Diagnostic accuracy of digital breast tomosynthesis and digital mammography in women with dense or non-dense breast tissue: A systematic review and meta-analysis.

BACKGROUND: Despite its excellent screening effectiveness and sensitivity for breast cancer (BC), digital breast tomosynthesis (DBT) is controversial due to its high radiation exposure and long reading time. This study examines the diagnostic accuracy of DBT and digital mammography (DM) for BC screening and diagnosis in women with dense or non-dense breast tissue. MATERIAL AND METHODS: PRISMA-compliant searches were performed on Medline, Embase, PubMed, Web of Science, and the Cochrane databases for articles comparing DBT and DM for BC screening until March 2023. Meta-analysis was performed using RevMan sofware, and the Cochrane Risk of Bias Assessment Tool was employed to assess study quality. RESULTS: This meta-analysis included 11 trials with a total of 2,124,018 individuals. Screening with DBT resulted in a greater cancer detection rate, as demonstrated by a risk ratio (RR) of 1.27 (95% confidence interval (95% CI): 1.14-1.41). Digital breast tomosynthesis also had a reduced recall rate, with a RR of 0.88 (95% CI: 0.78-0.99), higher sensitivity and specificity values (pooled sensitivity of 0.91 (95% CI: 0.59-0.99)) and pooled specificity of 0.90 (95% CI: 0.42-1.0)) than DM (pooled sensitivity of 0.86 (95% CI: 0.52-1.0) and pooled specificity of 0.81 (95% CI: 0.12-1.0)). All acquired data exhibited reliability, lack of bias and statistical significance (p < 0.05). CONCLUSION: Digital breast tomosynthesis is a more effective screening and diagnostic assessment tool for women with dense or non-dense breasts than DM in terms of incremental cancer detection, sensitivity and recall rate.

The mediating effect of depression on the association between lung disease and cardiovascular health.

Introduction: In this study, we investigated the effect of depression on the interaction between lung disease and cardiovascular health (CVH). Methods: Utilising data from the National Health and Nutrition Examination Survey (2013-2018), we employed multivariate regression and bootstrap mediation analysis to explore the relationships among lung diseases, depression, and CVH scores. Results: Complex and significant associations were identified among lung diseases, depression, and CVH scores, with depression mediating 9.42% of the effect on CVH, especially for chronic bronchitis patients. Conclusions: Depression significantly mediated the relationship between lung disease and reduced CVH scores, highlighting the importance of mental health management in lung disease patients.

Periphery Biomarkers Predicting Conversion of Type 2 Diabetes to Pre-Alzheimer-Like Cognitive Decline: A Multicenter Follow-Up Study.

Background: The prevalence of Alzheimer's disease (AD) is increasing, therefore, identifying biomarkers to predict those vulnerable to AD is imperative. Type 2 diabetes (T2D) serves as an independent risk factor for AD. Early prediction of T2D patients who may be more susceptible to AD, so as to achieve early intervention, is of great significance to reduce the prevalence of AD. Objective: To establish periphery biomarkers that could predict conversion of T2D into pre-AD-like cognitive decline. Methods: A follow-up study was carried out from 159 T2D patients at baseline. The correlations of cognitive states (by MMSE score) with multi-periphery biomarkers, including APOE genotype, plasma amyloid-ß level, platelet GSK-3ß activity, and olfactory score were analyzed by logistic regression. ROC curve was used for establishing the prediction model. Additionally, MRI acquired from 38 T2D patients for analyzing the correlation among cognitive function, biomarkers and brain structure. Results: Compared with the patients who maintained normal cognitive functions during the follow-up period, the patients who developed MCI showed worse olfactory function, higher platelet GSK-3ß activity, and higher plasma Aß42/Aß40 ratio. We conducted a predictive model which T2D patients had more chance of suffering from pre-AD-like cognitive decline. The MRI data revealed MMSE scores were positively correlated with brain structures. However, platelet GSK-3ß activity was negatively correlated with brain structures. Conclusions: Elevated platelet GSK-3ß activity and plasma Aß42/Aß40 ratio with reduced olfactory function are correlated with pre-AD-like cognitive decline in T2D patients, which used for predicting which T2D patients will convert into pre-AD-like cognitive decline in very early stage.

Intraosseous versus intravenous vascular access in upper extremity among adults with out-of-hospital cardiac arrest: cluster randomised clinical trial (VICTOR trial).

OBJECTIVE: To compare the effectiveness of intraosseous versus intravenous vascular access in the treatment of adult patients with out-of-hospital cardiac arrest. DESIGN: Cluster randomised controlled trial. SETTING: The VICTOR (Venous Injection Compared To intraOsseous injection during resuscitation of patients with out-of-hospital cardiac arrest) trial involved emergency medical service agencies with all four advanced life support ambulance teams in Taipei City, Taiwan. The enrolment period spanned 6 July 2020 to 30 June 2023 and was temporarily suspended between 20 May 2021 and 31 July 2021 owing to the covid-19 pandemic. PARTICIPANTS: Adult (age 20-80 years) patients with non-traumatic out-of-hospital cardiac arrest. INTERVENTIONS: Biweekly randomised clusters of four participating advanced life support ambulance teams were assigned to insert either intravenous or intraosseous access. MAIN OUTCOME MEASURES: The primary outcome was survival to hospital discharge. Secondary outcomes included return of spontaneous circulation, sustained return of spontaneous circulation (≥2 hours), and survival with favourable neurological outcomes (cerebral performance category score ≤2) at hospital discharge. RESULTS: Among 1771 enrolled patients, 1732 (741 in the intraosseous group and 991 in the intravenous group) were included in the primary analysis (median age 65.0 years; 1234 (71.2%) men). In the intraosseous group, 79 (10.7%) patients were discharged alive, compared with 102 (10.3%) patients in the intravenous group (odds ratio 1.04, 95% confidence interval 0.76 to 1.42; P=0.81). The odds ratio of intraosseous versus intravenous access was 1.23 (0.89 to 1.69; P=0.21) for pre-hospital return of spontaneous circulation, 0.92 (0.75 to 1.13; P=0.44) for sustained return of spontaneous circulation, and 1.17 (0.82 to 1.66; P=0.39) for survival with favourable neurological outcomes. CONCLUSIONS: Among adults with non-traumatic out-of-hospital cardiac arrest, initial attempts to establish vascular access through the intraosseous route did not result in different outcomes compared with intravenous access in terms of the proportion of patients surviving to hospital discharge, pre-hospital return of spontaneous circulation, sustained return of spontaneous circulation, and favourable neurological outcomes. TRIAL REGISTRATION: NCT04135547ClinicalTrials.gov NCT04135547.

Identification of key genes and pathways in duck fatty liver syndrome using gene set enrichment analysis.

High-laying ducks are often fed high-energy, nutritious feeds to maintain high productivity, which predisposes them to lipid metabolism disorders and the development of fatty liver syndrome (FLS), which seriously affects production performance and has a substantial economic impact on the poultry industry. Therefore, it is necessary to elucidate the mechanisms underlying the development of fatty liver syndrome. In this study, seven Shan Partridge ducks, each with fatty liver syndrome and normal laying ducks, were selected, and Hematoxylin Eosin staining (HE staining), Masson staining, and transcriptome sequencing were performed on liver tissue. In addition to exploring key genes and pathways using conventional analysis methods, we constructed the first Kyoto Encyclopedia of Genes and Genomes (KEGG) database-based predefined gene set containing 12,764 pathways and 16,836 genes and further performed gene set enrichment analysis (GSEA) on the liver transcriptome data. Finally, key nodes and biological processes were identified via the protein-protein interaction (PPI) network. The results showed that the liver in the FL group exhibited steatosis and fibrosis, and a total of 3,663 genes with upregulated expression versus 2,296 downregulated genes were screened by conventional analysis. GSEA analysis and PPI network analysis revealed that the liver in the FL group exhibited disruption of the mitochondrial electron transport chain, leading to decreased oxidative phosphorylation and the secretion of excessive proinflammatory factors amid the continuous accumulation of lipids. Under continuous chronic inflammation, cell cycle arrest triggers apoptosis, while fibrosis becomes more severe, and procarcinogenic genes are activated, leading to the continuous development and deterioration of the liver. In conclusion, the predefined gene set constructed in this study can be used for GSEA, and the identified hub genes provide useful reference data and a solid foundation for the study of the genetic regulatory mechanism of fatty liver syndrome in ducks.

Evolving treatment paradigms for platinum-resistant ovarian cancer: An update narrative review.

Platinum-resistant ovarian cancer (PROC) refers to disease progression within 6 months after the completion of platinum-based chemotherapy. Historically, treatment options for PROC were limited with a poor prognosis and non-platinum single agent plus bevacizumab has been the mainstay of treatment. Fortunately, there have been notable advancements in recent years, leading to an advance in treatment paradigms for this challenging disease. Various combinations of chemotherapy, targeted agents such as poly (ADP-ribose) polymerase (PARP) inhibitors, and immunotherapy are being explored for an improved treatment outcome. Antibody-drug conjugates targeting folate receptor alpha, which deliver a cytotoxic payload directly to cancer cells, have emerged as a promising therapeutic approach for PROC. WEE1 inhibitors, such as adavosertib, function by inhibiting the WEE1 kinase activity, leading to premature entry of a cell into mitosis phase and thus increased DNA damage. It has been observed that cancer cells with TP53 mutations may be more sensitive to WEE1 inhibitors. Biomarker testing such as analysis of the expression level of folate receptor alpha or mutation in TP53 may be applicable for identifying patients who are more likely to respond to the specific therapy, enabling a more personalized treatment approach. This overview summarizes key clinical findings on the efficacy and safety of theses novel biomarker-driven therapeutic approaches.

Evaluation of a novel vaginal cells self-sampling device for human papillomavirus testing in cervical cancer screening: A clinical trial assessing reliability and acceptability.

Cervical cancer is a significant public health concern, particularly in low- and middle-income countries where resources for prevention and treatment are limited. Routine screening, such as the Papanicolaou test (Pap smears) and human papillomavirus (HPV) testing, plays a crucial role in the early detection and prevention of cervical cancer. However, the participation rate in cervical cancer screening programs remains below optimal levels due to various factors. This study aimed to evaluate the reliability and acceptability of the HygeiaTouch Self Sampling Kit for Women in collecting vaginal samples for HPV typing, comparing the results with samples collected by physicians. The study included 1210 women aged 21-65 from three medical centers in Taiwan. The findings indicated that the self-sampling kit was as effective as physician-collected specimens in terms of obtaining valid samples and identifying HPV. The agreement between the two methods was 88%, with a κ value of 0.75. Furthermore, the study assessed the mechanical characteristics of the self-sampling applicator through tensile, bending, and torque tests, and determined that it was safe for intravaginal use. Additionally, the study evaluated the safety and satisfaction of self-sampling and found a low rate of adverse events (0.7%) and high levels of satisfaction (over 90%) among participants. Overall, we demonstrated that the HygeiaTouch Self Sampling Kit for Women is a reliable and acceptable device for HPV testing and cervical screening, providing a convenient, safe, and effective alternative for women.

Discovery of Fluorescent Naturally-occurring Inhibitor of SARS-CoV-2 Main Protease By AIE Fluorescent Probe.

Target-based high-throughput screening (HTS) is an efficient way to identify potent drugs. However, the accuracy of HTS could be affected by Pan-Assay Interference Compounds (PAINS). One reason for the generation of PAINS is that the inherent photophysical property of screened compounds could interfere with typically used assay signals including absorption and fluorescence. Our previous studies indicate that the fluorescent probe based on the fluorophore with characteristics of aggregation-induced emission (AIE) could provide high accuracy of HTS, especially for the fluorescent natural products. Herein, we report an AIE-based fluorescent probe for the main protease (Mpro) of SARS-CoV-2. We designed and synthesized an AIE fluorescent probe ZLHG5, which has a site that can be specifically cleaved by Mpro to produce a light-up fluorescence. Thanks to the large Stokes shift of AIE fluorophore (~300 nm), the probe could be effectively used for HTS of Mpro inhibitors. After screening a library of fluorescent natural products with ZLHG5, we obtained two coumarin-originated natural compounds with potent inhibitory activity towards Mpro protease. This study provides both useful fluorescent HTS probe and potent inhibitors for Mpro protease.

Quantitative and qualitative detection of target heavy metals using anti-interference colorimetric sensor Array combined with near-infrared spectroscopy.

An anti-interference colorimetric sensor array (CSA) technique was developed for the qualitative and quantitative detection of target heavy metals in corn oil. This method involves a binding mechanism that triggers changes in atomic energy levels and visible color changes. A custom-built olfactory visualization device was employed to gather spectral data, revealing distinct CSA color difference patterns. Subsequently, three pattern recognition algorithms were used to create an identification model for the target heavy metals. The results showed that the ACO-KNN (Ant Colony Optimization-K-Nearest Neighbor) model outperformed the other models, achieving accuracy rates of 90.28% and 89.58% for the calibration and prediction sets, respectively. The ACO-PLS (Partial Least Square) model was more stable with the lowest root mean square error of prediction (RMSEP), which were 0.1730 and 0.1180, respectively. The limit of detection (LOD) and quantification (LOQ) of Pb and Hg were (0.3, 0.6, 1.1 and 2.2) x 10-3 mg/L, respectively.

Chromosome-level genome assembly of Helwingia omeiensis: the first genome in the family Helwingiaceae.

Helwingia, a shrub of the monotypic cosmopolitan family Helwingiaceae, is distinguished by its inflorescence, in which flowers are borne on the midrib of the leaf-a trait not commonly observed in related plant families. Previous studies have investigated the development of this unusual structure using comparative anatomical methods. However, the scarcity of genomic data has hindered our understanding of the origins and evolutionary history of this uncommon trait at the molecular level. Here, we report the first high-quality genome of the family Helwingiaceae. Assembled using HiFi sequencing and Hi-C technologies, the genome of H. omeiensis is anchored to 19 chromosomes, with a total length of 2.75 Gb and a contig N50 length of 6.78 Mb. The BUSCO completeness score of the assembled genome was 98.2%. 53,951 genes were identified, of which 99.7% were annotated in at least one protein database. The high-quality reference genome of H. omeiensis provides an essential genetic resource and sheds light on the phylogeny and evolution of specific traits in the family Helwingiaceae.

How Progesterone Receptor Expression Impacts Platinum Sensitivity in Ovarian Clear Cell Carcinoma: Insights from Clinical and Experimental Perspectives.

Ovarian clear cell carcinoma (OCCC) is often considered a relatively platinum-resistant malignancy. The aim of this study was to explore the influence of progesterone receptor (PR) expression levels on platinum sensitivity and survival outcomes in people with OCCC. A retrospective analysis was conducted with 80 people with OCCC who underwent surgery followed by adjuvant chemotherapy. PR expression was assessed via immunohistochemical (IHC) staining and quantified using the H score. The platinum sensitivity and survival outcomes of patients with weak and strong PR expression were compared. Additionally, cisplatin viability and migration experiments were conducted with OCCC cell lines (ES-2 and TOV-21G) with varying PR isoform expressions. Among the 80 patients, 62 were classified as having platinum-sensitive disease, while 18 had platinum-resistant disease. The mean total PR H- score of platinum-sensitive tumors was significantly higher than that of platinum-resistant tumors (p = 0.002). Although no significant differences in progression-free and overall survival were observed between patients with high and low PR expression, those with high PR expression tended to have longer survival. While PR protein was only weakly detectable in ES-2 and TOV-21G cells, a transfection of the PR-A or PR-B gene resulted in a strong expression of PR-A or PR-B, which led to significantly reduced proliferation and migration in ES-2 and TOV-21G cells. Furthermore, overexpression of PR-A or PR-B enhanced cisplatin cytotoxicity in these cell lines. In conclusion, strong PR expression was associated with improved platinum sensitivity and survival outcomes, consistent with our experimental findings. The potential of PR as a tumor sensitizer to cisplatin in OCCC warrants further investigation.

Crenobacter oryzisoli sp. nov., a novel phosphate-solubilizing bacterium isolated from the paddy soil.

Two Gram-staining-negative, facultative anaerobic, rod-shaped and phosphate-solubilizing strains designated SG2303T and SG2305, were isolated from paddy soil in China. Phylogenetic analysis based on 16 S rRNA gene sequences indicated that SG2303T and SG2305 represented a member of the genus Crenobacter within the family Neisseriaceae of the phylum Pseudomonadota. Strain SG2303T displayed higher 16 S rRNA gene sequence similarities with members of the genus Crenobacter ranging from 93.5 to 94.0%. Strains C. luteus YIM 78141T and C. cavernae K1W11S-77T were closest related to the isolated strains and were considered as type strains. Growth of strain SG2303T occurred at 10-55 °C (optimum 37 °C), pH 5.0-9.0 (optimum pH 6.0-7.0) and 0-1% (w/v) NaCl (optimum 0%). The average nucleotide identity (ANI) and digital DNA-DNA hybridization (dDDH) values between strain SG2303T and its closely related taxa were 76.1-78.2% and 20.5-22.1%, respectively. The genomic DNA G + C content was 62.2%. The quinone of strain SG2303T was Q-8. The major fatty acids (> 10%) of strain SG2303T were C16:0 (30.6%), summed feature 3 (C16:1ω7c and/or C16:1ω6c) (26.0%) and C12:0 3OH (12.1%). The polar lipids were phosphatidylglycerol (PG), diphosphatidylglycerol (DPG), phosphatidylethanolamine (PE), phospholipids (PL), glycolipid (GL) and unidentified lipids (UL). Based on the results of the phylogenetic, physiological, biochemical, and morphological analysis, strain SG2303T is recognized as a novel species of the genus Crenobacter, for which the name Crenobacter oryzisoli sp. nov. is proposed. The type strain is SG2303T (= GDMCC 1.3970T = JCM 36468T). In addition, SG2303T was also able of phosphorus solubilization and promoting the growth of rice seeds. Strain SG2303T exhibited a relatively high dissolvable phosphorus content of 2.52 µg·mL- 1.

Single Atom Ag Bonding Between PF3T Nanocluster and TiO2 Leads the Ultra-Stable Visible-Light-Driven Photocatalytic H2 Production.

Atomic Ag cluster bonding is employed to reinforce the interface between PF3T nano-cluster and TiO2 nanoparticle. With an optimized Ag loading (Ag/TiO2 = 0.5 wt%), the Ag atoms will uniformly disperse on TiO2 thus generating a high density of intermediate states in the band gap to form the electron channel between the terthiophene group of PF3T and the TiO2 in the hybrid composite (denoted as T@Ag05-P). The former expands the photon absorption band width and the latter facilitates the core-hole splitting by injecting the photon excited electron (from the excitons in PF3T) into the conduction band (CB) of TiO2. These characteristics enable the high efficiency of H2 production to 16 580 µmol h-1 g-1 and photocatalysis stability without degradation under visible light exposure for 96 h. Compared to that of hybrid material without Ag bonding (TiO2@PF3T), the H2 production yield and stability are improved by 4.1 and 18.2-fold which shows the best performance among existing materials in similar component combination and interfacial reinforcement. The unique bonding method offers a new prospect to accelerate the development of photocatalytic hydrogen production technologies.

Identification of DNase I hypersensitive sites in the human genome by multiple sequence descriptors.

DNase I hypersensitive sites (DHSs) are chromatin regions highly sensitive to DNase I enzymes. Studying DHSs is crucial for understanding complex transcriptional regulation mechanisms and localizing cis-regulatory elements (CREs). Numerous studies have indicated that disease-related loci are often enriched in DHSs regions, underscoring the importance of identifying DHSs. Although wet experiments exist for DHSs identification, they are often labor-intensive. Therefore, there is a strong need to develop computational methods for this purpose. In this study, we used experimental data to construct a benchmark dataset. Seven feature extraction methods were employed to capture information about human DHSs. The F-score was applied to filter the features. By comparing the prediction performance of various classification algorithms through five-fold cross-validation, random forest was proposed to perform the final model construction. The model could produce an overall prediction accuracy of 0.859 with an AUC value of 0.837. We hope that this model can assist scholars conducting DNase research in identifying these sites.

PHF12 regulates HDAC1 to promote tumorigenesis via EGFR/AKT signaling pathway in non-small cell lung cancer.

BACKGROUND: Lung cancer stands as the second most prevalent malignant neoplasm worldwide. Addressing the underlying mechanisms propelling the progression of non-small cell lung cancer is of paramount importance. In this study, we have elucidated the pivotal role of PHF12 in this context. MATERIALS AND METHODS: We harnessed clinical lung cancer tissue samples and non-small cell lung cancer cell lines to discern the expression pattern of PHF12. In vitro assays probing cell proliferation were conducted to substantiate the functional impact of PHF12. Furthermore, an in vivo Xenograft model was employed to dissect the role of PHF12. Employing ChIP assays and qRT-PCR, we delved into the intricate binding dynamics between PHF12 and HDAC1. Mechanistic insights into the PHF12-HDAC1 axis in lung cancer progression were pursued via RNA-seq and GSEA analyses. RESULTS: Notably, PHF12 exhibited a substantial upregulation within tumor tissue, concomitant with its correlation to HDAC1. The trilogy of cell proliferation assays, transwell assays, and the Xenograft model collectively underscored the promoting influence of PHF12 on lung cancer proliferation, both in vitro and in vivo. The ChIP assay unveiled the transcriptional regulatory role of PHF12 in governing HDAC1 expression. This correlation extended to both mRNA and protein levels. PHF12 promotes NSCLC progression through regulating HDCA1 expression. Intriguingly, the rescue of function within NSCLC cell lines post PHF12 knockdown was achievable through HDAC1 overexpression. Additionally, our findings unveiled the capacity of the PHF12-HDAC1 axis to activate the EGFR/AKT signaling pathway, thereby further corroborating its significance in lung cancer progression. CONCLUSION: Our study identified PHF12 as an oncogenic role in lung cancer proliferation and migration for the first time. PHF12 transcriptionally regulate HDAC1 and activate EGFR/AKT signaling pathway in NSCLC progression. PHF12 may serve as an important target in lung cancer therapy.

VISTA: A promising target for overcoming immune evasion in gynecologic cancers.

Immune checkpoint blockade (ICB) therapy has revolutionized cancer treatment but has shown limited efficacy in gynecologic cancers. VISTA (V-domain Ig suppressor of T-cell activation), a member of the B7 family, is emerging as another checkpoint that regulates the anti-tumor immune responses within the tumor microenvironment. This paper reviews the structure, expression, and mechanism of action of VISTA. Furthermore, it highlights recent advances in VISTA-blocking therapies and their potential in improving outcomes for patients with gynecologic cancers. By understanding the role of VISTA in mediating the immune evasion of gynecologic tumors, we can develop more effective combinatory treatment strategies that could overcome resistance to current ICB therapies.

A Study on Data Selection for Object Detection in Various Lighting Conditions for Autonomous Vehicles.

In recent years, significant advances have been made in the development of Advanced Driver Assistance Systems (ADAS) and other technology for autonomous vehicles. Automated object detection is a crucial component of autonomous driving; however, there are still known issues that affect its performance. For automotive applications, object detection algorithms are required to perform at a high standard in all lighting conditions; however, a major problem for object detection is poor performance in low-light conditions due to objects being less visible. This study considers the impact of training data composition on object detection performance in low-light conditions. In particular, this study evaluates the effect of different combinations of images of outdoor scenes, from different times of day, on the performance of deep neural networks, and considers the different challenges encountered during the training of a neural network. Through experiments with a widely used public database, as well as a number of commonly used object detection architectures, we show that more robust performance can be obtained with an appropriate balance of classes and illumination levels in the training data. The results also highlight the potential of adding images obtained in dusk and dawn conditions for improving object detection performance in day and night.

Decoding human somatosensory sensitivity through resting EEG and behavioral analysis: a multimodal fusion approach.

In precision medicine and clinical pain management, the creation of quantitative, objective indicators to assess somatosensory sensitivity was essential. This study proposed a fusion approach for decoding human somatosensory sensitivity, which combined multimodal (quantitative sensory test and neurophysiology) features to classify the dataset on individual somatosensory sensitivity and reveal distinct types of brain activation patterns. Sixty healthy participants took part in the experiment on somatosensory sensitivity that implemented cold, heat, mechanical punctate, and pressure stimuli, and the resting-state electroencephalography (EEG) was collected using BrainVision. The quantitative sensory testing (QST) scores of the participants were clustered using the unsupervised k-means algorithm into four subgroups: generally hypersensitive (HS), generally non-sensitive (NS), predominantly thermally sensitive (TS), and predominantly mechanically sensitive (MS). Furthermore, two types of power spectral density (PSD), band-based PSD (BB-PSD) and frequency-based PSD (FB-PSD), and two types of inter-electrode connectivity (IEC), band-based connectivity (BBC) and frequency-based connectivity (FBC), derived from resting-state EEG were subjected to feature selection with a proposed prior-compared minimum-redundancy maximum-relevance (PCMRMR) protocol. Their effectiveness was then tested by the supervised classification tasks using support vector machine (SVM), k-nearest neighbor (kNN), random forest (RF), and Gaussian classifier (GC). Brain networks of four somatosensory types were revealed by decoding fused multimodal data, namely type-averaged connectivity. The data from sixty healthy individuals were divided into training (n = 59) and validation (n = 1) datasets according to leave-one-subject-out (LOSO) criteria. The FBC was identified, which can serve as better brain signatures than BB-PSD, FB-PSD, and BBC to classify subjects as HS, NS, TS, or MS groups. Using the SVM, kNN, RF, and GC models, the best accuracy of 87% was obtained when classifying participants into HS, NS, TS, or MS groups. Moreover, the brain networks were decoded from HS, NS, TS, and MS groups by decoding the type-averaged connectivity fused from somatosensory phenotypes and selected FBC. It indicated that quantified multi-parameter somatosensory sensitivity could be achieved with acceptable accuracy, leading to considerable possibilities for using objective pain perception evaluation in clinical practice.

A protein pre-trained model-based approach for the identification of the liquid-liquid phase separation (LLPS) proteins.

Liquid-liquid phase separation (LLPS) regulates many biological processes including RNA metabolism, chromatin rearrangement, and signal transduction. Aberrant LLPS potentially leads to serious diseases. Therefore, the identification of the LLPS proteins is crucial. Traditionally, biochemistry-based methods for identifying LLPS proteins are costly, time-consuming, and laborious. In contrast, artificial intelligence-based approaches are fast and cost-effective and can be a better alternative to biochemistry-based methods. Previous research methods employed word2vec in conjunction with machine learning or deep learning algorithms. Although word2vec captures word semantics and relationships, it might not be effective in capturing features relevant to protein classification, like physicochemical properties, evolutionary relationships, or structural features. Additionally, other studies often focused on a limited set of features for model training, including planar π contact frequency, pi-pi, and ß-pairing propensities. To overcome such shortcomings, this study first constructed a reliable dataset containing 1206 protein sequences, including 603 LLPS and 603 non-LLPS protein sequences. Then a computational model was proposed to efficiently identify the LLPS proteins by perceiving semantic information of protein sequences directly; using an ESM2-36 pre-trained model based on transformer architecture in conjunction with a convolutional neural network. The model could achieve an accuracy of 85.86 % and 89.26 %, respectively on training data and test data, surpassing the accuracy of previous studies. The performance demonstrates the potential of our computational methods as efficient alternatives for identifying LLPS proteins.