PocketDTA: A pocket-based multimodal deep learning model for drug-target affinity prediction.

Drug-target affinity prediction is a fundamental task in the field of drug discovery. Extracting and integrating structural information from proteins effectively is crucial to enhance the accuracy and generalization of prediction, which remains a substantial challenge. This paper proposes a pocket-based multimodal deep learning model named PocketDTA for drug-target affinity prediction, based on the principle of "structure determines function".

Incidence of Arrhythmias in Chronic Obstructive Pulmonary Disease, Obstructive Sleep Apnea and Overlap Syndrome: A Retrospective Cohort Study.

Background: New-onset arrhythmias are common in patients with chronic obstructive pulmonary disease (COPD) and obstructive sleep apnea (OSA). However, scarce data exists regarding arrhythmia risk in overlap syndrome (OS), encompassing COPD and OSA.

Objective: We compared the incidence of new onset atrial and ventricular arrhythmias in patients with COPD, OSA, and OS.

GBCT: Efficient and Adaptive Clustering via Granular-Ball Computing for Complex Data.

Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in the human brain, resulting in those methodsbad performance in efficiency, generalization ability, and robustness. To address this problem, we propose a new clustering algorithm called granular-ball clustering via granular-ball computing.

Posterior approach unilateral laminectomy, debridement, and preshaped titanium mesh bone grafting with internal fixation for treatment of lumbar tuberculosis.

Comparison of the efficacy of unilateral laminectomy, debridement, and fusion with preshaped titanium mesh (ULT) with bilateral laminectomy, debridement, and fusion with preshaped titanium mesh (BLT) for the treatment of single-segment lumbar tuberculosis. A total of 65 patients with lumbar tuberculosis in our hospital from 2016 to 2020 were enrolled. Data such as operation time, blood loss, and postoperative ambulation time were recorded.

A deep learning approach for early prediction of breast cancer neoadjuvant chemotherapy response on multistage bimodal ultrasound images.

Neoadjuvant chemotherapy (NAC) is a systemic and systematic chemotherapy regimen for breast cancer patients before surgery. However, NAC is not effective for everyone, and the process is excruciating. Therefore, accurate early prediction of the efficacy of NAC is essential for the clinical diagnosis and treatment of patients.

Association between the immune-inflammation indicators and osteoarthritis - NHANES 1999-2018.

Background: Investigate the link between systemic immune-inflammatory index (SII) and Systemic Immune Response Index (SIRI) with osteoarthritis (OA) using National Health and Nutrition Examination Survey (NHANES) data (1999-2018).

Methods: Extracted NHANES data (1999-2018) and selected a study population based on demographic, examination, and laboratory data. Calculated SII (platelet count ​× ​neutrophil count/lymphocyte count) and SIRI (neutrophil count ​× ​monocyte count/lymphocyte count).

Association of Craniofacial Skeletal and Soft Tissue Characteristics With Severe Obstructive Sleep Apnea in Age-specific and BMI-specific Patient Groups.

Purpose: To identify the key craniofacial anatomic characteristics associated with the prevalence of severe obstructive sleep apnea (OSA) in patient cohorts stratified by age and body mass index (BMI).

Methods: This prospective study was conducted at the Beijing Anzhen Hospital Center for Sleep Medicine and Science between December 2023 and March 2024. Patients suspected of having OSA underwent overnight polysomnography, along with computed tomography scans of the head and neck, to evaluate the skeletal and soft tissue characteristics.

Enhancing Nitrogen Nutrition Index estimation in rice using multi-leaf SPAD values and machine learning approaches.

Accurate nitrogen diagnosis is essential for optimizing rice yield and sustainability. This study investigates the potential of using multi-leaf SPAD measurements combined with machine learning models to improve nitrogen nutrition diagnostics in rice. Conducted across five locations with 15 rice cultivars, SPAD values from the first to fifth fully expanded leaves were collected at key growth stages.

Expression Profiles of Housekeeping Genes and Tissue-Specific Genes in Different Tissues of Chinese Sturgeon ().

The Chinese sturgeon () is an ancient, complex autooctoploid fish species that is currently facing conservation challenges throughout its distribution. To comprehensively characterize the expression profiles of genes and their associated biological functions across different tissues, we performed a transcriptome-scale gene expression analysis, focusing on housekeeping genes (HKGs), tissue-specific genes (TSGs), and co-expressed gene modules in various tissues. We collected eleven tissues to establish a transcriptomic repository, including data from Pacific Biosciences isoform sequencing (PacBio Iso-seq) and RNA sequencing (RNA-seq), and then obtained 25,434 full-length transcripts, with lengths from 307 to 9515 bp and an N50 of 3195 bp.

Waste clearance shapes aging brain health.

Brain health is intimately connected to fluid flow dynamics that cleanse the brain of potentially harmful waste material. This system is regulated by vascular dynamics, the maintenance of perivascular spaces, neural activity during sleep, and lymphatic drainage in the meningeal layers. However, aging can impinge on each of these layers of regulation, leading to impaired brain cleansing and the emergence of various age-associated neurological disorders, including Alzheimer's and Parkinson's diseases.

A Novel Deep Learning Model for Breast Tumor Ultrasound Image Classification with Lesion Region Perception.

Multi-task learning (MTL) methods are widely applied in breast imaging for lesion area perception and classification to assist in breast cancer diagnosis and personalized treatment. A typical paradigm of MTL is the shared-backbone network architecture, which can lead to information sharing conflicts and result in the decline or even failure of the main task's performance. Therefore, extracting richer lesion features and alleviating information-sharing conflicts has become a significant challenge for breast cancer classification.

Transepithelial transport of nanoparticles in oral drug delivery: From the perspective of surface and holistic property modulation.

Despite the promising prospects of nanoparticles in oral drug delivery, the process of oral administration involves a complex transportation pathway that includes cellular uptake, intracellular trafficking, and exocytosis by intestinal epithelial cells, which are necessary steps for nanoparticles to enter the bloodstream and exert therapeutic effects. Current researchers have identified several crucial factors that regulate the interaction between nanoparticles and intestinal epithelial cells, including surface properties such as ligand modification, surface charge, hydrophilicity/hydrophobicity, intestinal protein corona formation, as well as holistic properties like particle size, shape, and rigidity. Understanding these properties is essential for enhancing transepithelial transport efficiency and designing effective oral drug delivery systems.

METTL14-mediated HOXA5 mA modification alleviates osteoporosis via promoting WNK1 transcription to suppress NLRP3-dependent macrophage pyroptosis.

Background: Osteoporosis is a commonly diagnosed metabolic bone disease. NLRP3 inflammasome activation and pyroptosis are observed during osteoporosis. However, the mechanism by which NLRP3-mediated pyroptosis contributes to osteoporosis remains largely undefined.

Prognostic efficacy of non-invasive ventilation in patients with overlap syndrome: chronic obstructive pulmonary disease and obstructive sleep apnea.

Background: Limited evidence exists regarding the effects of non-invasive ventilation (NIV) on the prognosis of patients with concomitant chronic obstructive pulmonary disease (COPD) and obstructive sleep apnea (OSA), also known as overlap syndrome (OS). This study aimed to assess whether NIV alongside standard care could improve the prognosis of this cohort.

Methods: We retrospectively collected data from 229 patients with severe OS treated in Beijing Anzhen Hospital between January 1, 2016 and January 1, 2020, with follow-up until December 1, 2023.

Identification and Full-Length Sequence Analysis of a Novel Recombinant Goat Astrovirus Genotype in Guangxi, China.

Astroviruses are single-stranded, positive-sense RNA viruses capable of infecting humans as well as a wide range of mammalian and avian species, with a length of approximately 6.6-7.7 kb.

DRML-Ensemble: drug repurposing method based on feature construction of multi-layer ensemble.

Context: Computational drug repurposing methods have been continuously developed in recent years to alleviate the high costs associated with drug development. As drug targets or the products of disease-related genes, proteins play an important role in drug repurposing. Although the potential has been demonstrated, heterogeneous graphs with proteins as independent nodes have yet to be studied, where extracting high-quality protein features from heterogeneous graphs poses a significant challenge.

Placenta-specific CYP11A1 overexpression lead to autism-like symptom in offspring with altered steroid hormone biosynthesis in the placenta-brain axis and rescued by vitamin D intervention.

Alterations in steroid hormone regulation have been implicated in the etiology and progression of autism spectrum disorders (ASD), with the enzyme cytochrome P450 family 11 subfamily A member 1 (CYP11A1)-a key catalyst in cholesterol side-chain cleavage, prominently expressed in the adrenal glands, ovaries, testes, and placenta-standing at the forefront of these investigations. The potential link between aberrations in placental Cyp11a1 expression and the resultant neurodevelopmental disorders, along with the mechanisms underpinning such associations, remains inadequately delineated. In this study, we employed a placental trophoblast-specific Cyp11a1 Hipp11 (H11) knock-in murine model to dissect the phenotypic manifestations within the placenta and progeny, thereby elucidating the underlying mechanistic pathways.

A combined nutritional risk index and carcinoembryonic antigen score predicts the outcome in radically resected colorectal cancer.

Background: Nutritional risk index (NRI) and carcinoembryonic antigen (CEA) are useful prognostic markers in colorectal cancer (CRC); however, the prognostic value of a combination of the NRI and CEA, namely, the NRI and CEA score (NCS), needs further investigation.

Methods: Stage I-III CRC patients were collected and then divided into three subgroups by counting the NCS: NCS 1: high NRI with normal CEA; NCS 2: high NRI with elevated CEA or low NRI with normal CEA; and NCS 3: low NRI with elevated CEA. The differences in outcome, counted as disease-free survival (DFS) and overall survival (OS), were tested among the subgroups.

EMPDTA: An End-to-End Multimodal Representation Learning Framework with Pocket Online Detection for Drug-Target Affinity Prediction.

Accurately predicting drug-target interactions is a critical yet challenging task in drug discovery. Traditionally, pocket detection and drug-target affinity prediction have been treated as separate aspects of drug-target interaction, with few methods combining these tasks within a unified deep learning system to accelerate drug development. In this study, we propose EMPDTA, an end-to-end framework that integrates protein pocket prediction and drug-target affinity prediction to provide a comprehensive understanding of drug-target interactions.

Recognition of autism spectrum disorder in children based on electroencephalogram network topology.

Although our knowledge of autism spectrum disorder (ASD) has been deepened, the accurate diagnosis of ASD from normal individuals is still left behind. In this study, we proposed to apply the spatial pattern of the network topology (SPN) to identify children with ASD from normal ones. Based on two independent batches of electroencephalogram datasets collected separately, the accurate recognition of ASD from normal children was achieved by applying the proposed SPN features.

MGNR: A Multi-Granularity Neighbor Relationship and Its Application in KNN Classification and Clustering Methods.

In the real world, data distributions often exhibit multiple granularities. However, the majority of existing neighbor-based machine-learning methods rely on manually setting a single-granularity for neighbor relationships. These methods typically handle each data point using a single-granularity approach, which severely affects their accuracy and efficiency.

Association between blood ethylene oxide levels and the prevalence of periodontitis: evidence from NHANES 2013-2014.

Background: The study aimed to establish a link between blood ethylene oxide (EO) levels and periodontitis, given the growing concern about EO's detrimental health effects.

Materials And Methods: The study included 1006 adults from the 2013-2014 National Health and Nutrition Examination Survey (NHANES) dataset. We assessed periodontitis prevalence across groups, used weighted binary logistic regression and restricted cubic spline fitting for HbEO-periodontitis association, and employed Receiver Operating Characteristic (ROC) curves for prediction.

Systemic Immune-Inflammation Index and Systemic Inflammation Response Index are Associated With Periodontitis: Evidence From NHANES 2009 to 2014.

Introduction And Aims: Periodontitis, a chronic inflammatory condition affecting the supporting structures of the teeth, is a substantial public health burrden whilst impacting the life quality of those affected. Elevated levels of systemic immune-inflammation index (SII) and systemic inflammation response index (SIRI) have been implicated in various inflammatory conditions. This study aimed to investigate the relationship between SII and SIRI with periodontitis.