Single-ion-conducted covalent organic framework serving as Li-ion pump in polyethylene oxide-based electrolyte for robust solid-state Li-S batteries.

Poly(ethylene oxide) (PEO)-based electrolytes are widely used for building solid-state lithium-sulfur (Li-S) batteries but suffer from poor lithium-ion (Li+) transportation kinetics. Here, a lithium-sulfonated covalent organic framework (TpPa-SO3Li) was synthesized and functionalized as a Li+ pump in a PEO-based solid-state electrolyte to fabricate robust Li-S batteries. The designed TpPa-SO3, Li with its porous skeleton and abundant lithium sulfonate groups not only provided iontransport channels but also enhanced the fast migration of Li+. The PEO composite electrolyte containing 5 %-TpPa-SO3Li exhibited a notable ionic conductivity of 6.28 × 10-4 S cm-1 and an impressive Li+ transference number of 0.78 at 60 °C. As a result, Li-Li symmetric batteries with the optimized PEO/TpPa-SO3Li composite electrolyte stably cycled for 300 h, with a minimal overpotential of only 100 mV at 0.5 mA cm-2. Moreover, the customized solid-state Li-S batteries based on PEO/TpPa-SO3Li were stable for 600 cycles at 60 oC with a high Coulombic efficiency of approximately 98 %. This study provides a promising strategy for introducing covalent-organic-framework (COF)-based Li+ pumps to build robust solid-state Li-S batteries.

Particle-Particle Random Phase Approximation for Predicting Correlated Excited States of Point Defects.

The particle-particle random phase approximation (ppRPA) within the hole-hole channel was recently proposed as an efficient tool for computing excitation energies of point defects in solids [J. Phys. Chem. Lett. 2024, 15, 2757-2764]. In this work, we investigate the application of ppRPA within the particle-particle channel for predicting correlated excited states of point defects, including the carbon-vacancy (VC) in diamond, the oxygen-vacancy (VO) in magnesium oxide (MgO), and the carbon dimer defect (CBCN) in two-dimensional hexagonal boron nitride (h-BN). Starting from a density functional theory calculation of the (N - 2)-electron ground state, vertical excitation energies of the N-electron system are obtained as the differences between the two-electron addition energies. We show that active-space ppRPA with the B3LYP functional yields accurate excitation energies, with errors mostly smaller than 0.1 eV for tested systems compared to available experimental values. We further develop a natural transition orbital scheme within ppRPA, which provides insights into the multireference character of defect states. This study, together with our previous work, establishes ppRPA as a low-cost and accurate method for investigating excited-state properties of point defect systems.

Molecular Engineering of Pure Superoxide Radical Photogenerator for Hypoxia-Tolerant Tumor Theranostics.

Photodynamic therapy (PDT) is a promising cancer treatment, but limited oxygen supply in tumors (hypoxia) can hinder its effectiveness. This is because traditional PDT relies on Type-II reactions that require oxygen. Type-I photosensitizers (PSs) offer a promising approach to overcome the limitations of tumor photodynamic therapy (PDT) in hypoxic environments. To leverage the advantages of Type-I PDT, the design and evaluation of a series of Type-I PSs for developing pure Type-1 PSs, by incorporating benzene, thiophene, or bithiophene into the donor-acceptor molecular skeleton are reported. Among them, CTTI (with bithiophene) shows the best performance, generating the most superoxide radical (O2 •-) upon light irradiation. Importantly, CTTI exclusively produced superoxide radicals, avoiding the less effective Type-II pathway. This efficiency is due to CTTI's energy gap and low reduction potential, which favor electron transfer to oxygen for O2 •- generation. Finally, CTTI NPs are successfully fabricated by encapsulating CTTI into liposomes, and validated to be effective in killing tumor cells, even under hypoxic conditions, making them promising hypoxia-tolerant tumor phototheranostic agents in both in vitro and in vivo applications.

A real-world pharmacovigilance study of FDA adverse event reporting system (FAERS) events for sunitinib.

Background: Sunitinib is approved for the treatment of metastatic renal cell carcinoma (mRCC), imatinib-resistant gastrointestinal stromal tumors (GIST), and advanced pancreatic neuroendocrine tumors (PNET). This study aims to investigate the safety profiles of sunitinib through data mining of the US Food and Drug Administration Adverse Event Reporting System (FAERS). Methods: The individual case safety reports (ICSRs) on sunitinib from 2006 Q1 to 2024 Q1 were collected from the ASCII data packages in the Food and Drug Administration Adverse Event Reporting System (FAERS). After standardizing the data, a variety of disproportionality analyses, including the reporting odds ratio (ROR), the proportional reporting ratio (PRR), the bayesian confidence propagation neural network (BCPNN), and the multi-item gamma Poisson shrinker (MGPS) were employed to identify the potential safety signals of sunitinib-associated AEs. Results: A total of 35,923 ICSRs of sunitinib as the "primary suspected" drug were identified within the reporting period. The search detected 276 disproportionate preferred terms (PTs). The most common AEs, including diarrhea, asthenia, decreased appetite, hypertension, and dysgeusia, were consistent with the drug label and clinical trials. Unexpected significant AEs, such as uveal melanocytic proliferation, salivary gland fistula, yellow skin, eyelash discoloration, scrotal inflammation, were detected. The median onset time of sunitinib-related AEs was 57 days (interquartile range [IQR]16-170 days), with most of the ICSRs developing within the first month (n = 4,582, 39.73%) after sunitinib therapy as initiated. Conclusion: The results of our study were consistent with routine clinical observations, and some unexpected AEs signals were also identified for sunitinib, providing valuable evidence for the safe use of sunitinib in the real-world and contributing to the clinical monitoring and risk identification of sunitinib.

AI-Powered Mining of Highly Customized and Superior ESIPT-Based Fluorescent Probes.

Excited-state intramolecular proton transfer (ESIPT) has attracted great attention in fluorescent sensors and luminescent materials due to its unique photobiological and photochemical features. However, the current structures are far from meeting the specific demands for ESIPT molecules in different scenarios; the try-and-error development method is labor-intensive and costly. Therefore, it is imperative to devise novel approaches for the exploration of promising ESIPT fluorophores. This research proposes an artificial intelligence approach aiming at exploring ESIPT molecules efficiently. The first high-quality ESIPT dataset and a multi-level prediction system are constructed that realized accurate identification of ESIPT molecules from a large number of compounds under a stepwise distinguishing from conventional molecules to fluorescent molecules and then to ESIPT molecules. Furthermore, key structural features that contributed to ESIPT are revealed by using the SHapley Additive exPlanations (SHAP) method. Then three strategies are proposed to ensure the ESIPT process while keeping good safety, pharmacokinetic properties, and novel structures. With these strategies, >700 previously unreported ESIPT molecules are screened from a large pool of 570 000 compounds. The ESIPT process and biosafety of optimal molecules are successfully validated by quantitative calculation and experiment. This novel approach is expected to bring a new paradigm for exploring ideal ESIPT molecules.

Synthesis of curcumin derivatives targeting androgen receptor for castration-resistant prostate cancer therapy.

In this work, a series of curcumin derivatives (1a-1h, 2a-2g, and 3a-3c) were synthesized for the suppression of castration-resistant prostate cancer cells. All synthesized compounds were characterized by 1H NMR, 13C NMR, HRMS, and melting point. The in vitro cytotoxicity study shows that compounds 1a, 1e, 1f, 1h, 2g, 3a, and 3c display similar or enhanced cytotoxicity against 22Rv1 and C4-2 cells as compared to ASC-J9, other synthesized compounds display reduced cytotoxicity against 22Rv1 and C4-2 cells as compared to ASC-J9. Molecular docking simulation was performed to study the binding affinity and probable binding modes of the synthesized compounds with androgen receptor. The results show that all synthesized compounds exhibit higher cdocker interaction energies as compared to ASC-J9. Compounds 1h, 2g, and 3c not only show strong cytotoxicity against 22Rv1 and C4-2 cells but also exhibit high binding affinity with androgen receptor. In androgen receptor suppression study, compounds 1f and 2g show similar androgen receptor suppression effect as compared to ASC-J9 on C4-2 cells, compound 3c displays significantly enhanced AR suppression effect as compared to ASC-J9, 1f and 2g. Compounds 1a, 1e, 1f, 1h, 2g, 3a and 3c prepared in this work have significant potential for castration-resistant prostate cancer therapy.

Restoring translational symmetry in periodic all-orbital dynamical mean-field theory simulations.

Dynamical mean-field theory (DMFT) and its cluster extensions provide an efficient Green's function formalism to simulate spectral properties of periodic systems at the quantum many-body level. However, traditional cluster DMFT breaks translational invariance in solid-state materials, and the best strategy to capture non-local correlation effects within cluster DMFT remains elusive. In this work, we investigate the use of overlapping atom-centered impurity fragments in recently-developed ab initio all-orbital DMFT, where all local orbitals within the impurity are treated with high-level quantum chemistry impurity solvers. We demonstrate how the translational symmetry of the lattice self-energy can be restored by designing symmetry-adapted embedding problems, which results in an improved description of spectral functions in two-dimensional boron nitride monolayers and graphene at the levels of many-body perturbation theory (GW) and coupled-cluster theory. Furthermore, we study the convergence of self-energy and density of states as the embedding size is systematically expanded in one-shot and self-consistent DMFT calculations.

Improvements and challenges in intraperitoneal laparoscopic para-aortic lymphadenectomy: The novel "tent-pitching" antegrade approach and vascular anatomical variations in the para-aortic region.

INTRODUCTION: This study introduces and compares a new intraperitoneal laparoscopic para-aortic lymphadenectomy method to reach the level of the renal vein, the "tent-pitching" antegrade approach with the retrograde approach in gynecological malignancy surgeries in terms of success rate, complication incidence, and the number of lymph nodes removed. It focuses on the feasibility, safety, and effectiveness. Meanwhile, this article reports on the vascular anatomical variations discovered in the para-aortic region to enhance surgical safety. MATERIAL AND METHODS: This was a retrospective cohort study including patients undergone laparoscopic para-aortic lymphadenectomy at a single center from January 2020 to December 2023 for high-risk endometrial and early-stage ovarian cancer. Patient charts were reviewed for mode of operation, perioperative complications, operative details, and histopathology. The patients were divided into anterograde group and retrograde group according to the operation mode. The two groups were further compared based on the success rate of lymph node clearance at the renal vein level, perioperative complications, and the number of removed lymph nodes. Quantitative data were analyzed using the t-test, non-normally distributed data using the rank-sum test, and categorical data using Fisher's exact test and the chi-square test, with statistical significance defined as P < 0.05. RESULTS: Among 173 patients, the antegrade group showed higher surgery success (97.5% vs 68.82%), more lymph nodes removed (median 14 vs 7), and less median blood loss. The operation time was shorter in the antegrade group. Postoperative complications like lymphocele and venous thrombosis were lower in the antegrade group. Vascular abnormalities were found in 28.9% of patients, with accessory lumbar vein routing anomaly and accessory renal arteries being most common. CONCLUSIONS: The antegrade approach is feasible, safe, and effective, improving surgical exposure, reducing difficulty without additional instruments or puncture sites, and minimizing organ damage risk. It is effective in achieving better access to the renal vein and removing more para-aortic lymph nodes than the retrograde method. Recognizing and carefully managing the diverse vascular abnormalities in the para-aortic area, including variations in renal arteries, veins, and the inferior vena cava, is essential to reduce intraoperative bleeding and the likelihood of converting to open surgery.

Surface-Engineered Polygonatum Sibiricum Polysaccharide CaCO3 Microparticles as Novel Vaccine Adjuvants to Enhance Immune Response.

Micro- and nanoparticles delivery systems have been widely studied as vaccine adjuvants to enhance immunogenicity and sustain long-term immune responses. Polygonatum sibiricum polysaccharide (PSP) has been widely studied as an immunoregulator in improving immune responses. In this study, we synthesized and characterized cationic modified calcium carbonate (CaCO3) microparticles loaded with PSP (PEI-PSP-CaCO3, CTAB-PSP-CaCO3), studied the immune responses elicited by PEI-PSP-CaCO3 and CTAB-PSP-CaCO3 carrying ovalbumin (OVA). Our results demonstrated that PEI-PSP-CaCO3 significantly enhanced the secretion of IgG and cytokines (IL-4, IL-6, IFN-γ, and TNF-α) in vaccinated mice. Additionally, PEI-PSP-CaCO3 induced the activation of dendritic cells (DCs), T cells, and germinal center (GC) B cells in draining lymph nodes (dLNs). It also enhanced lymphocyte proliferation, increased the ratio of CD4+/CD8+ T cells, and elevated the frequency of CD3+ CD69+ T cells in spleen lymphocytes. Therefore, PEI-PSP-CaCO3 microparticles induced a stronger cellular and humoral immune response and could be potentially useful as a vaccine delivery and adjuvant system.

ARID1A loss promotes RNA editing of CDK13 in an ADAR1-dependent manner.

BACKGROUND: ARID1A, a subunit of the SWI/SNF chromatin remodeling complex, is thought to play a significant role both in tumor suppression and tumor initiation, which is highly dependent upon context. Previous studies have suggested that ARID1A deficiency may contribute to cancer development. The specific mechanisms of whether ARID1A loss affects tumorigenesis by RNA editing remain unclear. RESULTS: Our findings indicate that the deficiency of ARID1A leads to an increase in RNA editing levels and alterations in RNA editing categories mediated by adenosine deaminases acting on RNA 1 (ADAR1). ADAR1 edits the CDK13 gene at two previously unidentified sites, namely Q113R and K117R. Given the crucial role of CDK13 as a cyclin-dependent kinase, we further observed that ADAR1 deficiency results in changes in the cell cycle. Importantly, the sensitivity of ARID1A-deficient tumor cells to SR-4835, a CDK12/CDK13 inhibitor, suggests a promising therapeutic approach for individuals with ARID1A-mutant tumors. Knockdown of ADAR1 restored the sensitivity of ARID1A deficient cells to SR-4835 treatment. CONCLUSIONS: ARID1A deficiency promotes RNA editing of CDK13 by regulating ADAR1.

Single-cell sequencing depicts tumor architecture and empowers clinical decision in metastatic conjunctival melanoma.

Conjunctival melanoma (CoM) is a potentially devastating tumor that can lead to distant metastasis. Despite various therapeutic strategies for distant metastatic CoM, the clinical outcomes remain unfavorable. Herein, we performed single-cell RNA sequencing (scRNA-seq) of 47,017 cells obtained from normal conjunctival samples (n = 3) and conjunctival melanomas (n = 7). Notably, we noticed a higher abundance of cancer-associated fibroblasts (CAFs) in tumor microenvironment (TME), correlated with enhanced angiogenic capacity and increased VEGFR expression in distal metastatic CoM. Additionally, we observed a significant decrease in the proportion of total CD8+ T cells and an increase in the proportion of naive CD8+ T cells, contributing to a relatively quiescent immunological environment in distal metastatic CoM. These findings were confirmed through the analyses of 70,303 single-cell transcriptomes of 7 individual CoM samples, as well as spatially resolved proteomes of an additional 10 samples of CoMs. Due to the increase of VEGFR-mediated angiogenesis and a less active T cell environment in distal metastatic CoMs, a clinical trial (ChiCTR2100045061) has been initiated to evaluate the efficacy of VEGFR blockade in combination with anti-PD1 therapy for patients with distant metastatic CoM, showing promising tumor-inhibitory effects. In conclusion, our study uncovered the landscape and heterogeneity of the TME during CoM tumorigenesis and progression, empowering clinical decisions in the management of distal metastatic CoM. To our knowledge, this is the initial exploration to translate scRNA-seq analysis to a clinical trial dealing with cancer, providing a novel concept by accommodating scRNA-seq data in cancer therapy.

Cistanche deserticola polysaccharide- functionalized dendritic fibrous nano-silica -based adjuvant for H9N2 oral vaccine enhance systemic and mucosal immunity in chickens.

Avian influenza virus subtype H9N2 has the ability to infect birds and humans, further causing significant losses to the poultry industry and even posing a great threat to human health. Oral vaccine received particular interest for preventing majority infection due to its ability to elicit both mucosal and systemic immune responses, but their development is limited by the bad gastrointestinal (GI) environment, compact epithelium and mucus barrier, and the lack of effective mucosal adjuvants. Herein, we developed the dendritic fibrous nano-silica (DFNS) grafted with Cistanche deserticola polysaccharide (CDP) nanoparticles (CDP-DFNS) as an adjuvant for H9N2 vaccine. Encouragingly, CDP-DFNS facilitated the proliferation of T and B cells, and further induced the activation of T lymphocytes in vitro. Moreover, CDP-DFNS/H9N2 significantly promoted the antigen-specific antibodies levels in serum and intestinal mucosal of chickens, indicating the good ability to elicit both systemic and mucosal immunity. Additional, CDP-DFNS facilitate the activation of CD4 + and CD8 + T cells both in spleen and intestinal mucosal, and the indexes of immune organs. This study suggested that CDP-DFNS may be a new avenue for development of oral vaccine against pathogens that are transmitted via mucosal route.

HyperComm: Hypergraph-based communication in multi-agent reinforcement learning.

In the realm of fully cooperative multi-agent reinforcement learning (MARL), effective communication can induce implicit cooperation among agents and improve overall performance. In current communication strategies, agents are allowed to exchange local observations or latent embeddings, which can augment individual local policy inputs and mitigate uncertainty in local decision-making processes. Unfortunately, in previous communication schemes, agents may potentially receive irrelevant information, which increases training difficulty and leads to poor performance in complex settings. Furthermore, most existing works lack the consideration of the impact of small coalitions formed by agents in the multi-agent system. To address these challenges, we propose HyperComm, a novel framework that uses the hypergraph to model the multi-agent system, improving the accuracy and specificity of communication among agents. Our approach brings the concept of hypergraph for the first time in multi-agent communication for MARL. Within this framework, each agent can communicate more effectively with other agents within the same hyperedge, leading to better cooperation in environments with multiple agents. Compared to those state-of-the-art communication-based approaches, HyperComm demonstrates remarkable performance in scenarios involving a large number of agents.

Controlling the speed of antigens transport in dendritic cells improves humoral and cellular immunity for vaccine.

Vaccines are an effective intervention for preventing infectious diseases. Currently many vaccine strategies are designed to improve vaccine efficacy by controlling antigen release, typically involving various approaches at the injection site. Yet, strategies for intracellular slow-release of antigens in vaccines are still unexplored. Our study showed that controlling the degradation of antigens in dendritic cells and slowing their transport from early endosomes to lysosomes markedly enhances both antigen-specific T-cell immune responses and germinal center B cell responses. This leads to the establishment of sustained humoral and cellular immunity in vivo imaging and flow cytometry indicated this method not only prolongs antigen retention at the injection site but also enhances antigen concentration in lymph nodes, surpassing traditional Aluminium (Alum) adjuvants. Additionally, we demonstrated that the slow antigen degradation induces stronger follicular helper T cell responses and increases proportions of long-lived plasma cells and memory B cells. Overall, these findings propose that controlling the speed of antigens transport in dendritic cells can significantly boost vaccine efficacy, offering an innovative avenue for developing highly immunogenic next-generation vaccines.

Cholinium Pyridinolate Ionic Pair-Catalyzed Fixation of CO2 into Cyclic Carbonates.

A halide-free ionic pair organocatalyst was proposed for the cycloaddition of CO2 into epoxide reactions. Cholinium pyridinolate ionic pairs with three different substitution positions were designed. Under conditions of temperature of 120 °C, pressure of 1 MPa CO2, and catalyst loading of 5 mol %, the optimal catalyst cholinium 4-pyridinolate ([Ch]+[4-OP]-) was employed. After a reaction time of 12 h, styrene oxide was successfully converted into the corresponding cyclic carbonate, and its selectivity was improved to 90%. A series of terminal epoxides were converted into cyclic carbonates within 12 h, with yields ranging from 80 to 99%. The proposed mechanism was verified by 1H NMR and 13C NMR titrations. Cholinium cations act as a hydrogen bond donor to activate epoxides, and pyridinolate anions combine with carbon dioxide to form intermediate carbonate anions that attack epoxides as nucleophiles and lead to ring opening. In summary, a halide-free ionic pair organocatalyst was designed and the catalytic mechanism in the cycloaddition of CO2 into epoxides reactions was proposed.

An improved epigenetic counter to track mitotic age in normal and precancerous tissues.

The cumulative number of stem cell divisions in a tissue, known as mitotic age, is thought to be a major determinant of cancer-risk. Somatic mutational and DNA methylation (DNAm) clocks are promising tools to molecularly track mitotic age, yet their relationship is underexplored and their potential for cancer risk prediction in normal tissues remains to be demonstrated. Here we build and validate an improved pan-tissue DNAm counter of total mitotic age called stemTOC. We demonstrate that stemTOC's mitotic age proxy increases with the tumor cell-of-origin fraction in each of 15 cancer-types, in precancerous lesions, and in normal tissues exposed to major cancer risk factors. Extensive benchmarking against 6 other mitotic counters shows that stemTOC compares favorably, specially in the preinvasive and normal-tissue contexts. By cross-correlating stemTOC to two clock-like somatic mutational signatures, we confirm the mitotic-like nature of only one of these. Our data points towards DNAm as a promising molecular substrate for detecting mitotic-age increases in normal tissues and precancerous lesions, and hence for developing cancer-risk prediction strategies.

Clinical and histopathological factors for recurrence and metastasis in lacrimal gland adenoid cystic carcinoma in Chinese patients.

PURPOSE: To investigate the association of metabolism-related proteins and clinicopathological features with poor prognosis in lacrimal gland adenoid cystic carcinoma (LGACC). METHODS: Clinicopathological data for 39 Chinese patients with LGACC enrolled were retrospectively analysed. Disease progression included death, recurrence, further nodal metastasis, and distant metastasis. Expression of ASCT2 and GLS1 were evaluated by immunohistochemistry. Kaplan-Meier survival curves and Cox proportional hazards regression models were used for risk factor analyses. RESULTS: At the end of follow-up, 14 patients (35.9%) developed local recurrence, 13 patients (33.3%) developed distant metastasis, 3 patients (7.7%) developed lymph node metastasis, and 9 patients (23.1%) died. Among the 13 patients who developed distant metastasis, lung metastasis was observed in 8 patients (61.5%), the brain in 8 patients (61.5%), and bone in 1 patient (7.7%). ASCT2 was expressed in 16 (57.14%) cases, while GLS1 had high expression in 19 (67.9%) cases. Advanced T category (≥T3), bone erosion, basaloid subtype, and ASCT2 (-) were associated with disease progression. Basaloid subtype was an independent risk factor for local recurrence (P = 0.028; HR, 12.12; 95% CI, 1.3-111.5). ASCT2(-) was an independent risk factor for distant metastasis (P = 0.016; HR, 14.46; 95% CI, 1.6-127.5) and was associated with basaloid subtype (P = 0.019). CONCLUSIONS: For LGACC, ≥T3 category, basaloid subtype, and bone erosion were high-risk predictors. ASCT2(-) was an independent risk factor for distant metastasis, which suggested that it could be a potential biomarker for LGACC.

Rosa laevigata Polysaccharides Ameliorate Dextran Sulfate Sodium-Induced Ulcerative Colitis of Beagles through Regulating Gut Microbiota.

Rosa laevigata Michx. polysaccharides (RLP) have been demonstrated to possess antioxidant and anti-inflammatory properties. However, the mechanisms and efficacy of these polysaccharide components in preventing ulcerative colitis (UC) remain to be elucidated. The efficacy and mechanisms of RLP were investigated in a study that utilized healthy adult beagles to establish a UC model, considering the similarities in gut microbiota between humans and dogs. In the study, the beagle model induced by sodium dextran sulfate exhibited typical symptoms of ulcerative colitis, such as weight loss and diarrhea. All these symptoms and changes were significantly ameliorated through oral supplementation of RLP. Additionally, microbial community analysis based on the 16S rDNA gene revealed that RLP alleviated UC by increasing the abundance of beneficial bacteria and reducing the abundance of harmful bacteria. In conclusion, our study has provided that RLP effectively alleviated colitis by preserving the intestinal barrier and regulating the gut microbiota composition.

The application of improved densenet algorithm in accurate image recognition.

Image recognition technology belongs to an important research field of artificial intelligence. In order to enhance the application value of image recognition technology in the field of computer vision and improve the technical dilemma of image recognition, the research improves the feature reuse method of dense convolutional network. Based on gradient quantization, traditional parallel algorithms have been improved. This improvement allows for independent parameter updates layer by layer, reducing communication time and data volume. The introduction of quantization error reduces the impact of gradient loss on model convergence. The test results show that the improvement strategy designed by the research improves the model parameter efficiency while ensuring the recognition effect. Narrowing the learning rate is conducive to refining the updating granularity of model parameters, and deepening the number of network layers can effectively improve the final recognition accuracy and convergence effect of the model. It is better than the existing state-of-the-art image recognition models, visual geometry group and EfficientNet. The parallel acceleration algorithm, which is improved by the gradient quantization, performs better than the traditional synchronous data parallel algorithm, and the improvement of the acceleration ratio is obvious. Compared with the traditional synchronous data parallel algorithm and stale synchronous parallel algorithm, the optimized parallel acceleration algorithm of the study ensures the image data training speed and solves the bottleneck problem of communication data. The model designed by the research improves the accuracy and training speed of image recognition technology and expands the use of image recognition technology in the field of computer vision.Please confirm the affiliation details of [1] is correct.The relevant detailed information in reference [1] has been confirmed to be correct.