MIBPred: Ensemble Learning-Based Metal Ion-Binding Protein Classifier.

In biological organisms, metal ion-binding proteins participate in numerous metabolic activities and are closely associated with various diseases. To accurately predict whether a protein binds to metal ions and the type of metal ion-binding protein, this study proposed a classifier named MIBPred. The classifier incorporated advanced Word2Vec technology from the field of natural language processing to extract semantic features of the protein sequence language and combined them with position-specific score matrix (PSSM) features. Furthermore, an ensemble learning model was employed for the metal ion-binding protein classification task. In the model, we independently trained XGBoost, LightGBM, and CatBoost algorithms and integrated the output results through an SVM voting mechanism. This innovative combination has led to a significant breakthrough in the predictive performance of our model. As a result, we achieved accuracies of 95.13% and 85.19%, respectively, in predicting metal ion-binding proteins and their types. Our research not only confirms the effectiveness of Word2Vec technology in extracting semantic information from protein sequences but also highlights the outstanding performance of the MIBPred classifier in the problem of metal ion-binding protein types. This study provides a reliable tool and method for the in-depth exploration of the structure and function of metal ion-binding proteins.

A First Computational Frame for Recognizing Heparin-Binding Protein.

Heparin-binding protein (HBP) is a cationic antibacterial protein derived from multinuclear neutrophils and an important biomarker of infectious diseases. The correct identification of HBP is of great significance to the study of infectious diseases. This work provides the first HBP recognition framework based on machine learning to accurately identify HBP. By using four sequence descriptors, HBP and non-HBP samples were represented by discrete numbers. By inputting these features into a support vector machine (SVM) and random forest (RF) algorithm and comparing the prediction performances of these methods on training data and independent test data, it is found that the SVM-based classifier has the greatest potential to identify HBP. The model could produce an auROC of 0.981 ± 0.028 on training data using 10-fold cross-validation and an overall accuracy of 95.0% on independent test data. As the first model for HBP recognition, it will provide some help for infectious diseases and stimulate further research in related fields.

Attention is all you need: utilizing attention in AI-enabled drug discovery.

Recently, attention mechanism and derived models have gained significant traction in drug development due to their outstanding performance and interpretability in handling complex data structures. This review offers an in-depth exploration of the principles underlying attention-based models and their advantages in drug discovery. We further elaborate on their applications in various aspects of drug development, from molecular screening and target binding to property prediction and molecule generation. Finally, we discuss the current challenges faced in the application of attention mechanisms and Artificial Intelligence technologies, including data quality, model interpretability and computational resource constraints, along with future directions for research. Given the accelerating pace of technological advancement, we believe that attention-based models will have an increasingly prominent role in future drug discovery. We anticipate that these models will usher in revolutionary breakthroughs in the pharmaceutical domain, significantly accelerating the pace of drug development.

Corrigendum: Exploration of the Role of Serine Proteinase Inhibitor A3 in Alcohol Dependence Using Gene Expression Omnibus Database.

[This corrects the article DOI: 10.3389/fpsyt.2021.779143.].

Exploration of the Role of Serine Proteinase Inhibitor A3 in Alcohol Dependence Using Gene Expression Omnibus Database.

Background: Alcohol dependence is an overall health-related challenge; however, the specific mechanisms underlying alcohol dependence remain unclear. Serine proteinase inhibitor A3 (SERPINA3) plays crucial roles in multiple human diseases; however, its role in alcohol dependence clinical practice has not been confirmed. Methods: We screened Gene Expression Omnibus (GEO) expression profiles, and identified differentially expressed genes (DEGs). Protein-protein interaction (PPI) networks were generated using STRING and Cytoscape, and the key clustering module was identified using the MCODE plugin. SERPINA3-based target microRNA prediction was performed using online databases. Functional enrichment analysis was performed. Fifty-eight patients with alcohol dependence and 20 healthy controls were recruited. Clinical variables were collected and follow-up was conducted for 8 months for relapse. Results: SERPINA3 was identified as a DEG. ELANE and miR-137 were identified after PPI analysis. The enriched functions and pathways included acute inflammatory response, response to stress, immune response, and terpenoid backbone biosynthesis. SERPINA3 concentrations were significantly elevated in the alcohol dependence group than in healthy controls (P < 0.001). According to the median value of SERPINA3 expression level in alcohol dependence group, patients were divided into high SERPINA3 (≥2677.33 pg/ml, n = 29) and low SERPINA3 groups (<2677.33 pg/ml, n = 29). Binary logistic analysis indicated that IL-6 was statistically significant (P = 0.015) Kaplan-Meier survival analysis did not indicate any difference in event-free survival between patients with low and high SERPINA3 levels (P = 0.489) after 8 months of follow-up. Receiver characteristic curve analysis revealed that SERPINA3 had an area under the curve of 0.921 (P < 0.0001), with a sensitivity and specificity of 93.1 and 80.0%, respectively. Cox regression analysis revealed that aspartate transaminase level was a negative predictor of relapse (ß = 0.003; hazard ratio = 1.003; P = 0.03). Conclusions: SERPINA3 level was remarkably elevated in patients with alcohol dependence than healthy controls, indicating that SERPINA3 is correlated with alcohol dependence. However, SERPINA3 may not be a potential predictive marker of relapse with patients in alcohol dependence.

Association of adenylate cyclase-2 gene polymorphism with bipolar disorder.

The pathogenesis of the Bipolar Disorder(BPD) is still unclear. Some studies suggest that abnormal signal transduction in specific pathways may play an important role in the pathogenesis of BPD (Sui et al., 2015). Adenylate cyclase (ADCY) is an essential component of the adenylate signaling pathway. Previous studies have shown that some SNPs within the adenylate cyclase gene could affect the therapeutic response to mood stabilizers and antidepressants. Moreover, in 2014, one whole-genome study suggested that the ADCY-2 gene may be associated with BPD (Mühleisen et al., 2014). This study aims to investigate the association between ADCY-2 gene polymorphism and BPD in Chinese Han population.

[Ecological executive function profiles in depression patients before and after treatment].

OBJECTIVE: To explore the ecological executive function profile in depression patients before and after antidepressants treatment and analyze the relationship of ecological executive function and depression symptoms and effect. METHODS: A total of 33 inpatients diagnosed as depression disorder according to ICD-10 completed the Behavior Rating Inventory of Executive Function-Adult Version (BRIEF-A) and Hamilton Depression Scale (HAMD) before and after a 6-week antidepressant treatment. RESULTS: (1) After treatment, they yielded lower scores significantly on most subscales of BRIEF-A (t = 2.061 - 4.229, P < 0.05), including total score [(127 ± 27) vs (113 ± 28)], shifting [(11.7 ± 2.7) vs (10.3 ± 2.6)], emotion control [(18.8 ± 4.6) vs (15.8 ± 4.4)], monitoring [(9.6 ± 3.0) vs (8.8 ± 2.7)], initiation [(15.6 ± 3.7) vs (13.2 ± 3.6)], working memory [(14.9 ± 3.4) vs (13.3 ± 3.9)], planning [(18.3 ± 4.4) vs (16.6 ± 4.4)], organization [(12.4 ± 3.8) vs (11.4 ± 3.1)], behavioral regulation index (BRI), metacognition index (MI) and global executive composite (GEC). (2) Before treatment, Person's correlation test showed that the total score of HAMD and all subscales of BRIEF-A had no significant correlation respectively (r = -0.145 - 0.220, P > 0.05). (3) After treatment, the deduction of total score of HAMD and the deduction of the scores of inhibiting belonging to behavioral regulation index (BRI) and initiation, planning belonging to metacognition index (MI) had moderate correlations respectively(r = 0.450, 0.432, 0.403, P < 0.05). (4) Multiple regression analysis showed that the scores of working memory, organization and the deduction of total score of HAMD had significantly negative correlations respectively (t = -2.295, -2.488, P < 0.05). CONCLUSION: The antidepressant treatment can improve ecological executive function of depression patients. And the improvements of ecological executive function and depression symptoms are partially correlated.