Graph Attention Network-Based Prediction of Drug-Gene Interactions of Signal Transducer and Activator of Transcription (STAT) Receptor in Periodontal Regeneration DOI Open Access

Shubhangini Chatterjee,

Pradeep Kumar Yadalam

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Сен. 6, 2024

Introduction The signal transducer and activator of transcription-1 (STAT-1) are tightly controlled signaling pathways, with induced genes acting as positive negative regulators. Persistent activation the transcription (STATs), particularly transcription-3 (STAT-3) transcription-5 (STAT-5), is common in human tumors cell lines. STAT molecules act factors, regulated by ligands like interferon-α (IFN-α), interferon-γ (IFN-γ), epidermal growth factor (EGF), platelet-derived (PDGF), interleukin-6 (IL-6) interleukin-27 (IL-27). STAT-1 mutations can cause infections periodontitis, a chronic inflammatory disease affecting gum tissue bone. drug-gene interactions being studied for therapeutic applications. Our study aims to predict receptors periodontal inflammation using graph attention networks (GATs). Methodology used dataset 215 train test GAT model. data was cleaned normalized before subjected GATs Python library. Cytoscape cytoHubba were visualize analyze biological networks, including interactome networks. model consisted two layers, first layer producing eight features second aggregating outputs binary classification. trained Adam optimizer CrossEntropyLoss function. Results network, analyzed Cytoscape, had 657 nodes, 1591 edges, 4.755 neighbors. predictive low accuracy due availability complexity. Conclusion limitations, complexity, inability capture all relevant features.

Язык: Английский

Artificial intelligence-powered innovations in periodontal diagnosis: a new era in dental healthcare DOI Creative Commons
Jarupat Jundaeng, Rapeeporn Chamchong, Choosak Nithikathkul

и другие.

Frontiers in Medical Technology, Год журнала: 2025, Номер 6

Опубликована: Янв. 10, 2025

The aging population is increasingly affected by periodontal disease, a condition often overlooked due to its asymptomatic nature. Despite silent onset, periodontitis linked various systemic conditions, contributing severe complications and reduced quality of life. With over billion people globally affected, diseases present significant public health challenge. Current diagnostic methods, including clinical exams radiographs, have limitations, emphasizing the need for more accurate detection methods. This study aims develop AI-driven models enhance precision consistency in detecting disease. We analyzed 2,000 panoramic radiographs using image processing techniques. YOLOv8 model segmented teeth, identified cemento-enamel junction (CEJ), quantified alveolar bone loss assess stages periodontitis. teeth segmentation achieved an accuracy 97%, while CEJ reached 98%. AI system demonstrated outstanding performance, with 94.4% perfect sensitivity (100%), surpassing periodontists who 91.1% 90.6% sensitivity. General practitioners (GPs) benefitted from assistance, reaching 86.7% 85.9% sensitivity, further improving outcomes. highlights that can effectively detect outperforming current integration into care offers faster, accurate, comprehensive treatment, ultimately patient outcomes alleviating healthcare burdens.

Язык: Английский

Процитировано

0
Predictive biomarkers and molecular subtypes in DLBCL: insights from PCD gene expression and machine learning DOI Creative Commons
Tiantian He, Jie Geng,

Chuandong Hou

и другие.

Discover Oncology, Год журнала: 2025, Номер 16(1)

Опубликована: Апрель 16, 2025

Язык: Английский

Процитировано

0
Identification and Validation of Aging- and Endoplasmic Reticulum Stress-Related Genes in Periodontitis Using a Competing Endogenous RNA Network DOI
Xinran Feng, Da Peng, Yunjing Qiu

и другие.

Inflammation, Год журнала: 2024, Номер unknown

Опубликована: Авг. 13, 2024

Язык: Английский

Процитировано

2
Analysis of the basement membrane-related genes ITGA7 and its regulatory role in periodontitis via machine learning: a retrospective study DOI Creative Commons

Huihuang Ye,

Xue Gao,

Yike Ma

и другие.

BMC Oral Health, Год журнала: 2024, Номер 24(1)

Опубликована: Дек. 24, 2024

Periodontitis is among the most prevalent inflammatory conditions and greatly impacts oral health. This study aimed to elucidate role of basement membrane-related genes in pathogenesis diagnosis periodontitis. GSE10334 was used for identification hub via differential analysis, protein-protein interaction network, MCC DMNC algorithms, evaluation LASSO regression support vector machine analysis identify markers patients with Findings were validated by GSE16134 dataset quantitative reverse transcription PCR. The regulatory interplay lncRNAs, miRNAs, mRNAs investigated through multiple databases. Immune infiltration performed assess immune landscape ITGA7 identified as a key gene periodontitis, supported learning validation expression, receiver operating characteristic from external datasets. revealed significant associations between expression numerous cells implicated Additionally, our findings suggest that lncRNA LINC-PINT significantly increased it can modulate hsa-miR-1293. potential diagnostic therapeutic target LINC-PINT/hsa-miR-1293/ITGA7 axis relationship provide new insights into molecular mechanisms underlying periodontitis highlight avenues clinical intervention.

Язык: Английский

Процитировано

0
The potential of machine learning applications in addressing antimicrobial resistance in periodontitis DOI
Carlos M. Ardila, Pradeep Kumar Yadalam, Giuseppe Minervini

и другие.

Journal of Periodontal Research, Год журнала: 2024, Номер 59(5), С. 1042 - 1043

Опубликована: Май 2, 2024

Records were obtained from the included investigations.

Язык: Английский

Процитировано

0
Graph Attention Network-Based Prediction of Drug-Gene Interactions of Signal Transducer and Activator of Transcription (STAT) Receptor in Periodontal Regeneration DOI Open Access

Shubhangini Chatterjee,

Pradeep Kumar Yadalam

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Сен. 6, 2024

Introduction The signal transducer and activator of transcription-1 (STAT-1) are tightly controlled signaling pathways, with induced genes acting as positive negative regulators. Persistent activation the transcription (STATs), particularly transcription-3 (STAT-3) transcription-5 (STAT-5), is common in human tumors cell lines. STAT molecules act factors, regulated by ligands like interferon-α (IFN-α), interferon-γ (IFN-γ), epidermal growth factor (EGF), platelet-derived (PDGF), interleukin-6 (IL-6) interleukin-27 (IL-27). STAT-1 mutations can cause infections periodontitis, a chronic inflammatory disease affecting gum tissue bone. drug-gene interactions being studied for therapeutic applications. Our study aims to predict receptors periodontal inflammation using graph attention networks (GATs). Methodology used dataset 215 train test GAT model. data was cleaned normalized before subjected GATs Python library. Cytoscape cytoHubba were visualize analyze biological networks, including interactome networks. model consisted two layers, first layer producing eight features second aggregating outputs binary classification. trained Adam optimizer CrossEntropyLoss function. Results network, analyzed Cytoscape, had 657 nodes, 1591 edges, 4.755 neighbors. predictive low accuracy due availability complexity. Conclusion limitations, complexity, inability capture all relevant features.

Язык: Английский

Процитировано

0