UNASSIGNED: The identification of microbe-drug associations can greatly facilitate drug research and development. Traditional methods for screening microbe-drug associations are time-consuming, manpower-intensive, and costly to conduct, so computational methods are a good alternative. However, most of them ignore the combination of abundant sequence, structural information, and microbe-drug network topology.
UNASSIGNED: In this study, we developed a computational framework based on a modified graph attention variational autoencoder (MGAVAEMDA) to infer potential microbedrug associations by combining biological information with the variational autoencoder. In MGAVAEMDA, we first used multiple databases, which include microbial sequences, drug structures, and microbe-drug association databases, to establish two comprehensive feature matrices of microbes and drugs after multiple similarity computations, fusion, smoothing, and thresholding. Then, we employed a combination of variational autoencoder and graph attention to extract low-dimensional feature representations of microbes and drugs. Finally, the lowdimensional feature representation and graphical adjacency matrix were input into the random forest classifier to obtain the microbe-drug association score to identify the potential microbe-drug association. Moreover, in order to correct the model complexity and redundant calculation to improve efficiency, we introduced a modified graph convolutional neural network embedded into the variational autoencoder for computing low dimensional features.
UNASSIGNED: The experiment results demonstrate that the prediction performance of MGAVAEMDA is better than the five state-of-the-art methods. For the major measurements (AUC =0.9357, AUPR =0.9378), the relative improvements of MGAVAEMDA compared to the suboptimal methods are 1.76 and 1.47%, respectively.
UNASSIGNED: We conducted case studies on two drugs and found that more than 85% of the predicted associations have been reported in PubMed. The comprehensive experimental results validated the reliability of our models in accurately inferring potential microbe-drug associations.

BACKGROUND: Previous models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients.
METHODS: The electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (Random Forest Classifier, Logistic Regression, Support Vector Machine Classifier, K-nearest Neighbors Classifier, Gaussian Naive Bayes, Gradient Boosting Decision Tree, and Perceptron.) were used to develop delirium prediction models under full (q = 31) and selected (q = 19) feature sets, respectively.
RESULTS: The Random Forest classifier performs exceptionally well in both feature datasets, with an Area Under the Curve (AUC) of 0.92 for the full feature dataset and an AUC of 0.86 for the selected feature dataset. Additionally, it achieves a relatively lower Expected Calibration Error (ECE) and the highest Average Precision (AP), with an AP of 0.80 for the full feature dataset and an AP of 0.73 for the selected feature dataset. To further evaluate the best-performing Random Forest classifier, SHAP (Shapley Additive Explanations) was used, and the importance matrix plot, scatter plots, and summary plots were generated.
CONCLUSIONS: We established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.

COVID-19 mortality prediction Background COVID-19 has become a major global public health problem, despite prevention and efforts. The daily number of COVID-19 cases rapidly increases, and the time and financial costs associated with testing procedure are burdensome. Method To overcome this, we aim to identify immunological and metabolic biomarkers to predict COVID-19 mortality using a machine learning model. We included inpatients from Hong Kong\'s public hospitals between January 1, and September 30, 2020, who were diagnosed with COVID-19 using RT-PCR. We developed three machine learning models to predict the mortality of COVID-19 patients based on data in their electronic medical records. We performed statistical analysis to compare the trained machine learning models which are Deep Neural Networks (DNN), Random Forest Classifier (RF) and Support Vector Machine (SVM) using data from a cohort of 5,059 patients (median age = 46 years; 49.3% male) who had tested positive for COVID-19 based on electronic health records and data from 532,427 patients as controls. Result We identified top 20 immunological and metabolic biomarkers that can accurately predict the risk of mortality from COVID-19 with ROC-AUC of 0.98 (95% CI 0.96-0.98). Of the three models used, our result demonstrate that the random forest (RF) model achieved the most accurate prediction of mortality among COVID-19 patients with age, glomerular filtration, albumin, urea, procalcitonin, c-reactive protein, oxygen, bicarbonate, carbon dioxide, ferritin, glucose, erythrocytes, creatinine, lymphocytes, PH of blood and leukocytes among the most important biomarkers identified. A cohort from Kwong Wah Hospital (131 patients) was used for model validation with ROC-AUC of 0.90 (95% CI 0.84-0.92). Conclusion We recommend physicians closely monitor hematological, coagulation, cardiac, hepatic, renal and inflammatory factors for potential progression to severe conditions among COVID-19 patients. To the best of our knowledge, no previous research has identified important immunological and metabolic biomarkers to the extent demonstrated in our study.
UNASSIGNED: The online version contains supplementary material available at 10.1186/s44247-022-00001-0.

Cerebral microbleeds (CMBs) in the brain are the essential indicators of critical brain disorders such as dementia and ischemic stroke. Generally, CMBs are detected manually by experts, which is an exhaustive task with limited productivity. Since CMBs have complex morphological nature, manual detection is prone to errors. This paper presents a machine learning-based automated CMB detection technique in the brain susceptibility-weighted imaging (SWI) scans based on statistical feature extraction and classification. The proposed method consists of three steps: (1) removal of the skull and extraction of the brain; (2) thresholding for the extraction of initial candidates; and (3) extracting features and applying classification models such as random forest and naïve Bayes classifiers for the detection of true positive CMBs. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data that consist of 14 subjects with 104 microbleeds and testing data that consist of 6 subjects with 63 microbleeds. We were able to achieve 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB, and the naïve Bayes classifier achieved 90.5% sensitivity with 5.5 false positives per CMB. The proposed technique outperformed many state-of-the-art methods proposed in previous studies.

[This corrects the article DOI: 10.3389/fneur.2023.1129470.].

Alzheimer\'s disease (AD) is a neurodegenerative disease that primarily occurs in elderly individuals with cognitive impairment. Although extracellular β-amyloid (Aβ) accumulation and tau protein hyperphosphorylation are considered to be leading causes of AD, the molecular mechanism of AD remains unknown. Therefore, in this study, we aimed to explore potential biomarkers of AD. Next-generation sequencing (NGS) datasets, GSE173955 and GSE203206, were collected from the Gene Expression Omnibus (GEO) database. Analysis of differentially expressed genes (DEGs), gene ontology (GO) functional enrichment, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment, and protein-protein networks were performed to identify genes that are potentially associated with AD. Analysis of the DEG based protein-protein interaction (PPI) network using Cytoscape indicated that neuroinflammation and T-cell antigen receptor (TCR)-associated genes (LCK, ZAP70, and CD44) were the top three hub genes. Next, we validated these three hub genes in the AD database and utilized two machine learning models from different AD datasets (GSE15222) to observe their general relationship with AD. Analysis using the random forest classifier indicated that accuracy (78%) observed using the top three genes as inputs differed only slightly from that (84%) observed using all genes as inputs. Furthermore, another data set, GSE97760, which was analyzed using our novel eigenvalue decomposition method, indicated that the top three hub genes may be involved in tauopathies associated with AD, rather than Aβ pathology. In addition, protein-protein docking simulation revealed that the top hub genes could form stable binding sites with acetylcholinesterase (ACHE). This suggests a potential interaction between hub genes and ACHE, which plays an essential role in the development of anti-AD drug design. Overall, the findings of this study, which systematically analyzed several AD datasets, illustrated that LCK, ZAP70, and CD44 may be used as AD biomarkers. We also established a robust prediction model for classifying patients with AD.

Osteosarcoma accounts for 28% of primary bone malignancies in adults and up to 56% in children and adolescents (<20 years). However, early diagnosis and treatment are still inadequate, and new improvements are still needed. Missed diagnoses exist due to fewer traditional diagnostic methods, and clinical symptoms are often already present before diagnosis. This study aimed to develop novel and efficient predictive models for the diagnosis of osteosarcoma and to identify potential targets for exploring osteosarcoma markers. First, osteosarcoma and normal tissue expression microarray datasets were downloaded from the Gene Expression Omnibus (GEO). Then we screened the differentially expressed genes (DEGs) in the osteosarcoma and normal groups in the training group. Next, in order to explore the biologically relevant role of DEGs, Metascape and enrichment analyses were also performed on DEGs. The \"randomForest\" and \"neuralnet\" packages in R software were used to select representative genes and construct diagnostic models for osteosarcoma. The next step is to validate the model of the artificial neural network. Then, we performed an immune infiltration analysis by using the training set data. Finally, we constructed a prognostic model using representative genes for prognostic analysis. The copy number of osteosarcoma was also analyzed. A random forest classifier identified nine representative genes (ANK1, TGFBR3, TNFRSF21, HSPB8, ITGA7, RHD, AASS, GREM2, NFASC). HSPB8, RHD, AASS, and NFASC were genes we identified that have not been previously reported to be associated with osteosarcoma. The osteosarcoma diagnostic model we constructed has good performance with areas under the curves (AUCs) of 1 and 0.987 in the training and validation groups, respectively. This study opens new horizons for the early diagnosis of osteosarcoma and provides representative markers for the future treatment of osteosarcoma. This is the first study to pioneer the establishment of a genetic diagnosis model for osteosarcoma and advance the development of osteosarcoma diagnosis and treatment.

Sauce-aroma Baijiu (SAB) is one of the most famous Baijius in China; SAB has more than 500 aroma compounds in it. However, the key aroma compound in SAB flavor remains unclear. Volatiles play an important role in SAB aroma and are highly correlated to SAB quality. In the present study, 63 volatile compounds were quantified among 66 SAB samples using gas chromatography with flame ionization detector (GC-FID). The authors analyzed odor contributions and volatile compound correlations in two quality groups of SAB samples. Moreover, an odor activity value (OAV) ratio-based random forest classifier was used to explain the volatile compound relationship differentiations between the two quality groups. Our results proved higher quality SABs had richer aromas and indicated a set of fruity-like ethyl valerate, green- and malt-like isobutyraldehyde and malt-like 3-methylbutyraldehyde and sweet-like furfural, had closer co-abundance correlations in higher quality SABs. These results indicated that the aroma and contributions of volatile compounds in SABs should be analyzed not only with compound odor activity values, but also the correlations between different aroma compounds.

Phenylketonuria (PKU) is a genetic disorder with amino acid metabolic defect, which does great harms to the development of newborns and children. Early diagnosis and treatment can effectively prevent the disease progression. Here we developed a PKU screening model using random forest classifier (RFC) to improve PKU screening performance with excellent sensitivity, false positive rate (FPR) and positive predictive value (PPV) in all the validation dataset and two testing Chinese populations. RFC represented outstanding advantages comparing several different classification models based on machine learning and the traditional logistic regression model. RFC is promising to be applied to neonatal PKU screening.

Switchgrass low-land ecotypes have significantly higher biomass but lower cold tolerance compared to up-land ecotypes. Understanding the molecular mechanisms underlying cold response, including the ones at transcriptional level, can contribute to improving tolerance of high-yield switchgrass under chilling and freezing environmental conditions. Here, by analyzing an existing switchgrass transcriptome dataset, the temporal cis-regulatory basis of switchgrass transcriptional response to cold is dissected computationally. We found that the number of cold-responsive genes and enriched Gene Ontology terms increased as duration of cold treatment increased from 30 min to 24 hours, suggesting an amplified response/cascading effect in cold-responsive gene expression. To identify genomic sequences likely important for regulating cold response, machine learning models predictive of cold response were established using k-mer sequences enriched in the genic and flanking regions of cold-responsive genes but not non-responsive genes. These k-mers, referred to as putative cis-regulatory elements (pCREs) are likely regulatory sequences of cold response in switchgrass. There are in total 655 pCREs where 54 are important in all cold treatment time points. Consistent with this, eight of 35 known cold-responsive CREs were similar to top-ranked pCREs in the models and only these eight were important for predicting temporal cold response. More importantly, most of the top-ranked pCREs were novel sequences in cold regulation. Our findings suggest additional sequence elements important for cold-responsive regulation previously not known that warrant further studies.