Promoting Photocatalytic Direct C-H Difluoromethylation of Heterocycles using Synergistic Dual-Active-Centered Covalent Organic Frameworks.

Difluoromethylation reactions are increasingly important for the creation of fluorine-containing heterocycles, which are core groups in a diverse range of biologically and pharmacologically active ingredients. Ideally, this typically challenging reaction could be performed photocatalytically under mild conditions. To achieve this separation of redox processes would be required for the efficient generation of difluoromethyl radicals and the reduction of oxygen. A covalent organic framework photocatalytic material was, therefore, designed with dual reactive centers. Here, anthracene was used as a reduction site and benzothiadiazole was used as an oxidation site, distributed in a tristyryl triazine framework. Efficient charge separation was ensured by the superior electron-donating and -accepting abilities of the dual centers, creating long-lived photogenerated electron-hole pairs. Photocatalytic difluoromethylation of 16 compounds with high yields and remarkable functional group tolerance was demonstrated; compounds included bioactive molecules such as xanthine and uracil. The structure-function relationship of the dual-active-center photocatalyst was investigated through electron spin resonance, femtosecond transient absorption spectroscopy, and density functional theory calculations.

Innate immune response to SARS-CoV-2 infection contributes to neuronal damage in human iPSC-derived peripheral neurons.

Severe acute respiratory coronavirus 2 (SARS-CoV-2) causes neurological disease in the peripheral and central nervous system (PNS and CNS, respectively) of some patients. It is not clear whether SARS-CoV-2 infection or the subsequent immune response are the key factors that cause neurological disease. Here, we addressed this question by infecting human induced pluripotent stem cell-derived CNS and PNS neurons with SARS-CoV-2. SARS-CoV-2 infected a low number of CNS neurons and did not elicit a robust innate immune response. On the contrary, SARS-CoV-2 infected a higher number of PNS neurons. This resulted in expression of interferon (IFN) λ1, several IFN-stimulated genes and proinflammatory cytokines. The PNS neurons also displayed alterations characteristic of neuronal damage, as increased levels of sterile alpha and Toll/interleukin receptor motif-containing protein 1, amyloid precursor protein and α-synuclein, and lower levels of cytoskeletal proteins. Interestingly, blockade of the Janus kinase and signal transducer and activator of transcription pathway by Ruxolitinib did not increase SARS-CoV-2 infection, but reduced neuronal damage, suggesting that an exacerbated neuronal innate immune response contributes to pathogenesis in the PNS. Our results provide a basis to study coronavirus disease 2019 (COVID-19) related neuronal pathology and to test future preventive or therapeutic strategies.

Versatile Deep Learning Pipeline for Transferable Chemical Data Extraction.

Chemical information disseminated in scientific documents offers an untapped potential for deep learning-assisted insights and breakthroughs. Automated extraction efforts have shifted from resource-intensive manual extraction toward applying machine learning methods to streamline chemical data extraction. While current extraction models and pipelines have ushered in notable efficiency improvements, they often exhibit modest performance, compromising the accuracy of predictive models trained on extracted data. Further, current chemical pipelines lack both transferability─where a model trained on one task can be adapted to another relevant task with limited examples─and extensibility, which enables seamless adaptability for new extraction tasks. Addressing these gaps, we present ChemREL, a versatile chemical data extraction pipeline emphasizing performance, transferability, and extensibility. ChemREL utilizes a custom, diverse data set of chemical documents, labeled through an active learning strategy to extract two properties: normal melting point and lethal dose 50 (LD50). The normal melting point is selected for its prevalence in diverse contexts and wider literature, serving as the foundation for pipeline training. In contrast, LD50 evaluates the pipeline's transferability to an unrelated property, underscoring variance in its biological nature, toxicological context, and units, among other differences. With pretraining and fine-tuning, our pipeline outperforms existing methods and GPT-4, achieving F1-scores of 96.1% for entity identification and 97.0% for relation mapping, culminating in an overall F1-score of 95.4%. More importantly, ChemREL displays high transferability, effectively transitioning from melting point extraction to LD50 extraction with 10 randomly selected training documents. Released as an open-source package, ChemREL aims to broaden access to chemical data extraction, enabling the construction of expansive relational data sets that propel discovery.

Proline-Functionalized Magnetic Nanoparticles as Highly Performing Asymmetric Catalysts.

Amino acids have a crucial role in the field of asymmetric organocatalysis for the production of chiral compounds with high added value and specific biological activity. In particular, proline offers high activity and stereoselectivity for catalyzing aldol reactions in organic solvents. However, proline-based catalysts often lack water-solubility, accessibility, catalytic performance, or recovery in aqueous media. This work reports the design of proline-functionalized poly(methyl methacrylate) (PMMA) nanoparticles with a magnetic core that offer high availability of chiral units in water and high recyclability. A proline-based copolymerizable surfactant is designed and integrated onto the surface of PMMA nanoparticles through a miniemulsion polymerization process without using additional surfactants. The miniemulsion technique allows the incorporation of magnetite to the system to create a magnetically separable catalyst. The chiral nanocatalyst presents a high diastereoselective catalytic activity for the intermolecular aldol reaction between p-nitrobenzaldehyde and cyclohexanone in water.

A Survey of Resistance Training Practices Among Physique Competitors During Peak Week.

ABSTRACT: Homer, KA, Cross, MR, and Helms, ER. A survey of resistance training practices among physique competitors during peak week. J Strength Cond Res XX(X): 000-000, 2024-Physique athletes are ranked by their on-stage presentation of muscle size, proportionality, and leanness. To acutely maximize muscle size, competitors manipulate resistance training (RT) variables in the days before the contest, commonly referred to as peak week (PW). Resistance training manipulations during PW may act synergistically with nutrition strategies such as carbohydrate loading. However, because little information exists on changes made to RT during PW, the purpose of this research was to determine the current practices of physique athletes and whether competitor characteristics were predictive of the RT variables manipulated. A total of 104 responses to the RT section of a survey on PW nutrition and training were analyzed through a series of multiple logistic regression models to examine the relationship between RT manipulations and competitor characteristics. Furthermore, to determine the magnitude of differences between PW and the week before PW (WBPW) for these variables, a McNemar-Bowker test, paired t-tests, and Wilcoxon signed-rank tests were conducted for nominal, continuous, and discrete outcomes, respectively. For all statistical analyses, p <0.05 was deemed significant. Competitors generally adjusted RT in a variety of ways, where proximity-to-failure was the most frequently manipulated and training frequency was the least; however, no competitor characteristic predicted any of the RT variables manipulated. Within those who manipulated RT variables during PW, frequency, volume, and intensity decreased while repetition ranges of compound exercises increased, empirically confirming that competitors seek to reduce training stress during PW. Such findings can be incorporated in future experimental designs examining the efficacy of peaking strategies to enhance the generalizability of results.

Triazine Frameworks for the Photocatalytic Selective Oxidation of Toluene.

Investigations into the selective oxidation of inert sp3 C-H bonds using polymer photocatalysts under mild conditions have been limited. Additionally, the structure-activity relationship of photocatalysts often remains insufficiently explored. Here, a series of thiophene-based covalent triazine frameworks (CTFs) are used for the efficient and selective oxidation of hydrocarbons to aldehydes or ketones under ambient aerobic conditions. Spectroscopic methods conducted in situ and density functional theory (DFT) calculations revealed that the sulfur atoms within the thiophene units play a pivotal role as oxidation sites due to the generation of photogenerated holes. The effect of photogenerated holes on photocatalytic toluene oxidation was investigated by varying the length of the spacer in a CTF donor-acceptor based photocatalyst. Furthermore, the manipulation of reactive oxygen species was employed to enhance selectivity by weakening the peroxidative capacity. As an illustrative example, this study successfully demonstrated the synthesis of a precursor of the neurological drug AMG-579 using a photocatalytic protocol.

Direct Synthesis of 1-Butanol with High Faradaic Efficiency from CO2 Utilizing Cascade Catalysis at a Ni-Enhanced (Cr2O3)3Ga2O3 Electrocatalyst.

Electrochemical transformation of CO2 into energy-dense liquid fuels provides a viable solution to challenges regarding climate change and nonrenewable resource dependence. Here, we report on the modification of a Cr-Ga oxide electrocatalyst through the introduction of nickel to generate a catalyst that generates 1-butanol at unprecedented faradaic efficiencies (ξ = 42%). This faradaic efficiency occurs at -1.48 V vs Ag/AgCl, with 1-butanol production commencing at an overpotential of 320 mV. At this potential, minor products include formate, methanol, acetic acid, acetone, and 3-hydroxybutanal. At -1.0 and -1.4 V, 3-hydroxybutanal becomes the primary product. This is in contrast to the nickel-free (Cr2O3)3(Ga2O3) system, where neither 3-hydroxybutanal nor 1-butanol was detected. Mechanistic studies show that formate is the initial CO2 reduction product and identify acetaldehyde as the key intermediate. Nickel is found responsible for the coupling and reduction of acetaldehyde to generate the higher molecular weight carbon products observed. To the best of our knowledge, this is the first electrocatalyst to generate 1-butanol with high faradaic efficiency.

Visible-Light-Promoted Switchable Selective Oxidations of Styrene Over Covalent Triazine Frameworks in Water.

Using photocatalytic oxidation to convert basic chemicals into high value compounds in environmentally benign reaction media is a current focus in catalytic research. The challenge lies in gaining controllability over product formation selectivity. We design covalent triazine frameworks as heterogeneous, metal-free, and recyclable photocatalysts for visible-light-driven switchable selective oxidation of styrene in pure water. Selectivity in product formation was achieved by activation or deactivation of the specific photogenerated oxygen species. Using the same photocatalyst, by deactivation of photogenerated H2 O2 , benzaldehyde was obtained with over 99 % conversion and over 99 % selectivity as a single product. The highly challenging and sensitive epoxidation of styrene was carried out by creating peroxymonocarbonate as an initial epoxidation agent in the presence of bicarbonate, which led to formation of styrene oxide with a selectivity up to 76 % with near quantitative conversion. This study demonstrates a preliminary yet interesting example for simple control over switchable product formation selectivity for challenging oxidation reactions of organic compounds in pure water.

Aerobic Photobiocatalysis Enabled by Combining Core-Shell Nanophotoreactors and Native Enzymes.

Biocatalysis has become a powerful tool in synthetic chemistry, where enzymes are used to produce highly selective products under mild conditions. Using photocatalytically regenerated cofactors in synergistic combination with enzymes in a cascade fashion offers an efficient synthetic route to produce specific compounds. However, the combination of enzymes and photocatalysts has been limited due to the rapid degradation of the biomaterials by photogenerated reactive oxygen species, which denature and deactivate the enzymatic material. Here, we design core-shell structured porous nano-photoreactors for highly stable and recyclable photobiocatalysis under aerobic conditions. The enzymatic cofactor NAD+ from NADH can be efficiently regenerated by the photoactive organosilica core, while photogenerated active oxygen species are trapped and deactivated through the non-photoactive shell, protecting the enzymatic material. The versatility of these photocatalytic core-shell nanoreactors was demonstrated in tandem with two different enzymatic systems, glycerol dehydrogenase and glucose 1-dehydrogenase, where long-term enzyme stability was observed for the core-shell photocatalytic system.

The transcription factor STAT-1 couples macrophage synthesis of 25-hydroxycholesterol to the interferon antiviral response.

Recent studies suggest that the sterol metabolic network participates in the interferon (IFN) antiviral response. However, the molecular mechanisms linking IFN with the sterol network and the identity of sterol mediators remain unknown. Here we report a cellular antiviral role for macrophage production of 25-hydroxycholesterol (cholest-5-en-3ß,25-diol, 25HC) as a component of the sterol metabolic network linked to the IFN response via Stat1. By utilizing quantitative metabolome profiling of all naturally occurring oxysterols upon infection or IFN-stimulation, we reveal 25HC as the only macrophage-synthesized and -secreted oxysterol. We show that 25HC can act at multiple levels as a potent paracrine inhibitor of viral infection for a broad range of viruses. We also demonstrate, using transcriptional regulatory-network analyses, genetic interventions and chromatin immunoprecipitation experiments that Stat1 directly coupled Ch25h regulation to IFN in macrophages. Our studies describe a physiological role for 25HC as a sterol-lipid effector of an innate immune pathway.

Convolution Neural Networks and Targeted Fluorescent Nanoparticles to Detect and ICDAS Score Caries.

Previous work has shown targeted fluorescent starch nanoparticles (TFSNs) can label the subsurface of carious lesions and assist dental professionals in the diagnostic process. In this study, we aimed to evaluate the potential of using artificial intelligence (AI) to detect and score carious lesions using ICDAS in combination with fluorescent imaging following application of TFSNs on teeth with a range of lesion severities, using ICDAS-labeled images as the reference standard. A total of 130 extracted human teeth with ICDAS scores from 0 to 6 were selected by a calibrated cariologist. Then, the same surface was imaged with a stereomicroscope under white light illumination, without visible fluorescence, and blue light illumination with an orange filter following application of the TFSNs. Both sets of images were labeled by another blinded ICDAS-calibrated cariologist to demarcate lesion position and severity. Convolutional neural networks, state-of-the-art models in imaging AI, were trained to determine the presence, location, ICDAS score (severity), and lesion surface porosity (as an indicator of activity) of carious lesions, and tested by 30 k-fold validation for white light, blue light, and the combined image sets. The best models showed high performance for the detection of carious lesions (sensitivity 80.26%, PPV 76.36%), potential for determining the severity via ICDAS scoring (accuracy 72%, SD 5.67%), and the detection of surface porosity as an indicator of the activity of the lesions (accuracy 90%, SD 7.00%). More broadly, the combination of targeted biopolymer nanoparticles with imaging AI is a promising combination of novel technologies that could be applied to many other applications.

Fast and Noninvasive Hair Test for Preliminary Diagnosis of Mood Disorders.

The main objective of this study was to develop a test for the fast and noninvasive prediagnosis of mood disorders based on the noninvasive analysis of hair samples. The database included 75 control subjects (who were not diagnosed with depression) and 40 patients diagnosed with mood disorders such as depression or bipolar disorder. Both women and men, aged 18-65 years, participated in the research. After taking the hair samples, they were washed (methanol-water-methanol by shaking in a centrifuge for two min) and air-dried in a fume hood. Each hair collection was analyzed using Fourier transform infrared spectroscopy attenuated total reflection (ATR-FTIR) spectroscopy. Subsequently, the results obtained were analyzed based on chemometric methods: hierarchical cluster analysis (HCA) and principal component analysis (PCA). As a results of the research conducted, potential differences were noticed. There was a visible change in the spectra intensity at around 2800-3100 cm-1 and smaller differences around 1460 cm-1; the bands can be assigned to protein vibrations. However, these are preliminary studies that provide a good basis for the development of a test for the initial diagnosis of mood disorders.

Curtailment of Civil Liberties and Subjective Life Satisfaction.

This analysis focuses on the lockdown measures in the context of the Covid-19 crisis in Spring 2020 in Germany. In a randomized survey experiment, respondents were asked to evaluate their current life satisfaction after being provided with varying degrees of information about the lethality of Covid-19. We use reactance as a measure of the intensity of a preference for freedom to explain the variation in the observed subjective life satisfaction loss. Our results suggest that it is not high reactance alone that is associated with large losses of life satisfaction due to the curtailment of liberties. The satisfaction loss occurs in particular in combination with receiving information about the (previously overestimated) lethality of Covid-19. Supplementary Information: The online version contains supplementary material available at 10.1007/s10902-021-00491-1.

A Nanographene-Based Two-Dimensional Covalent Organic Framework as a Stable and Efficient Photocatalyst.

Synthesis of covalent organic frameworks (COFs) with desirable organic units furnishes advanced materials with unique functionalities. As an emerging class of two-dimensional (2D) COFs, sp2 -carbon-conjugated COFs provide a facile platform to build highly stable and crystalline porous polymers. Herein, a 2D olefin-linked COF was prepared by employing nanographene, namely, dibenzo[hi,st]ovalene (DBOV), as a building block. The DBOV-COF exhibits unique ABC-stacked lattices, enhanced stability, and charge-carrier mobility of ≈0.6 cm2 V-1 s-1 inferred from ultrafast terahertz photoconductivity measurements. The ABC-stacking structure was revealed by the high-resolution transmission electron microscopy and powder X-ray diffraction. DBOV-COF demonstrated remarkable photocatalytic activity in hydroxylation, which was attributed to the exposure of narrow-energy-gap DBOV cores in the COF pores, in conjunction with efficient charge transport following light absorption.

Herpes Simplex Virus 2 Counteracts Neurite Outgrowth Repulsion during Infection in a Nerve Growth Factor-Dependent Manner.

During primary infection, herpes simplex virus 2 (HSV-2) replicates in epithelial cells and enters neurites to infect neurons of the peripheral nervous system. Growth factors and attractive and repulsive directional cues influence neurite outgrowth and neuronal survival. We hypothesized that HSV-2 modulates the activity of such cues to increase neurite outgrowth. To test this hypothesis, we exposed sensory neurons to nerve growth factor (NGF) and mock- or HSV-2-infected HEK-293T cells, since they express repellents of neurite outgrowth. We show that HEK-293T cells secrete factors that inhibit neurite outgrowth, while infection with HSV-2 strains MS and 333 reduces this repelling phenotype, increasing neurite numbers. The HSV-2-mediated restoration of neurite outgrowth required the activity of NGF. In the absence of infection, however, NGF did not overcome the repulsion mediated by HEK-293T cells. We previously showed that recombinant, soluble glycoprotein G of HSV-2 (rSgG2) binds and enhances NGF activity, increasing neurite outgrowth. However, the effect of gG2 during infection has not been investigated. Therefore, we addressed whether gG2 contributes to overcoming neurite outgrowth repulsion. To do so, we generated viruses lacking gG2 expression and complemented them by exogenous expression of gG2. Overall, our results suggest that HSV-2 infection of nonneuronal cells reduces their repelling effect on neurite outgrowth in an NGF-dependent manner. gG2 contributed to this phenotype, but it was not the only factor. The enhanced neurite outgrowth may facilitate HSV-2 spread from epithelial cells into neurons expressing NGF receptors and increase HSV-2-mediated pathogenesis.IMPORTANCE Herpes simplex virus 2 (HSV-2) is a prevalent human pathogen that establishes lifelong latency in neurons of the peripheral nervous system. Colonization of neurons is required for HSV-2 persistence and pathogenesis. The viral and cellular factors required for efficient infection of neurons are not fully understood. We show here that nonneuronal cells repel neurite outgrowth of sensory neurons, while HSV-2 infection overcomes this inhibition and, rather, stimulates neurite outgrowth. HSV-2 glycoprotein G and nerve growth factor contribute to this phenotype, which may attract neurites to sites of infection and facilitate virus spread to neurons. Understanding the mechanisms that modulate neurite outgrowth and facilitate HSV-2 infection of neurons might foster the development of therapeutics to reduce HSV-2 colonization of the nervous system and provide insights on neurite outgrowth and regeneration.

Topology optimization of 3D photonic crystals with complete bandgaps.

The design of photonic crystals with complete bandgaps has recently received considerable research focus for numerous reasons. This work leverages well-known nonlinear programming techniques to alleviate the non-smoothness caused by degenerate eigenvalues such that topology optimization problems can be solved with the open-source IPOPT software. A fully-vectorial plane wave expansion technique is used with an iterative eigensolver to efficiently predict dispersion properties of candidate structures. Nonlinear programming is employed to solve the inverse problem of designing three-dimensional periodic structures that exhibit complete two-dimensional (2D) and three-dimensional (3D) photonic bandgaps. Mesh refinement is performed to alleviate the large computational burden of designing and analyzing photonic crystals, and a periodic density filter is implemented to impose a minimum feature size for manufacturability considerations.

Acute Mesenteric Infarction: The Chameleon of Acute Abdomen Evaluating the Quality of the Diagnostic Parameters in Acute Mesenteric Ischemia.

INTRODUCTION/OBJECTIVE: Acute mesenteric ischemia (AMI) is difficult to diagnose. Since the established parameters have low sensitivity and specificity, the aim of this study is to analyze the diagnostic quality of the established parameters of AMI. METHODS: All patients that underwent emergency surgery due to suspected diagnosis of mesenteric ischemia at the University Medical Center Hamburg-Eppendorf between 2008 and 2014 were evaluated. Overall, 275 patients were enrolled and pre-, intra- and postoperative data were evaluated. RESULTS: In 200 patients, a mesenteric ischemia was confirmed intraoperatively, and 75 patients had no ischemia. Comparing these groups, the rate of patients with pH < 7.2 (25 vs. 12%; p = 0.021) and elevated mean CRP level (175 ± 117 mg/L vs. 139 ± 104 mg/L; p = 0.019) was significantly higher in ischemic patients. There was no significant difference in the level of preoperative lactate. Concerning abdominal CT scan, a sensitivity and specificity of 61 and 68%, respectively, was found. CONCLUSION: New diagnostic parameters are needed. So far, explorative laparotomy is the only reliable diagnostic method to detect mesenteric infarction.

Covalent Organic Frameworks Enabling Site Isolation of Viologen-Derived Electron-Transfer Mediators for Stable Photocatalytic Hydrogen Evolution.

Electron transfer is the rate-limiting step in photocatalytic water splitting. Viologen and its derivatives are able to act as electron-transfer mediators (ETMs) to facilitate the rapid electron transfer from photosensitizers to active sites. Nevertheless, the electron-transfer ability often suffers from the formation of a stable dipole structure through the coupling between cationic-radical-containing viologen-derived ETMs, by which the electron-transfer process becomes restricted. Herein, cyclic diquats, a kind of viologen-derived ETM, are integrated into a 2,2'-bipyridine-based covalent organic framework (COF) through a post-quaternization reaction. The content and distribution of embedded diquat-ETMs are elaborately controlled, leading to the favorable site-isolated arrangement. The resulting materials integrate the photosensitizing units and ETMs into one system, exhibiting the enhanced hydrogen evolution rate (34600 µmol h-1 g-1 ) and sustained performances when compared to a single-module COF and a COF/ETM mixture. The integration strategy applied in a 2D COF platform promotes the consecutive electron transfer in photochemical processes through the multi-component cooperation.

Metal-Free Multi-Heteroatom-Doped Carbon Bifunctional Electrocatalysts Derived from a Covalent Triazine Polymer.

The construction of multi-heteroatom-doped metal-free carbon with a reversibly oxygen-involving electrocatalytic performance is highly desirable for rechargeable metal-air batteries. However, the conventional approach for doping heteroatoms into the carbon matrix remains a huge challenge owing to multistep postdoping procedures. Here, a self-templated carbonization strategy to prepare a nitrogen, phosphorus, and fluorine tri-doped carbon nanosphere (NPF-CNS) is developed, during which a heteroatom-enriched covalent triazine polymer serves as a "self-doping" precursor with C, N, P, and F elements simultaneously, avoiding the tedious and inefficient postdoping procedures. Introducing F enhances the electronic structure and surface wettability of the as-obtained catalyst, beneficial to improve the electrocatalytic performance. The optimized NPF-CNS catalyst exhibits a superb electrocatalytic oxygen reduction reaction (ORR) activity, long-term durability in pH-universal conditions as well as outstanding oxygen evolution reaction (OER) performance in an alkaline electrolyte. These superior ORR/OER bifunctional electrocatalytic activities are attributed to the predesigned heteroatom catalytic active sites and high specific surface areas of NPF-CNS. As a demonstration, a zinc-air battery using the NPF-CNS cathode displays a high peak power density of 144 mW cm-2 and great stability during 385 discharging/charging cycles, surpassing that of the commercial Pt/C catalyst.

Machine learning to extract communication and history-taking skills in OSCE transcripts.

OBJECTIVES: Observed Structured Clinical Exams (OSCEs) allow assessment of, and provide feedback to, medical students. Clinical examiners and standardised patients (SP) typically complete itemised checklists and global scoring scales, which have known shortcomings. In this study, we applied machine learning (ML) to label some communication skills and interview content information in OSCE transcripts and to compare several ML methodologies by performance and transferability. METHODS: One-hundred and twenty-one transcripts of two OSCE scenarios were manually annotated per utterance across 19 communication skills and content areas. Utterances were converted to two types of numeric sentence vector representations and were paired with three types of ML algorithms. First, ML models (MLMs) were evaluated using a five K-fold cross-validation technique on all transcripts in one scenario to generate precision and recall, and their harmonic mean, F1 scores. Second, ML models were trained on all 101 transcripts from scenario 1 and tested for transferability on 20 scenario 2 transcripts. RESULTS: Performance testing in the K-fold cross-validation demonstrated relatively high mean F1 scores: median 0.87 and range 0.53-0.98 across all 19 labels. Transferability testing demonstrated success: F1 median 0.76 and range 0.46-0.97. The combination of a bi-directional long short-term memory neural network (biLSTM) algorithm with GenSen numeric sentence vector representations was associated with greater F1 scores across both performance and transferability (P < .005). CONCLUSIONS: We report the first application of ML in the context of student-SP OSCEs. We demonstrated that several MLMs automatically labelled OSCE transcripts for a range of interview content and some clinical communications skills. Some MLMs achieved greater performance and transferability. Optimised MLMs could provide automated and accurate assessment of OSCEs with potential to track student progress and identify areas for further practice.