Integrated convolution and self-attention for improving peptide toxicity prediction.

MOTIVATION: Peptides are promising agents for the treatment of a variety of diseases due to their specificity and efficacy. However, the development of peptide-based drugs is often hindered by the potential toxicity of peptides, which poses a significant barrier to their clinical application. Traditional experimental methods for evaluating peptide toxicity are time-consuming and costly, making the development process inefficient. Therefore, there is an urgent need for computational tools specifically designed to predict peptide toxicity accurately and rapidly, facilitating the identification of safe peptide candidates for drug development. RESULTS: We provide here a novel computational approach, CAPTP, which leverages the power of convolutional and self-attention to enhance the prediction of peptide toxicity from amino acid sequences. CAPTP demonstrates outstanding performance, achieving a Matthews correlation coefficient of approximately 0.82 in both cross-validation settings and on independent test dataset. This performance surpasses that of existing state-of-the-art peptide toxicity predictors. Importantly, CAPTP maintains its robustness and generalizability even when dealing with data imbalances. Further analysis by CAPTP reveals that certain sequential patterns, particularly in the head and central regions of peptides, are crucial in determining their toxicity. This insight can significantly inform and guide the design of safer peptide drugs. AVAILABILITY: The source code for CAPTP is freely available at https://github.com/jiaoshihu/CAPTP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A stacking-based algorithm for antifreeze protein identification using combined physicochemical, pseudo amino acid composition, and reduction property features.

Antifreeze proteins have wide applications in the medical and food industries. In this study, we propose a stacking-based classifier that can effectively identify antifreeze proteins. Initially, feature extraction was performed in three aspects: reduction properties, scalable pseudo amino acid composition, and physicochemical properties. A hybrid feature set comprised of the combined information from these three categories was obtained. Subsequently, we trained the training set based on LightGBM, XGBoost, and RandomForest algorithms, and the training outcomes were passed to the Logistic algorithm for matching, thereby establishing a stacking algorithm. The proposed algorithm was tested on the test set and an independent validation set. Experimental data indicates that the algorithm achieved a recognition accuracy of 98.3 %, and an accuracy of 98.5 % on the validation set. Lastly, we analyzed the reasons why numerical features achieved high recognition capabilities from multiple aspects. Data dimensionality reduction and the analysis from two-dimensional and three-dimensional views revealed separability between positive and negative samples, and the protein three-dimensional structure further demonstrated significant differences in related features between the two samples. Analysis of the classifier revealed that Hr*Hr, HrHr, and Sc-PseAAC_1, 188D(152,116,57,183) were among the seven most important numerical features affecting algorithm recognition. For Hr*Hr and HrHr, supportive sequence level evidence for the reduction dictionary was found in terms of conservation area analysis, multiple sequence alignment, and amino acid conservative substitution. Moreover, the importance of the reduction dictionary was recognized through a comparative analysis of importance before and after the reduction, realizing the effectiveness of the dictionary in improving feature importance. A decision tree model has been utilized to discern the distinctions between dipeptides associated with the physical and chemical properties of His(H), Iso(I), Leu(L), and Lys(K) and other dipeptides. We finally analyzed the other seven features of importance, and data analysis confirmed that hydrophobicity, secondary structure, charge properties, van der Waals forces, and solvent accessibility are also factors affecting the antifreeze capability of proteins.

Advancing cancer driver gene detection via Schur complement graph augmentation and independent subspace feature extraction.

Accurately identifying cancer driver genes (CDGs) is crucial for guiding cancer treatment and has recently received great attention from researchers. However, the high complexity and heterogeneity of cancer gene regulatory networks limit the precition accuracy of existing deep learning models. To address this, we introduce a model called SCIS-CDG that utilizes Schur complement graph augmentation and independent subspace feature extraction techniques to effectively predict potential CDGs. Firstly, a random Schur complement strategy is adopted to generate two augmented views of gene network within a graph contrastive learning framework. Rapid randomization of the random Schur complement strategy enhances the model's generalization and its ability to handle complex networks effectively. Upholding the Schur complement principle in expectations promotes the preservation of the original gene network's vital structure in the augmented views. Subsequently, we employ feature extraction technology using multiple independent subspaces, each trained with independent weights to reduce inter-subspace dependence and improve the model's expressiveness. Concurrently, we introduced a feature expansion component based on the structure of the gene network to address issues arising from the limited dimensionality of node features. Moreover, it can alleviate the challenges posed by the heterogeneity of cancer gene networks to some extent. Finally, we integrate a learnable attention weight mechanism into the graph neural network (GNN) encoder, utilizing feature expansion technology to optimize the significance of various feature levels in the prediction task. Following extensive experimental validation, the SCIS-CDG model has exhibited high efficiency in identifying known CDGs and uncovering potential unknown CDGs in external datasets. Particularly when compared to previous conventional GNN models, its performance has seen significant improved. The code and data are publicly available at: https://github.com/mxqmxqmxq/SCIS-CDG.

Integration of Glutamate Dehydrogenase and Nanoporous Gold for Electrochemical Detection of Glutamate.

Glutamate, a non-essential amino acid produced by fermentation, plays a significant role in disease diagnosis and food safety. It is important to enable the real-time monitoring of glutamate concentration for human health and nutrition. Due to the challenges in directly performing electrochemical oxidation-reduction reactions of glutamate, this study leverages the synergistic effect of glutamate dehydrogenase (GLDH) and nanoporous gold (NPG) to achieve the indirect and accurate detection of glutamate within the range of 50 to 700 µM by measuring the generated quantity of NADH during the enzymatic reaction. The proposed biosensor demonstrates remarkable performance characteristics, including a detection sensitivity of 1.95 µA mM-1 and a limit of detection (LOD) of 6.82 µM. The anti-interference tests indicate an average recognition error ranging from -3.85% to +2.60%, spiked sample recovery rates between 95% and 105%, and a relative standard deviation (RSD) of less than 4.97% for three replicate experiments. Therefore, the GLDH-NPG/GCE biosensor presented in this work exhibits excellent accuracy and repeatability, providing a novel alternative for rapid glutamate detection. This research contributes significantly to enhancing the precise monitoring of glutamate concentration, thereby offering more effective guidance and control for human health and nutrition.

Krüppel-like Factor 10 as a Prognostic and Predictive Biomarker of Radiotherapy in Pancreatic Adenocarcinoma.

The prognosis of pancreatic adenocarcinoma (PDAC) remains poor, with a 5-year survival rate of 12%. Although radiotherapy is effective for the locoregional control of PDAC, it does not have survival benefits compared with systemic chemotherapy. Most patients with localized PDAC develop distant metastasis shortly after diagnosis. Upfront chemotherapy has been suggested so that patients with localized PDAC with early distant metastasis do not have to undergo radical local therapy. Several potential tissue markers have been identified for selecting patients who may benefit from local radiotherapy, thereby prolonging their survival. This review summarizes these biomarkers including SMAD4, which is significantly associated with PDAC failure patterns and survival. In particular, Krüppel-like factor 10 (KLF10) is an early response transcription factor of transforming growth factor (TGF)-ß. Unlike TGF-ß in advanced cancers, KLF10 loss in two-thirds of patients with PDAC was associated with rapid distant metastasis and radioresistance; thus, KLF10 can serve as a predictive and therapeutic marker for PDAC. For patients with resectable PDAC, a combination of KLF10 and SMAD4 expression in tumor tissues may help select those who may benefit the most from additional radiotherapy. Future trials should consider upfront systemic therapy or include molecular biomarker-enriched patients without early distant metastasis.

A pilot study comparing the disinfecting effects of commercialized stable ClO2 solution (free of activation) with conventional H2O2 on dental unit waterlines in the dental practice setting.

Disinfection of dental unit waterlines (DUWLs) plays a key role in control and prevention of nosocomial infection in a dental clinic. The most conventional disinfectant is hydrogen peroxide (H2O2), while chlorine dioxide (ClO2) has been considered however was limited by the "activation" procedures. With the availability of commercialized stable ClO2 solution (free of activation), direct application of ClO2 in the dental practice became possible. This study was designed to compare the disinfecting effects of stable 5 ppm of ClO2 solution with conventional 0.24% of H2O2 on DUWLs in dental practice. Studies of colony-forming units (CFUs), confocal laser scanning microscopy (CLSM) and scanning electron microscope (SEM) were employed for evaluation. In CFUs studies, we found that the efficiency of ClO2 was no less than those of H2O2. In the morphological studies, the stronger disinfecting effects of ClO2 was verified by both CLSM and SEM studies for removal and prevention of biofilm. Importantly, ClO2 solution achieved a better disinfecting efficiency not only at the surface of bacterial biofilm, but also, it has penetrating effects, presented disinfecting effects from the surface to the bottom of the biofilm. This pilot study provided evidence regarding the efficiency of stable ClO2 solution on disinfection of DUWLs in the dental practice setting. Application of stable ClO2 solution in dental practice is therefore become possible.

Tracheal tunica adventitia invasion after lobectomy in patients with non-small cell lung cancer.

BACKGROUND: For patients with non-small cell lung cancer, a negative margin status is required for radical pulmonary surgery. Residual disease of the margin has been thoroughly studied in the past few decades. However, the prognostic significance of tracheal tunica adventitia invasion after lobectomy remains unclear. In this study, we aimed to investigate the clinical influence of tracheal tunica adventitia invasion after lobectomy. METHODS: We retrospectively collected the clinical data of 591 patients who consecutively underwent pulmonary lobectomy, including sleeve lobectomy, between 2012 and 2018 at Shanghai Chest Hospital. According to the tracheal tunica adventitia invasion status, we allocated the patients into 2 groups (tracheal tunica adventitia invasion and non-tracheal tunica adventitia). Disease-free and overall survival were evaluated, and we discussed the necessity of radiotherapy in patients with tracheal tunica adventitia. RESULTS: After propensity score matching to balance baseline characteristics, there were 167 individuals in the tracheal tunica adventitia invasion and non-tracheal tunica adventitia groups. In the hazard analysis, we found that tracheal tunica adventitia increased the risk of recurrence (hazard ratio: 0.652; P = .002) and impaired long-term survival (P < .001). Subgroup analysis revealed that tracheal tunica adventitia was an important risk factor, especially when the hilar lymph nodes were positive. In addition, tracheal tunica adventitia invasion promoted extra-thoracic lymph node metastasis. We discovered that radiotherapy did not improve the prognosis of patients in the tracheal tunica adventitia invasion group. CONCLUSIONS: After lobectomy, tracheal tunica adventitia invasion is a risk factor for non-small cell lung cancer and potentially increases extra-thoracic lymph node metastasis. Moreover, tracheal tunica adventitia invasion is not sensitive to postoperative radiotherapy.

The Implication of Liquid Biopsy in the Non-small Cell Lung Cancer: Potential and Expectation.

Nowadays, lung cancer has remained the most lethal cancer, despite great advances in diagnosis and treatment. However, a large proportion of patients were diagnosed with locally advanced or metastatic disease and have poor prognosis. Immunotherapy and targeted drugs have greatly improved the survival and prognosis of patients with advanced lung cancer. However, how to identify the optimal patients to accept those therapies and how to monitor therapeutic efficacy are still in dispute. In the past few decades, tissue biopsy, including percutaneous fine needle biopsy and surgical excision, has still been the gold standard for examining the gene mutation such as EGFR, ALK, ROS, and PD-1/PD/L1, which can indicate the follow-up treatment. Nevertheless, the biopsy techniques mentioned above were invasive and unrepeatable, which were not suitable for advanced patients. Liquid biopsy, accounting for heterogeneity compared with tissue biopsy, is an alternative technique for monitoring the mutation, and a large quantity of research has demonstrated its feasibility to detect the circulating tumor cell, cell-free DNA, circulating tumor DNA, and extracellular vesicles from peripheral venous blood. The proposal of the concept of precision medicine brings a novel medical model developed with the rapid progress of genome sequencing technology and the cross-application of bioinformation, which was based on personalized medicine. The emerging method of liquid biopsy might contribute to promoting the development of precision medicine. In this review, we intend to describe the liquid biopsy in non-small cell lung cancer in detail in the aspect of screening, diagnosis, monitoring, treatment, and drug resistance.

Prediction of strand-specific and cell-type-specific G-quadruplexes based on high-resolution CUT&Tag data.

G-quadruplex (G4), a non-classical deoxyribonucleic acid structure, is widely distributed in the genome and involved in various biological processes. In vivo, high-throughput sequencing has indicated that G4s are significantly enriched at functional regions in a cell-type-specific manner. Therefore, the prediction of G4s based on computational methods is necessary instead of the time-consuming and laborious experimental methods. Recently, G4 CUT&Tag has been developed to generate higher-resolution sequencing data than ChIP-seq, which provides more accurate training samples for model construction. In this paper, we present a new dataset construction method based on G4 CUT&Tag sequencing data and an XGBoost prediction model based on the machine learning boost method. The results show that our model performs well within and across cell types. Furthermore, sequence analysis indicates that the formation of G4 structure is greatly affected by the flanking sequences, and the GC content of the G4 flanking sequences is higher than non-G4. Moreover, we also identified G4 motifs in the high-resolution dataset, among which we found several motifs for known transcription factors (TFs), such as SP2 and BPC. These TFs may directly or indirectly affect the formation of the G4 structure.

Identification of DNA-binding proteins by Kernel Sparse Representation via L2,1-matrix norm.

An understanding of DNA-binding proteins is helpful in exploring the role that proteins play in cell biology. Furthermore, the prediction of DNA-binding proteins is essential for the chemical modification and structural composition of DNA, and is of great importance in protein functional analysis and drug design. In recent years, DNA-binding protein prediction has typically used machine learning-based methods. The prediction accuracy of various classifiers has improved considerably, but researchers continue to spend time and effort on improving prediction performance. In this paper, we combine protein sequence evolutionary information with a classification method based on kernel sparse representation for the prediction of DNA-binding proteins, and based on the field of machine learning, a model for the identification of DNA-binding proteins by sequence information was finally proposed. Based on the confirmation of the final experimental results, we achieved good prediction accuracy on both the PDB1075 and PDB186 datasets. Our training result for cross-validation on PDB1075 was 81.37%, and our independent test result on PDB186 was 83.9%, both of which outperformed the other methods to some extent. Therefore, the proposed method in this paper is proven to be effective and feasible for predicting DNA-binding proteins.

Enhanced electricity generation and storage by nitrogen-doped hierarchically porous carbon modification of the capacitive bioanode in microbial fuel cells.

Microbial fuel cells (MFCs) can potentially be utilized for power generation, but their low power density and low energy storage capabilities remain major bottlenecks for their large-scale development. In this research, a simplistic nitrogen-doped hierarchically porous carbon material (HPC-A) was developed through a one-step carbonization and activation process and was successfully hot-pressed on the carbon cloth (CC) substrate. This process fabricates capacitive bioanodes (HPC-A-CC) that can enhance electricity generation and storage in MFCs. The as-prepared HPC-A-CC anode delivered a power density of 2043.6 mW·m-2 and a cumulative total charge (Qm) of 426.4 ± 13.4C·m-2 at each cycle, which was 2.1 and 34.8 times higher than that of the plain CC anode, respectively. This was a result of the hierarchical and interconnected porous structure, improved hydrophilic surface, and increased number of active centers which host the bacteria for enhanced electron transfer. Electrochemical measurements indicated the superior electrochemical activity and capacitive behavior of the HPC-A-CC anode. Furthermore, biofilm analysis revealed that the HPC-A-CC biofilm exhibited higher cell viability and a more uniform spatial distribution. These findings not only demonstrate the potential of HPC-A-CC for power enhancement in MFCs but also provide a feasible solution to the problem of power generation and demand mismatch in MFC applications.

Research progress on risk factors related to intracranial artery, carotid artery, and coronary artery stenosis.

In recent decades, with the rapid development of economy, the acceleration of social aging and urbanization, and the prevalence of unhealthy lifestyles, the number of patients with cardiovascular and cerebrovascular diseases has shown an increasing trend year by year. It has also become one of the important causes of disability and death in all ages and groups. Atherosclerosis is the main pathological change of ischemic cardiovascular and cerebrovascular diseases, which mainly invades the large and medium arteries of the body circulation. In particular, cerebral artery and coronary artery lesions have the most significant impact on life. There is the same pathogenic mechanism between intracranial and extracranial arteries and coronary atherosclerosis, so there is a certain relationship between the degree of atherosclerosis. In this paper, the risk factors related to intracranial and extracranial arteries and coronary artery stenosis were reviewed. It provides a theoretical basis for early detection, early diagnosis and early treatment of intracranial and extracranial artery and coronary artery stenosis to reduce the occurrence and development of cardiovascular and cerebrovascular diseases.

shRNA­mediated knockdown of KNTC1 inhibits non-small-cell lung cancer through regulating PSMB8.

In view of the important roles played by Kinetochore proteins in mitosis, we believed that they may contribute to the development and progression of human cancers, which has been reported recently elsewhere. Kinetochore-associated 1 (KNTC1) participates in the segregation of sister chromatids during mitosis, the effects of which on non-small-cell lung cancer (NSCLC) remain unclear. Here, we sought to identify the biological significance of KNTC1 in NSCLC. KNTC1 protein expression in NSCLC tissues was investigated by immunohistochemistry. Lentivirus delivered short hairpin RNA (shRNA) was utilized to establish KNTC1 silence NSCLC cell lines. The effects of KNTC1 depletion on NSCLC cell proliferation, migration, apoptosis, and tumor formation were analyzed by MTT assay, wound-healing assay, transwell assay, flow cytometry assay, and in nude mouse models in vivo. After KNTC1 reduction, NSCLC cell viability, proliferation, migration, and invasion were restrained. A xenograft tumor model was also provided to demonstrate the inhibited tumorigenesis in NSCLC. In addition, the downstream mechanism analysis indicated that KNTC1 depletion was positively associated with PSMB8. The findings of the present study suggested that KNTC1 may have a pivotal role in mediating NSCLC progression and may act as a novel therapeutic target for NSCLC.

The outcomes of margin status after sleeve lobectomy for patients of non-small cell lung cancer.

BACKGROUND: Sleeve lobectomy is recognized as an alternative surgical operation to pneumonectomy because it preserves the most pulmonary function and has a considerable prognosis. In this study, we aimed to investigate the implications of residual status for patients after sleeve lobectomy. METHODS: In this retrospective cohort study, we summarized 58 242 patients who underwent surgeries from 2015 to 2018 in Shanghai Chest Hospital and found 456 eligible patients meeting the criteria. The status of R2 was excluded. The outcomes were overall survival (OS) and recurrence-free survival (RFS). We performed a subgroup analysis to further our investigation. RESULTS: After the propensity score match, the baseline characteristic was balanced between two groups. The survival analysis showed no significant difference of overall survival and recurrence-free survival between R0 and R1 groups (OS: p = 0.053; RFS: p = 0.14). In the multivariate Cox analysis, we found that the margin status was not a dependent risk factor to RFS (p = 0.119) and OS (p = 0.093). In the patients of R1, N stage and age were closely related to OS, but we did not find any significant risk variable in RFS for R1 status. In the subgroup analysis, R1 status may have a worse prognosis on patients with more lymph nodes examination. On further investigation, we demonstrated no differences among the four histological types of margin status. CONCLUSION: In our study, we confirmed that the margin status after sleeve lobectomies was not the risk factor to prognosis. However, patients with more lymph nodes resection should pay attention to the margin status.

Homologous recombination deficiency (HRD) can predict the therapeutic outcomes of immuno-neoadjuvant therapy in NSCLC patients.

BACKGROUND: Neoadjuvant immunotherapy is emerging as novel effective intervention in lung cancer, but study to unearth effective surrogates indicating its therapeutic outcomes is limited. We investigated the genetic changes between non-small cell lung cancer (NSCLC) patients with varied response to neoadjuvant immunotherapy and discovered highly potential biomarkers with indicative capability in predicting outcomes. METHODS: In this study, 3 adenocarcinoma and 11 squamous cell carcinoma NSCLC patients were treated by neoadjuvant immunotherapy with variated regimens followed by surgical resection. Treatment-naive FFPE or fresh tissues and blood samples were subjected to whole-exome sequencing (WES). Genetic alternations were compared between differently-responded patients. Findings were further validated in multiple public cohorts. RESULTS: DNA damage repair (DDR)-related InDel signatures and DDR-related gene mutations were enriched in better-responded patients, i.e., major pathological response (MPR) group. Besides, MPR patients exhibited provoked genome instability and unique homologous recombination deficiency (HRD) events. By further inspecting alternation status of homology-dependent recombination (HR) pathway genes, the clonal alternations were exclusively enriched in MPR group. Additionally, associations between HR gene alternations, percentage of viable tumor cells and HRD event were identified, which orchestrated tumor mutational burden (TMB), mutational intratumor heterogeneity (ITH), somatic copy number alteration (SCNA) ITH and clonal neoantigen load in patients. Validations in public cohorts further supported the generality of our findings. CONCLUSIONS: We reported for the first time the association between HRD event and enhanced neoadjuvant immunotherapy response in lung cancer. The power of HRD event in patient therapeutic stratification persisted in multifaceted public cohorts. We propose that HR pathway gene status could serve as novel and additional indicators guiding immune-neoadjuvant and immunotherapy treatment decisions for NSCLC patients.

Therapeutic Effects and Repair Mechanism of HGF Gene-Transfected Mesenchymal Stem Cells on Injured Endometrium.

There are many studies on the advantages of using mesenchymal stem cells (MSCs) that secrete various paracrine factors for repairing endometrial injury. However, the stability and effectiveness of MSCs require improvement to become a viable therapy. Hepatocyte growth factor (HGF), one of the cytokines secreted by MSCs, promotes vascular repair and mesenchymal to epithelial transformation (MET). Therefore, HGF likely promotes the repair process of the endometrium. We prepared MSCs transfected with the HGF gene to explore its repair effects and mechanism using a damaged endometrium mouse model. HGF gene-transfected MSCs were prepared by electroporation. The transfected MSCs retained their cellular characteristics and significantly increased the expression of HGF (P < 0.01). HGF gene-transfected MSCs helped damaged endometrium to recover its morphological characteristics, improved proliferation and decreased apoptosis of endometrial cells, increased the expression of endometrial vascular growth-related factors, and activated phosphorylated c-Met and AKT in the mouse endometrial damage model (P < 0.05). Compared with normal MSCs, HGF gene-transfected MSCs produced a more significant effect on damaged endometrial epithelium repair by activating the HGF/c-Met and downstream signaling pathways. Our results indicate that HGF gene-transfected MSCs provide an effective and promising tool for injured endometrium therapy.

Identification of a 7-miRNA signature for predicting the prognosis of patients with lung adenocarcinoma.

The role of microRNAs (miRNAs) in tumor diagnosis and patients' prognosis has recently gained extensive research attention. This study was designed to analyze miRNA in lung adenocarcinoma (LUAD) using bioinformatics analysis and to identify novel biomarkers to predict overall survival (OS) for LUAD patients. Differential miRNA expression analysis was performed on LUAD, and normal tissues were extracted from The Cancer Genome Atlas (TCGA). Univariate Cox risk regression and least absolute shrinkage and selection operator (LASSO) Cox analysis were used to screen prognostic miRNAs and develop a risk score model. The prognostic performance of the system was examined utilizing the Kaplan-Meier and receiver operating characteristic (ROC) curves. Independent prognostic factors of LUAD were determined by multivariate Cox regression analysis. Nomogram was constructed according to the independent prognostic factors to evaluate the patients' one-, three- and five-year OS. A 7-miRNA signature based on miR-584-5p, miR-31-3p, miR-490-3, miR-4661-5p, miR-30e-5p, miR-582-5p, and miR-148a-3p was established. To categorize patients into high- and low-risk groups, the risk score was computed. The OS of the low-risk group was significantly longer than the high-risk group, and the signature showed high sensitivity and specificity in anticipating the one-, three- and five-year OS. The system was an independent factor in predicting the OS of LUAD patients and performed better when combined with the N stage in nomogram. A 7-miRNA signature developed in this study could accurately predict LUAD survival.

Predictive value of machine learning in diagnosing cognitive impairment in patients with Parkinson's disease: a systematic review and meta-analysis.

BACKGROUND: The current process used to diagnose cognitive impairment in patients with Parkinson's disease (PD) is unsatisfactory. More and more researchers had introduced machine learning into this field in recent years. This study explored the application of machine learning and its diagnostic performance in this field. METHODS: Since Parkinson's concurrent cognitive impairment is currently divided into different periods, most studies focus on the prodromal or early stages of Parkinson's cognitive impairment, and a few focuses on the dementia stage of Parkinson's. To ensure comprehensiveness, and model stability, we included patients with Parkinson's concurrent cognitive impairment in different periods who met the nadir criteria. A comprehensive literature search was carried out of the PubMed, Cochrane, Embase, and Web of Science databases. We used Prediction Model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias for the machine learning models covered by the included original studies. The outcome indicators included the concordance-index (C-index), sensitivity, and specificity. A meta-analysis using the random-effects model was conducted to determine the C-index, and a double variable mixed-effects model was used to determine the sensitivity and specificity. The meta-analysis in this article was completed in STATA. RESULTS: A total of 32 articles, comprising 10,778 patients and 51 prognostic models [summary c-statistic: 0.857, 95% confidence interval (CI) (0.842-0.873)], met the selection criteria and were included in this analysis. The total sensitivity and specificity of all models were 0.77 (95% CI: 0.72-0.81) and 0.83 (95% CI: 0.80-0.85), respectively, and those of the testing test were 0.85 (95% CI: 0.79-0.89), and 0.74 (95% CI: 0.70-0.78), respectively. A large part of the model showed a high risk of bias mainly because the study design was almost retrospective investigation. CONCLUSIONS: This study constitutes a detailed mapping and assessment of the machine learning for prediction in PD patients with cognitive decline, which may provide stronger discriminative performance and can be used as a potential tool for early diagnosis.

Two new and one poorly known species of the Cryptoperla formosana species group (Plecoptera: Peltoperlidae) from China.

One poorly known and two new species of the Cryptoperla formosana species group from China, C. aculeata (Wu, 1973), C. bicornata sp. nov., and C. cunicidata sp. nov. are presented. Cryptoperla bicornata is the first record of the genus from Henan Province, while C. cunicidata is a new generic and family record for Guangdong Province. A complementary description of C. aculeata is given. Illustrations and color images are provided for each species and each is compared with related congeners of the C. formosana species group. A provisional key to the known species of the group is also presented.

Endoplasmic reticulum-related E3 ubiquitin ligases: Key regulators of plant growth and stress responses.

Accumulating evidence has revealed that the ubiquitin proteasome system plays fundamental roles in the regulation of diverse cellular activities in eukaryotes. The ubiquitin protein ligases (E3s) are central to the proteasome system because of their ability to determine its substrate specificity. Several studies have demonstrated the essential role of a group of ER (endoplasmic reticulum)-localized E3s in the positive or negative regulation of cell homeostasis. Most ER-related E3s are conserved between plants and mammals, and a few plant-specific components have been reported. In this review, we summarize the functions of ER-related E3s in plant growth, ER-associated protein degradation and ER-phagy, abiotic and biotic stress responses, and hormone signaling. Furthermore, we highlight several questions that remain to be addressed and suggest directions for further research on ER-related E3 ubiquitin ligases.