Assessing parameter efficient methods for pre-trained language model in annotating scRNA-seq data.

Annotating cell types of single-cell RNA sequencing (scRNA-seq) data is crucial for studying cellular heterogeneity in the tumor microenvironment. Recently, large-scale pre-trained language models (PLMs) have achieved significant progress in cell-type annotation of scRNA-seq data. This approach effectively addresses previous methods' shortcomings in performance and generalization. However, fine-tuning PLMs for different downstream tasks demands considerable computational resources, rendering it impractical. Hence, a new research branch introduces parameter-efficient fine-tuning (PEFT). This involves optimizing a few parameters while leaving the majority unchanged, leading to substantial reductions in computational expenses. Here, we utilize scBERT, a large-scale pre-trained model, to explore the capabilities of three PEFT methods in scRNA-seq cell type annotation. Extensive benchmark studies across several datasets demonstrate the superior applicability of PEFT methods. Furthermore, downstream analysis using models obtained through PEFT showcases their utility in novel cell type discovery and model interpretability for potential marker genes. Our findings underscore the considerable potential of PEFT in PLM-based cell type annotation, presenting novel perspectives for the analysis of scRNA-seq data.

Multi-prior underwater image restoration method via adaptive transmission.

Captured underwater images usually suffer from severe color cast and low contrast due to wavelength-dependent light absorption and scattering. These degradation issues affect the accuracy of target detection and visual understanding. The underwater image formation model is widely used to improve the visual quality of underwater images. Accurate transmission map and background light estimation are the keys to obtaining clear images. We develop a multi-priors underwater image restoration method with adaptive transmission (MUAT). Concretely, we first propose a calculation method of the dominant channel transmission to cope with pixel interference, which combines two priors of the difference between atmospheric light and pixel values and the difference between the red channel and the blue-green channel. Besides, the attenuation ratio between the superior and inferior channels is adaptively calculated with the background light to solve the color distortion and detail blur caused by the imaging distance. Ultimately, the global white balance method is introduced to solve the color distortion. Experiments on several underwater scene images show that our method obtains accurate transmission and yields better visual results than state-of-the-art methods.

The effect of 17-methoxyl-7-hydroxy-benzene-furanchalcone on NF-κB and the inflammatory response during myocardial ischemia reperfusion injury in rats.

The aim of this study was to investigate the effect of 17-methoxyl-7-hydroxy-benzene-furanchalcone (MHBFC) on nuclear factor-kappa-binding (NF-κB) and the inflammatory response in rats with myocardial ischemia reperfusion injury (MI/RI). Sprague-Dawley rats were randomly divided into 7 groups, and the rat MI/RI model was established by the ligation of the left anterior descending for 30 minutes followed by ligation release for 1 hour. Areas of myocardial infarction were measured using Evans blue-2,3,5-Triphenyltetrazolium chloride (TTC) staining. Levels of malondialdehyde, glutathione peroxidase, and total superoxide dismutase were assessed. Release of interleukin-1ß (IL-1ß), interleukin-6 (IL-6), and interleukin-10 (IL-10) was measured by means of an enzyme-linked immunosorbent assay. NF-κBp65 and intercellular adhesion molecule-1 protein expression and caspase-3 and adenine nucleotide translocator-1 messenger RNA expression were evaluated by immunohistochemistry and reverse transcription polymerase chain reaction, respectively. Pretreatment with MHBFC decreased the infarction areas, the malondialdehyde, IL-1ß and IL-6 levels, the expression of caspase-3, NF-κBp65, and intercellular adhesion molecule-1. Further, MHBFC increased total superoxide dismutase and glutathione peroxidase activities, the release of IL-10, and the expression of adenine nucleotide translocator-1 messenger RNA compared with the results of the model group. The experiment showed that MHBFC protected the heart against MI/RI possibly by reducing lipid peroxidation damage while inhibiting the activity of NF-κBp65 and the inflammatory response.

Stroke Phase Is Essential for Pneumonia in Dysphagia Patients After Cerebral Infarction.

BACKGROUND: The risk of pneumonia increases after stroke, especially in poststroke dysphagia patients. Propensity score matching (PSM) is a statistical method in SPSS, which can be used to balance the difference between the 2 groups of known factors. Nasogastric tube feeding is an important factor of stroke-associated pneumonia. However, few studies have used PSM to eliminate the effect of confounding factor. METHODS: Our research was a retrospective case-control study. Retrospective review of the patient database between December 1, 2019, and June 30, 2022, to identify consecutive dysphagia patients after cerebral infarction during hospitalization. An 1:1 PSM in SPSS 25.0 was used to balance nasogastric tube feeding between patients with and without pneumonia. The characteristics of these 2 groups were analyzed. Univariate and binary logistic regression analyses were used to screen the risk factors of dysphagia after cerebral infarction. RESULTS: After 1:1 PSM, 198 subjects met our criteria and were included in the analysis. Age [odds ratio (OR)=1.047, 95% CI: 1.013-1.081, P =0.006], stroke phase (acute stroke) (OR=5.931, 95% CI: 1.133-31.054, P =0.035), admission National Institutes of Health Stroke Scale score (OR=1.058, 95% CI: 1.004-1.115, P =0.034), and length of hospital stay (OR=1.025, 95% CI: 1.001-1.049, P =0.042) had statistically significant correlation with pneumonia in patients with dysphagia after cerebral infarction. CONCLUSION: In clinical practice, for the prevention of pneumonia in patients with dysphagia after cerebral infarction, we should pay more attention to admission National Institutes of Health Stroke Scale score, age, and stroke phase, especially in acute cerebral infarction patients.

Introduction to the Meta-analysis method of functional magnetic resonance imaging research and the exploration of its application in the field of acupuncture. / åŠŸèƒ½ç£å ±æŒ¯ç ”ç©¶å ƒåˆ†æžæ–¹æ³•ä»‹ç»åŠå ¶åœ¨é’ˆåˆºé¢†åŸŸçš„åº”ç”¨æŽ¢æž.

In recent years, the number of functional magnetic resonance imaging (fMRI) research in acupuncture grows increasingly. However, due to the differences in acupoint selection, acupuncture technique and sample size, the problems get more prominent in terms of the diverse results and the lack of common rules of acupuncture among researches. By taking the fMRI research for post-stroke motor dysfunction (PSMD) treated with acupuncture as the example, this paper introduces the fMRI Meta-analysis technology for integrating the relevant research results and extracting the common rules, namely image-based Meta-analysis (IBMA) and coordinate-based Meta-analysis (CBMA). Considering the higher feasibility of CBMA, three available CBMA methods are explained specially, including activation likelihood estimation (ALE), kernel density analysis (KDA), and seed-based d mapping (SDM). Focusing on the precautions and operation procedure of CBMA, the review is conducted systematically on the type of fMRI research, task design, analytical method, and the thinking integrity of fMRI Meta-analysis, and the review findings are collated in charts. It aims to assist readers to understand the abstract and complex theories and practical information of this technology efficiently, conveniently and systematically, and hopes to provide the references for the future learning and the application.