Browsing by Author "Ali Moni, Mohammad"

Now showing 1 - 5 of 5

GDRNet: A Novel Graph Neural Network Architecture for Diabetic Retinopathy Detection
(2024-01-24) Hossain, Shahed; Hasan, Md. Zahid; Jim, Risul Islam; Bulbul, Abdullah Al-Mamun; Khan, Risala Tasin; Kaise, M. Shamim; Ali Moni, Mohammad
Diabetic retinopathy is a significant cause of global blindness, requiring practical early detection approaches that could save vision loss in millions of people. However, manual DR analysis is time-consuming and requires skilled clinicians. The advancement of artificial intelligence can facilitate early DR predictions. This study proposed GDRNet, a novel AI-empowered diagnosis system that utilizes graph theory for effective feature selection in DR grading classification. The EyePACS, Messidor, APTOS, IDRid, and DDR datasets are initially balanced using the nearest neighbor oversampling approach. A deep graph correlation network (DGCN) extracts unique features from color eye fundus images by identifying intra-class connections. Then, an iterative random forest algorithm is employed for feature curation, ranking the most significant features from the DGCN. Subsequently, the iterative random forest enhances classification robustness by refining feature representations and aggregating multi-scale contextual information. Finally, a classifier using extreme gradient boosting based on a decision tree algorithm is trained with the optimized features to predict the outcomes. Experimental results reveal that GDRNet outperforms state-of-the-art DR grading classification methods with outstanding performance across various datasets: 100% specificity, 99.67% sensitivity, and 99.80% accuracy on Messidor; 100% specificity, 99.61% sensitivity, and 99.41% accuracy on APTOS; and comparable results on IDRid and DDR datasets. On the EyePACS dataset, it achieves 100% specificity, 99.20% sensitivity, and 99.50% accuracy. Based on these numerical findings, we expect that GDRNet could be utilized in healthcare for early and automated DR detection.
Identification of Biomarkers and Molecular Pathways Implicated in Smoking and COVID-19 Associated Lung Cancer Using Bioinformatics and Machine Learning Approaches
(2024-10-22) Hossain, Md Ali; Zahidur Rahman, Mohammad; Bhuiyan, Touhid; Ali Moni, Mohammad
Lung cancer (LC) is a significant global health issue, with smoking as the most common cause. Recent epidemiological studies have suggested that individuals who smoke are more susceptible to COVID-19. In this study, we aimed to investigate the influence of smoking and COVID-19 on LC using bioinformatics and machine learning approaches. We compared the differentially expressed genes (DEGs) between LC, smoking, and COVID-19 datasets and identified 26 down-regulated and 37 up-regulated genes shared between LC and smoking, and 7 down-regulated and 6 up-regulated genes shared between LC and COVID-19. Integration of these datasets resulted in the identification of ten hub genes (SLC22A18, CHAC1, ROBO4, TEK, NOTCH4, CD24, CD34, SOX2, PITX2, and GMDS) from protein-protein interaction network analysis. The WGCNA R package was used to construct correlation network analyses for these shared genes, aiming to investigate the relationships among them. Furthermore, we also examined the correlation of these genes with patient outcomes through survival curve analyses. The gene ontology and pathway analyses were performed to find out the potential therapeutic targets for LC in smoking and COVID-19 patients. Moreover, machine learning algorithms were applied to the TCGA RNAseq data of LC to assess the performance of these common genes and ten hub genes, demonstrating high performances. The identified hub genes and molecular pathways can be utilized for the development of potential therapeutic targets for smoking and COVID-19-associated LC.
Identification of molecular biomarkers and pathways of NSCLC
(Journal of Genetic Engineering and Biotechnology, Springer, 2021-03-19) Islam, Rakibul; Ahmed, Liton; Paul, Bikash Kumar; Ahmed, Kawsar; Bhuiyan, Touhid; Ali Moni, Mohammad
Background Worldwide, more than 80% of identified lung cancer cases are associated to the non-small cell lung cancer (NSCLC). We used microarray gene expression dataset GSE10245 to identify key biomarkers and associated pathways in NSCLC. Results To collect Differentially Expressed Genes (DEGs) from the dataset GSE10245, we applied the R statistical language. Functional analysis was completed using the Database for Annotation Visualization and Integrated Discovery (DAVID) online repository. The Differential Net database was used to construct Protein–protein interaction (PPI) network and visualized it with the Cytoscape software. Using the Molecular Complex Detection (MCODE) method, we identify clusters from the constructed PPI network. Finally, survival analysis was performed to acquire the overall survival (OS) values of the key genes. One thousand eighty two DEGs were unveiled after applying statistical criterion. Functional analysis showed that overexpressed DEGs were greatly involved with epidermis development and keratinocyte differentiation; the under-expressed DEGs were principally associated with the positive regulation of nitric oxide biosynthetic process and signal transduction. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway investigation explored that the overexpressed DEGs were highly involved with the cell cycle; the under-expressed DEGs were involved with cell adhesion molecules. The PPI network was constructed with 474 nodes and 2233 connections. Conclusions Using the connectivity method, 12 genes were considered as hub genes. Survival analysis showed worse OS value for SFN, DSP, and PHGDH. Outcomes indicate that Stratifin may play a crucial role in the development of NSCLC
MLAFP-XN: Leveraging neural network model for development of antifungal peptide identification tool
(2024-09-30) Sultana, Md. Fahim; Shaona, Md. Shazzad Hossain; Karima, Tasmin; Ali, Md. Mamun; Hasana, Md. Zahid; Ahmed, Kawsar; M. Bui, Francis; Dhasarathang, Vigneswaran; Ali Moni, Mohammad
Infectious fungi have been an increasing global concern in the present era. A promising approach to tackle this pressing concern involves utilizing Antifungal peptides (AFP) to develop an antifungal drug that can selectively eliminate fungal pathogens from a host with minimal toxicity to the host. Accordingly, identifying precise therapeutic antifungal peptides is crucial for developing effective drugs and treatments. This study proposed MLAFP-XN, a neural network-based strategy for accurately detecting active AFP in sequencing data to achieve this objective. In this work, eight feature extraction techniques and the XGB feature selection strategy are utilized together to present an enhanced methodology. A total of 24 classification models were evaluated, and the most effective four have been selected. Each of these models demonstrated superior accuracy on independent test sets, with respective scores of 97.93 %, 99.47 %, and 99.48 %. Our model outperforms current state of the art methods. In addition, we created a companion website to demonstrate our AFP recognition process and use SHAP to identify the most influential properties.
Multi-View Soft Attention-Based Model for the Classification of Lung Cancer-Associated Disabilities
(2024-10-14) Esha, Jannatul Ferdous; Islam, Tahmidul; Pranto, Md. Appel Mahmud; Borno, Abrar Siam; Faruqui, Nuruzzaman; Abu Yousuf, Mohammad; Azad, AKM; Al-Moisheer, Asmaa Soliman; Alotaibi, Naif; Alyami, Salem A.; Ali Moni, Mohammad
The detection of lung nodules at their early stages may significantly enhance the survival rate and prevent progression to severe disability caused by advanced lung cancer, but it often requires manual and laborious efforts for radiologists, with limited success. To alleviate it, we propose a Multi-View Soft Attention-Based Convolutional Neural Network (MVSA-CNN) model for multi-class lung nodular classifications in three stages (benign, primary, and metastatic). Initially, patches from each nodule are extracted into three different views, each fed to our model to classify the malignancy. A dataset, namely the Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI), is used for training and testing. The 10-fold cross-validation approach was used on the database to assess the model’s performance. The experimental results suggest that MVSA-CNN outperforms other competing methods with 97.10% accuracy, 96.31% sensitivity, and 97.45% specificity. Conclusions: We hope the highly predictive performance of MVSA-CNN in lung nodule classification from lung Computed Tomography (CT) scans may facilitate more reliable diagnosis, thereby improving outcomes for individuals with disabilities who may experience disparities in healthcare access and quality.