GPSFun: geometry-aware protein sequence function predictions with language models.

Knowledge of protein function is essential for elucidating disease mechanisms and discovering new drug targets. However, there is a widening gap between the exponential growth of protein sequences and their limited function annotations. In our prior studies, we have developed a series of methods including GraphPPIS, GraphSite, LMetalSite and SPROF-GO for protein function annotations at residue or protein level. To further enhance their applicability and performance, we now present GPSFun, a versatile web server for Geometry-aware Protein Sequence Function annotations, which equips our previous tools with language models and geometric deep learning. Specifically, GPSFun employs large language models to efficiently predict 3D conformations of the input protein sequences and extract informative sequence embeddings. Subsequently, geometric graph neural networks are utilized to capture the sequence and structure patterns in the protein graphs, facilitating various downstream predictions including protein-ligand binding sites, gene ontologies, subcellular locations and protein solubility. Notably, GPSFun achieves superior performance to state-of-the-art methods across diverse tasks without requiring multiple sequence alignments or experimental protein structures. GPSFun is freely available to all users at https://bio-web1.nscc-gz.cn/app/GPSFun with user-friendly interfaces and rich visualizations.

EVLncRNAs 3.0: an updated comprehensive database for manually curated functional long non-coding RNAs validated by low-throughput experiments.

Long noncoding RNAs (lncRNAs) have emerged as crucial regulators across diverse biological processes and diseases. While high-throughput sequencing has enabled lncRNA discovery, functional characterization remains limited. The EVLncRNAs database is the first and exclusive repository for all experimentally validated functional lncRNAs from various species. After previous releases in 2018 and 2021, this update marks a major expansion through exhaustive manual curation of nearly 25 000 publications from 15 May 2020, to 15 May 2023. It incorporates substantial growth across all categories: a 154% increase in functional lncRNAs, 160% in associated diseases, 186% in lncRNA-disease associations, 235% in interactions, 138% in structures, 234% in circular RNAs, 235% in resistant lncRNAs and 4724% in exosomal lncRNAs. More importantly, it incorporated additional information include functional classifications, detailed interaction pathways, homologous lncRNAs, lncRNA locations, COVID-19, phase-separation and organoid-related lncRNAs. The web interface was substantially improved for browsing, visualization, and searching. ChatGPT was tested for information extraction and functional overview with its limitation noted. EVLncRNAs 3.0 represents the most extensive curated resource of experimentally validated functional lncRNAs and will serve as an indispensable platform for unravelling emerging lncRNA functions. The updated database is freely available at https://www.sdklab-biophysics-dzu.net/EVLncRNAs3/.

Accurately identifying nucleic-acid-binding sites through geometric graph learning on language model predicted structures.

The interactions between nucleic acids and proteins are important in diverse biological processes. The high-quality prediction of nucleic-acid-binding sites continues to pose a significant challenge. Presently, the predictive efficacy of sequence-based methods is constrained by their exclusive consideration of sequence context information, whereas structure-based methods are unsuitable for proteins lacking known tertiary structures. Though protein structures predicted by AlphaFold2 could be used, the extensive computing requirement of AlphaFold2 hinders its use for genome-wide applications. Based on the recent breakthrough of ESMFold for fast prediction of protein structures, we have developed GLMSite, which accurately identifies DNA- and RNA-binding sites using geometric graph learning on ESMFold predicted structures. Here, the predicted protein structures are employed to construct protein structural graph with residues as nodes and spatially neighboring residue pairs for edges. The node representations are further enhanced through the pre-trained language model ProtTrans. The network was trained using a geometric vector perceptron, and the geometric embeddings were subsequently fed into a common network to acquire common binding characteristics. Finally, these characteristics were input into two fully connected layers to predict binding sites with DNA and RNA, respectively. Through comprehensive tests on DNA/RNA benchmark datasets, GLMSite was shown to surpass the latest sequence-based methods and be comparable with structure-based methods. Moreover, the prediction was shown useful for inferring nucleic-acid-binding proteins, demonstrating its potential for protein function discovery. The datasets, codes, and trained models are available at https://github.com/biomed-AI/nucleic-acid-binding.

Fast and accurate protein function prediction from sequence through pretrained language model and homology-based label diffusion.

Protein function prediction is an essential task in bioinformatics which benefits disease mechanism elucidation and drug target discovery. Due to the explosive growth of proteins in sequence databases and the diversity of their functions, it remains challenging to fast and accurately predict protein functions from sequences alone. Although many methods have integrated protein structures, biological networks or literature information to improve performance, these extra features are often unavailable for most proteins. Here, we propose SPROF-GO, a Sequence-based alignment-free PROtein Function predictor, which leverages a pretrained language model to efficiently extract informative sequence embeddings and employs self-attention pooling to focus on important residues. The prediction is further advanced by exploiting the homology information and accounting for the overlapping communities of proteins with related functions through the label diffusion algorithm. SPROF-GO was shown to surpass state-of-the-art sequence-based and even network-based approaches by more than 14.5, 27.3 and 10.1% in area under the precision-recall curve on the three sub-ontology test sets, respectively. Our method was also demonstrated to generalize well on non-homologous proteins and unseen species. Finally, visualization based on the attention mechanism indicated that SPROF-GO is able to capture sequence domains useful for function prediction. The datasets, source codes and trained models of SPROF-GO are available at https://github.com/biomed-AI/SPROF-GO. The SPROF-GO web server is freely available at http://bio-web1.nscc-gz.cn/app/sprof-go.

An uncertainty-based interpretable deep learning framework for predicting breast cancer outcome.

BACKGROUND: Predicting outcome of breast cancer is important for selecting appropriate treatments and prolonging the survival periods of patients. Recently, different deep learning-based methods have been carefully designed for cancer outcome prediction. However, the application of these methods is still challenged by interpretability. In this study, we proposed a novel multitask deep neural network called UISNet to predict the outcome of breast cancer. The UISNet is able to interpret the importance of features for the prediction model via an uncertainty-based integrated gradients algorithm. UISNet improved the prediction by introducing prior biological pathway knowledge and utilizing patient heterogeneity information. RESULTS: The model was tested in seven public datasets of breast cancer, and showed better performance (average C-index = 0.691) than the state-of-the-art methods (average C-index = 0.650, ranged from 0.619 to 0.677). Importantly, the UISNet identified 20 genes as associated with breast cancer, among which 11 have been proven to be associated with breast cancer by previous studies, and others are novel findings of this study. CONCLUSIONS: Our proposed method is accurate and robust in predicting breast cancer outcomes, and it is an effective way to identify breast cancer-associated genes. The method codes are available at: https://github.com/chh171/UISNet .

Enhancing healthy aging with small molecules: A mitochondrial perspective.

The pursuit of enhanced health during aging has prompted the exploration of various strategies focused on reducing the decline associated with the aging process. A key area of this exploration is the management of mitochondrial dysfunction, a notable characteristic of aging. This review sheds light on the crucial role that small molecules play in augmenting healthy aging, particularly through influencing mitochondrial functions. Mitochondrial oxidative damage, a significant aspect of aging, can potentially be lessened through interventions such as coenzyme Q10, alpha-lipoic acid, and a variety of antioxidants. Additionally, this review discusses approaches for enhancing mitochondrial proteostasis, emphasizing the importance of mitochondrial unfolded protein response inducers like doxycycline, and agents that affect mitophagy, such as urolithin A, spermidine, trehalose, and taurine, which are vital for sustaining protein quality control. Of equal importance are methods for modulating mitochondrial energy production, which involve nicotinamide adenine dinucleotide boosters, adenosine 5'-monophosphate-activated protein kinase activators, and compounds like metformin and mitochondria-targeted tamoxifen that enhance metabolic function. Furthermore, the review delves into emerging strategies that encourage mitochondrial biogenesis. Together, these interventions present a promising avenue for addressing age-related mitochondrial degradation, thereby setting the stage for the development of innovative treatment approaches to meet this extensive challenge.

Prioritizing genomic variants pathogenicity via DNA, RNA, and protein-level features based on extreme gradient boosting.

Genetic diseases are mostly implicated with genetic variants, including missense, synonymous, non-sense, and copy number variants. These different kinds of variants are indicated to affect phenotypes in various ways from previous studies. It remains essential but challenging to understand the functional consequences of these genetic variants, especially the noncoding ones, due to the lack of corresponding annotations. While many computational methods have been proposed to identify the risk variants. Most of them have only curated DNA-level and protein-level annotations to predict the pathogenicity of the variants, and others have been restricted to missense variants exclusively. In this study, we have curated DNA-, RNA-, and protein-level features to discriminate disease-causing variants in both coding and noncoding regions, where the features of protein sequences and protein structures have been shown essential for analyzing missense variants in coding regions while the features related to RNA-splicing and RBP binding are significant for variants in noncoding regions and synonymous variants in coding regions. Through the integration of these features, we have formulated the Multi-level feature Genomic Variants Predictor (ML-GVP) using the gradient boosting tree. The method has been trained on more than 400,000 variants in the Sherloc-training set from the 6th critical assessment of genome interpretation with superior performance. The method is one of the two best-performing predictors on the blind test in the Sherloc assessment, and is further confirmed by another independent test dataset of de novo variants.

Genome-wide assessment of shared genetic landscape of idiopathic pulmonary fibrosis and its comorbidities.

Idiopathic pulmonary fibrosis (IPF) is a progressive interstitial lung disease accompanied by both local and systemic comorbidities. Genetic factors play a role in the development of IPF and certain associated comorbidities. Nevertheless, it is uncertain whether there are shared genetic factors underlying IPF and these comorbidities. To bridge this knowledge gap, we conducted a systematic investigation into the shared genetic architecture between IPF and ten prevalent heritable comorbidities (i.e., body mass index [BMI], coronary artery disease [CAD], chronic obstructive pulmonary disease [COPD], gastroesophageal reflux disease, lung cancer, major depressive disorder [MDD], obstructive sleep apnoea, pulmonary hypertension [PH], stroke, and type 2 diabetes), by utilizing large-scale summary data from their respective genome-wide association studies and multi-omics studies. We revealed significant (false discovery rate [FDR] < 0.05) and moderate genetic correlations between IPF and seven comorbidities, excluding lung cancer, MDD and PH. Evidence suggested a partially putative causal effect of IPF on CAD. Notably, we observed FDR-significant genetic enrichments in lung for the cross-trait between IPF and CAD and in liver for the cross-trait between IPF and COPD. Additionally, we identified 65 FDR-significant genes over-represented in 20 biological pathways related to the etiology of IPF, BMI, and COPD, including inflammation-related mucin gene clusters. Several of these genes were associated with clinically relevant drugs for the treatment of IPF, CAD, and/or COPD. Our results underscore the pervasive shared genetic basis between IPF and its common comorbidities and hold future implications for early diagnosis of IPF-related comorbidities, drug repurposing, and the development of novel therapies for IPF.

Genome-wide association and Mendelian randomization analysis provide insights into the shared genetic architecture between high-dimensional electrocardiographic features and ischemic heart disease.

Observational studies have revealed that ischemic heart disease (IHD) has a unique manifestation on electrocardiographic (ECG). However, the genetic relationships between IHD and ECG remain unclear. We took 12-lead ECG as phenotypes to conduct genome-wide association studies (GWAS) for 41,960 samples from UK-Biobank (UKB). By leveraging large-scale GWAS summary of ECG and IHD (downloaded from FinnGen database), we performed LD score regression (LDSC), Mendelian randomization (MR), and polygenic risk score (PRS) regression to explore genetic relationships between IHD and ECG. Finally, we constructed an XGBoost model to predict IHD by integrating PRS and ECG. The GWAS identified 114 independent SNPs significantly (P value < 5 × 10-8/800, where 800 denotes the number of ECG features) associated with ECG. LDSC analysis indicated significant (P value < 0.05) genetic correlations between 39 ECG features and IHD. MR analysis performed by five approaches showed a putative causal effect of IHD on four S wave related ECG features at lead III. Integrating PRS for these ECG features with age and gender, the XGBoost model achieved Area Under Curve (AUC) 0.72 in predicting IHD. Here, we provide genetic evidence supporting S wave related ECG features at lead III to monitor the IHD risk, and open up a unique approach to integrate ECG with genetic factors for pre-warning IHD.

Genetic evidence for T-wave area from 12-lead electrocardiograms to monitor cardiovascular diseases in patients taking diabetes medications.

Aims Many studies indicated use of diabetes medications can influence the electrocardiogram (ECG), which remains the simplest and fastest tool for assessing cardiac functions. However, few studies have explored the role of genetic factors in determining the relationship between the use of diabetes medications and ECG trace characteristics (ETC). Methods Genome-wide association studies (GWAS) were performed for 168 ETCs extracted from the 12-lead ECGs of 42,340 Europeans in the UK Biobank. The genetic correlations, causal relationships, and phenotypic relationships of these ETCs with medication usage, as well as the risk of cardiovascular diseases (CVDs), were estimated by linkage disequilibrium score regression (LDSC), Mendelian randomization (MR), and regression model, respectively. Results The GWAS identified 124 independent single nucleotide polymorphisms (SNPs) that were study-wise and genome-wide significantly associated with at least one ETC. Regression model and LDSC identified significant phenotypic and genetic correlations of T-wave area in lead aVR (aVR_T-area) with usage of diabetes medications (ATC code: A10 drugs, and metformin), and the risks of ischemic heart disease (IHD) and coronary atherosclerosis (CA). MR analyses support a putative causal effect of the use of diabetes medications on decreasing aVR_T-area, and on increasing risk of IHD and CA. ConclusionPatients taking diabetes medications are prone to have decreased aVR_T-area and an increased risk of IHD and CA. The aVR_T-area is therefore a potential ECG marker for pre-clinical prediction of IHD and CA in patients taking diabetes medications.

VCAT: an integrated variant function annotation tools.

The development of sequencing technology has promoted discovery of variants in the human genome. Identifying functions of these variants is important for us to link genotype to phenotype, and to diagnose diseases. However, it usually requires researchers to visit multiple databases. Here, we presented a one-stop webserver for variant function annotation tools (VCAT, https://biomed.nscc-gz.cn/zhaolab/VCAT/ ) that is the first one connecting variant to functions via the epigenome, protein, drug and RNA. VCAT is also the first one to make all annotations visualized in interactive charts or molecular structures. VCAT allows users to upload data in VCF format, and download results via a URL. Moreover, VCAT has annotated a huge number (1,262,041,068) of variants collected from dbSNP, 1000 Genomes projects, gnomAD, ICGC, TCGA, and HPRC Pangenome project. For these variants, users are able to searcher their functions, related diseases and drugs from VCAT. In summary, VCAT provides a one-stop webserver to explore the potential functions of human genomic variants including their relationship with diseases and drugs.

Capturing large genomic contexts for accurately predicting enhancer-promoter interactions.

Enhancer-promoter interaction (EPI) is a key mechanism underlying gene regulation. EPI prediction has always been a challenging task because enhancers could regulate promoters of distant target genes. Although many machine learning models have been developed, they leverage only the features in enhancers and promoters, or simply add the average genomic signals in the regions between enhancers and promoters, without utilizing detailed features between or outside enhancers and promoters. Due to a lack of large-scale features, existing methods could achieve only moderate performance, especially for predicting EPIs in different cell types. Here, we present a Transformer-based model, TransEPI, for EPI prediction by capturing large genomic contexts. TransEPI was developed based on EPI datasets derived from Hi-C or ChIA-PET data in six cell lines. To avoid over-fitting, we evaluated the TransEPI model by testing it on independent test datasets where the cell line and chromosome are different from the training data. TransEPI not only achieved consistent performance across the cross-validation and test datasets from different cell types but also outperformed the state-of-the-art machine learning and deep learning models. In addition, we found that the improved performance of TransEPI was attributed to the integration of large genomic contexts. Lastly, TransEPI was extended to study the non-coding mutations associated with brain disorders or neural diseases, and we found that TransEPI was also useful for predicting the target genes of non-coding mutations.

AlphaFold2-aware protein-DNA binding site prediction using graph transformer.

Protein-DNA interactions play crucial roles in the biological systems, and identifying protein-DNA binding sites is the first step for mechanistic understanding of various biological activities (such as transcription and repair) and designing novel drugs. How to accurately identify DNA-binding residues from only protein sequence remains a challenging task. Currently, most existing sequence-based methods only consider contextual features of the sequential neighbors, which are limited to capture spatial information. Based on the recent breakthrough in protein structure prediction by AlphaFold2, we propose an accurate predictor, GraphSite, for identifying DNA-binding residues based on the structural models predicted by AlphaFold2. Here, we convert the binding site prediction problem into a graph node classification task and employ a transformer-based variant model to take the protein structural information into account. By leveraging predicted protein structures and graph transformer, GraphSite substantially improves over the latest sequence-based and structure-based methods. The algorithm is further confirmed on the independent test set of 181 proteins, where GraphSite surpasses the state-of-the-art structure-based method by 16.4% in area under the precision-recall curve and 11.2% in Matthews correlation coefficient, respectively. We provide the datasets, the predicted structures and the source codes along with the pre-trained models of GraphSite at https://github.com/biomed-AI/GraphSite. The GraphSite web server is freely available at https://biomed.nscc-gz.cn/apps/GraphSite.

Alignment-free metal ion-binding site prediction from protein sequence through pretrained language model and multi-task learning.

More than one-third of the proteins contain metal ions in the Protein Data Bank. Correct identification of metal ion-binding residues is important for understanding protein functions and designing novel drugs. Due to the small size and high versatility of metal ions, it remains challenging to computationally predict their binding sites from protein sequence. Existing sequence-based methods are of low accuracy due to the lack of structural information, and time-consuming owing to the usage of multi-sequence alignment. Here, we propose LMetalSite, an alignment-free sequence-based predictor for binding sites of the four most frequently seen metal ions in BioLiP (Zn2+, Ca2+, Mg2+ and Mn2+). LMetalSite leverages the pretrained language model to rapidly generate informative sequence representations and employs transformer to capture long-range dependencies. Multi-task learning is adopted to compensate for the scarcity of training data and capture the intrinsic similarities between different metal ions. LMetalSite was shown to surpass state-of-the-art structure-based methods by more than 19.7, 14.4, 36.8 and 12.6% in area under the precision recall on the four independent tests, respectively. Further analyses indicated that the self-attention modules are effective to learn the structural contexts of residues from protein sequence. We provide the data sets, source codes and trained models of LMetalSite at https://github.com/biomed-AI/LMetalSite.

Long-term abuse of caffeine sodium benzoate induces endothelial cells injury and leads to coagulation dysfunction.

Our hospital admitted a patient who had difficulty in coagulation even after blood replacement, and the patient had abused caffeine sodium benzoate (CSB) for more than 20 years. Hence, we aimed to explore whether CSB may cause dysfunction in vascular endothelial cells and its possible mechanism. Low, medium, and high concentrations of serum of long-term CSB intake patients were used to treat HUVECs, with LPS as the positive control. MTT and CCK8 were performed to verify CSB's damaging effect on HUVECs. The expression of ET-1, ICAM-1, VCAM-1, and E-selectin were measured by ELISA. TUNEL assay and Matrigel tube formation assay were carried out to detect apoptosis and angiogenesis of HUVECs. Flow cytometry was applied to analyze cell cycles and expression of CD11b, PDGF, and ICAM-1. Expression of PDGF-BB and PCNA were examined by western blot. The activation of MAPK signaling pathway was detected by qRT-PCR and western blot. Intracellular Ca2+ density was detected by fluorescent probes. CCK8 assay showed high concentration of CSB inhibited cell viability. Cell proliferation and angiogenesis were inhibited by CSB. ET-1, ICAM-1, VCAM-1, and E-selectin upregulated in CSB groups. CSB enhanced apoptosis of HUVECs. CD11b, ICAM-1 increased and PDGF reduced in CSB groups. The expression level and phosphorylation level of MEK, ERK, JUN, and p38 in MAPK pathway elevated in CSB groups. The expression of PCNA and PDGF-BB was suppressed by CSB. Intracellular Ca2+ intensity was increased by CSB. Abuse of CSB injured HUVECs and caused coagulation disorders.

Autoimmune diseases exhibit shared alterations in the gut microbiota.

OBJECTIVE: Accumulating evidence from microbial studies have highlighted the modulatory roles of intestinal microbes in numerous human diseases, however, the shared microbial signatures across different diseases remain relatively unclear. METHODS: To consolidate existing knowledge across multiple studies, we performed meta-analyses of 17 disease types, covering 34 case-control datasets of 16S rRNA sequencing data, to identify shared alterations among different diseases. Furthermore, the impact of a microbial species, Lactobacillus salivarius, was established in a dextran sodium sulphate-induced colitis model and a collagen type II-induced arthritis mouse model. RESULTS: Microbial alterations among autoimmune diseases were substantially more consistent compared with that of other diseases (cancer, metabolic disease and nervous system disease), with microbial signatures exhibiting notable discriminative power for disease prediction. Autoimmune diseases were characterized by the enrichment of Enterococcus, Veillonella, Streptococcus and Lactobacillus and the depletion of Ruminococcus, Gemmiger, Oscillibacter, Faecalibacterium, Lachnospiracea incertae sedis, Anaerostipes, Coprococcus, Alistipes, Roseburia, Bilophila, Barnesiella, Dorea, Ruminococcus2, Butyricicoccus, Phascolarctobacterium, Parabacteroides and Odoribacter, among others. Functional investigation of L. salivarius, whose genus was commonly enriched in numerous autoimmune diseases, demonstrated protective roles in two separate inflammatory mouse models. CONCLUSION: Our study highlights a strong link between autoimmune diseases and the gut microbiota, with notably consistent microbial alterations compared with that of other diseases, indicating that therapeutic strategies that target the gut microbiome may be transferable across different autoimmune diseases. Functional validation of L. salivarius highlighted that bacterial genera associated with disease may not always be antagonistic, but may represent protective or adaptive responses to disease.

Clinical Characteristics and Nomogram for Predicting Mortality in Patients with Postoperative Bloodstream Infection in Surgical Intensive Care Unit.

Background: Bloodstream infection is amongst the leading causes of mortality for critical postoperative patients. However, data, especially from developing countries, are scary. Clinical decision-making tools for predicting postoperative bloodstream infection-related mortality are important but still lacking. Objective: To analyze the distribution of pathogens and develop a nomogram for predicting mortality in patients with postoperative bloodstream infection in the surgical intensive care unit. Methods: The clinical data, infection and pathogen-related data, and prognosis of patients with PBSI in the SICU from January 2017 to January 2022 were retrospectively collected. The distribution of pathogens and clinical characteristics of patients with PBSI were analyzed. The patients were assigned to a died group and a survived group according to their survival status. Independent predictors for mortality were identified by univariate and multivariate analyses. A nomogram for predicting PBSI-related death was developed based on these independent predictors. Calibration and decision-curve analysis were established to evaluate the nomogram. We collected postoperative patients admitted to our center from February 2022 to June 2023 as external validation sets to verify the nomogram. We also add the Brier score to further validate the model. Results: In the training set, 7128 patients admitted to the SICU after different types of surgery were collected. A total of 198 patients and 308 pathogens were finally enrolled. The mean age of patients with PBSI was 64.38 ± 16.22 (range 18-90) years, and 56.1% were male. Forty-five patients (22.7%) died in the hospital. Five independent predictors including BMI, APACHE II score, estimated glomerular filtration rate (eGFR), urine volume in the first 24 hours after surgery, and peak temperature before positive blood cultures were selected to establish the nomogram. The area under the receiver operating characteristic curve for the prediction model was 0.922. Calibration curve and decision curve analysis showed good performance of the nomogram. Seventy patients with PBSI were collected as an external validation set, and thirteen patients died in this set. The external validation set was used to validate the nomogram, and the results showed that the AUC was 0.930 which was higher than that in the training set indicating that the nomogram had a good discrimination. The brier score was 0.087 for training set and 0.050 for validation set. Conclusions: PBSI was one of the key issues that clinicians were concerned and could be assessed with a good predictive model using simple clinical factors.

Preclinical Safety Evaluation of the Human-Identical Milk Oligosaccharide Lacto-N-Triose II.

Lacto-N-triose II (LNT II), an essential human milk oligosaccharide and precursor to lacto-N-tetraose (LNT) and lacto-N-neotetraose (LNnT), was evaluated for safety. Genotoxicity was assessed through in vitro tests including Bacterial Reverse Mutation Test and mammalian cell micronucleus test, and a subchronic oral gavage toxicity study was conducted on juvenile Sprague-Dawley rats. In this study, LNT II was administered at dose levels of 0, 1,500, 2,500, or 5,000 mg/kg body weight (bw)/day for 90 days, followed by a 4-week treatment-free recovery period. LNT II was non-genotoxic in the in vitro assays. No compound-related effects were observed across all dosage levels based on various measures, including clinical observations, body weight gain, feed consumption, clinical pathology, organ weights, and histopathology. Consequently, the highest dosage of 5,000 mg/kg bw/day was established as the no-observed-adverse-effect-level (NOAEL). These results suggest the safe use of LNT II in young children formula and as a food ingredient, within the limits found naturally in human breast milk.

Machine learning-based prediction models affecting the recovery of postoperative bowel function for patients undergoing colorectal surgeries.

PURPOSE: The debate surrounding factors influencing postoperative flatus and defecation in patients undergoing colorectal resection prompted this study. Our objective was to identify independent risk factors and develop prediction models for postoperative bowel function in patients undergoing colorectal surgeries. METHODS: A retrospective analysis of medical records was conducted for patients who undergoing colorectal surgeries at Peking University People's Hospital from January 2015 to October 2021. Machine learning algorithms were employed to identify risk factors and construct prediction models for the time of the first postoperative flatus and defecation. The prediction models were evaluated using sensitivity, specificity, the Youden index, and the area under the receiver operating characteristic curve (AUC) through logistic regression, random forest, Naïve Bayes, and extreme gradient boosting algorithms. RESULTS: The study included 1358 patients for postoperative flatus timing analysis and 1430 patients for postoperative defecation timing analysis between January 2015 and December 2020 as part of the training phase. Additionally, a validation set comprised 200 patients who undergoing colorectal surgeries from January to October 2021. The logistic regression prediction model exhibited the highest AUC (0.78) for predicting the timing of the first postoperative flatus. Identified independent risk factors influencing the time of first postoperative flatus were Age (p < 0.01), oral laxatives for bowel preparation (p = 0.01), probiotics (p = 0.02), oral antibiotics for bowel preparation (p = 0.02), duration of operation (p = 0.02), postoperative fortified antibiotics (p = 0.02), and time of first postoperative feeding (p < 0.01). Furthermore, logistic regression achieved an AUC of 0.72 for predicting the time of first postoperative defecation, with age (p < 0.01), oral antibiotics for bowel preparation (p = 0.01), probiotics (p = 0.01), and time of first postoperative feeding (p < 0.01) identified as independent risk factors. CONCLUSIONS: The study suggests that he use of probiotics and early recovery of diet may enhance the recovery of bowel function in patients undergoing colorectal surgeries. Among the various analytical methods used, logistic regression emerged as the most effective approach for predicting the timing of the first postoperative flatus and defecation in this patient population.

Effectiveness and feasibility of 5G-based remote interactive ultrasound training in critical care.

BACKGROUND: Ultrasound has widely used in various medical fields related to critical care. While online and offline ultrasound trainings are faced by certain challenges, remote ultrasound based on the 5G cloud platform has been gradually adopted in many clinics. However, no study has used the 5G remote ultrasound cloud platform operating system for standardized critical care ultrasound training. This study aimed to evaluate the feasibility and effectiveness of 5G-based remote interactive ultrasound training for standardized diagnosis and treatment in critical care settings. METHODS: A 5G-based remote interactive ultrasound training system was constructed, and the course was piloted among critical care physicians. From July 2022 to July 2023, 90 critical care physicians from multiple off-site locations were enrolled and randomly divided into experimental and control groups. The 45 physicians in the experimental group were trained using the 5G-based remote interactive ultrasound training system, while the other 45 in the control group were taught using theoretical online videos. The theoretical and practical ultrasonic capabilities of both groups were evaluated before and after the training sessions, and their levels of satisfaction with the training were assessed as well. RESULTS: The total assessment scores for all of the physicians were markedly higher following the training (80.7 ± 11.9) compared to before (42.1 ± 13.4) by a statistically significant margin (P < 0.001). Before participating in the training, the experimental group scored 42.2 ± 12.5 in the critical care ultrasound competency, and the control group scored 41.9 ± 14.3-indicating no significant differences in their assessment scores (P = 0.907). After participating in the training, the experimental group's assessment scores were 88.4 ± 6.7, which were significantly higher than those of the control group (72.9 ± 10.8; P < 0.001). The satisfaction score of the experimental group was 42.6 ± 2.3, which was also significantly higher than that of the control group (34.7 ± 3.1, P < 0.001). CONCLUSION: The 5G-based remote interactive ultrasound training system was well-received and effective for critical care. These findings warrant its further promotion and application.