Independent Datasets Research Articles

A cross-tissue transcriptome-wide association study reveals GRK4 as a novel susceptibility gene for COPD

Chronic obstructive pulmonary disease (COPD) is a prevalent respiratory disorder with environmental factors being the primary risk determinants. However, genetic factors also substantially contribute to the susceptibility and progression of COPD. Although genome-wide association studies (GWAS) have identified several loci associated with COPD susceptibility, the specific pathogenic genes underlying these loci, along with their biological functions and roles within regulatory networks, remain unclear. This lack of clarity constrains our ability to achieve a deeper understanding of the genetic basis of COPD. This study leveraged the FinnGen R11 genetic dataset, comprising 21,617 cases and 372,627 controls, along with GTEx V8 eQTLs data to conduct a cross-tissue transcriptome-wide association study (TWAS). Initially, we performed a cross-tissue TWAS analysis using the Unified Test for Molecular Signatures (UTMOST), followed by validation of the UTMOST findings in single tissues using the Functional Summary-based Imputation (FUSION) method and conditional and joint (COJO) analyses of the identified genes. Subsequently, candidate susceptibility genes were screened using Multi-marker Analysis of Genomic Annotation (MAGMA). The causal relationship between these candidate genes and COPD was further evaluated through summary data-based Mendelian randomization (SMR), colocalization analysis, and Mendelian randomization (MR). Additionally, the identified results were validated against the COPD dataset in the GWAS Catalog (GCST90399694). GeneMANIA was employed to further explore the functional significance of these susceptibility genes. In the cross-tissue TWAS analysis (UTMOST), we identified 17 susceptibility genes associated with COPD. Among these, a novel susceptibility gene, G protein-coupled receptor kinase 4 (GRK4), was validated through single-tissue TWAS (FUSION) and MAGMA analyses, with further confirmation via SMR, MR, and colocalization analyses. Moreover, GRK4 was validated in an independent dataset. This study identifies GRK4 as a potential novel susceptibility gene for COPD, which may influence disease risk by exacerbating inflammatory responses. The findings address gaps in previous single-tissue GWAS studies, revealing consistent expression and potential function of GRK4 across different tissues. However, considering the study’s limitations, further investigation and validation of GRK4’s role in COPD are warranted.

Using Machine Learning and Feature Importance to Identify Risk Factors for Mortality in Pediatric Heart Surgery.

Background: The objective of this IRB-approved retrospective monocentric study was to identify risk factors for mortality after surgery for congenital heart defects (CHDs) in pediatric patients using machine learning (ML). CHD belongs to the most common congenital malformations, and remains the leading mortality cause from birth defects. Methods: The most recent available hospital encounter for each patient with an age <18 years hospitalized for CHD-related cardiac surgery between the years 2011 and 2020 was included in this study. The cohort consisted of 1302 eligible patients (mean age [SD]: 402.92 [±562.31] days), who were categorized into four disease groups. A random survival forest (RSF) and the 'eXtreme Gradient Boosting' algorithm (XGB) were applied to model mortality (incidence: 5.6% [n = 73 events]). All models were then applied to predict the outcome in an independent holdout test dataset (40% of the cohort). Results: RSF and XGB achieved average C-indices of 0.85 (±0.01) and 0.79 (±0.03), respectively. Feature importance was assessed with 'SHapley Additive exPlanations' (SHAP) and 'Time-dependent explanations of machine learning survival models' (SurvSHAP(t)), both of which revealed high importance of the maximum values of serum creatinine observed within 72 h post-surgery for both ML methods. Conclusions: ML methods, along with model explainability tools, can reveal interesting insights into mortality risk after surgery for CHD. The proposed analytical workflow can serve as a blueprint for translating the analysis into a federated setting that builds upon the infrastructure of the German Medical Informatics Initiative.

PRITrans: A Transformer-Based Approach for the Prediction of the Effects of Missense Mutation on Protein-RNA Interactions.

Protein-RNA interactions are essential to many cellular functions, and missense mutations in RNA-binding proteins can disrupt these interactions, often leading to disease. To address this, we developed PRITrans, a specialized computational method aimed at predicting the effects of missense mutations on protein-RNA interactions, which is vital for understanding disease mechanisms and advancing molecular biology research. PRITrans is a novel deep learning model designed to predict the effects of missense mutations on protein-RNA interactions, which employs a Transformer architecture enhanced with multiscale convolution modules for comprehensive feature extraction. Its primary innovation lies in integrating protein language model embeddings with a deep feature fusion strategy, effectively handling high-dimensional feature representations. By utilizing multi-layer self-attention mechanisms, PRITrans captures nuanced, high-level sequence information, while multiscale convolutions extract features across various depths, thereby enhancing predictive accuracy. Consequently, this architecture enables significant improvements in ΔΔG prediction compared to traditional approaches. We validated PRITrans using three different cross-validation strategies on two newly reconstructed mutation datasets, S315 and S630 (containing 315 forward and 315 reverse mutations). The results consistently demonstrated PRITrans's strong performance on both datasets. PRITrans demonstrated strong predictive capability, achieving a Pearson correlation coefficient of 0.741 and a root mean square error (RMSE) of 1.168 kcal/mol on the S630 dataset. Moreover, its robust performance extended to independent test sets, achieving a Pearson correlation of 0.699 and an RMSE of 1.592 kcal/mol. These results underscore PRITrans's potential as a powerful tool for protein-RNA interaction studies. Moreover, when tested against existing prediction methods on an independent dataset, PRITrans showed improved predictive accuracy and robustness.

Predicting brain age with global-local attention network from multimodal neuroimaging data: Accuracy, generalizability, and behavioral associations

Brain age, an emerging biomarker for brain diseases and aging, is typically predicted using single-modality T1-weighted structural MRI data. This study investigates the benefits of integrating structural MRI with diffusion MRI to enhance brain age prediction. We propose an attention-based deep learning model that fuses global-context information from structural MRI with local details from diffusion metrics. The model was evaluated using two large datasets: the Human Connectome Project (HCP, n = 1064, age 22–37) and the Cambridge Center for Aging and Neuroscience (Cam-CAN, n = 639, age 18–88). It was tested for generalizability and robustness on three independent datasets (n = 546, age 20–86), reproducibility on a test-retest dataset (n = 44, age 22–35), and longitudinal consistency (n = 129, age 46–92). We also examined the relationship between predicted brain age and behavioral measures. Results showed that the multimodal model improved prediction accuracy, achieving mean absolute errors (MAEs) of 2.44 years in the HCP dataset (sagittal plane) and 4.36 years in the Cam-CAN dataset (axial plane). The corresponding R2 values were 0.258 and 0.914, respectively, reflecting the model's ability to explain variance in the predictions across both datasets. Compared to single-modality models, the multimodal approach showed better generalization, reducing MAEs by 10–76 % and enhancing robustness by 22–82 %. While the multimodal model exhibited superior reproducibility, the sMRI model showed slightly better longitudinal consistency. Importantly, the multimodal model revealed unique associations between predicted brain age and behavioral measures, such as walking endurance and loneliness in the HCP dataset, which were not detected with chronological age alone. In the Cam-CAN dataset, brain age and chronological age exhibited similar correlations with behavioral measures. By integrating sMRI and dMRI through an attention-based model, our proposed approach enhances predictive accuracy and provides deeper insights into the relationship between brain aging and behavior.

Senescence cell signature associated with poor prognosis, epithelial-mesenchymal transition, solid histology, and spread through air spaces in lung adenocarcinoma.

Cellular senescence is involved in critical processes in tumor progression. Despite this potential relationship, the relationship between tumor cell senescence, prognostic significance, spread through air spaces (STAS), and tumor histology has not been investigated in lung adenocarcinoma (LUAD). We used the LUAD PanCancer Atlas dataset to assess senescence cell signature (SCS) based on the SenMayo gene set. We examined the relationship between SCS, prognostic significance, STAS, and tumor histology. This relationship was confirmed in independent LUAD datasets by validation using immunohistochemical senescence markers. In the LUAD PanCancer Atlas dataset, patients with high SCS expression had a higher prevalence of solid histology and STAS patterns than those with low SCS expression. In the independent LUAD datasets, high p21 expression and low HMGB1 expression were correlated with solid histology or STAS patterns. SCS level was also independent prognostic factor in four different LUAD datasets. The HMGB1 expression was an independent prognostic factor in the independent LUAD dataset in multivariate analysis. The expression of p21 and the presence of solid histology were linked to the epithelial-mesenchymal transition (EMT) phenotype. In LUAD cell lines, inducing senescence with a DNA-damaging agent led to an increase in EMT marker expression. Our findings suggest a strong link between senescence, EMT, and solid histology, offering valuable insight into how cancer cell senescence may promote tumor progression through particular pathways.

Accurately Identifying Sound vs. Rotten Cranberries Using Convolutional Neural Network

Cranberries, native to North America, are known for their nutritional value and human health benefits. One hurdle to commercial production is losses due to fruit rot. Cranberry fruit rot results from a complex of more than ten filamentous fungi, challenging breeding for resistance. Nonetheless, our collaborative breeding program has fruit rot resistance as a significant target. This program currently relies heavily on manual sorting of sound vs. rotten cranberries. This process is labor-intensive and time-consuming, prompting the need for an automated classification (sound vs. rotten) system. Although many studies have focused on classifying different fruits and vegetables, no such approach has been developed for cranberries yet, partly because datasets are lacking for conducting the necessary image analyses. This research addresses this gap by introducing a novel image dataset comprising sound and rotten cranberries to facilitate computational analysis. In addition, we developed CARP (Cranberry Assessment for Rot Prediction), a convolutional neural network (CNN)-based model to distinguish sound cranberries from rotten ones. With an accuracy of 97.4%, a sensitivity of 97.2%, and a specificity of 97.2% on the training dataset and 94.8%, 95.4%, and 92.7% on the independent dataset, respectively, our proposed CNN model shows its effectiveness in accurately differentiating between sound and rotten cranberries.

Ab-Amy 2.0: Predicting light chain amyloidogenic risk of therapeutic antibodies based on antibody language model

Therapeutic antibodies have emerged as a promising treatment option for a wide range of diseases. However, the light chain of antibodies can potentially induce amyloidosis, a condition characterized by protein misfolding and aggregation, posing a significant safety concern. Therefore, it is crucial to assess the amyloidogenic risk of therapeutic antibodies during the early stages of drug development. In this study, we introduce AB-Amy 2.0, a new computational model with enhanced performance for assessing the light chain amyloidogenic risk of therapeutic antibodies. By employing pretrained protein language models (PLMs) embeddings, AB-Amy 2.0 achieves higher accuracy in amyloidogenic risk prediction compared with traditional features offering a crucial tool for early-stage identification of antibodies with low aggregation propensity. The AB-Amy 2.0 was trained on antiBERTy embeddings and utilizes the SVM algorithm, resulting in superior performance metrics. On an independent test dataset, the model achieved high sensitivity, specificity, ACC, MCC and AUC of 93.47%, 89.23%, 91.92%, 0.8261 and 0.9739, respectively. These results highlight the effectiveness and robustness of AB-Amy 2.0 in predicting light chain amyloidogenic risk accurately. To facilitate user-friendly access, we have developed an online web server (http://i.uestc.edu.cn/AB-Amy2) and a command line tool (https://github.com/zzyywww/ABAmy2). These resources enable the broader application of this advanced model and promise to enhance the development of safer therapeutic antibodies.

Assessing the predictive efficacy of European-based systolic blood pressure polygenic risk scores in diverse Brazilian cohorts

Despite the identification of numerous genetic variants affecting SBP in European populations, their applicability in admixed populations remains unclear. This study evaluates the predictive efficacy of a systolic blood pressure (SBP) polygenic risk score (PRS), derived from the UK Biobank data, in two Brazilian cohorts. We analyzed 944 K genetic variants consistent across an independent UK Biobank dataset, Brazilian cohorts, and HapMap database. Results show a significant association between increased PRS and SBP, as well as hypertension, in each study groups analyzed. An increase of one standard deviation in the PRS showed a significant association with SBP (β [95% CI] (mmHg) = 5.2 [5.1–5.3], 2.8 [2.1–3.5] and 2.6 [2.2–3.0]) and hypertension (odds ratio (OR) [95% CI] = 1.56 [1.54–1.56], 1.28 [1.2–1.4] and 1.47 [1.3–1.6]) in an independent UKB dataset, Baependi, and Pelotas, respectively. The associations were weaker in the Brazilian samples and the reduced association was noticeable in the Pelotas vs. the UK comparison for hypertension stages 1 and 2 (OR [95% CI] = 2.1 [1.5–3.1] and 3.0 [1.9–4.7] vs. 2.5 [2.2–2.8] and 4.9 [4.4–5.6]), whereas the Baependi data showed no significance for stage 1 hypertension. This trend mirrors findings in homogeneous African and Asian populations with diverse genetic architecture, highlighting the limitations of European-based PRS also in admixed populations. These insights are crucial for developing tailored disease prevention and management strategies in ethnically diverse groups.

Nifedipine May Be an Inhibitor of Clozapine Metabolism, as Seen in 5 Patients: 2 from a US Double-Blind Study and 3 from a German TDM Study

Background: Clozapine is the only licensed antipsychotic for treatment-refractory schizophrenia. Therapeutic drug monitoring (TDM) refers to the measurement of clozapine concentration. Clozapine TDM can be used to optimize treatment, particularly by identifying pharmacokinetic interactions between clozapine and comedications. Methods: We identified 5 cases of patients with available clozapine concentrations who were concomitantly receiving nifedipine and clozapine. These cases were drawn from 2 independent datasets: 2 from a double-blind, randomized clinical trial in the United States and 3 from a German TDM naturalistic database. As an index of clozapine clearance, we used the trough-level concentration-to-dose (C/D) ratios to estimate the minimum therapeutic doses. To estimate dose-correction factors for nifedipine treatment, we included only clozapine concentrations at steady state. We divided the clozapine minimum therapeutic doses (MTD) from the on-condition by the off-nifedipine condition. Results: In 4 patients, the ratio of on/off nifedipine for MTD ranged between 0.58 and 0.82. Another patient had no data and had to be compared with published control data (female smoker of African ancestry), providing a correction factor of 0.52 after eliminating 5 concentrations contaminated by the development of obesity. Conclusions: In the absence of access to TDM, when prescribing nifedipine to clozapine-treated patients, we recommend reducing the daily dose of clozapine by one-third because of the weak inhibition of clozapine metabolism. With access to TDM, TDM should guide dosing as unusual patients may need larger dose reductions, as it is possible that in some patients, nifedipine may be a moderate inhibitor requiring halving clozapine dose. Further prospective studies are warranted.

BreathVisionNet: A pulmonary-function-guided CNN-transformer hybrid model for expiratory CT image synthesis

Background and objectiveChronic obstructive pulmonary disease (COPD) has high heterogeneity in etiologies and clinical manifestations. Expiratory Computed tomography (CT) can effectively assess air trapping, aiding in disease diagnosis. However, due to concerns about radiation exposure and cost, expiratory CT is not routinely performed. Recent work on synthesizing expiratory CT has primarily focused on imaging features while neglecting patient-specific pulmonary function. MethodsTo address these issues, we developed a novel model named BreathVisionNet that incorporates pulmonary function data to guide the synthesis of expiratory CT from inspiratory CT. An architecture combining a convolutional neural network and transformer is introduced to leverage the irregular phenotypic distribution in COPD patients. The model can better understand the long-range and global contexts by incorporating global information into the encoder. The utilization of edge information and multi-view data further enhances the quality of the synthesized CT. Parametric response mapping (PRM) can be estimated by using synthesized expiratory CT and inspiratory CT to quantify COPD phenotypes of the normal, emphysema, and functional small airway disease (fSAD), including their percentages, spatial distributions, and voxel distribution maps. ResultsBreathVisionNet outperforms other generative models in terms of synthesized image quality. It achieves a mean absolute error, normalized mean square error, structural similarity index and peak signal-to-noise ratio of 78.207 HU, 0.643, 0.847 and 25.828 dB, respectively. Comparing the predicted and real PRM, the Dice coefficient can reach 0.732 (emphysema) and 0.560 (fSAD). The mean of differences between true and predicted fSAD percentage is 4.42 for the development dataset (low radiation dose CT scans), and 9.05 for an independent external validation dataset (routine dose), indicating that model has great generalizability. A classifier trained on voxel distribution maps can achieve an accuracy of 0.891 in predicting the presence of COPD. ConclusionsBreathVisionNet can accurately synthesize expiratory CT images from inspiratory CT and predict their voxel distribution. The estimated PRM can help to quantify COPD phenotypes of the normal, emphysema, and fSAD. This capability provides additional insights into COPD diversity while only inspiratory CT images are available.

Novel fuel consumption models integrating vehicular speed, acceleration, and jerk

Novel computational models were developed to enhance Eco-driving in intelligent transportation systems (ITS). Initially, the relationship between fuel consumption, speed, acceleration, and jerk was analyzed. Two kinds of mathematical models integrating speed, acceleration, and jerk were established. Next, the correlation between model components and fuel consumption was analyzed using Pearson Correlation Coefficients (PCC) to further optimize the models. Finally, the predictive performance of the proposed models and the widely used Vehicle Specific Power (VSP) and the Virginia Tech Microscopic (VT-micro) models were compared using mean absolute percentage error (MAPE), root-mean-square error (RMSE), correlation coefficient (R), and coefficient of determination (R 2). The results indicated that the fuel consumption prediction models considering jerk were superior to the VSP and VT-Micro models: MAPE decreased by 32.8 and 8.9%, RMSE decreased by 41.1 and 15.3%, R increased by 4.2 and 1.3%, and R 2 increased by 23.5 and 4.0%, respectively. External validation using independent datasets confirmed the effectiveness of the proposed models.

Identification of key programmed cell death genes for predicting prognosis and treatment sensitivity in colorectal cancer

Colorectal cancer (CRC) ranks third in global incidence and second in mortality. However, a comprehensive predictive model for CRC prognosis, immunotherapy response, and drug sensitivity is still lacking. Various types of programmed cell death (PCD) are crucial for cancer occurrence, progression, and treatment, indicating their potential as valuable predictors. Fourteen PCD genes were collected and subjected to dimensionality reduction using regression methods to identify key hub genes. Predictive models were constructed and validated based on bulk transcriptomes and single-cell transcriptomes. Furthermore, the tumor microenvironment, immunotherapy response, and drug sensitivity profiles among patients with CRC were explored and stratified by risk. A risk score incorporating the PCD genes FABP4, AQP8, and NAT1 was developed and validated across four independent datasets. Patients with CRC who had a high-risk score exhibited a poorer prognosis. Unsupervised clustering algorithms were used to identify two molecular subtypes of CRC with distinct features. The risk score was combined with the clinical features to create a nomogram model with superior predictive performance. Additionally, patients with high-risk scores exhibited decreased immune cell infiltration, higher stromal scores, and reduced responsiveness to immunotherapy and first-line clinical drugs compared with low-risk patients. Furthermore, the top ten non-clinical first-line drugs for treating CRC were selected based on their predicted IC50 values. Our results indicate the efficacy of the model and its potential value in predicting prognosis, response to immunotherapy, and sensitivity to different drugs in patients with CRC.

Identification and characterization of novel ferroptosis-related genes in acute myocardial infarction

BackgroundAcute myocardial infarction (AMI) is a leading cause of death and morbidity worldwide. Ferroptosis, a form of regulated cell death, plays a critical role in modulating immune functions during AMI. This study aimed to identify ferroptosis-related hub genes that could serve as potential therapeutic targets in the progression of AMI.MethodsBioinformatics was used to identify overlapping genes associated with ferroptosis and the infiltration of 22 immune cells by Cell-type Identification by Estimating Relative Subsets of RNA Transcript (CIBERSORT) analysis. The expression of ferroptosis-related genes in AMI was validated across independent datasets, clinical samples, and in vitro cellular experiments. The predictive value for heart failure was evaluated in the first dimension of principal component analysis (PCA) using receiver operating characteristic (ROC) analysis.ResultsThe study identified 11 key ferroptosis-related genes significantly correlated with immune cell abundance. CIBERSORT analysis highlighted immune dysregulation in AMI. JDP2, DUSP1, TLR4, NFS1, and SLC1A5 were identified as potential biomarkers for AMI progression. Additionally, JDP2, DUSP1, and DDIT4 demonstrated strong predictive value for long-term heart failure.ConclusionThis study highlights the potential association of ferroptosis-related genes with the pathogenesis of AMI, suggesting a role in the molecular mechanisms that may underlie acute coronary events.

Utilizing Artificial Intelligence for Microbiome Decision-Making: Autism Spectrum Disorder in Children from Bosnia and Herzegovina.

The study of microbiome composition shows positive indications for application in the diagnosis and treatment of many conditions and diseases. One such condition is autism spectrum disorder (ASD). We aimed to analyze gut microbiome samples from children in Bosnia and Herzegovina to identify microbial differences between neurotypical children and those with ASD. Additionally, we developed machine learning classifiers to differentiate between the two groups using microbial abundance and predicted functional pathways. A total of 60 gut microbiome samples (16S rRNA sequences) were analyzed, with 44 from children with ASD and 16 from neurotypical children. Four machine learning algorithms (Random Forest, Support Vector Classification, Gradient Boosting, and Extremely Randomized Tree Classifier) were applied to create eight classification models based on bacterial abundance at the genus level and KEGG pathways. Model accuracy was evaluated, and an external dataset was introduced to test model generalizability. The highest classification accuracy (80%) was achieved with Random Forest and Extremely Randomized Tree Classifier using genus-level taxa. The Random Forest model also performed well (78%) with KEGG pathways. When tested on an independent dataset, the model maintained high accuracy (79%), confirming its generalizability. This study identified significant microbial differences between neurotypical children and children with ASD. Machine learning classifiers, particularly Random Forest and Extremely Randomized Tree Classifier, achieved strong accuracy. Validation with external data demonstrated that the models could generalize across different datasets, highlighting their potential use.

A mapping-free natural language processing-based technique for sequence search in nanopore long-reads

BackgroundIn unforeseen situations, such as nuclear power plant’s or civilian radiation accidents, there is a need for effective and computationally inexpensive methods to determine the expression level of a selected gene panel, allowing for rough dose estimates in thousands of donors. The new generation in-situ mapper, fast and of low energy consumption, working at the level of single nanopore output, is in demand. We aim to create a sequence identification tool that utilizes natural language processing techniques and ensures a high level of negative predictive value (NPV) compared to the classical approach.ResultsThe training dataset consisted of RNA sequencing data from 6 samples. Multiple natural language processing models were examined, differing in the type of dictionary components (word length, step, context) as well as the encoding length and number of sequences required for algorithm training. The best configuration analyses the entire sequence and uses a word length of 3 base pairs with one-word neighbor on each side. For the considered FDXR gene, the achieved mean balanced accuracy (BACC) was 98.29% and NPV was 99.25%, compared to minimap2’s performance in a cross-validation scenario. The next stage focused on exploring the dictionary components and attempting to optimize it, employing statistical techniques as well as those relying on the explainability of the decisions made. Reducing the dictionary from 1024 to 145 changed BACC to 96.49% and the NPV to 98.15%. Obtained model, validated on an external independent genome sequencing dataset, gave NPV of 99.64% for complete and 95.87% for reduced dictionary. The salmon-estimated read counts differed from the classical approach on average by 3.48% for the complete dictionary and by 5.82% for the reduced one.ConclusionsWe conclude that for long Oxford nanopore reads, a natural language processing-based approach can reliably replace classical mapping when there is a need for fast, reliable and energy and computationally efficient targeted mapping of a pre-defined subset of transcripts. The developed model can be easily retrained to identify selected transcripts and/or work with various long-read sequencing techniques. Our results of the study clearly demonstrate the potential of applying techniques known from classical text processing to nucleotide sequences.

EPID-02. BLOOD-BASED CLASSIFICATION OF IDH-STATUS OF NON-ENHANCING GLIOMAS: A MACHINE LEARNING APPROACH

Abstract BACKGROUND Non-invasive determination of IDH mutational status in patients with glioma could offer significant therapeutic opportunities. While IDH wildtype (WT) tumors typically show enhancement on MRI, IDH mutant (MUT) tumors often lack this enhancement. However, relying solely on anatomic radiology may lead to misclassification, and currently, tissue acquisition is the primary method for assessing IDH-status in gliomas. These limitations hamper the development of neoadjuvant or intraoperative therapeutic strategies based on IDH-status; thus, more minimally invasive methods to determine IDH-status are needed. In this study, we assessed peripheral immune cell proportions, which vary by glioma subtype, from pre-surgery peripheral blood samples as an alternative method of classifying the IDH-status in gliomas without enhancement. MATERIALS AND METHODS We employed a highly accurate large language model (GPT-4-Turbo-128k) with over 99% accuracy to read radiology notes and exclude patients with enhancing gliomas. Then, we identified 12 immune cell subtypes from whole blood using deconvolution algorithms based on DNA methylation data. These immune cell subtypes, along with patient age, were integrated into a machine learning model (random forest) to predict IDH-status (WT vs. MUT), leveraging conditional Generative Adversarial Networks to generate synthetic data and mitigate bias in the datasets. Two independent datasets were included for training and validating the model. RESULTS The random forest model had an AUC of 0.90 and accurately identified IDH-status in 81% of a training set of 287 gliomas (65 WT and 222 MUT at varied time points after diagnosis). In an independent validation data set of 99 gliomas (6 WT and 93 MUT) from pre-surgery blood samples, the AUC was 0.93, and accurately predicted IDH-status in 92% of cases with a sensitivity of 93% and specificity of 83%. CONCLUSIONS We predicted the IDH-status of non-enhancing gliomas using patients’ age and immunomethylomic data from pre-surgical peripheral blood samples. This minimally invasive approach is a promising step toward reducing risk and enabling earlier therapies based on IDH-status.

BIOM-22. SPATIAL, SINGLE-CELL, AND BULK RNA SEQUENCING IDENTIFY MOLECULAR PROGRAMS UNDERLYING MENINGIOMA BRAIN INVASION

Abstract Brain invasion is a negative prognostic factor for meningiomas, but the molecular programs underlying meningioma brain invasion are poorly understood. To address this, we performed transcriptomic analyses of 3 independent datasets: Bulk RNA sequencing from 199 meningiomas (n=33 with brain invasion), single-cell RNA sequencing of 2 regionally distinct samples from the brain tumor interface (BTI) versus tumor core (TC) (n=22,118 single-cell transcriptomes), and spatial RNA sequencing from 6 samples with (n=4) versus without (n=2) brain invasion (n=18,471 spatial transcriptomes). Single-cell and spatial datasets were integrated with Harmony, cell interactions were defined using CellChat, and cross-platform comparisons were performed with the Seurat data integration pipeline. Bulk RNA sequencing revealed enrichment of 1835 genes in meningiomas with brain invasion compared to those without brain invasion, including glial markers (GFAP, NCAN) and markers of extracellular matrix remodeling (PDGFRA, COL9A1). Single-cell RNA sequencing comparison of BTI versus TC meningioma cells identified 2793 genes that were enriched in BTI cells, 268 of which were conserved across bulk and single-cell transcriptomes from brain-invasive meningiomas. Gene ontology enrichment analysis showed molecular programs underlying cell migration and regulation of neurogenesis at the BTI, while glycolysis and antigen presentation programs were enriched in the TC. Cholesterol, CSPG4, and LIF signaling were active in the TC, while SLIT signaling was enriched at the BTI. Spatial RNA sequencing showed enrichment of 439 genes at the BTI, and a conserved set of 12 genes were enriched in BTI meningioma cells across bulk, single-cell, and spatial datasets (TGM2, APOC1, IGFBP6, PLEKHO1, GFPT2, ZYX, IQGAP3, LUM, S100A11, ARPC1B, CDK1, CYCS). Comparison of tumor microenvironment monocytes at the BTI versus TC demonstrated enrichment of 1571 genes that were associated with macrophage migration and activation. These data elucidate molecular programs underlying meningioma brain invasion and provide insights into meningioma intratumor heterogeneity.

EPCO-33. OMICON: A CLOUD PLATFORM FOR FAIR RESEARCH ON GENE COEXPRESSION NETWORKS IN NORMAL HUMAN BRAIN AND BRAIN TUMORS

Abstract Genome-wide coexpression analysis of bulk human brain samples is a powerful approach for identifying highly reproducible transcriptional signatures of cell types and cell states, since it can survey huge numbers of individuals, cells, and transcripts. However, it is difficult to optimize gene coexpression network construction, compare gene coexpression modules from independent datasets, or even locate gene expression datasets with similar attributes. To address these challenges, we have developed the OMICON platform (theomicon.ucsf.edu) to promote FAIR (Findable, Accessible, Interoperable, Reusable) research practices involving human brain gene coexpression networks. OMICON contains structured gene expression data for &amp;gt;17K bulk human brain samples (~10K normal and ~7K malignant glioma), which were collected from diverse public repositories and consortia (e.g., GEO, TCGA, CGGA, CPTAC, REMBRANDT, IvyGAP, GTEx, NABEC, the Allen Institute). To promote interoperability, we have standardized metadata for hundreds of dataset and sample attributes, including single-nucleotide and copy-number mutations. For each dataset, we have used the FindModules R function to construct dozens of gene coexpression networks by iterating over module detection parameters. These efforts have identified ~100K gene coexpression modules, which have been extensively characterized via enrichment analysis with thousands of curated gene sets. All datasets, metadata, gene coexpression networks, enrichment results, and analysis steps can be browsed with an interactive workflow visualization tool, which promotes accessibility, reusability, and reproducibility by maintaining complete data provenance with unique identifiers. To promote findability, we have built an advanced search engine to identify datasets, samples, modules, and more, by filtering standardized metadata (e.g., find gene coexpression modules in human glioblastoma datasets that are significantly enriched with markers of T-cells). A detailed description of OMICON’s functionality is described on our Help page: theomicon.ucsf.edu/home/help. Through this functionality, OMICON seeks to build community and focus therapeutic efforts around reproducible analyses of transcriptional variation in normal human brain and brain tumors.

Advancing nitrogen nutrition index estimation in summer maize using continuous wavelet transform.

Rapid and non-destructive diagnosis of plant nitrogen (N) status is crucial to optimize N management during the growth of summer maize. This study aimed to evaluate the effectiveness of continuous wavelet analysis (CWA) in estimating the nitrogen nutrition index (NNI), to determine the most suitable wavelet analysis method, and to identify the most sensitive wavelet features across the visible to near-infrared spectrum (325-1,025 nm) for accurate NNI estimation. Field experiments were conducted across two sites (Kaifeng and Weishi) during the 2022 and 2023 growing seasons using four summer maize cultivars (XD20, ZD958, DH661, and DH605) under varying N application rates (0, 80, 160, 240, and 320 kg N ha-1). Canopy reflectance spectra and plant samples were collected from the V6 to V12 growth stages. The wavelet features for each spectral band were calculated across different scales using the CWA method, and their relationships with NNI, plant dry matter (PDM), and plant N concentration (PNC) were analyzed using four regression models. The results showed that NNI varied from 0.61 to 1.19 across different N treatments during the V6 to V12 stages, and the Mexican Hat wavelet was identified as the most suitable mother wavelet, achieving an R ² value of 0.73 for NNI assessment. The wavelet features derived from the Mexican Hat wavelet were effective in estimating NNI, PDM, and PNC under varying N treatments, with the most sensitive wavelet features identified as 745 nm at scale 7 for NNI, 819 nm at scale 5 for PDM, and 581 nm at scale 6 for PNC using linear regression models. The direct and indirect methods for NNI estimation were compared using independent field data sets. Both methods proved valid to predict NNI in summer maize, with relative root mean square errors of 10.8% for the direct method and 13.4% for the indirect method. The wavelet feature at 745 nm, scale 7, from the direct method (NNI = 0.14 WF (745 nm, 7) + 0.3) was found to be simpler and more accurate for NNI calculation. These findings provide new insights into the application of the CWA method for precise spectral estimation of plant N status in summer maize.

M5C related-regulator-mediated methylation modification patterns and prognostic significance in breast cancer

5-Methylcytosine (m5C) is closely associated with cancer. However, the role of m5C in breast cancer(BC)remains unclear. This study combined single-cell RNA sequencing (scRNA-Seq) and transcriptomics datasets to screen m5C regulators associated with BC progression and analyze their clinical values. Firstly, This study elucidates the mechanisms of the m5C landscape and the specific roles of m5C regulators in BC patients. we found that the dysregulation of m5C regulators with m5Cscore play the essential role of the carcinogenesis and progression in epithelial cells and myeloid cells of BC at single cell level. External validation was conducted using an independent scRNA-Seq datasets. Then, three distinct m5C modification patterns were identified by transcriptomics datasets. Based on the m5C differentially expressed regulators, the m5Cscore was constructed, and used to divide patients with BC into high and low m5Cscore groups. Patients with a high m5Cscore had more abundant immune cell infiltration, stronger antitumor immunity, and better prognoses. Finally, Quantitative real-time (PCR) and immunohistochemistry were used for the in vitro experimental validation, which had extensive prognostic value. In this study, we aimed to assess the expression of m5C regulators involved in BC and investigate their correlation with the tumor microenvironment, clinicopathological characteristics, and prognosis of BC. The m5C regulators could be used to effectively assess the cell specific regulation prognosis of patients with BC and develop more effective immunotherapy strategies.