Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12511/4475

Listeleniyor 1 - 20 / 92

BioLake: an RNA expression analysis framework for prostate cancer biomarker powered by data lakehouse
(2025) Li, Qiaowang; Gamallat, Yaser; Rokne, Jon George; Bismar, Tarek; Alhajj, Reda
Biomedical researchers must often deal with large amounts of raw data, and analysis of this data might provide significant insights. However, if the raw data size is large, it might be difficult to uncover these insights. In this paper, a data framework named BioLake is presented that provides minimalist interactive methods to help researchers conduct bioinformatics data analysis. Unlike some existing analytical tools on the market, BioLake supports a wide range of web-based bioinformatics data analysis for public datasets, while allowing researchers to analyze their private datasets instantly. The tool also significantly enhances result interpretability by providing the source code and detailed instructions. In terms of data storage design, BioLake adopts the data lakehouse architecture to provide storage scalability and analysis flexibility. To further enhance the analysis efficiency, BioLake supports online analysis for custom data, allowing researchers to upload their own data via a designed procedure without waiting for server-side approval. BioLake allows a one-time upload of custom data of up to 500 MB to ensure that researchers avoid issues with data being too large for upload. In terms of the built-in dataset, BioLake applies reactive continuous data integration, helping the analysis pipeline to get rid of most preprocessing steps. The only pre-built-in dataset of BioLake in the first public version is TCGA-PRAD mRNA expression data for prostate cancer research, which is the primary focus of the development team of BioLake. In summary, BioLake offers a lightweight online tool to facilitate bioinformatic mRNA data analysis with the support of custom online data processing.
Computational study of the activation mechanism of wild-type parkin and its clinically relevant mutant
(2025) Cinviz, Zeynep Nur; Şensoy, Özge
Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder. It impairs the control of movement and balance. Parkin mutations worsen the symptoms in sporadic cases and cause the early onset of the disease. Therefore, recent efforts have focused on the rescue of defective parkin by engineered proteins or small-molecule activators to enhance parkin activation. These attempts require holistic understanding of the multistep activation mechanism and molecular effects of disease-associated mutations. Hereby, we provided a comprehensive analysis of the activation mechanism of parkin and a clinically relevant mutant, parkinS167N, using molecular dynamics simulations based on the following crystal structures: (1) parkin, (2) parkin/pUb (phosphorylated Ubiquitin), (3) pparkin/pUb, and (4) pparkin/pUb/UbcH7-Ub. Each of these represents an individual step in the activation process. We showed that the mutation impacted the dynamics of not only the RING0 domain, where it is localized, but also the RING2, Ubl, and IBR domains. We identified residues participating in the allosteric interaction network involved in parkin activation. Some of them are mutated in PD-associated parkin variants. The RING0 domain provides a binding interface with various proteins, so understanding problems associated with the mutation paves the way to the discovery of effective engineered proteins or small molecules that activate mutant parkin.
AutoCOR: autonomous condylar offset ratio calculator for post-operative total knee arthroplasty radiographs
(2025) Çakmak, Gülsade Rabia; Hamamcı, İbrahim Ethem; Yılmaz, Mehmet Kürşat; Alhajj, Reda; Azboy, İbrahim; Özdemir, Mehmet Kemal
Background: This study aims to automate the measurement process of posterior condylar offset ratio (PCOR) and anterior condylar offset ratio (ACOR) to improve the Total Knee Arthroplasty (TKA) evaluation. Accurate calculation of PCOR and ACOR, performed manually by orthopedic surgeons, is crucial for assessing postoperative range of motion and implant positioning. Manual measurements, however, are time-consuming, prone to human error, and subject to variability. Automating this process could improve precision in clinical practice. Methods: We developed AutoCOR, a software system that autonomously calculates PCOR and ACOR by utilizing built-in function, employing k-means clustering, from the OpenCV library for image segmentation. The software detects key anatomical landmarks on true postoperative lateral radiographs. The definitions of PCOR and ACOR are PCO (posterior condylar offset) divided by femoral diameter, and ACOR is defined as ACO (anterior condylar offset) divided by femoral diameter, respectively. We tested the algorithm on 50 postoperative lateral radiographs of 32 patients from the Istanbul Kosuyolu Medipol Hospital, which included data from. The assessment process included calculating the mean, standard deviation and plotting the Bland-Altman plots, comparing AutoCOR's results against ground truth values. Results: The mean PCOR was 0.984 (SD 0.235) for AutoCOR and 0.972 (SD 0.164) for ground truth values, showing a strong correlation (Pearson r = 0.845, p < 0.0001). The mean ACOR was 0.107 (SD 0.092) for AutoCOR and 0.107 (SD 0.070) for ground truth values, with moderate correlation (Spearman's rs = 0.519, p = 0.0001). Conclusion: AutoCOR provides accurate measurements and shows potential to reduce variability in TKA evaluation, improving precision in clinical practice.
Xse-tomatonet: an explainable ai based tomato leaf disease classification method using efficientnetb0 with squeeze-and-excitation blocks and multi-scale feature fusion
(2025) Assaduzzaman, Md; Bishshash, Prayma; Nirob, Asraful Sharker; Marouf, Ahmed Al; Rokne, Jon George; Alhajj, Reda
Tomatoes are globally valued for their nutritional benefits and unique taste, playing a crucial role in agricultural productivity. Accurate diagnosis of tomato leaf diseases is vital to avoid ineffective treatments that can harm plants and ecosystems. While deep learning models excel in classifying these diseases, distinguishing subtle variations remains challenging. This study introduces XSE-TomatoNet, an enhanced version of EfficientNetB0, incorporating Squeeze-and-Excitation (SE) blocks and multi-scale feature fusion to boost classification performance. XSE-TomatoNet extracts multi-scale features, refines them with SE blocks, and merges them through Global Average Pooling, providing detailed and broad insights for precise disease classification. Our approach achieves an impressive accuracy of 99.11%, with 99% precision and recall, outperforming models like MobileNet and VGG19, especially when combined with data augmentation and ablation studies. The model achieved an average training accuracy of 99.41% and a validation accuracy of 98.88% in 10-fold cross-validation, showing strong generalization to unseen data. We also used LIME and SHAP for model interpretability, offering insights into the decision-making process, and employed Grad-CAM and Grad-CAM++ to visually highlight key areas in leaf images. Finally, the best model was integrated into a web-based system for practical use by tomato cultivators. • XSE-TomatoNet is an enhanced version of EfficientNetB0 which incorporates Squeeze-and-Excitation (SE) blocks and multi-scale feature fusion. • XSE-TomatoNet outperformed MobileNet (87.44%) and VGG-19 (95.50%), in terms of accuracy, achieving 99.41%. • Integration of interpretation using LIME and SHAP models gives higher level understanding of the diseases and employment of Grad-CAM and Grad-CAM++ shows visual representation of the diseased leaves.
Rice leaf disease classification-a comparative approach using convolutional neural network (cnn), cascading autoencoder with attention residual u-net (caar-u-net), and mobilenet-v2 architectures
(2024) Dutta, Monoronjon; Islam Sujan, Md Rashedul; Mojumdar, Mayen Uddin; Chakraborty, Narayan Ranjan; Marouf, Ahmed Al; Rokne, Jon George; Alhajj, Reda
Classifying rice leaf diseases in agricultural technology helps to maintain crop health and to ensure a good yield. In this work, deep learning algorithms were, therefore, employed for the identification and classification of rice leaf diseases from images of crops in the field. The initial algorithmic phase involved image pre-processing of the crop images, using a bilateral filter to improve image quality. The effectiveness of this step was measured by using metrics like the Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). Following this, this work employed advanced neural network architectures for classification, including Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), MobileNetV2, and Convolutional Neural Network (CNN). The proposed CNN model stood out, since it demonstrated exceptional performance in identifying rice leaf diseases, with test Accuracy of 98% and high Precision, Recall, and F1 scores. This result highlights that the proposed model is particularly well suited for rice leaf disease classification. The robustness of the proposed model was validated through k-fold cross-validation, confirming its generalizability and minimizing the risk of overfitting. This study not only focused on classifying rice leaf diseases but also has the potential to benefit farmers and the agricultural community greatly. This work highlights the advantages of custom CNN models for efficient and accurate rice leaf disease classification, paving the way for technology-driven advancements in farming practices.
Rice leaf disease classification—a comparative approach using convolutional neural network (cnn), cascading autoencoder with attention residual u-net (caar-u-net), and mobilenet-v2 architectures
(2024) Dutta, Monoronjon; Islam Sujan, Md Rashedul; Mojumdar, Mayen Uddin; Chakraborty, Narayan Ranjan; Marouf, Ahmed Al; Rokne, Jon George; Alhajj, Reda
Classifying rice leaf diseases in agricultural technology helps to maintain crop health and to ensure a good yield. In this work, deep learning algorithms were, therefore, employed for the identification and classification of rice leaf diseases from images of crops in the field. The initial algorithmic phase involved image pre-processing of the crop images, using a bilateral filter to improve image quality. The effectiveness of this step was measured by using metrics like the Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). Following this, this work employed advanced neural network architectures for classification, including Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), MobileNetV2, and Convolutional Neural Network (CNN). The proposed CNN model stood out, since it demonstrated exceptional performance in identifying rice leaf diseases, with test Accuracy of 98% and high Precision, Recall, and F1 scores. This result highlights that the proposed model is particularly well suited for rice leaf disease classification. The robustness of the proposed model was validated through k-fold cross-validation, confirming its generalizability and minimizing the risk of overfitting. This study not only focused on classifying rice leaf diseases but also has the potential to benefit farmers and the agricultural community greatly. This work highlights the advantages of custom CNN models for efficient and accurate rice leaf disease classification, paving the way for technology-driven advancements in farming practices.
Enhanced potato pest identification: a deep learning approach for identifying potato pests
(2024) Sohel, Amir; Shakil, Md. Shahriar; Siddiquee, Shah Md. Tanvir; Marouf, Ahmed Al; Rokne, Jon G.; Alhajj, Reda
Potato crops and their salability are influenced by potato pests in that both crop yield and quality are reduced. This in turn reduces the income for potato farmers due to lower prices for the crop, lower crop yield, trade restriction and reduced market access. Agricultural viability over the long run therefore depends on sustainable pest management. In order to efficiently detect potato pests, a dataset was constructed which contains eight prevalent potato species that were taken from several sources. Image pre-processing techniques were employed enhance image quality for compatibility with deep learning models. Among InceptionV3, VGG-16, and MobileNetV2 models, VGG-16 attained the highest accuracy of 94.44%, outperforming others. Inception-V3 achieved 58% accuracy, while MobileNetV2 reached 75%. Pre-processing has a major influence on improving result accuracy, which emphasizes its significance in enhancing model performance, according to an evaluation of its effects. These findings might lead to the development of pest management strategies for potato farming that are more effective. The efficient use of VGG-16 in potato pest identification systems is demonstrated by its excellent performance. Using deep learning models can therefore reduce financial losses and promote sustainable potato production. This study provides an approach for further investigation into the best ways to control pests in potato production, allowing farmers to overcome the obstacles and take advantage of valuable market prospects even in the face of pest threats.
Improving predictive efficacy for drug resistance in novel hiv-1 protease inhibitors through transfer learning mechanisms
(2024) Tunç, Hüseyin; Yılmaz, Sümeyye; Darendeli Kiraz, Büşra Nur; Sarı, Murat; Kotil, Seyfullah Enes; Şensoy, Özge; Durdağı, Serdar
The human immunodeficiency virus presents a significant global health challenge due to its rapid mutation and the development of resistance mechanisms against antiretroviral drugs. Recent studies demonstrate the impressive performance of machine learning (ML) and deep learning (DL) models in predicting the drug resistance profile of specific FDA-approved inhibitors. However, generalizing ML and DL models to learn not only from isolates but also from inhibitor representations remains challenging for HIV-1 infection. We propose a novel drug-isolate-fold change (DIF) model framework that aims to predict drug resistance score directly from the protein sequence and inhibitor representation. Various ML and DL models, inhibitor representations, and protein representations were analyzed through realistic validation mechanisms. To enhance the molecular learning capacity of DIF models, we employ a transfer learning approach by pretraining a graph neural network (GNN) model for activity prediction on a data set of 4855 HIV-1 protease inhibitors (PIs). By performing various realistic validation strategies on internal and external genotype-phenotype data sets, we statistically show that the learned representations of inhibitors improve the predictive ability of DIF-based ML and DL models. We achieved an accuracy of 0.802, AUROC of 0.874, and r of 0.727 for the unseen external PIs. By comparing the DIF-based models with a null model consisting of isolate-fold change (IF) architecture, it is observed that the DIF models significantly benefit from molecular representations. Combined results from various testing strategies and statistical tests confirm the effectiveness of DIF models in testing novel PIs for drug resistance in the presence of an isolate.
Global human obesity and political globalization; asymmetric relationship through world human development levels
(2024) Munir, Mubbasher; Zakaria, Zahrahtul Amani; Alhajj, Reda; Mohamad, Mumtazimah Binti; Baig, Atif Amin; Arshed, Noman
Purpose - Political globalization is a crucial and distinct component of strengthening global organizations. Obesity is a global epidemic in a few nations, and it is on the verge of becoming a pandemic that would bring plenty of diseases. This research aims to see how the political globalization index affects worldwide human obesity concerning global human development levels. Methods- To assess any cross-sectional dependence among observed 109 nations, the yearly period from 1990 to 2017 is analyzed using second generation panel data methods. KAO panel cointegration test and Fully Modified Least Square model were used to meet our objectives. Finding- Low level of political globalization tends to increase global human obesity because countries cannot sway international decisions and resources towards them. While the high level of political globalization tends to reduce obesity because it can control and amends international decisions. For the regression model, a fully modified Least Square model was utilized. The study observed that the R squared values for all models are healthy, with a minimum of 87 percent variables explaining differences in global obesity at the country level. Originality: There is very important to tackle the globalization issue to reduce global human obesity. With the simplicity of dietary options and the amount of physical labour they undergo in their agricultural duties, an increase in rural population percentage tends to lower the average national obesity value.
Global impact on human obesity – a robust non-linear panel data analysis
(2024) Munir, Mubbasher; Zakaria, Zahrahtul Amani; Baig, Atif Amin; Mohamad, Mumtazimah Binti; Arshed, Noman; Alhajj, Reda
Purpose: Recent studies in economics showed that humans are bounded rational. This being consumers, they are not perfect judges of what matters for the standard of living. While with a marked increase in economic and social wellbeing, there is a consistent rise in obesity levels, especially in the developed world. Thus, this study intends to explore the empirical and socio-economic antecedents of human obesity across countries using six global indexes. Methods: This study used the data of 40 countries between 1975 to 2018 and used the Panel FGLS Regression with the quadratic specification. Findings: The results showed that health and food indicators increase global human obesity, environment and education indicators decrease global human obesity, and economic and social indicators follow an inverted U-shaped pattern in affecting global human obesity. Originality: Previous studies have used infant mortality and life expectancy as the major health indicator in determining the standard of living while overlooking global human obesity as a major deterrent to welfare. This study has provided a holistic assessment of the causes of obesity in global contexts.
Twitter analysis in emergency management: recent research and trends
(2024) Arvandi, Alireza; Rokne, Jon; Alhajj, Reda
A disaster is an unexpected event with negative consequences for individuals and societies. Typically it is interfering with a community’s or society’s ability to function. Disasters can be man-made events, accidental events, or a natural catastrophes. These events create emergencies that require rapid responses. Timely information about the emergencies has to be obtained so that the responses can aid in dealing with the emergencies. One source of timely information about disasters is provided by social media postings which often provide on-site information about a disaster. An ideally suited social media tool for disaster information is Twitter due to the sort message format. This format enables the rapid composition of short messages by entities close to a disaster describing the nature of the disaster. The contents of the messages can then be used to guide emergency responses. The aim of this paper is to review the research on the usage of Twitter for emergency management that has been published so far. There are three steps required when using messages for information about disasters. The first step is to collect the data contained in the messages. Then the data has to be preprocessed for unification of format, duplication etc. Finally relevant information has to be extracted. These steps are considered in this paper reviewing the use of Twitter for emergency management. Papers using Twitter published within the past 5 years have been included.
Lstm-driven drug design using selfies for target-focused de novo generation of hiv-1 protease inhibitor candidates for aids treatment
(2024) Albrijawi, M. Taleb; Alhajj, Reda
The battle against viral drug resistance highlights the need for innovative approaches to replace time-consuming and costly traditional methods. Deep generative models offer automation potential, especially in the fight against Human immunodeficiency virus (HIV), as they can synthesize diverse molecules effectively. In this paper, an application of an LSTM-based deep generative model named "LSTM-ProGen"is proposed to be tailored explicitly for the de novo design of drug candidate molecules that interact with a specific target protein (HIV-1 protease). LSTM-ProGen distinguishes itself by employing a longshort- term memory (LSTM) architecture, to generate novel molecules target specificity against the HIV-1 protease. Following a thorough training process involves fine-tuning LSTM-ProGen on a diverse range of compounds sourced from the ChEMBL database. The model was optimized to meet specific requirements, with multiple iterations to enhance its predictive capabilities and ensure it generates molecules that exhibit favorable target interactions. The training process encompasses an array of performance evaluation metrics, such as drug-likeness properties. Our evaluation includes extensive silico analysis using molecular docking and PCA-based visualization to explore the chemical space that the new molecules cover compared to those in the training set. These evaluations reveal that a subset of 12 de novo molecules generated by LSTM-ProGen exhibit a striking ability to interact with the target protein, rivaling or even surpassing the efficacy of native ligands. Extended versions with further refinement of LSTM-ProGen hold promise as versatile tools for designing efficacious and customized drug candidates tailored to specific targets, thus accelerating drug development and facilitating the discovery of new therapies for various diseases.
Exploring the prognostic significance of set-domain containing 2 (setd2) expression in advanced and castrate-resistant prostate cancer
(2024) Gamallat, Yaser; Felipe Lima, Joema; Seyedi, Sima; Li, Qiaowang; Rokne, Jon George; Alhajj, Reda; Ghosh, Sunita; Bismar, Tarek A.
SET-domain containing 2 (SETD2) is a histone methyltransferase and an epigenetic modifier with oncogenic functionality. In the current study, we investigated the potential prognostic role of SETD2 in prostate cancer. A cohort of 202 patients’ samples was assembled on tissue microarrays (TMAs) containing incidental, advanced, and castrate-resistant CRPCa cases. Our data showed significant elevated SETD2 expression in advanced and castrate-resistant disease (CRPCa) compared to incidental cases (2.53 ± 0.58 and 2.21 ± 0.63 vs. 1.9 ± 0.68; p < 0.001, respectively). Interestingly, the mean intensity of SETD2 expression in deceased vs. alive patients was also significantly different (2.31 ± 0.66 vs. 2 ± 0.68; p = 0.003, respectively). Overall, high SETD2 expression was found to be considered high risk and was significantly associated with poor prognosis and worse overall survival (OS) (HR 1.80; 95% CI: 1.28–2.53, p = 0.001) and lower cause specific survival (CSS) (HR 3.14; 95% CI: 1.94–5.08, p < 0.0001). Moreover, combining high-intensity SETD2 with PTEN loss resulted in lower OS (HR 2.12; 95% CI: 1.22–3.69, p = 0.008) and unfavorable CSS (HR 3.74; 95% CI: 1.67–8.34, p = 0.001). Additionally, high SETD2 intensity with ERG positive expression showed worse prognosis for both OS (HR 1.99, 95% CI 0.87–4.59; p = 0.015) and CSS (HR 2.14, 95% CI 0.98–4.68, p = 0.058). We also investigated the protein expression database TCPA, and our results showed that high SETD2 expression is associated with a poor prognosis. Finally, we performed TCGA PRAD gene set enrichment analysis (GSEA) data for SETD2 overexpression, and our data revealed a potential association with pathways involved in tumor progression such as the AMPK signaling pathway, the cAMP signaling pathway, and the PI3K-Akt signaling pathway, which are potentially associated with tumor progression, chemoresistance, and a poor prognosis.
Cyber-WISE: A cyber-physical deep wireless indoor positioning system and digital twin approach
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Karakuşak, Muhammed Zahid; Kıvrak, Hasan; Watson, Simon; Özdemir, Mehmet Kemal
In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of <= 2.16 m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as 1.55 m and 1.97 m with 83.33% and 81.05% of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability.
Exploring deep learning for adaptive energy detection threshold determination: A multistage approach
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Bedir, Oğuz; Ekti, Ali Rıza; Özdemir, Mehmet Kemal
The concept of spectrum sensing has emerged as a fundamental solution to address the growing demand for accessing the limited resources of wireless communications networks. This paper introduces a straightforward yet efficient approach that incorporates multiple stages that are based on deep learning (DL) techniques to mitigate Radio Frequency (RF) impairments and estimate the transmitted signal using the time domain representation of received signal samples. The proposed method involves calculating the energies of the estimated transmitted signal samples and received signal samples and estimating the energy of the noise using these estimates. Subsequently, the received signal energy and the estimated noise energy, adjusted by a correction factor (k), are employed in binary hypothesis testing to determine the occupancy of the wireless channel under investigation. The proposed system demonstrates encouraging outcomes by effectively mitigating RF impairments, such as carrier frequency offset (CFO), phase offset, and additive white Gaussian noise (AWGN), to a considerable degree. As a result, it enables accurate estimation of the transmitted signal from the received signal, with 3.85% false alarm and 3.06% missed detection rates, underscoring the system’s capability to adaptively determine a decision threshold for energy detection.
Genomic biomarker discovery in disease progression and therapy response in bladder cancer utilizing machine learning
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Liosis, Konstantinos Christos; Marouf, Ahmed Al; Rokne, Jon G.; Ghosh, Sunita; Bismar, Tarek A.; Alhajj, Reda
Cancer in all its forms of expression is a major cause of death. To identify the genomic reason behind cancer, discovery of biomarkers is needed. In this paper, genomic data of bladder cancer are examined for the purpose of biomarker discovery. Genomic biomarkers are indicators stemming from the study of the genome, either at a very low level based on the genome sequence itself, or more abstractly such as measuring the level of gene expression for different disease groups. The latter method is pivotal for this work, since the available datasets consist of RNA sequencing data, transformed to gene expression levels, as well as data on a multitude of clinical indicators. Based on this, various methods are utilized such as statistical modeling via logistic regression and regularization techniques (elastic-net), clustering, survival analysis through Kaplan–Meier curves, and heatmaps for the experiments leading to biomarker discovery. The experiments have led to the discovery of two gene signatures capable of predicting therapy response and disease progression with considerable accuracy for bladder cancer patients which correlates well with clinical indicators such as Therapy Response and T-Stage at surgery with Disease Progression in a time-to-event manner.
Synthesis, structural investigations, DNA/BSA interactions, molecular docking studies, and anticancer activity of a new 1,4-disubstituted 1,2,3-triazole derivative
(American Chemical Society, 2023) Göktürk, Tolga; Sakallı Çetin, Esin; Hökelek, Tuncer; Pekel, Hanife; Şensoy, Özge; Aksu, Ebru Nur; Güp, Ramazan
We report herein a new 1,2,3-triazole derivative, namely, 4-(( 1-( 3,4-dichlorophenyl)-1H-1,2,3- triazol- 4-yl)methoxy)-2-hydroxybenzaldehyde, which was synthesized by copper(I)-catalyzed azide-alkyne cycloaddition (CuAAC). The structure of the compound was analyzed using Fourier transform infrared spectroscopy (FTIR), H-1 NMR, C-13 NMR, UV-vis, and elemental analyses. Moreover, X- ray crystallography studies demonstrated that the compound adapted a monoclinic crystal system with the P2(1)/c space group. The dominant interactions formed in the crystal packing were found to be hydrogen bonding and van der Waals interactions according to Hirshfeld surface (HS) analysis. The volume of the crystal voids and the percentage of free spaces in the unit cell were calculated as 152.10 A(3) and 9.80%, respectively. The evaluation of energy frameworks showed that stabilization of the compound was dominated by dispersion energy contributions. Both in vitro and in silico investigations on the DNA/bovine serum albumin (BSA) binding activity of the compound showed that the CT-DNA binding activity of the compound was mediated via intercalation and BSA binding activity was mediated via both polar and hydrophobic interactions. The anticancer activity of the compound was also tested by the 3-(4,5-dimethylthiazol2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay using human cell lines including MDA-MB-231, LNCaP, Caco-2, and HEK293. The compound exhibited more cytotoxic activity than cisplatin and etoposide on Caco-2 cancer cell lines with an IC50 value of 16.63 +/- 0.27 mu M after 48 h. Annexin V suggests the induction of cell death by apoptosis. Compound 3 significantly increased the loss of mitochondrial membrane potential (MMP) levels in Caco-2 cells, and the reactive oxygen species (ROS) assay proved that compound 3 could induce apoptosis by ROS generation.
MCNN-LSTM: Combining CNN and LSTM to classify multi-class text in imbalanced news data
(Institute of Electrical and Electronics Engineers Inc., 2023) Hasib, Khan Md; Azam, Sami; Karim, Asif; Marouf, Ahmed Al; Shamrat, F. M. Javed Mehedi; Montaha, Sidratul; Yeo, Kheng Cher; Jonkman, Mirjam; Alhajj, Reda; Rokne, Jon G.
Searching, retrieving, and arranging text in ever-larger document collections necessitate more efficient information processing algorithms. Document categorization is a crucial component of various information processing systems for supervised learning. As the quantity of documents grows, the performance of classic supervised classifiers has deteriorated because of the number of document categories. Assigning documents to a predetermined set of classes is called text classification. It is utilized extensively in a wide range of data-intensive applications. However, the fact that real-world implementations of these models are plagued with shortcomings begs for more investigation. Imbalanced datasets hinder the most prevalent high-performance algorithms. In this paper, we propose an approach name multi-class Convolutional Neural Network (MCNN)-Long Short-Time Memory (LSTM), which combines two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Time Memory, for text classification in news data. CNN's are used as feature extractors for the LSTMs on text input data and have the spatial structure of words in a sentence, paragraph, or document. The dataset is also imbalanced, and we use the Tomek-Link algorithm to balance the dataset and then apply our model, which shows better performance in terms of F1-score (98%) and Accuracy (99.71%) than the existing works. The combination of deep learning techniques used in our approach is ideal for the classification of imbalanced datasets with underrepresented categories. Hence, our method outperformed other machine learning algorithms in text classification by a large margin. We also compare our results with traditional machine learning algorithms in terms of imbalanced and balanced datasets.
A comparative study of different pre-trained deeplearning models and custom CNN for pancreatic tumor detection
(Zarka Private University, 2023) Zavalsız, Muhammed Talha; Alhajj, Sleiman; Sailunaz, Kashfia; Özyer, Tansel; Alhajj, Reda
Artificial Intelligence and its sub-branches like MachineLearning (ML) and Deep Learning (DL) applications have the potential to have positive effects that can directly affect human life. Medical imaging is briefly making the internal structure of the human body visible with various methods. With deep learning models, cancer detection, which is one of the most lethal diseases in the world, can be made possible with high accuracy. Pancreatic Tumor detection, which is one of the cancer types with the highest fatality rate, is one of the main targets of this project, together with the data set of computed tomography images,which is one of the medical imaging techniques and has an effective structure in Pancreatic Cancer imaging. In the field of image classification, which is a computer vision task, the transfer learning technique, which has gained popularity in recent years, has been applied quite frequently. Using pre-trained models werepreviously trained on a fairly large dataset and using them on medical images is common nowadays. The main objective of this article is to use this method, which is very popular inthe medical imaging field, in the detection of PDAC, one of the deadliest types of pancreatic cancer, and to investigate how it per-forms compared to the custom model created and trained from scratch. The pre-trained models which are used in this project areVGG-16 and ResNet, which are popular Convolutional Neutral Network models, for Pancreatic Tumor Detection task. With the use of these models, early diagnosis of pancreatic cancer, which progresses insidiously and therefore does not spread to neighboring tissues and organs when the treatment process is started, may be possible. Due to the abundance of medical images reviewed by medical professionals, which is one of the main causes for heavy workload of healthcare systems, this applicationcan assist radiologists and other specialists in Pancreatic Tumor detection by providing faster and more accurate method.
Brain tumor detection and segmentation: Interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust
(Public Library of Science, 2023) Sailunaz, Kashfia; Beştepe, Deniz; Alhajj, Sleiman; Özyer, Tansel; Rokne, Jon; Alhajj, Reda
Brain cancers caused by malignant brain tumors are one of the most fatal cancer types with a low survival rate mostly due to the difficulties in early detection. Medical professionals therefore use various invasive and non-invasive methods for detecting and treating brain tumors at the earlier stages thus enabling early treatment. The main non-invasive methods for brain tumor diagnosis and assessment are brain imaging like computed tomography (CT), positron emission tomography (PET) and magnetic resonance imaging (MRI) scans. In this paper, the focus is on detection and segmentation of brain tumors from 2D and 3D brain MRIs. For this purpose, a complete automated system with a web application user interface is described which detects and segments brain tumors with more than 90% accuracy and Dice scores. The user can upload brain MRIs or can access brain images from hospital databases to check presence or absence of brain tumor, to check the existence of brain tumor from brain MRI features and to extract the tumor region precisely from the brain MRI using deep neural networks like CNN, U-Net and U-Net++. The web application also provides an option for entering feedbacks on the results of the detection and segmentation to allow healthcare professionals to add more precise information on the results that can be used to train the model for better future predictions and segmentations.

Güncel Gönderiler