-1 neutralizing epitope.

Support of deep learning to classify vocal fold images in flexible laryngoscopy.

PURPOSE: To collect a dataset with adequate laryngoscopy images and identify the appearance of vocal folds and their lesions in flexible laryngoscopy images by objective deep learning models. METHODS: We adopted a number of novel deep learning models to train and classify 4549 flexible laryngoscopy images as no vocal fold, normal vocal folds, and abnormal vocal folds. This could help these models recognize vocal folds and their lesions within these images. Ultimately, we made a comparison between the results of the state-of-the-art deep learning models, and another comparison of the results between the computer-aided classification system and ENT doctors. RESULTS: This study exhibited the performance of the deep learning models by evaluating laryngoscopy images collected from 876 patients. The efficiency of the Xception model was higher and steadier than almost the rest of the models. The accuracy of no vocal fold, normal vocal folds, and vocal fold abnormalities on this model were 98.90 %, 97.36 %, and 96.26 %, respectively. Compared to our ENT doctors, the Xception model produced better results than a junior doctor and was near an expert. CONCLUSION: Our results show that current deep learning models can classify vocal fold images well and effectively assist physicians in vocal fold identification and classification of normal or abnormal vocal folds.