Variational Autoencoders for Generative Drug-Gene Interactions in Periodontal Bone Resorption.

Introduction Periodontal bone resorption is a significant dental problem causing tooth loss and impaired oral function. It is influenced by factors such as bacterial plaque, genetic predisposition, smoking, systemic diseases, medications, hormonal changes, and poor oral hygiene. This condition disrupts bone remodeling, favoring resorptive processes. Variational autoencoders (VAEs) can learn the distribution of drug-gene interactions from existing data, identify potential drug targets, and predict therapeutic effects. This study investigates the generation of drug-gene interactions in periodontal bone resorption using VAEs. Methods A bone resorptive drugs dataset was retrieved from Probes and Drugs and analyzed using Cytoscape (https://cytoscape.org/) and CytoHubba (https://apps.cytoscape.org/apps/cytohubba), powerful tools for studying drug-gene interactions in bone resorption. The dataset was then prepared for matrix representation, with normalized input data. It was subsequently divided into training, validation, and testing sets. We then built an encoder-decoder network, defined a loss function, optimized parameters, and fine-tuned hyperparameters. Using VAEs, we generated new drug-gene interactions, assessed model performance, and visualized the latent space with reconstructed drug-gene interactions for further insights. Results The analysis revealed the top hub genes in drug-gene interactions, including Matrix Metalloproteinase (MMP) 14, MMP 9, HIF1A, STAT1, MAPT, CAS9, MMP2, CASP3, MMP1, and MAK1. The VAE's reconstruction accuracy was measured using mean squared error (MSE), with an average squared difference of 0.077. Additionally, the KL divergence value was 2.349, and the average reconstruction log-likelihood was -246. Conclusion The generative variational encoder model for drug-gene interactions in bone resorption demonstrates high accuracy and reliability in representing complex drug-gene relationships within this context.

Deep Learning Prediction of Inflammatory Inducing Protein Coding mRNA in P. gingivalis Released Outer Membrane Vesicles.

Aim: The Insilco study uses deep learning algorithms to predict the protein-coding pg m RNA sequences. Material and methods: The NCBI GEO DATA SET GSE218606's GEO R tool discovered P.G's outer membrane vesicles' most differentially expressed mRNA. Genemania analyzed differentially expressed gene networks. Transcriptomics data were collected and labeled on P. gingivalis protein-coding mRNA sequence and pseudogene, lincRNA, and bidirectional promoter lincRNA. Orange, a machine learning tool, analyzed and predicted data after preprocessing. Naïve Bayes, neural networks, and gradient descent partition data into training and testing sets, yielding accurate results. Cross-validation, model accuracy, and ROC curve were evaluated after model validation. Results: Three models, Neural Networks, Naive Bayes, and Gradient Boosting, were evaluated using metrics like Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Specificity. Gradient Boosting achieved a balanced performance (AUC: 0.72, CA: 0.41, F1: 0.32) compared to Neural Networks (AUC: 0.721, CA: 0.391, F1: 0.314) and Naive Bayes (AUC: 0.701, CA: 0.172, F1: 0.114). While statistical tests revealed no significant differences between the models, Gradient Boosting exhibited a more balanced precision-recall relationship. Conclusion: In silico analysis using machine learning techniques successfully predicted protein-coding mRNA sequences within Porphyromonas gingivalis OMVs. Gradient Boosting outperformed other models (Neural Networks, Naive Bayes) by achieving a balanced performance across metrics like AUC, classification accuracy, and precision-recall, suggests its potential as a reliable tool for protein-coding mRNA prediction in P. gingivalis OMVs.

Advanced machine learning for estimating vascular occlusion percentage in patients with ischemic heart disease and periodontitis.

Objective: The study aimed to assess the efficacy of advanced machine learning algorithms in estimating the percentage of vascular occlusion in ischemic heart disease (IHD) cases with periodontitis. Methods: This study involved 300 IHD patients aged 45 to 65 with stage III periodontitis undergoing coronary angiograms. Dental and periodontal examinations assessed various factors. Coronary angiograms categorized patients into three groups based on artery stenosis. Clinical data were processed, outliers were identified, and machine learning algorithms were applied for analysis using the orange tool, including confusion matrices and receiver operating characteristic (ROC) curves for assessment. Results: The results showed that Random Forest, Naïve Bayes, and Neural Networks were 97 %, 84 %, and 92 % accurate, respectively. Random Forest did exceptionally well in identifying the severity of conditions, with 95.70 % accuracy for mild cases, 84.80 % for moderate cases, and a perfect 100.00 % for severe cases. Conclusions: The current study, using Periodontal Inflammatory Surface Area (PISA) scores, revealed that the Random Forest model accurately predicted the percentage of vascular occlusion.

AI-based 3D-QSAR model of FDA-approved repurposed drugs for inhibiting sclerostin.

BACKGROUND: Wnt activation promotes bone formation and prevents bone loss. The Wnt pathway antagonist sclerostin and additional anti-sclerostin antibodies were discovered as a result of the development of the monoclonal antibody romosozumab. These monoclonal antibodies greatly increase the risk of cardiac arrest. Three-dimensional quantitative structure-activity relationships (3D-QSAR) predicts biological activities of ligands based on their three-dimensional features by employing powerful chemometric investigations such as artificial neural networks (ANNs) and partial least squares (PLS). OBJECTIVE: In this study, ligand-receptor interactions were investigated using 3D-QSAR Comparative molecular field analysis (CoMFA). Estimates of steric and electrostatic characteristics in CoMFA are made using Lennard-Jones and Coulomb potentials. METHODS: To identify the conditions necessary for the activity of these molecules, fifty Food and Drug Administration (FDA)-approved medications were chosen for 3D-QSAR investigations and done by CoMFA. For QSAR analysis, there are numerous tools available. This study employed Open 3D-QSAR for analysis due to its simplicity of use and capacity to produce trustworthy results. Four tools were used for the analysis on this platform: Py-MolEdit, Py-ConfSearch, and Py-CoMFA. RESULTS: Maps that were generated were used to determine the screen's r2 (Coefficient of Multiple Determinations) value and q2 (correlation coefficient). These numbers must be fewer than 1, suggesting a good, trustworthy model. Cross-validated (q2) 0.532 and conventional (r2) correlation values of 0.969 made the CoMFA model statistically significant. The model showed that hydroxamic acid inhibitors are significantly more sensitive to the steric field than the electrostatic field (70%) (30%). This hypothesis states that steric (43.1%), electrostatic (26.4%), and hydrophobic (20.3%) qualities were important in the design of sclerostin inhibitors. CONCLUSION: With 3D-QSAR and CoMFA, statistically meaningful models were constructed to predict ligand inhibitory effects. The test set demonstrated the model's robustness. This research may aid in the development of more effective sclerostin inhibitors that are synthesised using FDA-approved medications.

Machine learning in the detection of dental cyst, tumor, and abscess lesions.

BACKGROUND AND OBJECTIVE: Dental panoramic radiographs are utilized in computer-aided image analysis, which detects abnormal tissue masses by analyzing the produced image capacity to recognize patterns of intensity fluctuations. This is done to reduce the need for invasive biopsies for arriving to a diagnosis. The aim of the current study was to examine and compare the accuracy of several texture analysis techniques, such as Grey Level Run Length Matrix (GLRLM), Grey Level Co-occurrence Matrix (GLCM), and wavelet analysis in recognizing dental cyst, tumor, and abscess lesions. MATERIALS & METHODS: The current retrospective study retrieved a total of 172 dental panoramic radiographs with lesion including dental cysts, tumors, or abscess. Radiographs that failed to meet technical criteria for diagnostic quality (such as significant overlap of teeth, a diffuse image, or distortion) were excluded from the sample. The methodology adopted in the study comprised of five stages. At first, the radiographs are improved, and the area of interest was segmented manually. A variety of feature extraction techniques, such GLCM, GLRLM, and the wavelet analysis were used to gather information from the area of interest. Later, the lesions were classified as a cyst, tumor, abscess, or using a support vector machine (SVM) classifier. Eventually, the data was transferred into a Microsoft Excel spreadsheet and statistical package for social sciences (SPSS) (version 21) was used to conduct the statistical analysis. Initially descriptive statistics were computed. For inferential analysis, statistical significance was determined by a p value < 0.05. The sensitivity, specificity, and accuracy were used to find the significant difference between assessed and actual diagnosis. RESULTS: The findings demonstrate that 98% accuracy was achieved using GLCM, 91% accuracy using Wavelet analysis & 95% accuracy using GLRLM in distinguishing between dental cyst, tumor, and abscess lesions. The area under curve (AUC) number indicates that GLCM achieves a high degree of accuracy. The results achieved excellent accuracy (98%) using GLCM. CONCLUSION: The GLCM features can be used for further research. After improving the performance and training, it can support routine histological diagnosis and can assist the clinicians in arriving at accurate and spontaneous treatment plans.

CRISPR-Cas-Based Adaptive Immunity Mediates Phage Resistance in Periodontal Red Complex Pathogens.

Periodontal diseases are polymicrobial immune-inflammatory diseases that can severely destroy tooth-supporting structures. The critical bacteria responsible for this destruction include red complex bacteria such as Porphoromonas gingivalis, Tanerella forsythia and Treponema denticola. These organisms have developed adaptive immune mechanisms against bacteriophages/viruses, plasmids and transposons through clustered regularly interspaced short palindromic repeats (CRISPR) and their associated proteins (Cas). The CRISPR-Cas system contributes to adaptive immunity, and this acquired genetic immune system of bacteria may contribute to moderating the microbiome of chronic periodontitis. The current research examined the role of the CRISPR-Cas system of red complex bacteria in the dysbiosis of oral bacteriophages in periodontitis. Whole-genome sequences of red complex bacteria were obtained and investigated for CRISPR using the CRISPR identification tool. Repeated spacer sequences were analyzed for homologous sequences in the bacteriophage genome and viromes using BLAST algorithms. The results of the BLAST spacer analysis for T. denticola spacers had a 100% score (e value with a bacillus phage), and the results for T. forsthyia and P. gingivalis had a 56% score with a pectophage and cellulophage (e value: 0.21), respectively. The machine learning model of the identified red complex CRISPR sequences predicts with area an under the curve (AUC) accuracy of 100 percent, indicating phage inhibition. These results infer that red complex bacteria could significantly inhibit viruses and phages with CRISPR immune sequences. Therefore, the role of viruses and bacteriophages in modulating sub-gingival bacterial growth in periodontitis is limited or questionable.

Indigenous Oral and Gut Phages Defeat the Deadly NDM-1 Superbug.

Aim: Antibiotics treat various diseases by targeting microorganisms by killing them or reducing their multiplication rate. New Delhi Metallo-beta-lactamase-1 (NDM-1) is produced by bacteria possessing the resistance gene blaNDM-1, the enzyme that makes bacteria resistant to beta-lactams. Bacteriophages, especially Lactococcus, have shown their ability to break down lactams. Hence, the current study computationally evaluated the binding potential of Lactococcus bacteriophages with NDM using Molecular docking and dynamics. Methods: Modelling of NDM I-TASSER for Main tail protein gp19 OS=Lactococcus phage LL-H or Lactobacillus delbrueckii subsp. lactis after downloading from UNIPROT ID- Q38344. Cluspro tool helps in Understanding cellular function and organization with protein-protein interactions. MD simulations(19) typically compute atom movements over time. Simulations were used to predict the ligand binding status in the physiological environment. Results: The best binding affinity score was found -1040.6 Kcal/mol compared to other docking scores. MD simulations show in RMSD values for target remains within 1.0 Angstrom, which is acceptable. The ligand-protein fit to receptor protein RMSD values of 2.752 fluctuates within 1.5 Angstrom after equilibration. Conclusions: Lactococcus bacteriophages showed a strong affinity to the NDM. Hence, this hypothesis, supported by evidence from a computational approach, will solve this life-threatening superbug problem.

Designing Novel Multi-Epitope Vaccine Construct against Prevotella intermedia-Interpain A: An Immunoinformatics Approach.

Background and Objectives: Periodontitis is a chronic multifactorial inflammatory infectious disease marked by continuous degradation of teeth and surrounding parts. One of the most important periodontal pathogens is P. intermedia, and with its interpain A proteinase, it leads to an increase in lethal infection. Materials and Methods: The current study was designed to create a multi-epitope vaccine using an immunoinformatics method that targets the interpain A of P. intermedia. For the development of vaccines, P. intermedia peptides InpA were found appropriate. To create a multi-epitope vaccination design, interpain A, B, and T-cell epitopes were found and assessed depending on the essential variables. The vaccine construct was evaluated based on its stability, antigenicity, and allergenicity. Results: The vaccine construct reached a more significant population and was able to bind to both the binding epitopes of major histocompatibility complex (MHC)-I and MHC-II. Through the C3 receptor complex route, P. intermedia InpA promotes an immunological subunit. Utilizing InpA-C3 and vaccination epitopes as the receptor and ligand, the molecular docking and dynamics were performed using the ClusPro 2.0 server. Conclusion: The developed vaccine had shown good antigenicity, solubility, and stability. Molecular docking indicated the vaccine's 3D structure interacts strongly with the complement C3. The current study describes the design for vaccine, and steady interaction with the C3 immunological receptor to induce a good memory and an adaptive immune response against Interpain A of P. intermedia.

Clinical efficacy of subepithelial connective tissue graft and A-PRF in the treatment of gingival recession.

OBJECTIVE: The current study was designed to clinically compare and evaluate subepithelial connective tissue graft (SCTG) and advanced platelet-rich fibrin (A-PRF) membrane-based root coverage in the treatment of gingival recession type 1 (RT1). METHOD AND MATERIALS: The current study involved 17 patients with bilateral gingival recession (RT1). Thirty-four sites were randomly allocated to test (A-PRF) and control (SCTG) sites and all the procedures were performed by a single operator. A single blinded observer evaluated the test and control sites at baseline, 3 months, and 6 months. The clinical parameters such as recession depth, recession width, width of keratinized gingiva, clinical attachment level, and percentage of root coverage were recorded. P < .05 was considered statistically significant. RESULTS: The mean recession depth at baseline for control and test groups was 3.06 ± 0.56 mm and 2.35 ± 0.49 mm, respectively (P < .001). At the end of the study period, the mean recession depth was 0.53 ± 0.62 mm in the control group and 1.12 ± 0.49 mm in the test group (P < .05). No complications were associated with both the groups. The mean percentage of root coverage was 84.31 ± 17.89% in the control group and 51.96 ± 15.45% in the test group (P < .001). CONCLUSION: In conclusion, the study results suggest that both SCTG and A-PRF can be used in treating gingival recessions. However, SCTG is a better material in achieving root coverage and increasing keratinized tissue width. (Quintessence Int 2023;54:134-141; doi: 10.3290/j.qi.b3512389).

Autologous platelet-rich fibrin as an adjunct to non-surgical periodontal therapy-A follow up clinical pilot study.

The aim was to evaluate the effectiveness of autologous platelet-rich fibrin (PRF) as an adjunct to scaling and root planing (SRP) in moderate periodontal pockets. The split-mouth study involved 32 sites from 16 patients. Baseline parameters were recorded followed by complete full-mouth SRP. The test and control sites were randomly selected and autologous PRF was placed in the test site and other site served as control. The blinded examiner recorded clinical parameters at baseline, 60 days, and 90 days. No statistical significance was found at baseline in probing depth (PD) and clinical attachment level (CAL). Statistically, significant improvement was observed within test and control groups at 90 days compared to baseline values. A statistically significant difference in test sites was found in terms of reduction in PD and clinical attachment gain (CAG) compared to the control sites at the end of the study period (p value <0.05). This split-mouth pilot study emphasized a statistically significant improvement in pocket depth reduction and CAL gain when PRF was used as an adjunct to SRP in moderate periodontal pockets.

Gingival biotype as an indicator for the buccal bone thickness - a systematic review of the literature.

Introduction A relationship between thin gingiva and thin buccal bone has been proposed but concrete evidence for this is lacking. This study was undertaken to assess the reliability of measuring gingival thickness in estimating the buccal bone thickness.Objectives To answer the following PICO question: do periodontally healthy individuals exhibit any correlation between gingival biotype and buccal/labial/facial bone thickness?Data sources and selection An electronic search was performed in PubMed and Embase databases. English language articles that have met the inclusion and exclusion criteria were selected. Only observational studies were considered. Since the studies have demonstrated heterogeneity, conducting a meta-analysis was not possible, so the results were synthesised using a vote counting method and narrative synthesis.Data synthesis After screening the titles and abstracts, 13 studies which met the study criteria were included in the systematic review. Out of these 13 studies, nine studies assessed only the maxillary anterior/premolars; one study assessed the mandibular anterior, and three studies assessed both maxillary and mandibular anterior/premolars.Conclusions The findings of this systematic review indicated that the gingival biotype may be a reliable indicator for estimating the thickness of buccal bone in maxillary anterior. However, its relation to the buccal bone thickness in mandible is unclear.