Independent Datasets Research Articles

Use of Cannabinoids by People Who Consume Kratom in the United States.

To estimate lifetime, past-year, and past-month prevalence of kratom, cannabis, and cannabidiol-only product use among adults 18 years and older in the United States, using 2 independent datasets. Utilizing (a) the 2022 National Survey on Drug Use and Health (NSDUH) and (b) a 2022 online national convenience sample of adults who use kratom regularly (from our research group at the National Institute on Drug Abuse [NIDA]), we examined key demographic information as well as lifetime, past-year, and past-month substance use and preferences. Among the full sample of adults from the 2022 NSDUH, the prevalence of lifetime use was 49.69% for cannabis, 34.09% for cannabidiol-only products, and 1.93% for kratom. When solely examining participants who have used kratom, both independent datasets showed higher proportions of cannabis use over the lifetime-92.81% (95% confidence interval: 90.31-95.31) in the NSDUH subset and 92.16% (95% confidence interval: 89.37-94.95) in our NIDA sample. Our study demonstrates that people are co-using kratom with cannabis and/or cannabidiol-only products at the same time or during the same time period, though more research is needed to understand people's motivations and practices for such co-use. Co-use might result in herb-herb interactions that may impact research findings and clinical outcomes for people who use kratom.

The role of Immune cells in Alzheimer's disease: a bidirectional Mendelian randomization study

BackgroundAlzheimer's disease (AD) is a leading cause of dementia, characterized by the accumulation of amyloid-beta (Aβ) and hyperphosphorylated tau proteins, leading to neuroinflammation and neuronal damage. The role of the immune system in AD pathogenesis is increasingly recognized, prompting an exploration of the causal relationship between immune cells and AD by using Mendelian randomization (MR) approaches.MethodsUtilizing genome-wide association study (GWAS) data from European cohorts, we conducted an MR study to investigate the causal links between immune cell phenotypes and AD. We selected single nucleotide polymorphisms (SNPs) associated with immune cell traits at a genome-wide significance threshold and applied various MR methods, including MR Egger, Weighted median, and inverse variance weighted analysis, to assess the causality between 731 immune phenotypes and AD.ResultsOur MR analysis identified 15 immune cell types with significant causal relationships to AD pathogenesis. Notably, the absolute count of CD28−CD4−CD8− T cells and the expression of HLA DR on B cells were linked to a protective effect against AD, while 13 other immune phenotypes were identified as contributing to the risk factors for the disease. The causal effects of AD on immunophenotypic traits are predominantly negative, implying that AD may impair the functionality of immune cells. Validation through independent datasets, such as FinnGen and GCST90027158, confirmed the causal association between six specific immune cells and AD.ConclusionThis comprehensive MR study elucidates the intricate network of causal relationships between diverse immunophenotypic traits and AD, providing novel insights into the immunopathogenesis of AD. The findings suggest potential immunological targets that could be leveraged for early diagnosis, disease monitoring, and therapeutic intervention.

Neurochemical organization of cortical proteinopathy and neurophysiology along the Alzheimer's disease continuum.

Despite parallel research indicating amyloid-β accumulation, alterations in cortical neurophysiological signaling, and multi-system neurotransmitter disruptions in Alzheimer's disease (AD), the relationships between these phenomena remains unclear. Using magnetoencephalography, positron emission tomography, and an atlas of 19 neurotransmitters, we studied the alignment between neurophysiological alterations, amyloid-β deposition, and the neurochemical gradients of the cortex. In patients with mild cognitive impairment and AD, changes in cortical rhythms were topographically aligned with cholinergic, serotonergic, and dopaminergic systems. These alignments correlated with the severity of clinical impairments. Additionally, cortical amyloid-β plaques were preferentially deposited along neurochemical boundaries, influencing how neurophysiological alterations align with muscarinic acetylcholine receptors. Most of the amyloid-β-neurochemical and alpha-band neuro-physio-chemical alignments replicated in an independent dataset of individuals with asymptomatic amyloid-β accumulation. Our findings demonstrate that AD pathology aligns topographically with the cortical distribution of chemical neuromodulator systems and scales with clinical severity, with implications for potential pharmacotherapeutic pathways. Changes in cortical rhythms in Alzheimer's are organized along neurochemical boundaries. The strength of these alignments is related to clinical symptom severity. Deposition of amyloid-β (Aβ) is aligned with similar neurotransmitter systems. Aβ deposition mediates the alignment of beta rhythms with cholinergic systems. Most alignments replicate in participants with pre-clinical Alzheimer's pathology.

Exploring the butyrate metabolism-related shared genes in metabolic associated steatohepatitis and ulcerative colitis

Metabolic-associated steatohepatitis (MASH) and ulcerative colitis (UC) exhibit a complex interconnection with immune dysfunction, dysbiosis of the gut microbiota, and activation of inflammatory pathways. This study aims to identify and validate critical butyrate metabolism-related shared genes between both UC and MASH. Clinical information and gene expression profiles were sourced from the Gene Expression Omnibus (GEO) database. Shared butyrate metabolism-related differentially expressed genes (sBM-DEGs) between UC and MASH were identified via various bioinformatics methods. Functional enrichment analysis was performed, and UC patients were categorized into subtypes using the consensus clustering algorithm based on sBM-DEGs. Key genes within sBM-DEGs were screened through Random Forest, Support Vector Machines-Recursive Feature Elimination, and Light Gradient Boosting. The diagnostic efficacy of these genes was evaluated using receiver operating characteristic (ROC) analysis on independent datasets. Additionally, the expression levels of characteristic genes were validated across multiple independent datasets and human specimens. Forty-nine shared DEGs between UC and MASH were identified, with enrichment analysis highlighting significant involvement in immune, inflammatory, and metabolic pathways. The intersection of butyrate metabolism-related genes with these DEGs produced 10 sBM-DEGs. These genes facilitated the identification of molecular subtypes of UC patients using an unsupervised clustering approach. ANXA5, CD44, and SLC16A1 were pinpointed as hub genes through machine learning algorithms and feature importance rankings. ROC analysis confirmed their diagnostic efficacy in UC and MASH across various datasets. Additionally, the expression levels of these three hub genes showed significant correlations with immune cells. These findings were validated across independent datasets and human specimens, corroborating the bioinformatics analysis results. Integrated bioinformatics identified three significant biomarkers, ANXA5, CD44, and SLC16A1, as DEGs linked to butyrate metabolism. These findings offer new insights into the role of butyrate metabolism in the pathogenesis of UC and MASH, suggesting its potential as a valuable diagnostic biomarker.

Single cell transcriptomes and multiscale networks from persons with and without Alzheimer’s disease

The emergence of single nucleus RNA sequencing (snRNA-seq) offers to revolutionize the study of Alzheimer’s disease (AD). Integration with complementary multiomics data such as genetics, proteomics and clinical data provides powerful opportunities to link cell subpopulations and molecular networks with a broader disease-relevant context. We report snRNA-seq profiles from superior frontal gyrus samples from 101 well characterized subjects from the Banner Brain and Body Donation Program in combination with whole genome sequences. We report findings that link common AD risk variants with CR1 expression in oligodendrocytes as well as alterations in hematological parameters. We observed an AD-associated CD83(+) microglial subtype with unique molecular networks and which is associated with immunoglobulin IgG4 production in the transverse colon. Our major observations were replicated in two additional, independent snRNA-seq data sets. These findings illustrate the power of multi-tissue molecular profiling to contextualize snRNA-seq brain transcriptomics and reveal disease biology.

Gene-age interaction study of breast cancer prognosis based on epigenomic data

Objective: Exploring gene-age interactions associated with breast cancer prognosis based on epigenomic data. Methods: Differential expression analysis of DNA methylation was conducted using multiple independent epigenomic datasets of breast cancer from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO). The false discovery rate (FDR) method was used for multiple corrections, retaining differentially methylated sites with q-FDR≤0.05. A three-stage analytic strategy was implemented, using a multivariable Cox proportional hazards regression model to examine gene-age interactions. In the discovery phase, signals with q-FDR ≤ 0.05 were screened out using TCGA-BRCA database. In validation phaseⅠ, the interaction was validated using GSE72245 data, with criteria of P≤0.05 and consistent effect direction. In validation phaseⅡ, the signals were further validated using GSE37754 and GSE75067 data. A prognostic prediction model was constructed by incorporating clinical indicators and interaction signals. Results: The three-stage analytic strategy identified a methylation site (cg16126280EBF1), which interacted with age to jointly affect the overall survival time of patients (interaction HR= 1.001 1,95%CI:1.000 7-1.001 5,P<0.001). Stratified analysis by age showed that the effect of hypermethylation of cg16126280EBF1 was completely opposite in younger patients (HR=0.550 5, 95%CI: 0.383 8-0.789 6, P=0.001) and older patients (HR=2.166 5, 95%CI: 1.285 2-3.652 2, P=0.004). Conclusions: The DNA methylation site cg16126280EBF1 exhibits an interaction with age, jointly influencing the prognosis of breast cancer in a complex association pattern. This finding contributes new population-based evidence for the development of age-specific targeted drugs.

Genetically predicted 1091 blood metabolites and 309 metabolite ratios in relation to risk of type 2 diabetes: a Mendelian randomization study

BackgroundMetabolic dysregulation represents a defining characteristic of Type 2 diabetes (T2DM). Nevertheless, there remains an absence of substantial evidence establishing a direct causal link between circulating blood metabolites and the promotion or prevention of T2DM. In addressing this gap, we employed Mendelian randomization (MR) analysis to investigate the potential causal association between 1,091 blood metabolites, 309 metabolite ratios, and the occurrence of T2DM.MethodsData encompassing single-nucleotide polymorphisms (SNPs) for 1,091 blood metabolites and 309 metabolite ratios were extracted from a Canadian Genome-wide association study (GWAS) involving 8,299 participants. To evaluate the causal link between these metabolites and Type 2 diabetes (T2DM), multiple methods including Inverse Variance Weighted (IVW), Weighted Median, MR Egger, Weighted Mode, and Simple Mode were employed. p-values underwent correction utilizing False Discovery Rates (FDR). Sensitivity analyses incorporated Cochran’s Q test, MR-Egger intercept test, MR-PRESSO, Steiger test, leave-one-out analysis, and single SNP analysis. The causal effects were visualized via Circos plot, forest plot, and scatter plot. Furthermore, for noteworthy, an independent T2DM GWAS dataset (GCST006867) was utilized for replication analysis. Metabolic pathway analysis of closely correlated metabolites was conducted using MetaboAnalyst 5.0.ResultsThe IVW analysis method utilized in this study revealed 88 blood metabolites and 37 metabolite ratios demonstrating a significant causal relationship with T2DM (p &amp;lt; 0.05). Notably, strong causal associations with T2DM were observed for specific metabolites: 1-linoleoyl-GPE (18:2) (IVW: OR:0.930, 95% CI: 0.899–0.962, p = 2.16 × 10−5), 1,2-dilinoleoyl-GPE (18:2/18:2) (IVW: OR:0.942, 95% CI: 0.917–0.968, p = 1.64 × 10−5), Mannose (IVW: OR:1.133, 95% CI: 1.072–1.197, p = 1.02 × 10−5), X-21829 (IVW: OR:1.036, 95% CI: 1.036–1.122, p = 9.44 × 10−5), and Phosphate to mannose ratio (IVW: OR:0.870, 95% CI: 0.818–0.926, p = 1.29 × 10−5, FDR = 0.008). Additionally, metabolic pathway analysis highlighted six significant pathways associated with T2DM development: Valine, leucine and isoleucine biosynthesis, Phenylalanine metabolism, Glycerophospholipid metabolism, Alpha-Linolenic acid metabolism, Sphingolipid metabolism, and Alanine, aspartate, and glutamate metabolism.ConclusionThis study identifies both protective and risk-associated metabolites that play a causal role in the development of T2DM. By integrating genomics and metabolomics, it presents novel insights into the pathogenesis of T2DM. These findings hold potential implications for early screening, preventive measures, and treatment strategies for T2DM.

Advancing driver fatigue detection in diverse lighting conditions for assisted driving vehicles with enhanced facial recognition technologies.

Against the backdrop of increasingly mature intelligent driving assistance systems, effective monitoring of driver alertness during long-distance driving becomes especially crucial. This study introduces a novel method for driver fatigue detection aimed at enhancing the safety and reliability of intelligent driving assistance systems. The core of this method lies in the integration of advanced facial recognition technology using deep convolutional neural networks (CNN), particularly suited for varying lighting conditions in real-world scenarios, significantly improving the robustness of fatigue detection. Innovatively, the method incorporates emotion state analysis, providing a multi-dimensional perspective for assessing driver fatigue. It adeptly identifies subtle signs of fatigue in rapidly changing lighting and other complex environmental conditions, thereby strengthening traditional facial recognition techniques. Validation on two independent experimental datasets, specifically the Yawn and YawDDR datasets, reveals that our proposed method achieves a higher detection accuracy, with an impressive 95.3% on the YawDDR dataset, compared to 90.1% without the implementation of Algorithm 2. Additionally, our analysis highlights the method's adaptability to varying brightness levels, improving detection accuracy by up to 0.05% in optimal lighting conditions. Such results underscore the effectiveness of our advanced data preprocessing and dynamic brightness adaptation techniques in enhancing the accuracy and computational efficiency of fatigue detection systems. These achievements not only showcase the potential application of advanced facial recognition technology combined with emotional analysis in autonomous driving systems but also pave new avenues for enhancing road safety and driver welfare.

Deep Learning-Based Vascular Aging Prediction From Retinal Fundus Images.

The purpose of this study was to establish and validate a deep learning model to screen vascular aging using retinal fundus images. Although vascular aging is considered a novel cardiovascular risk factor, the assessment methods are currently limited and often only available in developed regions. We used 8865 retinal fundus images and clinical parameters of 4376 patients from two independent datasets for training a deep learning algorithm. The gold standard for vascular aging was defined as a pulse wave velocity ≥1400 cm/s. The probability of the presence of vascular aging was defined as deep learning retinal vascular aging score, the Reti-aging score. We compared the performance of the deep learning model and clinical parameters by calculating the area under the receiver operating characteristics curve (AUC). We recruited clinical specialists, including ophthalmologists and geriatricians, to assess vascular aging in patients using retinal fundus images, aiming to compare the diagnostic performance between deep learning models and clinical specialists. Finally, the potential of Reti-aging score for identifying new-onset hypertension (NH) and new-onset carotid artery plaque (NCP) in the subsequent three years was examined. The Reti-aging score model achieved an AUC of 0.826 (95% confidence interval [CI] = 0.793-0.855) and 0.779 (95% CI = 0.765-0.794) in the internal and external dataset. It showed better performance in predicting vascular aging compared with the prediction with clinical parameters. The average accuracy of ophthalmologists (66.3%) was lower than that of the Reti-aging score model, whereas geriatricians were unable to make predictions based on retinal fundus images. The Reti-aging score was associated with the risk of NH and NCP (P < 0.05). The Reti-aging score model might serve as a novel method to predict vascular aging through analysis of retinal fundus images. Reti-aging score provides a novel indicator to predict new-onset cardiovascular diseases. Given the robust performance of our model, it provides a new and reliable method for screening vascular aging, especially in undeveloped areas.

MFTP-Tool: A Wide &amp; Deep Learning Framework for Multi-Functional Therapeutic Peptides Prediction

Background: The identification and functional prediction of Multifunctional Therapeutic Peptides (MFTP) play a pivotal role in drug discovery, particularly for conditions such as inflammation and hyperglycemia. Current computational methods exhibit limitations in their ability to accurately predict the multifunctionality of these peptides. Methods: We propose a novel Wide and Deep Learning Framework that integrates both deep learning and machine learning approaches. The deep learning segment processes word vectors using a neural network model, while the wide segment utilizes the physicochemical properties of peptides in a random forest-based model. This hybrid approach aims to enhance the accuracy of MFTP function prediction. Results: Our framework outperformed the existing PrMFTP predictor in terms of precision, coverage, accuracy, and absolute true values. The evaluation was conducted on both training and independent testing datasets, demonstrating the robustness and generalizability of our model. Conclusion: The proposed Wide &amp; Deep Learning Framework offers a significant advancement in the computational prediction of MFTP functions. The availability of our model through a userfriendly web interface at MFTP-Tool.m6aminer.cn provides a valuable tool for researchers in the field of therapeutic peptide-based drug discovery, potentially accelerating the development of new treatments.

A comprehensive meta-analysis of tissue resident memory T cells and their roles in shaping immune microenvironment and patient prognosis in non-small cell lung cancer

Tissue-resident memory T cells (TRM) are a specialized subset of long-lived memory T cells that reside in peripheral tissues. However, the impact of TRM-related immunosurveillance on the tumor-immune microenvironment (TIME) and tumor progression across various non-small-cell lung cancer (NSCLC) patient populations is yet to be elucidated. Our comprehensive analysis of multiple independent single-cell and bulk RNA-seq datasets of patient NSCLC samples generated reliable, unique TRM signatures, through which we inferred the abundance of TRM in NSCLC. We discovered that TRM abundance is consistently positively correlated with CD4+ T helper 1 cells, M1 macrophages, and resting dendritic cells in the TIME. In addition, TRM signatures are strongly associated with immune checkpoint and stimulatory genes and the prognosis of NSCLC patients. A TRM-based machine learning model to predict patient survival was validated and an 18-gene risk score was further developed to effectively stratify patients into low-risk and high-risk categories, wherein patients with high-risk scores had significantly lower overall survival than patients with low-risk. The prognostic value of the risk score was independently validated by the Cancer Genome Atlas Program (TCGA) dataset and multiple independent NSCLC patient datasets. Notably, low-risk NSCLC patients with higher TRM infiltration exhibited enhanced T-cell immunity, nature killer cell activation, and other TIME immune responses related pathways, indicating a more active immune profile benefitting from immunotherapy. However, the TRM signature revealed low TRM abundance and a lack of prognostic association among lung squamous cell carcinoma patients in contrast to adenocarcinoma, indicating that the two NSCLC subtypes are driven by distinct TIMEs. Altogether, this study provides valuable insights into the complex interactions between TRM and TIME and their impact on NSCLC patient prognosis. The development of a simplified 18-gene risk score provides a practical prognostic marker for risk stratification.

Size normalizing planktonic Foraminifera abundance in the water column

AbstractPlanktonic Foraminifera have been collected from the water column with different plankton sampling devices equipped with nets of various mesh sizes, which impedes direct comparison of observed quantifications. Here, we use data on the community size structure of planktonic Foraminifera to assess the impact of mesh size on the measured abundance (ind m−3) of planktonic Foraminifera. We use data from the FORCIS database (Chaabane et al., 2023, Scientific Data 10: 354) on the global ocean at different sampling depths over the past century. We find a global cumulative increase in abundance with size, which is best described using a Michaelis–Menten function. This function yields multiplication factors by which one size fraction can be normalized to any other size fraction equal to or larger than 100 μm. The resulting size normalization model is calibrated over a range of different depth intervals, and validated with an independent dataset from various depth ranges. The comparison to Berger's (1969, Deep. Res. Oceanogr. Abstr. 16: 1–24) equivalent catch approach shows a significant increase in the predictive skill of the model. The new size normalization scheme enables comparison of Foraminifera abundance data sampled with plankton nets of different mesh sizes, such as compiled in the FORCIS database. The correction methodology may be effectively employed for various other plankton groups such as diatoms and dinoflagellates.

Size normalizing planktonic Foraminifera abundance in the water column

AbstractPlanktonic Foraminifera have been collected from the water column with different plankton sampling devices equipped with nets of various mesh sizes, which impedes direct comparison of observed quantifications. Here, we use data on the community size structure of planktonic Foraminifera to assess the impact of mesh size on the measured abundance (ind m−3) of planktonic Foraminifera. We use data from the FORCIS database (Chaabane et al., 2023, Scientific Data 10: 354) on the global ocean at different sampling depths over the past century. We find a global cumulative increase in abundance with size, which is best described using a Michaelis–Menten function. This function yields multiplication factors by which one size fraction can be normalized to any other size fraction equal to or larger than 100 μm. The resulting size normalization model is calibrated over a range of different depth intervals, and validated with an independent dataset from various depth ranges. The comparison to Berger's (1969, Deep. Res. Oceanogr. Abstr. 16: 1–24) equivalent catch approach shows a significant increase in the predictive skill of the model. The new size normalization scheme enables comparison of Foraminifera abundance data sampled with plankton nets of different mesh sizes, such as compiled in the FORCIS database. The correction methodology may be effectively employed for various other plankton groups such as diatoms and dinoflagellates.

Genetically proxied IL-13 inhibition is associated with risk of psoriatic disease: Mendelian randomization study.

Inhibitors of the IL-13 pathway, such as dupilumab, are licensed for atopic dermatitis and asthma. Adverse events resembling psoriatic disease after dupilumab initiation have been reported, but evidence is limited to case reports with uncertain causality. We aimed to investigate whether genetically mimicked IL-13 inhibition (IL-13i) is associated with risk of psoriatic arthritis (PsA) and psoriasis. We instrumented IL-13i using a protein-coding variant in the IL13 gene, rs20541, that is associated with circulating eosinophil count (biomarker of IL-13i) at genome-wide significance in a study of 563,946 individuals. Outcome genetic data were taken from studies of PsA, psoriasis, and related spondyloarthritis traits in up to 10,588 cases and 209,287 controls. Colocalization analysis was performed to examine genetic confounding. We additionally used circulating immunoglobulin E (IgE) as a biomarker to test whether associations were replicated, both in the test and in an independent genetic dataset. We also replicated analyses using individual-level data from the UK Biobank. Genetically proxied IL-13i was associated with increased risk of PsA (OR 37.39; 95%CI 11.52, 121.34; p=1.64x10-9) and psoriasis (OR 20.08; 4.38, 92.01; p=1.12x10-4). No consistent associations were found for Crohn's disease, ulcerative colitis, ankylosing spondylitis or iritis. Colocalization showed no strong evidence of genetic confounding for psoriatic disease. Results were replicated using circulating IgE for the exposure, using independent outcome data and using individual-level data. We provide supportive genetic evidence that IL-13i is linked to increased risk of PsA and psoriasis. Physicians prescribing IL-13 inhibitors should be vigilant for these adverse events.

Gastric cancer fibroblasts affect the effect of immunotherapy and patient prognosis by inducing micro-vascular production

IntroductionImmunotherapy is critical for treating many cancers, and its therapeutic success is linked to the tumor microenvironment. Although anti-angiogenic drugs are used to treat gastric cancer (GC), their efficacy remains limited. Cancer-associated fibroblast (CAF)-targeted therapies complement immunotherapy; however, the lack of CAF-specific markers poses a challenge. Therefore, we developed a CAF angiogenesis prognostic score (CAPS) system to evaluate prognosis and immunotherapy response in patients with GC, aiming to improve patient stratification and treatment efficacy.MethodsWe assessed patient-derived GC CAFs for promoting angiogenesis using EdU, cell cycle, apoptosis, wound healing, and angiogenesis analysis.ResultsWe then identified CAF-angiogenesis-associated differentially-expressed genes, leading to the development of CAPS, which included THBS1, SPARC, EDNRA, and VCAN. We used RT-qPCR to conduct gene-level validation, and eight GEO datasets and the HPA database to validate the CAPS system at the gene and protein levels. Six independent GEO datasets were utilized for validation. Overall survival time was shorter in the high- than the low-CAPS group. Immune microenvironment and immunotherapy response analysis showed that the high-CAPS group had a greater tendency toward immune escape and reduced immunotherapy efficacy than the low-CAPS group.DiscussionCAPS is closely associated with GC prognosis and immunotherapy outcomes. It is therefore an independent predictor of GC prognosis and immunotherapy efficacy.

Gastric cancer fibroblasts affect the effect of immunotherapy and patient prognosis by inducing micro-vascular production

IntroductionImmunotherapy is critical for treating many cancers, and its therapeutic success is linked to the tumor microenvironment. Although anti-angiogenic drugs are used to treat gastric cancer (GC), their efficacy remains limited. Cancer-associated fibroblast (CAF)-targeted therapies complement immunotherapy; however, the lack of CAF-specific markers poses a challenge. Therefore, we developed a CAF angiogenesis prognostic score (CAPS) system to evaluate prognosis and immunotherapy response in patients with GC, aiming to improve patient stratification and treatment efficacy.MethodsWe assessed patient-derived GC CAFs for promoting angiogenesis using EdU, cell cycle, apoptosis, wound healing, and angiogenesis analysis.ResultsWe then identified CAF-angiogenesis-associated differentially-expressed genes, leading to the development of CAPS, which included THBS1, SPARC, EDNRA, and VCAN. We used RT-qPCR to conduct gene-level validation, and eight GEO datasets and the HPA database to validate the CAPS system at the gene and protein levels. Six independent GEO datasets were utilized for validation. Overall survival time was shorter in the high- than the low-CAPS group. Immune microenvironment and immunotherapy response analysis showed that the high-CAPS group had a greater tendency toward immune escape and reduced immunotherapy efficacy than the low-CAPS group.DiscussionCAPS is closely associated with GC prognosis and immunotherapy outcomes. It is therefore an independent predictor of GC prognosis and immunotherapy efficacy.

Germline Sequencing of DNA Damage Repair Genes in Two Hereditary Prostate Cancer Cohorts Reveals New Disease Risk-Associated Gene Variants.

Rare, inherited variants in DNA damage repair (DDR) genes have a recognised role in prostate cancer (PrCa) susceptibility. In addition, these genes are therapeutically targetable. While rare variants are informing clinical management in other common cancers, defining the rare disease-associated variants in PrCa has been challenging. Here, whole-genome and -exome sequencing data from two independent, high-risk Australian and North American familial PrCa datasets were interrogated for novel DDR risk variants. Rare DDR gene variants (predicted to be damaging and present in two or more family members) were identified and subsequently genotyped in 1963 individuals (700 familial and 459 sporadic PrCa cases, 482 unaffected relatives, and 322 screened controls), and association analyses accounting for relatedness (MQLS) undertaken. In the combined datasets, rare ERCC3 (rs145201970, p = 2.57 × 10-4) and BRIP1 (rs4988345, p = 0.025) variants were significantly associated with PrCa risk. A PARP2 (rs200603922, p = 0.028) variant in the Australian dataset and a MUTYH (rs36053993, p = 0.031) variant in the North American dataset were also associated with risk. Evaluation of clinicopathological characteristics provided no evidence for a younger age or higher-grade disease at diagnosis in variant carriers, which should be taken into consideration when determining genetic screening eligibility criteria for targeted, gene-based treatments in the future. This study adds valuable knowledge to our understanding of PrCa-associated DDR genes, which will underpin effective clinical screening and treatment strategies.

Ensemble Machine Learning and Predicted Properties Promote Antimicrobial Peptide Identification.

The emergence of antibiotic-resistant microbes raises a pressing demand for novel alternative treatments. One promising alternative is the antimicrobial peptides (AMPs), a class of innate immunity mediators within the therapeutic peptide realm. AMPs offer salient advantages such as high specificity, cost-effective synthesis, and reduced toxicity. Although some computational methodologies have been proposed to identify potential AMPs with the rapid development of artificial intelligence techniques, there is still ample room to improve their performance. This study proposes a predictive framework which ensembles deep learning and statistical learning methods to screen peptides with antimicrobial activity. We integrate multiple LightGBM classifiers and convolution neural networks which leverages various predicted sequential, structural and physicochemical properties from their residue sequences extracted by diverse machine learning paradigms. Comparative experiments exhibit that our method outperforms other state-of-the-art approaches on an independent test dataset, in terms of representative capability measures. Besides, we analyse the discrimination quality under different varieties of attribute information and it reveals that combination of multiple features could improve prediction. In addition, a case study is carried out to illustrate the exemplary favorable identification effect. We establish a web application at http://amp.denglab.org to provide convenient usage of our proposal and make the predictive framework, source code, and datasets publicly accessible at https://github.com/researchprotein/amp .

LVPocket: integrated 3D global-local information to protein binding pockets prediction with transfer learning of protein structure classification

BackgroundPrevious deep learning methods for predicting protein binding pockets mainly employed 3D convolution, yet an abundance of convolution operations may lead the model to excessively prioritize local information, thus overlooking global information. Moreover, it is essential for us to account for the influence of diverse protein folding structural classes. Because proteins classified differently structurally exhibit varying biological functions, whereas those within the same structural class share similar functional attributes.ResultsWe proposed LVPocket, a novel method that synergistically captures both local and global information of protein structure through the integration of Transformer encoders, which help the model achieve better performance in binding pockets prediction. And then we tailored prediction models for data of four distinct structural classes of proteins using the transfer learning. The four fine-tuned models were trained on the baseline LVPocket model which was trained on the sc-PDB dataset. LVPocket exhibits superior performance on three independent datasets compared to current state-of-the-art methods. Additionally, the fine-tuned model outperforms the baseline model in terms of performance.Scientific contributionWe present a novel model structure for predicting protein binding pockets that provides a solution for relying on extensive convolutional computation while neglecting global information about protein structures. Furthermore, we tackle the impact of different protein folding structures on binding pocket prediction tasks through the application of transfer learning methods.Graphical

LVPocket: integrated 3D global-local information to protein binding pockets prediction with transfer learning of protein structure classification

BackgroundPrevious deep learning methods for predicting protein binding pockets mainly employed 3D convolution, yet an abundance of convolution operations may lead the model to excessively prioritize local information, thus overlooking global information. Moreover, it is essential for us to account for the influence of diverse protein folding structural classes. Because proteins classified differently structurally exhibit varying biological functions, whereas those within the same structural class share similar functional attributes.ResultsWe proposed LVPocket, a novel method that synergistically captures both local and global information of protein structure through the integration of Transformer encoders, which help the model achieve better performance in binding pockets prediction. And then we tailored prediction models for data of four distinct structural classes of proteins using the transfer learning. The four fine-tuned models were trained on the baseline LVPocket model which was trained on the sc-PDB dataset. LVPocket exhibits superior performance on three independent datasets compared to current state-of-the-art methods. Additionally, the fine-tuned model outperforms the baseline model in terms of performance.Scientific contributionWe present a novel model structure for predicting protein binding pockets that provides a solution for relying on extensive convolutional computation while neglecting global information about protein structures. Furthermore, we tackle the impact of different protein folding structures on binding pocket prediction tasks through the application of transfer learning methods.Graphical