Independent Test Research Articles

Factors influencing intentional self-harm in Chungcheongbuk Province relative to the Seoul region in the Republic of Korea: a retrospective study.

This study investigated factors influencing intentional self-harm in Chungcheongbuk Province (hereinafter, Chungbuk) compared to Seoul in the Republic of Korea. Raw data from the Discharge In-depth Injury Survey conducted by the Korea Disease Control and Prevention Agency were utilized. From 2,329,149 cases recorded over 9 years (2013-2021), 911 were identified as intentional self-harm cases (248 from Chungbuk and 633 from Seoul). We analyzed the differences in and influencing factors of intentional self-harm in Chungbuk relative to Seoul using the independent sample t-test, chi-square test, and binomial logistic regression analysis. Intentional self-harm was found to be 1.232 times more prevalent among females than males (p<0.05); 2.327 times more prevalent among middle-aged and older adults, ages 50 to 64, compared to those under 50 years old (p<0.01); 8.603 times more prevalent among those using hospitals with fewer than 500 beds compared to those with 500 beds or more (p<0.001); 2.412 times more prevalent among individuals using hospitals in different regions compared to those within the same region (p<0.01); 2.217 times more prevalent among those attempting intentional self-harm during daily activities compared to other specified activities (p<0.01); and 6.987 times more prevalent among those using pesticides or herbicides compared to other poisons (p<0.001) in Chungbuk relative to Seoul. In the Chungbuk region, intentional self-harm prevention programs should be implemented, specifically targeting women, particularly those aged 50 to 64. Additionally, due to the high incidence of intentional self-harm involving pesticides or herbicides in Chungbuk, these substances should be stringently monitored to restrict access.

A data-driven compact drain current model for InGaAs FinFET using TCAD assisted machine learning approach

Abstract This article presents a novel machine learning-based framework for modeling the drain current of InGaAs FinFETs. An artificial neural network, trained on a comprehensive dataset generated by 3D numerical device simulations, forms the core of this model. The simulations covered a wide range of device geometries and bias conditions, resulting in diverse current-voltage characteristics. Using TensorFlow in a Python environment, we built and trained a neural network to accurately predict drain current. The model’s performance was evaluated on independent test datasets, demonstrating its effectiveness on unseen data. The model accurately captures the effects of varying gate length, drain voltage, and gate voltage. Multiple error metrics, including mean squared error, mean absolute error, root mean squared error, and correlation coefficient, were used to assess its performance. At shorter gate lengths, the calculated relative error in drain current was 2.18% and 1.17% at VDS=50mV and 1V, respectively.&amp;#xD;After training, the network parameters were extracted to create a Verilog-A model. This model was integrated into the SPICE simulator for circuit simulations. A resistive load inverter circuit was designed to demonstrate the model’s capabilities, and voltage&amp;#xD;transfer characteristics and transient analysis were performed within SPICE. These results validate the effectiveness of the developed machine learning-based InGaAs FinFET model.

A CT-based deep learning for segmenting tumors and predicting microsatellite instability in patients with colorectal cancers: a multicenter cohort study.

To develop and validate deep learning (DL) models using preoperative contrast-enhanced CT images for tumor auto-segmentation and microsatellite instability(MSI) prediction incolorectal cancer (CRC). Patients with CRC who underwent surgery or biopsy between January 2018 and April 2023 were retrospectively enrolled. Mismatch repair protein expression was determined via immunohistochemistry or fluorescence multiplex polymerase chain reaction-capillary electrophoresis. Manually delineated tumor contours using arterial and venous phase CT images by three abdominal radiologists are served as ground truth. Tumor auto-segmentation used nnU-Net. MSI prediction employed ViT or convolutional neural networks models, trained and validated with arterial and venous phase images (image model) or combined clinical-pathological factors (combined model). The segmentation model was evaluated using patch coverage ratio, Dice coefficient, recall, precision, and F1-score. The predictive models' efficacy was assessed using areas under the curves and decision curve analysis. Overall, 2180 patients (median age: 61years ± 17 [SD]; 1285 males) were divided into training (n = 1159), validation (n = 289), and independent external test (n = 732) groups. High-level MSI status was present in 435 patients (20%). In the external test set, the segmentation model performed well in the arterial phase, with patch coverage ratio, Dice coefficient, recall, precision, and F1-score values of 0.87, 0.71, 0.72, 0.74, and 0.71, respectively. For MSI prediction, the combined models outperformed the clinical model (AUC = 0.83 and 0.82 vs 0.67, p < 0.001) and two image models (AUC = 0.75 and 0.77, p < 0.001). Decision curve analysis confirmed the higher net benefit of the combined model compared to the other models across probability thresholds ranging from 0.1 to 0.45. DL enhances tumor segmentation efficiency and, when integrated with contrast-enhanced CT and clinicopathological factors, exhibits good diagnostic performance in predicting MSI in CRC.

The Effectiveness Of Pregnant Exercise In Squat Position With Perineal Rupture In Maternity Mothers At TPMB Siti Salmah In 2022

Background : In the majority of first-time births, perineal tears last for some time. Unexpected tension that occurs in the head or body of the hatchlings causes tears in the skin and perineal tissue Writing Purpose: to determine the Effectiveness of Pregnant Squat Exercise with Perineal Rupture in Maternity Mothers at TPMB Siti Salmah Year 2022 Research Methods: this type of quantitative research uses an experimental design (quasi-experimental) ) with the Nonrandomized Control Group Pretest Posttest Design. The total population of this study was 30 mothers giving birth at TPMB Sti Salmah divided into 15 intervention groups and 15 control groups. Research Results: The results of the independent sample test obtained Asymp. Sig (2 – Sided) has a value of 0.001, because 0.001 &lt;0.05, the hypothesis is accepted. This means that there is a difference between doing pregnancy exercise in the squat position and not doing pregnancy exercise in the squat position on the incidence of perineal rupture in pregnant women so that it can be concluded that there is effectiveness of pregnancy exercise in the squat position with perineal rupture in maternity mothers at TPMB Siti Salmah in 2022 Conclusions and Suggestions: Expected results this research allows midwives to do pregnancy exercises in a squatting position. This research will also serve as a guide for its implementation, making it easier for patients, especially pregnant women, to prepare for delivery to prevent perineal rupture.

Characterization of the Freshness of Pork by Near-Infrared Spectroscopy (NIRS) and Ensemble Learning

Pork is a perishable food and often needs to be stored in the refrigerator to maintain its quality as much as possible. Traditional methods for discriminating fresh and refrigerated pork are subjective, time-consuming, or destructive. The feasibility of using near-infrared (NIR) spectroscopy combined with chemometrics was explored to discriminate fresh and refrigerated pork. A total of 104 samples including 40 fresh and 64 refrigerated samples were first prepared and split into the training and test sets. Both partial least squares (PLS) and a subspace-based ensemble algorithm were used to establish classifiers. Also, both the number of learners and the size of subspace were optimized for ensemble modeling. On the independent test set, three measures, that is, the sensitivity, specificity, and total accuracy of the ensemble classifier were 95%, 93.8%, and 94.2%, respectively, each of which is superior to that of the PLS classifier. In addition, the influence of training set composition on classifier performance was also studied, indicating that ensemble modeling is robust. The results show that the NIR spectroscopy coupled with such an ensemble model can serve as a potential tool of discriminating fresh and refrigerated pork.

Influence of patient factors on target plasma volume treated attainment rate during double filtration plasmapheresis in patients with hypertriglyceridemic acute pancreatitis.

This study aims to investigate patient factors affecting the rate of plasma volume target attained in hypertriglyceridemic pancreatitis (HTG-AP) patients undergoing double filtration plasmapheresis (DFPP). A retrospective analysis of 82 HTG-AP-interpreted patients from January 2019 to April 2024 compared target plasma volume treated between up-to-scratch and non-scratch groups. The group comparison used independent samples t-test, Mann-Whitney U-test, and chi-square test. Binary logistic regression was used to identify independent risk factors for patients' plasma volume target failure. The ROC curve assessed these risk factors' diagnostic efficacy. Of 82 patients, 52 were classified as belonging to the up-to-scratch group, while the remaining 30 were classified as belonging to the non-to-scratch group. Statistically significant differences were seen between the groups regarding admission heart rate, triglyceride, calcitonin gene, C-reactive protein, D-dimer, and fibrinogen (FIB) levels (p <0.05). The binary logistic regression analysis showed that for every 1 mmol/L increase in triglycerides (TG), the probability of experiencing substandard target plasma handling increased by 5.0% (OR = 1.05, 95%CI 1.01-1.08, p = 0.009). Furthermore, for each g/L rise in FIB, there was a 74% increase in the likelihood of encountering suboptimal target plasma handling (OR = 1.74, 95%CI 1.18-2.56, p = 0.005). The ROC curve study revealed that the AUC for TG was 0.67, for FIB was 0.77, and for the combination of both markers was 0.80; all the p values were below 0.05. The increased levels of TG and FIB are independent risk factors affecting the target plasma handling achievement rate in HTG-AP patients undergoing DFPP.

Ion channel classification through machine learning and protein language model embeddings.

Ion channels are critical membrane proteins that regulate ion flux across cellular membranes, influencing numerous biological functions. The resource-intensive nature of traditional wet lab experiments for ion channel identification has led to an increasing emphasis on computational techniques. This study extends our previous work on protein language models for ion channel prediction, significantly advancing the methodology and performance. We employ a comprehensive array of machine learning algorithms, including k-Nearest Neighbors, Random Forest, Support Vector Machines, and Feed-Forward Neural Networks, alongside a novel Convolutional Neural Network (CNN) approach. These methods leverage fine-tuned embeddings from ProtBERT, ProtBERT-BFD, and MembraneBERT to differentiate ion channels from non-ion channels. Our empirical findings demonstrate that TooT-BERT-CNN-C, which combines features from ProtBERT-BFD and a CNN, substantially surpasses existing benchmarks. On our original dataset, it achieves a Matthews Correlation Coefficient (MCC) of 0.8584 and an accuracy of 98.35 %. More impressively, on a newly curated, larger dataset (DS-Cv2), it attains an MCC of 0.9492 and an ROC AUC of 0.9968 on the independent test set. These results not only highlight the power of integrating protein language models with deep learning for ion channel classification but also underscore the importance of using up-to-date, comprehensive datasets in bioinformatics tasks. Our approach represents a significant advancement in computational methods for ion channel identification, with potential implications for accelerating research in ion channel biology and aiding drug discovery efforts.

Linear and neural network models for predicting N-glycosylation in Chinese Hamster Ovary cells based on B4GALT levels

Glycosylation is an essential modification to proteins that has positive effects, such as improving the half-life of antibodies, and negative effects, such as promoting cancers. Despite the importance of glycosylation, data-driven models to predict quantitative N-glycan distributions have been lacking. This article constructs linear and neural network models to predict the distribution of glycans on N-glycosylation sites. The models are trained on data containing normalized B4GALT1–B4GALT4 levels in Chinese Hamster Ovary cells. The ANN models achieve a median prediction error of 1.59% on an independent test set, an error 9-fold smaller than for previously published models using the same data, and a narrow error distribution. We also discuss issues with other models in the literature and the advantages of this work’s model over other data-driven models. We openly provide all of the software used, allowing other researchers to reproduce the work and reuse or improve the code in future endeavors.

Exploratory study on the enhancement of O-RADS application effectiveness for novice ultrasonographers via deep learning.

The study aimed to create a deep convolutional neural network (DCNN) model based on ConvNeXt-Tiny to identify classic benign lesions (CBL) from other lesions (OL) within the Ovarian-Adnexal Reporting and Data System (O-RADS), enhancing the system's utility for novice ultrasonographers. Two sets of sonographic images of pathologically confirmed adnexal lesions were retrospectively collected [development dataset (DD) and independent test dataset (ITD)]. The ConvNeXt-Tiny model, optimized through transfer learning, was trained on the DD using the original images directly and after automatic lesion segmentation by a U-Net model. Models derived from both training paradigms were validated on the ITD for sensitivity, specificity, accuracy, and area under the curve (AUC). Two novice ultrasonographers were assessed in O-RADS with and without assistance from the model for Application Effectiveness. The ConvNeXt-Tiny model trained on original images scored AUCs of 0.978 for DD and 0.955 for ITD, while the U-Net segmented image model achieved 0.967 for DD and 0.923 for ITD; neither showed significant differences. When assessing the malignancy of lesions using O-RADS 4 and 5, the diagnostic performances of two novice ultrasonographers and senior ultrasonographer, as well as model-assisted classifications, showed no significant differences, except for one novice's low accuracy. This approach reduced classification time by 62 and 64 min. The kappa values with senior doctors' classifications rose from 0.776 and 0.761 to 0.914 and 0.903, respectively. The ConvNeXt-Tiny model demonstrated excellent and stable performance in distinguishing CBL from OL within O-RADS. The diagnostic performance of novice ultrasonographers using O-RADS is essentially equivalent to that of senior ultrasonographer, and the assistance of the model can enhance their classification efficiency and consistency with the results of senior ultrasonographer.

Early versus late construct failure in spine metastatic disease: implications for surgical strategy and oncologic outcome.

This study aimed to identify variables that portend early construct failure requiring surgical revision in patients undergoing instrumented fusion for spine metastases. A detailed retrospective chart review was performed. Demographic, surgical, and oncologic variables were collected and analyzed via independent samples t-testing, chi-square testing, and Kaplan-Meier method with log-rank testing. Significance was determined as p < 0.05. 482 spinal fusion operations for solid tumor metastases were performed between 2012 and 2022. Of these, 24 (5.0%) required revision surgery for construct failure. There were no major differences between the revision and non-revision patients in terms of several surgical characteristics. Thirteen (54.1%) were revised within 3 months of index surgery. These early construct failures were more likely to have functional neurological deficits at surgery (6/13 vs. 0/11 [p = 0.009]), longer constructs (mean 6.4±2.4 vs. 4.2 ± 1.4 levels [p = 0.015]), and cement-augmented pedicle screws (4/13 vs. 0/11 [p = 0.044)) compared to late construct failures (> 3 months after index surgery). Additionally, 17 symptomatic failures were identified, compared to 7 asymptomatic failures which were identified incidentally with routine follow-up imaging. All 7 asymptomatic construct failures occurred in the early revisions group [p = 0.004]. Revision surgery for early construct failure was associated with significantly reduced median overall survival compared to late failure (p = 0.010). Construct failures in our cohort were not associated with any classical characteristics of patients undergoing revision spine surgery. Early revision (< 3 months) portends a reduction in overall survival when compared with late revisions, and early revised patients were more likely to have had more extensive surgery and poorer neurological status at the time of index cases.

A multi-class support vector machine classification model based on 14 microRNAs for forensic body fluid identification

MicroRNAs (miRNAs) are promising biomarkers for forensic body fluid identification owing to their small size, stability against degradation, and differential expression patterns. However, the expression of most body fluid-miRNAs is relative (differentially expressed in certain body fluids) rather than absolute (exclusively expressed in a specific body fluid). Moreover, different body fluids contain heterogeneous cell types, complicating their identification. Therefore, appropriate normalization strategies to eliminate non-biological variations and robust models to interpret expression levels accurately are necessary prerequisites for applying miRNAs in body fluid identification. In this study, the expression stability of six candidate reference genes (RGs) across five body fluids was validated using geNorm, NormFinder, BestKeeper and RankAggreg, and the most suitable combination of RGs (hsa-miR-484 and hsa-miR-191–5p) was identified under our experimental conditions. Subsequently, we systematically evaluated the expression patterns of the 28 most promising body fluid-specific miRNA markers using TaqMan RT-qPCR and selected the optimal combination of markers (12 miRNAs) to establish a multi-class support vector machine (MSVM) classification model. An independent test set (60 samples) was used to validate the accuracy of the proposed classification model, while an additional 30 casework samples were used to assess its robustness. The MSVM model accurately predicted the body fluid origin for almost all (59/60) single-source samples. Moreover, this model demonstrated the capability to identify aged forensic samples and to predict the primary components of mixed stains to a certain extent. In summary, this study presented a miRNA-based MSVM classification model for forensic body fluid identification using the qPCR platform. However, extensive validation, especially inter-laboratory collaborative exercises, is necessary before miRNA can be routinely applied in forensic identification practice.

Deep learning image burst stacking to reconstruct high-resolution ground-based solar observations

Large aperture ground-based solar telescopes allow the solar atmosphere to be resolved in unprecedented detail. However, ground-based observations are inherently limited due to Earth's turbulent atmosphere, requiring image correction techniques. Recent post-image reconstruction techniques are based on using information from bursts of short-exposure images. Shortcomings of such approaches are the limited success, in case of stronger atmospheric seeing conditions, and computational demand. Real-time post-image reconstruction is of high importance to enabling automatic processing pipelines and accelerating scientific research. In an attempt to overcome these limitations, we provide a deep learning approach to reconstruct an original image burst into a single high-resolution high-quality image in real time. We present a novel deep learning tool for image burst reconstruction based on image stacking methods. Here, an image burst of 100 short-exposure observations is reconstructed to obtain a single high-resolution image. Our approach builds on unpaired image-to-image translation. We trained our neural network with seeing degraded image bursts and used speckle reconstructed observations as a reference. With the unpaired image translation, we aim to achieve a better generalization and increased robustness in case of increased image degradations. We demonstrate that our deep learning model has the ability to effectively reconstruct an image burst in real time with an average of 0.5 s of processing time while providing similar results to standard reconstruction methods. We evaluated the results on an independent test set consisting of high- and low-quality speckle reconstructions. Our method shows an improved robustness in terms of perceptual quality, especially when speckle reconstruction methods show artifacts. An evaluation with a varying number of images per burst demonstrates that our method makes efficient use of the combined image information and achieves the best reconstructions when provided with the full-image burst.

A Method for Detecting Depression in Adolescence Based on an Affective Brain-Computer Interface and Resting-State Electroencephalogram Signals.

Depression is increasingly prevalent among adolescents and can profoundly impact their lives. However, the early detection of depression is often hindered by the time-consuming diagnostic process and the absence of objective biomarkers. In this study, we propose a novel approach for depression detection based on an affective brain-computer interface (aBCI) and the resting-state electroencephalogram (EEG). By fusing EEG features associated with both emotional and resting states, our method captures comprehensive depression-related information. The final depression detection model, derived through decision fusion with multiple independent models, further enhances detection efficacy. Our experiments involved 40 adolescents with depression and 40 matched controls. The proposed model achieved an accuracy of 86.54% on cross-validation and 88.20% on the independent test set, demonstrating the efficiency of multimodal fusion. In addition, further analysis revealed distinct brain activity patterns between the two groups across different modalities. These findings hold promise for new directions in depression detection and intervention.

Near Infrared Reflectance Spectroscopy-Driven Chemometric Modeling for Predicting Key Quality Traits in Lablab Bean (Lablab purpureus L.) Germplasm

Lablab bean (Lablab purpureus L.) is a multipurpose crop, commonly used for food, feed, and fodder, and its potential as a plant-based meat alternative. Its nutritional diversity, including high protein, starch, and phenolic content, makes it a suitable candidate for nutritional profiling, which is essential for developing nutritionally enhanced varieties. Traditional methods for analyzing its nutritional parameters are labor-intensive, time-consuming, and expensive. This study employs Near-Infrared Reflectance Spectroscopy (NIRS) as a rapid, non-destructive alternative to evaluate 112 Lablab bean genotypes. We developed prediction models for starch, amylose, protein, fat, and phenols using a Modified Partial Least Squares (MPLS) approach, with spectral pre-processing using Standard Normal Variate (SNV) to remove scatter effects and Detrending (DT) to reduce baseline shifts and noise. The models were optimized for derivatives, gap selection, and smoothing, and evaluated using independent test data and key performance metrics including coefficient of determination (R²), bias, and Residual Prediction Deviation (RPD). The best-performing models were: starch (R² = 0.959, RPD = 4.57), amylose (R² = 0.737, RPD = 1.76), protein (R² = 0.911, RPD = 3.09), fat (R² = 0.894, RPD = 2.92), and phenols (R² = 0.816, RPD = 2.36). Statistical tests, including paired t-tests, correlation, and reliability analysis, confirmed the robustness of these models. This study presents a first report offering rapid, multi-trait assessment method for evaluating Lablab bean germplasm, demonstrating high predictive accuracy for pre-breeding practices. It has broad applications in developing nutritionally enhanced varieties, supporting plant-based protein alternatives, and optimizing food production processes to meet the growing demand for healthier, sustainable foods.

The significant influence of the sea surface temperature anomalies over North Atlantic and the Maritime Continent on maize yield in Northeast China

Northeastern China (NEC) is the largest grain base in China. Improving understanding of the effect of climate change on grain production over NEC is conducive to providing immediate response strategies for grain production. In this study, the relationships of the maize production with the dry state during the different maize growth stage have been investigated using the year-to-year increment method. Results showed that the severe drought that occurred from the jointing to maturity period have exerted severe effects on the maize growth. Further analysis indicated that the sea surface temperature (SST) anomalies over North Atlantic and Maritime Continent in later spring are the important factors affecting the summer droughts over NEC. The late spring SST anomaly over North Atlantic can excite the Rossby waves from the western North Atlantic and propagate eastward to NEC. The snow anomaly over western Siberia in late spring and the soil moisture anomaly over NEC in summer are key factors linking the SST anomaly to drought over the NEC. On the other hand, the Maritime Continent SST anomaly in late spring can modulate the activity of the East Asian jet stream via the East Asia-Pacific (EAP) teleconnection, which can provide the favorable conditions for the soil moisture reduction over NEC. Eventually, a predictive model for maize yield over NEC is successfully developed by using the predictive indices of the North Atlantic and the Maritime Continental SST during late spring. Both the cross-validation and independent sample tests show that the calibrated prediction model is robust and exhibits high skill in predicting maize yield over NEC.

A multi-perspective deep learning framework for enhancer characterization and identification

Enhancers are vital elements in the genome that boost the transcriptional activity of neighboring genes and are essential in regulating cell-specific gene expression. Therefore, accurately identifying and characterizing enhancers is essential for comprehending gene regulatory networks and the development of related diseases. This study introduces MPDL-Enhancer, a novel multi-perspective deep learning framework aimed at enhancer characterization and identification. In this study, enhancer sequences are encoded using the dna2vec model along with features derived from the structural properties of DNA sequences. Subsequently, these representations are processed through a novel dual-scale deep neural network designed to discern subtle correlations and extended interactions embedded within the semantic content of DNA. The predictive phase of our methodology employs a Support Vector Machine classifier to render the final classification. To rigorously assess the efficacy of our approach, a comprehensive evaluation was executed utilizing an independent test dataset, thereby substantiating the robustness and accuracy of our model. Our methodology demonstrated superior performance over existing computational techniques, with an accuracy (ACC) of 81.00 %, a sensitivity (SN) of 79.00 %, and specificity (SP) of 83.00 %. The innovative dual-scale deep neural network and the unique feature representation strategy contributed to this performance improvement. MPDL-Enhancer has effectively characterized enhancer sequences and achieved excellent predictive performance. Building upon this foundation, we conducted an interpretability analysis of the model, which can assist researchers in identifying key features and patterns that affect the functionality of enhancers, thereby promoting a deeper understanding of gene regulatory networks.

Knowledge of Metabolic Syndrome Among Third and Sixth Year Medical Students in Saudi Arabia.

Metabolic syndrome has become a public health challenge, and its prevalence is increasing among young adults. Little is known about the knowledge of medical students about this syndrome. The study aimed to assess the level of knowledge of the medical students about conditions relevant to metabolic syndrome. A cross-sectional survey was administered using a self-administered questionnaire to students in a medical college in Saudi Arabia. The survey was divided into four sections: diabetes, adiposity, hypertension, and hypercholesterolemia. Students' responses were gathered and interpreted as adequate knowledge (81-100%), moderate knowledge (51-80%), and low knowledge (≤50%). Independent samples t-test and Chi-square tests were done to examine the association between students' knowledge with the academic year (thirdand sixth years). The level of significance was set at 0.05. There were a total of 224 respondents, 102 (46%) from the third year and 122 (54%) from the sixth year. More than 70% of students correctly identified symptoms, complications, and risk factors of diabetes, adiposity, and hypertension, and 90% were aware of different types of diabetes. There were some false beliefs held by students such as 91% of third-year students believed that fatigue is a frequent symptom of high serum cholesterol compared to 70% of sixth-year students (p <0.001). Likewise, 36% of students falsely identified liposuction as the best possible treatment in adiposity therapy. The sixth year of study and family history of hypercholesterolemia was found to be positively associated with a higher knowledge score for most categories. The study concludes that the student's knowledge about conditions relevant to metabolic syndrome can be enhanced and preventative measures can be implemented to raise awareness about the syndrome.

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.

NO classifier prediction of anti neuroinflammatory agents using text mining of 3D molecular fingerprints

CNS Drug discovery has been challenging due to the lack of clarity on CNS diseases’ basic biological and pathological mechanisms. Despite the difficulty, some CNS drugs have been developed based on phenotypic effects. Herein, we propose a phenotype-structure relationship model, which predicts an anti-neuroinflammatory potency based on 3D molecular structures of the phenotype-active or inactive compounds without specifying targets. For this chemo-centric study, a predictive model of the nitric oxide (NO) inhibitory potency in hyper-activated microglia is built from the 548 agents, which were collected from 95 research articles (28 substructures consisting of natural products and synthetic scaffolds) and doubly externally validated by the agents of 9 research articles as third set. 3D Structures (multi-conformer ensemble) of every agent were encoded into the E3FP molecular fingerprint of the Keiser group as a 3D molecular representation. The location information of the molecular fingerprints could be learned and validated to classify the inhibitory potency of compounds (IC50 cut-off between the active and inactive: 37.1 µM): (1) multi-layer perceptron (MLP) (AUC-CV: 0.997, AUC-Test: 0.992), (2) recurrent neural network (RNN) (AUC-CV: 0.999, AUC-Test: 0.995), and (3) convolutional neural network (CNN) (AUC-CV: 0.998, AUC-Test: 0.994). The high performance of these models was compared with that of four classical machine classification models (Logistic, Ridge, Lasso, and Naïve Bayes). We named the binary classification models NO-Classifier. Independent test set validation and decision region analysis of the independent test set doubly demonstrated NO-Classifier effectively discerned the anti-inflammatory potency of testing compounds in inflammatory cell phenotype with the webserver in https://no-classifier.onrender.com.