External Set Research Articles

Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults.

Computed tomography (CT) body compositions reflect age-related metabolic derangements. We aimed to develop a multi-outcome deep learning model using CT multi-level body composition parameters to detect metabolic syndrome (MS), osteoporosis and sarcopenia by identifying metabolic clusters simultaneously. We also investigated the prognostic value of metabolic phenotyping by CT model for long-term mortality. The derivation set (n=516; 75% train set, 25% internal test set) was constructed using age- and sex-stratified random sampling from two community-based cohorts. Data from participants in the individual health assessment programme (n=380) were used as the external test set 1. Semi-automatic quantification of body compositions at multiple levels of abdominal CT scans was performed to train a multi-layer perceptron (MLP)-based multi-label classification model. External test set 2 to test the prognostic value of the model output for mortality was built using data from individuals who underwent abdominal CT in a tertiary-level institution (n=10141). The mean ages of the derivation and external sets were 62.8 and 59.7years, respectively, without difference in sex distribution (women 50%) or body mass index (BMI; 23.9kg/m2). Skeletal muscle density (SMD) and bone density (BD) showed a more linear decrement across age than skeletal muscle area. Alternatively, an increase in visceral fat area (VFA) was observed in both men and women. Hierarchical clustering based on multi-level CT body composition parameters revealed three distinctive phenotype clusters: normal, MS and osteosarcopenia clusters. The L3 CT-parameter-based model, with or without clinical variables (age, sex and BMI), outperformed clinical model predictions of all outcomes (area under the receiver operating characteristic curve: MS, 0.76 vs. 0.55; osteoporosis, 0.90 vs. 0.79; sarcopenia, 0.85 vs. 0.81 in external test set 1; P<0.05 for all). VFA contributed the most to the MS predictions, whereas SMD, BD and subcutaneous fat area were features of high importance for detecting osteoporosis and sarcopenia. In external test set 2 (mean age 63.5years, women 79%; median follow-up 4.9years), a total of 907 individuals (8.9%) died during follow-up. Among model-predicted metabolic phenotypes, sarcopenia alone (adjusted hazard ratio [aHR] 1.55), MS+sarcopenia (aHR 1.65), osteoporosis+sarcopenia (aHR 1.83) and all three combined (aHR 1.87) remained robust predictors of mortality after adjustment for age, sex and comorbidities. A CT body composition-based MLP model detected MS, osteoporosis and sarcopenia simultaneously in community-dwelling and hospitalized adults. Metabolic phenotypes predicted by the CT MLP model were associated with long-term mortality, independent of covariates.

A multi-step attack identification and correlation method based on multi-information fusion

With the continuous development of Internet technology, network security issues are becoming more and more complex. In order to obtain or damage user information, attackers usually need to use multiple attack steps to attack different network nodes to achieve the final goal. Currently, traditional intrusion detection mainly focuses on classifying attacks on a single piece of traffic information, and lacks the use of correlation and timing information between multi-step attack traffic to carry out multi-step attack identification and correlation research. To this end, we introduce an edge-based graph attention network to aggregate the neighbor information of flows and use a long short-term memory neural network to obtain time series information. By considering neighbor traffic and time information during the classification process, we are able to achieve accurate classification in multi-step attack scenarios. Then, based on the classification results, the sum of the number of attacks and the number of attacks is counted for each host node. Then standardize the statistical counts of internal network host nodes and external network host nodes and set thresholds to exclude low-risk nodes. Finally, a time-based depth-first traversal algorithm is used to obtain the key attack chain. However, this method may face some challenges, such as high computational complexity, the ability to handle large-scale data, and the generalization ability of the model. Experimental results show that the method we proposed is significantly better than the traditional method in terms of accuracy and recall rate for multi-step attacks, and it can effectively correlate attack steps and obtain multiple key attack chains.

ProTox 3.0: a webserver for the prediction of toxicity of chemicals.

Interaction with chemicals, present in drugs, food, environments, and consumer goods, is an integral part of our everyday life. However, depending on the amount and duration, such interactions can also result in adverse effects. With the increase in computational methods, the in silico methods can offer significant benefits to both regulatory needs and requirements for risk assessments and the pharmaceutical industry to assess the safety profile of a chemical. Here, we present ProTox3.0, which incorporates molecular similarity and machine-learning models for the prediction of 61 toxicity endpoints such as acute toxicity, organ toxicity, clinical toxicity, molecular-initiating events (MOE), adverse outcomes (Tox21) pathways, several other toxicological endpoints and toxicity off-targets. All the ProTox 3.0 models are validated on independent external sets and have shown strong performance. ProTox envisages itself as a complete, freely available computational platform for in silico toxicity prediction for toxicologists, regulatory agencies, computational chemists, and medicinal chemists. The ProTox 3.0 webserver is free and open to all users, and there is no login requirement and can be accessed via https://tox.charite.de. The web server takes a 2D chemical structure as input and reports the toxicological profile of the compound for each endpoint with a confidence score and overall toxicity radar plot and network plot.

Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning.

Cancer of unknown primary (CUP) site poses diagnostic challenges due to its elusive nature. Many cases of CUP manifest as pleural and peritoneal serous effusions. Leveraging cytological images from 57,220 cases at four tertiary hospitals, we developed a deep-learning method for tumor origin differentiation using cytological histology (TORCH) that can identify malignancy and predict tumor origin in both hydrothorax and ascites. We examined its performance on three internal (n = 12,799) and two external (n = 14,538) testing sets. In both internal and external testing sets, TORCH achieved area under the receiver operating curve values ranging from 0.953 to 0.991 for cancer diagnosis and 0.953 to 0.979 for tumor origin localization. TORCH accurately predicted primary tumor origins, with a top-1 accuracy of 82.6% and top-3 accuracy of 98.9%. Compared with results derived from pathologists, TORCH showed better prediction efficacy (1.677 versus 1.265, P < 0.001), enhancing junior pathologists' diagnostic scores significantly (1.326 versus 1.101, P < 0.001). Patients with CUP whose initial treatment protocol was concordant with TORCH-predicted origins had better overall survival than those who were administrated discordant treatment (27 versus 17 months, P = 0.006). Our study underscores the potential of TORCH as a valuable ancillary tool in clinical practice, although further validation in randomized trials is warranted.

The rat acute oral toxicity of trifluoromethyl compounds (TFMs): a computational toxicology study combining the 2D-QSTR, read-across and consensus modeling methods.

All areas of the modern society are affected by fluorine chemistry. In particular, fluorine plays an important role in medical, pharmaceutical and agrochemical sciences. Amongst various fluoro-organic compounds, trifluoromethyl (CF3) group is valuable in applications such as pharmaceuticals, agrochemicals and industrial chemicals. In the present study, following the strict OECD modelling principles, a quantitative structure-toxicity relationship (QSTR) modelling for the rat acute oral toxicity of trifluoromethyl compounds (TFMs) was established by genetic algorithm-multiple linear regression (GA-MLR) approach. All developed models were evaluated by various state-of-the-art validation metrics and the OECD principles. The best QSTR model included nine easily interpretable 2D molecular descriptors with clear physical and chemical significance. The mechanistic interpretation showed that the atom-type electro-topological state indices, molecular connectivity, ionization potential, lipophilicity and some autocorrelation coefficients are the main factors contributing to the acute oral toxicity of TFMs against rats. To validate that the selected 2D descriptors can effectively characterize the toxicity, we performed the chemical read-across analysis. We also compared the best QSTR model with public OPERA tool to demonstrate the reliability of the predictions. To further improve the prediction range of the QSTR model, we performed the consensus modelling. Finally, the optimum QSTR model was utilized to predict a true external set containing many untested/unknown TFMs for the first time. Overall, the developed model contributes to a more comprehensive safety assessment approach for novel CF3-containing pharmaceuticals or chemicals, reducing unnecessary chemical synthesis whilst saving the development cost of new drugs.

Study on energy capture characteristics of piezoelectric stack energy harvester for railway track

Railway traffic plays a pivotal role within the current transportation system, with ensuring its safety being of paramount importance. Real-time monitoring of train track health through sensor technology has emerged as a significant approach for achieving this objective. However, a persistent challenge lies in providing cost-effective and stable power to sensors in remote areas. This paper proposes the utilization of a novel piezoelectric stack energy harvester in railway systems to address this issue. The substantial and consistent vibration energy produced by railway operations makes it an ideal source for energy harvesting, unaffected by environmental conditions. Through simulation analysis and experimental verification, this study explores the impact of load size, load frequency, and external resistance on the energy harvesting efficiency of the proposed piezoelectric stack energy harvester. The results indicate that the output power of the energy harvester increases with the load size. Furthermore, the frequency significantly influences the energy capture efficiency when below 8 Hz, with minimal impact on frequencies above 8 Hz. Interestingly, the load dramatically affects the energy capture efficiency, even at higher frequencies. With the external resistance set to 250 kΩ, the harvester achieves a maximum output power of 42.76 mW.

Evaluation of the prognostic performance of different cutoff values of lymph node ratio staging system for stage III colorectal cancer.

This study attempted to compare the prognostic performance of lymph node ratio (LNR) staging system with different cutoff values relative to American Joint Committee on Cancer (AJCC) pN staging system in stage III colorectal cancer (CRC). Overall, 45,069 patients from the SEER dataset and 69 patients from the Second Affiliated Hospital of Nanjing Medical University (the External set) who underwent surgical resection of the primary tumor and were diagnosed with stage III CRC by postoperative pathology were included. Patients were divided into three subgroups based on the LNR cutoff used in previous studies, Kaplan-Meier curves were plotted, and log-rank test was used to compare the differences among groups in terms of cancer-specific survival (CSS). Cox regression model was applied for survival analysis. To evaluate the discriminatory power of different lymph node staging systems, Harrell's C statistic(C-index) and Akaike's Information Criterion (AIC) were applied. A set of optimal cutoff values (0.11; 0.36; 0.66) of LNR staging system with the most considerable discriminatory power to the prognosis in patients with stage III CRC (SEER set: C-index = 0.714; AIC = 58,942.46, External set: C-index = 0.809; AIC = 164.36) were obtained, and both were superior to the AJCC pN staging system (SEER set: C-index = 0.708; AIC = 59,071.20, External set: C-index = 0.788; AIC = 167.06). For evaluating the prognostic efficacy of patients with stage III colorectal cancer, the cutoff value (0.11; 0.36; 0.66) of LNR staging system had the best discrimination and prognostic ability, which was superior to LNR staging system under other cutoff values and AJCC pN staging system.

Improving predictions of compound amenability for liquid chromatography-mass spectrometry to enhance non-targeted analysis.

Mass-spectrometry-based non-targeted analysis (NTA), in which mass spectrometric signals are assigned chemical identities based on a systematic collation of evidence, is a growing area of interest for toxicological risk assessment. Successful NTA results in better identification of potentially hazardous pollutants within the environment, facilitating the development of targeted analytical strategies to best characterize risks to human and ecological health. A supporting component of the NTA process involves assessing whether suspected chemicals are amenable to the mass spectrometric method, which is necessary in order to assign an observed signal to the chemical structure. Prior work from this group involved the development of a random forest model for predicting the amenability of 5517 unique chemical structures to liquid chromatography-mass spectrometry (LC-MS). This work improves the interpretability of the group's prior model of the same endpoint, as well as integrating 1348 more data points across negative and positive ionization modes. We enhance interpretability by feature engineering, a machine learning practice that reduces the input dimensionality while attempting to preserve performance statistics. We emphasize the importance of interpretable machine learning models within the context of building confidence in NTA identification. The novel data were curated by the labeling of compounds as amenable or unamenable by expert curators, resulting in an enhanced set of chemical compounds to expand the applicability domain of the prior model. The balanced accuracy benchmark of the newly developed model is comparable to performance previously reported (mean CV BA is 0.84 vs. 0.82 in positive mode, and 0.85 vs. 0.82 in negative mode), while on a novel external set, derived from this work's data, the Matthews correlation coefficients (MCC) for the novel models are 0.66 and 0.68 for positive and negative mode, respectively. Our group's prior published models scored MCC of 0.55 and 0.54 on the same external sets. This demonstrates appreciable improvement over the chemical space captured by the expanded dataset. This work forms part of our ongoing efforts to develop models with higher interpretability and higher performance to support NTA efforts.

Graph to Activation Energy Models Easily Reach Irreducible Errors but Show Limited Transferability.

Activation energy characterization of competing reactions is a costly but crucial step for understanding the kinetic relevance of distinct reaction pathways, product yields, and myriad other properties of reacting systems. The standard methodology for activation energy characterization has historically been a transition state search using the highest level of theory that can be afforded. However, recently, several groups have popularized the idea of predicting activation energies directly based on nothing more than the reactant and product graphs, a sufficiently complex neural network, and a broad enough data set. Here, we have revisited this task using the recently developed Reaction Graph Depth 1 (RGD1) transition state data set and several newly developed graph attention architectures. All of these new architectures achieve similar state-of-the-art results of ∼4 kcal/mol mean absolute error on withheld testing sets of reactions but poor performance on external testing sets composed of reactions with differing mechanisms, reaction molecularity, or reactant size distribution. Limited transferability is also shown to be shared by other contemporary graph to activation energy architectures through a series of case studies. We conclude that an array of standard graph architectures can already achieve results comparable to the irreducible error of available reaction data sets but that out-of-distribution performance remains poor.

Multiparametric MRI-Based Interpretable Radiomics Machine Learning Model Differentiates Medulloblastoma and Ependymoma in Children: A Two-Center Study

Rationale and ObjectivesMedulloblastoma (MB) and Ependymoma (EM) in children, share similarities in age group, tumor location, and clinical presentation. Distinguishing between them through clinical diagnosis is challenging. This study aims to explore the effectiveness of using radiomics and machine learning on multiparametric magnetic resonance imaging (MRI) to differentiate between MB and EM and validate its diagnostic ability with an external set. Materials and methodsAxial T2 weighted image (T2WI) and contrast-enhanced T1weighted image (CE-T1WI) MRI sequences of 135 patients from two centers were collected as train/test sets. Volume of interest (VOI) was manually delineated by an experienced neuroradiologist, supervised by a senior. Feature selection analysis and the least absolute shrinkage and selection operator (LASSO) algorithm identified valuable features, and Shapley additive explanations (SHAP) evaluated their significance. Five machine-learning classifiers- extreme gradient boosting (XGBoost), Bernoulli naive Bayes (Bernoulli NB), Logistic Regression (LR), support vector machine (SVM), linear support vector machine (Linear SVC) classifiers were built based on T2WI (T2 model), CE-T1WI (T1 model), and T1+T2WI (T1+T2 model). A human expert diagnosis was developed and corrected by senior radiologists. External validation was performed at Sun Yat-Sen University Cancer Center. Results31 valuable features were extracted from T2WI and CE-T1WI. XGBoost demonstrated the highest performance with an area under the curve (AUC) of 0.92 on the test set and maintained an AUC of 0.80 during external validation. For the T1 model, XGBoost achieved the highest AUC of 0.85 on the test set and the highest accuracy of 0.71 on the external validation set. In the T2 model, XGBoost achieved the highest AUC of 0.86 on the test set and the highest accuracy of 0.82 on the external validation set. The human expert diagnosis had an AUC of 0.66 on the test set and 0.69 on the external validation set. The integrated T1+T2 model achieved an AUC of 0.92 on the test set, 0.80 on the external validation set, achieved the best performance. Overall, XGBoost consistently outperformed in different classification models. ConclusionThe combination of radiomics and machine learning on multiparametric MRI effectively distinguishes between Medulloblastoma and Ependymoma in childhood, surpassing human expert diagnosis in training and testing sets.

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilotstudy

BackgroundTo describe the diagnostic performance of a deep learning (DL) algorithm in detecting Fuchs endothelial corneal dystrophy (FECD) based on specular microscopy (SM) and to reliably detect widefield peripheral SM images with an endothelial cell density (ECD) > 1000 cells/mm2.MethodsFive hundred and forty-seven subjects had SM imaging performed for the central cornea endothelium. One hundred and seventy-three images had FECD, while 602 images had other diagnoses. Using fivefold cross-validation on the dataset containing 775 central SM images combined with ECD, coefficient of variation (CV) and hexagonal endothelial cell ratio (HEX), the first DL model was trained to discriminate FECD from other images and was further tested on an external set of 180 images. In eyes with FECD, a separate DL model was trained with 753 central/paracentral SM images to detect SM with ECD > 1000 cells/mm2 and tested on 557 peripheral SM images. Area under curve (AUC), sensitivity and specificity were evaluated.ResultsThe first model achieved an AUC of 0.96 with 0.91 sensitivity and 0.91 specificity in detecting FECD from other images. With an external validation set, the model achieved an AUC of 0.77, with a sensitivity of 0.69 and specificity of 0.68 in differentiating FECD from other diagnoses. The second model achieved an AUC of 0.88 with 0.79 sensitivity and 0.78 specificity in detecting peripheral SM images with ECD > 1000 cells/mm2.ConclusionsOur pilot study developed a DL model that could reliably detect FECD from other SM images and identify widefield SM images with ECD > 1000 cells/mm2 in eyes with FECD. This could be the foundation for future DL models to track progression of eyes with FECD and identify candidates suitable for therapies such as Descemet stripping only.

Prediction of cytochrome P450-mediated bioactivation using machine learning models and in vitro validation.

Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.e., Random Forest, Random Subspace, SVM and Naïve Bayes. The models were assessed by metrics like "Precision", "Recall", "F-Measure", "AUC" (Area Under the Curve), etc. Random Forest algorithms illustrated the best predictability, with nice AUC values of 0.949, 0.973 and 0.958 for the test sets of Benzene ring, Nitrogen heterocycle and Sulfur heterocycle models, respectively. 2D descriptors like topological indices, 2D autocorrelations and Burden eigenvalues, etc. contributed most to the models. Furthermore, the models were applied to predict the occurrence of bioactivation of an external verification set. Drugs like selpercatinib, glafenine, encorafenib, etc. were predicted to undergo bioactivation into toxic RMs. In vitro, IC50 shift experiment was performed to assess the potential of bioactivation to validate the prediction. Encorafenib and tirbanibulin were observed of bioactivation potential with shifts of 3-6 folds or so. Overall, this study provided a reliable and robust strategy to predict the P450-mediated bioactivation, which will be helpful to the assessment of adverse drug reactions (ADRs) in clinic and the design of new candidates with lower toxicities.

Optimization of Ganciclovir and Valganciclovir Starting Dose in Children by Machine Learning.

Ganciclovir (GCV) and valganciclovir (VGCV) show large interindividual pharmacokinetic variability, particularly in children.The objectives of this study were (1) to develop machine learning (ML) algorithms trained on simulated pharmacokinetics profiles obtained by Monte Carlo simulations to estimate the best gancicloviror valganciclovirstarting dose in children and (2) to compare its performances on real-world profiles to previously published equation derived from literature population pharmacokinetic (POPPK) models achieving about 20% of profiles within the target. The pharmacokinetic parameters of four literature POPPK models in addition to the World Health Organization (WHO) growth curve for children were used in the mrgsolve R package to simulate 10,800 pharmacokinetic profiles. ML algorithms were developed and benchmarked to predict the probability to reach the steady-state, area-under-the-curve target (AUC0-24within 40-60 mg × h/L) based on demographic characteristics only. The best ML algorithm was then used to calculate the starting dose maximizing the target attainment. Performances were evaluated for ML and literature formula in a test set and in an external set of 32 and 31 actual patients (GCV and VGCV, respectively). A combination of Xgboost, neural network, and random forest algorithms yielded the best performances and highest target attainment in the test set (36.8% for GCV and 35.3% for the VGCV). In actual patients, the best GCV ML starting dose yielded the highest target attainment rate (25.8%) and performed equally for VGCV with the Franck model formula (35.3% for both). The ML algorithms exhibit good performances in comparison with previously validated models and should be evaluated prospectively.

Development of an easy-to-set-up multiple heart-cutting achiral-chiral LC-LC method for the analysis of branched-chain amino acids in commercial tablets.

In this paper, the development and application of a multiple heart-cutting achiral-chiral LC-LC method (mLC-LC) for the analysis of dansylated (Dns) branched-chain amino acids in commercial tablets are described. In the first dimension, a Waters Xbridge RP C18 achiral column was used under gradient conditions with buffered aqueous solution and acetonitrile. The elution order Dns-valine (Dns-Val)<Dns-isoleucine (Dns-Ile)<Dns-leucine (Dns-Leu) turned out with full resolution between adjacent peaks: 7.25 and 1.50 for the Val/Ile and the Ile/Leu pairs, respectively. A "research" validation study was performed, revealing high accuracy (Recovery%) and precision (RSD%) using two external set solutions, respectively, in the range 93.7%-104.1% and 0.4%-3.2%. The C18 column was connected via a two-position six-port switching valve to the quinidine-based Chiralpak quinidine-anion-exchange chiral column. A water/acetonitrile, 30/70 (v/v) with 50mM ammonium acetate (apparent pH of 5.5) eluent allowed getting the three enantiomers' pairs resolved: RS equal to 4.3 for Dns-Val and Dns-Ile, and 1.7 for Dns-Leu. The application of the mLC-LC method confirmed that the content of Val, Ile, and Leu in the tablets was compliant with that labeled by the producer. Only l-enantiomers were found in the food supplement, as confirmed by LC-MS/MS analysis.

Automatic segmentation of hepatocellular carcinoma on dynamic contrast-enhanced MRI based on deep learning

Objective. Precise hepatocellular carcinoma (HCC) detection is crucial for clinical management. While studies focus on computed tomography-based automatic algorithms, there is a rareness of research on automatic detection based on dynamic contrast enhanced (DCE) magnetic resonance imaging. This study is to develop an automatic detection and segmentation deep learning model for HCC using DCE. Approach: DCE images acquired from 2016 to 2021 were retrospectively collected. Then, 382 patients (301 male; 81 female) with 466 lesions pathologically confirmed were included and divided into an 80% training-validation set and a 20% independent test set. For external validation, 51 patients (42 male; 9 female) in another hospital from 2018 to 2021 were included. The U-net architecture was modified to accommodate multi-phasic DCE input. The model was trained with the training-validation set using five-fold cross-validation, and furtherly evaluated with the independent test set using comprehensive metrics for segmentation and detection performance. The proposed automatic segmentation model consisted of five main steps: phase registration, automatic liver region extraction using a pre-trained model, automatic HCC lesion segmentation using the multi-phasic deep learning model, ensemble of five-fold predictions, and post-processing using connected component analysis to enhance the performance to refine predictions and eliminate false positives. Main results. The proposed model achieved a mean dice similarity coefficient (DSC) of 0.81 ± 0.11, a sensitivity of 94.41 ± 15.50%, a precision of 94.19 ± 17.32%, and 0.14 ± 0.48 false positive lesions per patient in the independent test set. The model detected 88% (80/91) HCC lesions in the condition of DSC > 0.5, and the DSC per tumor was 0.80 ± 0.13. In the external set, the model detected 92% (58/62) lesions with 0.12 ± 0.33 false positives per patient, and the DSC per tumor was 0.75 ± 0.10. Significance. This study developed an automatic detection and segmentation deep learning model for HCC using DCE, which yielded promising post-processed results in accurately identifying and delineating HCC lesions.

First report on chemometrics-driven multilayered lead prioritization in addressing oxysterol-mediated overexpression of G protein-coupled receptor 183.

Contemporary research has convincingly demonstrated that upregulation of G protein-coupled receptor 183 (GPR183), orchestrated by its endogenous agonist, 7α,25-dihydroxyxcholesterol (7α,25-OHC), leads to the development of cancer, diabetes, multiple sclerosis, infectious, and inflammatory diseases. A recent study unveiled the cryo-EM structure of 7α,25-OHC bound GPR183 complex, presenting an untapped opportunity for computational exploration of potential GPR183 inhibitors, which served as our inspiration for the current work. A predictive and validated two-dimensional QSAR model using genetic algorithm (GA) and multiple linear regression (MLR) on experimental GPR183 inhibition data was developed. QSAR study highlighted that structural features like dissimilar electronegative atoms, quaternary carbon atoms, and CH2RX fragment (X: heteroatoms) influence positively, while the existence of oxygen atoms with a topological separation of 3, negatively affects GPR183 inhibitory activity. Post assessment of true external set prediction capability, the MLR model was deployed to screen 12,449 DrugBank compounds, followed by a screening pipeline involving molecular docking, druglikeness, ADMET, protein-ligand stability assessment using deep learning algorithm, molecular dynamics, and molecular mechanics. The current findings strongly evidenced DB05790 as a potential lead for prospective interference of oxysterol-mediated GPR183 overexpression, warranting further in vitro and in vivo validation.

Towards clinically applicable automated mandibular canal segmentation on CBCT

ObjectivesTo develop a deep learning-based system for precise, robust, and fully automated segmentation of the mandibular canal on cone beam computed tomography (CBCT) images. MethodsThe system was developed on 536 CBCT scans (training set: 376, validation set: 80, testing set: 80) from one center and validated on an external dataset of 89 CBCT scans from 3 centers. Each scan was annotated using a multi-stage annotation method and refined by oral and maxillofacial radiologists. We proposed a three-step strategy for the mandibular canal segmentation: extraction of the region of interest based on 2D U-Net, global segmentation of the mandibular canal, and segmentation refinement based on 3D U-Net. ResultsThe system consistently achieved accurate mandibular canal segmentation in the internal set (Dice similarity coefficient [DSC], 0.952; intersection over union [IoU], 0.912; average symmetric surface distance [ASSD], 0.046 mm; 95% Hausdorff distance [HD95], 0.325 mm) and the external set (DSC, 0.960; IoU, 0.924; ASSD, 0.040 mm; HD95, 0.288 mm). ConclusionsThese results demonstrated the potential clinical application of this AI system in facilitating clinical workflows related to mandibular canal localization. Clinical significanceAccurate delineation of the mandibular canal on CBCT images is critical for implant placement, mandibular third molar extraction, and orthognathic surgery. This AI system enables accurate segmentation across different models, which could contribute to more efficient and precise dental automation systems.

Predicting Silicate Glass Geochemistry Using Raman Spectroscopy and Supervised Machine Learning: Partial Least Square Applications to Amorphous Raman Spectra.

Here, Raman spectroscopy is used to develop a univariate partial least squares (PLS) calibration capable of quantifying geochemistry in synthetic and natural silicate glass samples. The calibration yields eight oxide-specific models that allow predictions of silicon dioxide (SiO2), sodium oxide (Na2O), potassium oxide (K2O), calcium oxide (CaO), titanium dioxide (TiO2), aluminum oxide (Al2O3), ferrous oxide (FeOT), and magnesium oxide (MgO) (wt%) in glasses spanning a wide range of compositions, while also providing correlation-coefficient matrices that highlight the importance of specific Raman channels in the regression of a particular oxide. The PLS suite is trained on 48 of the 69 total glasses, and tested against 21 validation samples (i.e., held out of training). Trends in root mean square error of calibration (RMSEC), root mean square error of cross-validation (RMSECV), and root mean square error of prediction (RMSEP) model accuracy metrics are investigated to uncover the efficacy of utilizing multivariate analysis for such Raman data and are contextualized against recently produced strategies. The technique yields an average root mean of calibration (∼2.4 wt%), cross-validation (∼ 2.9 wt%), prediction (∼ 2.6 wt%), and normalized variance (∼ 28%). Raman band positional shifts are also mapped against underlying chemical variations; with major influences arising primarily as a function of overall oxidation state and silica concentration: via ferric cation (Fe3+)/ferrous cation (Fe2+) ratios and SiO2 (wt%). The algorithm is further validated preliminarily against a separate external set of 11 natural basaltic glasses to unravel the limitations of the synthetic models on natural samples, and to determine the suitability of "universal" Raman-model applications in scenarios where prior chemical contextualization of the target sample is possible. This study represents the first time Raman spectra of amorphous silicates have been paired with PLS, offering a foundation for future improvements utilizing these systems.

A pyroptosis-related lncRNA-based prognostic index for hepatocellular carcinoma by relative expression orderings.

Hepatocellular carcinoma (HCC) is an invasive malignant tumor, and pyroptosis makes an important contribution to the pathology and progression of liver cancer. Many prognostic models have been proposed for HCC based on the quantitative expression level of candidate genes, which are unsuitable for clinical application due to their vulnerability against experimental batch effects. The aim of this study was to develop a novel pyroptosis-related long non-coding RNA (lncRNA)-based prognostic index (PLPI) for HCC based on relative expression orderings (REOs). Firstly, the pyroptosis-related lncRNAs were identified through the Wilcoxon rank-sum test and gene co-expression analyses. Then, the novel prognostic model PLPI was constructed by pyroptosis-related lncRNA pairs, which were identified by multiple machine learning algorithms. Gene set enrichment, somatic mutation, and drug sensitivity analyses were conducted to measure the differences between high- and low-risk patients. Multiple immune analyses were used to explore the association between PLPI and the immunological microenvironment. In this study, a novel prognostic model PLPI based on 10 pyroptosis-related lncRNA pairs was constructed, which was proven to be an independent prognostic risk factor. The receiver operating characteristic (ROC) curves showed that the model had a good prognostic ability in the training, testing, and external set, respectively [5-year area under the curve (AUC) =0.73, 5-year AUC =0.81, 4-year AUC =0.79]. The results of survival, somatic mutation, and immune analyses showed that the patients in the low-risk group had a better prognosis, lower rates of somatic mutation, and better immune cell infiltration. Personalized chemotherapeutic drugs were also identified for the patients with HCC. The novel PLPI not only greatly predicted the prognosis of patients with HCC but could also offer novel ideas and approaches for the therapeutic management of HCC.

Antibiotic cement nails manufactured with threaded rods or cannulated intramedullary nails are better than those made with guidewires and do not debond.

The purpose of this study was to comparatively evaluate cement debonding at the time of removal of antibiotic cemented coated nails (ABNs) with cores made with a guidewire ($120), a regular intramedullary nail ($1100) or a threaded rod from a circular frame external fixator set ($60). A retrospective study was performed on 32 ABNs that had been implanted for long bone infections after intramedullary nailing. All ABNs were manufactured intraoperatively by the treating surgeon using 2 grams of vancomycin and single package of Tobramycin Simplex Cement (Stryker, Kalamazoo, MI). The powder, antibiotics, and polymer were mixed and then injected into an ABN cement mold (Bonesetter Holdings USA). Debonding was assessed at time of removal by the operating surgeon. Rates of cement debonding between the 3 groups were statistically compared. Debonding occurred in 0/12 of the cement nails manufactured with an intramedullary nail, 0/7 threaded rod ABNs, and 6/13 guidewire ABNs. There was a significant difference in the rate of debonding between the 3 groups (P < 0.01). Removal of the remnant cement was accomplished with thin osteotomes, long pituitary rongeurs, or reamers. The canal was visualized using an arthroscope to ensure complete removal of the cement. ABNs fabricated with standard intramedullary nails or threaded rods did not lead to any debonding. Debonding of the cement from the inner core of an antibiotic nail often requires significant effort to remove the remnant cement. Given that threaded rods are often cheaper than guidewires, we recommend that ABNs be fabricated with either threaded rods or interlocking nails, but not guidewires, depending on the level of stability required.