جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

71 مُخرَج نتائج البحث عن «Algorithm»

مقالمفتوح (مستودع)2024

The Transformative Impact of Artificial Intelligence and Robotics in Healthcare: Applications, Challenges, and Ethical Implications

Saudi Journal of Medicine and Public Health · مجلد 1 (1) · 37-46

Background: The integration of artificial intelligence (AI) and robotics into healthcare has the potential to transform various medical applications, enhancing operational efficiency, precision, and patient outcomes. However, ethical considerations surrounding these technologies remain a critical concern. Methods: This paper conducts a comprehensive literature review, examining the current applications of AI and robotics in healthcare, including diagnostics, treatment, rehabilitation, and patient care. Key methodologies analyzed include machine learning algorithms, natural language processing, and robotic-assisted surgical techniques. The review synthesizes findings from recent studies and evaluates the efficacy and challenges associated with these technologies. Results: The analysis reveals significant advancements in AI-driven diagnostic tools, particularly in medical imaging, where algorithms enhance accuracy and reduce human error. Robotics has also shown promise in surgical procedures, rehabilitation, and elder care, improving patient engagement and operational workflows. Despite these advancements, challenges such as data privacy, algorithm transparency, and the need for healthcare professionals’ training in AI technologies persist. Conclusion: The future of medical robotics and AI appears promising, with the potential to revolutionize healthcare delivery. However, addressing ethical, operational, and educational challenges is crucial for successful integration. Ongoing collaboration among technologists, healthcare providers, and policymakers will be essential to navigate these complexities and enhance patient care.

artificial intelligence in healthcaremedical roboticsrobotic surgeryAI-assisted diagnosis
تصحيحوصول مفتوح2024

Corrigendum: Targeting p53 misfolding conundrum by stabilizing agents and their analogues in breast cancer therapy: a comprehensive computational analysis

Frontiers in Pharmacology · مجلد 15 · 1494110-1494110

Breast carcinoma is one of the most frequent malignancies diagnosed globally and the chief cause of mortality among females (Siegel et al., 2021;Mir and Qayoom, 2023). Nearly 30% of all cancer incidences in women are due to breast cancer (Sung et al., 2021). Globally, BC represents recurrent malignancy among women. In 2020, it exceeded lung cancer to become the top reason of cancer incidence worldwide. A total of 2.3 million additional cases were anticipated, accounting for approximately 11.7% of all cancer cases (Hall et al., 1990).Epidemiological studies have revealed that the burden of breast cancer globally is thought to cross nearly 2 million by the year 2030 (Wooster et al., 1994). The primary major gene that was identified to be associated with hereditary BC in 1990 is BRCA1. Additionally, it was identified by employing linkage analysis in families by exploring suggestive pedigrees (Gallanis et al., 2021). Following this, BRCA2 was mapped to chromosome 13 in 1994 (Baldin et al., 1993). An alteration in either BRCA1 or BRCA2 increases susceptibility to cancer risk, especially BC. Metastatic breast cancer remains almost completely incurable, with an average overall survival (OS) of 3 years and a merely 25% 5-year OS (Cardoso et al., 2018;Sofi et al., 2022a).Although there have been significant advances in the strategies for curing breast cancer, the poor prognosis is still a matter of concern (Waks and Winer, 2019;Sofi et al., 2022b;Mir and Haq, 2023a;Qayoom et al., 2023a;Mir and Haq, 2023b). Due to its heterogeneous nature, it becomes hard to access the surviving individuals (Turashvili and Brogi, 2017;Mehraj et al., 2021;Qayoom et al., 2021). Multiple studies on breast cancer previously identified several genes which possess prognostic value. However, the developing field of bioinformatics along with advancing algorithms has provided researchers with the environment to discover potential genes by employing a different approach (Mehraj et al., 2022;Qayoom et al., 2023b;Sofi et al., 2023). The p53 protein has an essential role in prevention of genomic mutation in the body, but this protein is prone to mutations at a higher rate as witnessed in cancers. Moreover, a malfunction is witnessed in approximately all cancers along the p53 pathway. The altered p53 protein not only loses its function but is also susceptible to misfolding and accumulation, ultimately leading to the formation of amyloid aggregates. Protein misfolding and accumulation have a part to play in cancer development. Recognized as the "guardian of the genome," p53 plays a crucial role in preventing genomic mutations. Structurally, p53 represents a tetrameric transcription factor that modulates multiple cellular roles like expression of target genes that lead to apoptosis, repair of DNA, and arrest of the cell cycle in damaged cells in addition to cellular metabolism (Helton and Chen, 2007;Lukin et al., 2015;Mir et al., 2023a). Due to the fact that more than 50% of cancers are caused due to direct point mutations of p53 (Petitjean et al., 2007;Olivier et al., 2010) and the p53 malfunction as seen in aggressive cancer types like gastric cancer (Blanchet et al., 2021); thus, reverting or restoring the normal p53 function is a marked strategy for possible cancer cure (Hong et al., 2014;Bykov et al., 2018;Miller et al., 2020). The levels of P53 are highly modulated through posttranslational alterations and a pivotal modifier modulator mouse double minute 2 homolog (MDM2). However, during cellular stress, there is an inhibition to p53 degradation; in addition, the protein is accumulated in the nucleus (Friedman et al., 1993;Nag et al., 2013;Mir et al., 2022). The same causes target gene upregulation and triggers reaction mechanisms to bypass the multiplication of injured cells (Brooks and Gu, 2010). For example, when DNA damage occurs, p53 may either force the injured cell to be removed or trigger a cell cycle blockage mechanism that allows DNA repair to proceed (Helton and Chen, 2007;Lukin et al., 2015). The studies have revealed that the DNA-binding domain (DBD) of wild-type p53 displays less thermodynamic and kinetic stability (Natan et al., 2011) and several mutations lead to instability, ultimately causing protein unfolding. Cancer cells acquire high amounts of mutant p53 because it avoids the MDM2-mediated proteasomal destruction (Scian et al., 2004).MDM2 has been shown to play a post-ubiquitination function in the degradation of p53 (Kulikov et al., 2010). Aggregation and unfolding are intricate processes; however, destabilization exposes an adhesive sequence that attaches to the same section in other p53 units and triggers aggregation. Consequently, there is significant interest in the creation of novel agents that can both stabilize folded structures and prevent aggregation or split preformed aggregates (Miller et al., 2020;Miller et al., 2022). There are multiple ways through which altered p53 protein can be stabilized in its active and folded form. A comprehensive set of Michael acceptors, including CP-31398 and PRIMA1, has been seen to rectify the native information on mutant p53 and initiate p53-dependent cytotoxicity (Foster et al., 1999;Bykov et al., 2002;Rangel et al., 2019;Mir et al., 2023b). PhiKan-083 represents a small molecule and a carbazole derivative, which binds to the surface cavity and leads to the stabilization of a p53 mutant, namely, Y220C, possessing a Kd of 167 μM. Thus, we attempted to explore PhiKan-083 for breast cancer research. Y220C mutation, which is not involved in DNA interaction, causes a destabilization of the protein. PhiKan-083 binding stabilizes the mutant p53 and slows the rate of denaturation.Hence, for this study, we screened and examined many analogs of PhiKan-083 with better docking scores in comparison to PhiKan-083 for stabilizing misfolded p53. We evaluated the molecule-to-molecule docking of selected compounds to determine the therapeutic potential of screened PhiKan-083-related analogs by calculating the drug-likeliness of those compounds. This work identified two novel compounds that, in addition to their potential as PhiKan-083 substitutes, have advantages such as potential activity against a variety of p53-misfolded malignancies and not just breast cancer. We also looked at p53's expression patterns and predictive values across a range of cancer types, especially breast cancer.UALCAN (http://ualcan.path.uab.edu/) represents a web-based interactive portal to investigate cancer omics data (Chandrashekar et al., 2017). UALCAN has been made to furnish access to publicly available cancer OMICS data easily with the aim of running in silico validation of genes that are of interest or to identify related biomarkers. These databases furnish the graphical representation along with the plots displaying the expression profiles along with the subject survival information. We selected TCGA invasive breast carcinoma data, and P53 expression was examined among different cancer stages, sample types, and sub-classes.TIMER 2.0 (http://timer.comp-genomics.org/) is an instructive tool used to thoroughly evaluate the expression and quantification of immune infiltrates across malignancies. Users can investigate the connection between gene expression and other variables using the database's algorithms, including quanTIseq, CIBERSORT, MCPcounter, and EPIC algorithms; the status of its mutation; and its association with different immune cell kinds. To better comprehend the gene expression profiles of all malignancies, a heatmap of TP53 was created using TIMER 2.0 (Li et al., 2020).Through TCGA and GTEx projects, RNA-sequencing expression data from 9,736 tumors and 8,587 normal samples were analyzed using the web-based application GEPIA2 (http://gepia2.cancer-pku.cn). Subject survival analysis, dimensionality reduction study, identification of related genes, profiling based on cancer types or pathological stages, assessment of differential expression between tumors and normal tissues, and correlation analysis are a few of the resources that can be tailored. By gathering RNA-seq datasets from the UCSC Xena project (http://xena.ucsc.edu), the GEPIA2 followed a pre-established process (Tang et al., 2019). The TP53 expression in varied cancers was obtained by employing the GEPIA2 portal.The breast cancer gene-expressionminer v4.5 (http://bcgenex.ico.unicancer.fr/) is a bioinformatics tool available online that contains published BC transcriptomic and RNA-seq data in an annotated form (Jézéquel et al., 2012;Jezequel et al., 2013). It was employed to analyze the link between p53 expression levels and distinct clinical factors of breast tumor subjects. P53 expression analysis results were analyzed for basal-like luminal A and luminal B types.For researchers who want to carefully examine the functional proteomics of various cancer types, the University of Texas MD Anderson Cancer Center's Cancer Proteome Atlas Portal is a goto source (https://tcpaportal.org/tcpa/). Using the website's database of patient cohorts, the users can search through the datasets of patient tumors that have been obtained and sequenced by the Center. Users can obtain thorough explanations of each dataset and use a network model or heatmap to evaluate the interactions of the proteins in the data. This website offers a database of cancer cell lines in addition to the patient's cohort database, which researchers can browse and analyze.The National Human Genome Research Institute (NHGRI) and the National Cancer Institute (NCI), both of which are divisions of the National Institutes of Health of the U.S. Department of Health and Human Services, have collaborated on it (https://portal.gdc.cancer.gov/). A pilot study for the Cancer Genome Atlas was conducted to see whether a larger project must be undertaken to systematically examine every type of genetic mutation connected to human cancer. Next, using matched normal samples, the scientists molecularly defined almost 20,000 initial cancer samples from 33 distinct cancer types. It is open to all members of the scientific community to use the almost 2.5 petabytes of data generated by TCGA.Since 1992, PredictProtein (https://predictprotein.org) has predicted the structure and functional characteristics of proteins using sequence analysis. Multiple sequence alignments anticipated structural elements [solvent accessibility, secondary structure, coiled-coil regions, transmembrane helices (TMSEG) and strands, disulfide bonds, and disordered areas] and functional elements are returned in response to a protein sequence query. Among the analysis techniques included in the service are functional region identification (ConSurf), homologybased inference of GO terms (meta-student), precise subcellular localization prediction (LocTree3), protein-polynucleotide binding sites (SomeNA), protein-polynucleotide binding sites (ISIS2), and predictions of the impact of point mutations (non-synonymous SNPs) on protein function (SNAP2). Their objective has consistently been to provide a tailored solution that satisfies the needs of researchers with less experience in bioinformatics. To achieve this, the PredictProtein results are given as text along with a number of coherent, engaging, and visually appealing images. The sources and web server may be accessed at (http://ppopen.rostlab.org).In this work, PhiKan-083 served as the reference compound, and 100 compounds with similar structural properties were examined. We collected these compounds from the PubChem database (https://pubchem.ncbi.nlm.nih.gov/) and investigated all of the physico-chemical characteristics of the compounds. The specific compounds were analyzed using Discovery Studio v18 after copying them in SDF format (Kim et al., 2019).The retrieved PhiKan-083 analogues were assessed for drug-likeness using Swiss ADME, an online portal that assesses a drug's potential by examining characteristics such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) of the selected 100 analogues (http://www.swissadme.ch). Numerous parameters, such as hydrogen bond acceptors (nHBAs), the log of the n-octanol/water partition coefficient (LogP), hydrogen bond donors (nHBDs), molecular polar surface area (PSA), molecular weight (MW), and number of rotatable bonds (nRotBs), were calculated by incorporating Lipinski's rule of five and the Veber rule. The ADMET prediction technique took into account a number of parameters, including aqueous solubility, cytochrome P450 (CYP) 2D6 inhibition, hepatotoxicity, intestinal absorption, and plasma protein binding. After being chosen, the compounds that complied with ADMET drug likeliness guidelines underwent molecular docking (Rudrapal et al., 2022).The target protein TP53 (PDB ID 8dc4) was obtained from the Protein Data Bank (PDB) in a PDB format (Kulikov et al., 2010). By removing the extra structural moieties like heteroatoms, water molecules, and any associated ligands, the p53 protein was cleared up for further study using the Discovery studio (Nguyen et al., 2014).To ascertain the ligands' affinities for binding to TP53, the compounds were first exposed to molecular docking after undergoing ADMET analysis. Every ligand was docked with the TP53 protein using Auto Dock v4.2.6. Using the co-crystallized X-ray structure of the p53 protein from the RCSB PDB, the binding cavity was built. The co-crystallized ligand's three spacers' residue locations were computed. Following the selection of a cavity, the energy was reduced by applying conjugate gradient and steepest descent algorithms. By merging the nonpolar hydrogens, the receptor and target molecules were finally stored in pdbqt format. We created grid boxes at 0.3 intervals. The protein-ligand complex was docked using the Lamarckian Genetic Algorithm (LGA) in order to determine the lowest free energy of binding (G). Three similar sets of molecular modeling experiments were carried out, with the default settings being a maximum of 2700 generations, 2,500,000 evaluations, and 50 solutions each set (Qayoom et al., 2022).As shown in the heatmap in Figure 1 A, the TIMER 2.0 analysis of the TP53 expression pattern showed overexpression of TP53 across all TCGA datasets. TP53 levels were further assessed using CPTAC samples from the UALCAN database. When compared to normal samples, it was also discovered that the levels of the protein TP53 were significantly raised in a number Using the web-based Enrichr programme for GO analysis, it was demonstrated that MF was considerably enriched compared to BP and CC. The Figure 3 Using KM-plotter from GEPIA2, the prognostic significance of TP53 was assessed across all cancer types. The relationship between overall survival (OS) and relapse-free survival (RFS) and the median expression of TP53 was investigated. According to the study, reduced overall survival (OS) is associated with elevated TP53 expression in the ACC, BRCA, KIRP, LAML,LGG, LIHC, PRAD, SARC, THCA, and UCS Figure 4. The hazard ratio for all malignancies ranged from 1 to 12, with LIHC having the lowest and PRAD having the highest. High TP53 mRNA levels are linked to worse relapse-free survival (RFS) in LGG, UCS, and BRCA, followed by LAML, SARC, ACC, KIRP, LIHC, PRAD, and THCA according to the connection between TP53 mRNA levels and RFS. These investigations demonstrated the importance of TP53 in cancer prognosis, making it a promising target for treating various malignancies. Using UALCAN database, we analyzed the expression pattern of p53 in breast cancer. The heat map was generated by correlating p53 with other overexpressed genes in BC using correlation coefficient The study showed that among all the genes, p53 was We compared the p53 expression in both normal and tumor samples, p53 was in breast cancer. Using the same database, we also analyzed the expression of p53 among various of BC the major associated with p53 misfolding is due to its point mutation we the sequence of P53 using database to the of the status of It was revealed that p53 protein sequence has higher of structural mutations that have significantly its its tumor protein misfolding is it was further assessed to the of mutations that are or mutations that lead to of tumor It was seen that protein misfolding to the of function potential of P53 protein as is shown in the Figure was revealed from the results that P53 protein expression was highly in several cancers including breast cancer and the misfolding was to its of function tumor development. We further the protein secondary structure using the tool and the functional of point mutations of p53 protein and the of it by a heatmap using as shown in Figure for its potential and higher of cases due to the same In order to 100 molecules that are similar to the PubChem database was Following that, the compounds were examined ADMET analysis. compounds specific drug-likeliness characteristics were from the screened including PhiKan-083 as in Using molecular docking the binding of these compounds with TP53 was further Following ADMET each drug underwent a molecular docking study with the target TP53 activity of the was from the binding of the compounds. According to the study, two with the PubChem and higher binding compared to the reference molecule The TIMER 2.0 analysis of the TP53 expression pattern revealed overexpression of TP53 across all TCGA datasets. TP53 levels were further assessed using CPTAC samples from the UALCAN database. After with normal samples, it was also witnessed that the levels of TP53 protein were significantly elevated in various tumor GEPIA2 database, we further examined the expression pattern of TP53 in several malignancies. These results that TP53 is highly in several malignancies, including BRCA, luminal A, luminal and the it was witnessed that MF was significantly enriched in comparison to BP and through GO analysis. By employing KM-plotter from GEPIA2, the prognostic importance of TP53 was assessed across all cancer types. the study, reduced overall survival (OS) was linked with TP53 expression in the ACC, BRCA, KIRP, LAML, LGG, LIHC, PRAD, SARC, THCA, and TP53 mRNA levels were to worse relapse-free survival (RFS) in LGG, UCS, and BRCA, followed by LAML, SARC, ACC, KIRP, LIHC, PRAD, and THCA as the link between TP53 mRNA levels and RFS. These investigations demonstrated the significance of TP53 in cancer prognosis, it as a promising target for treating various malignancies. UALCAN database, we analyzed the expression pattern of p53 in breast cancer. is the most aggressive of breast cancer, study revealed that among all P53 was in and it was most in the major associated with p53 misfolding is due to its point mutation we examined the sequence of P53 using database to the of the status of It was that protein misfolding to the of function potential of P53 protein. We further the protein secondary structure by exploring the web-based PredictProtein tool and examined the functional of point mutations of p53 protein and its by a heatmap using In order to analyze the 100 molecules that are similar to the PubChem database was Following this, the same compounds were analyzed through ADMET analysis. The top compounds specific drug-likeliness characteristics were from the screened including PhiKan-083 by using the molecular docking the binding of these compounds with TP53 was the we to explore the expression of TP53 in its therapeutic prognostic and the impact of overexpression on overall and relapse-free survival in a range of cancers. We the TP53 expression profiles across all TCGA using the TIMER 2.0 database. When TP53 was compared to normal samples for study of differential it was shown that malignancies such BRCA, and elevated TP53 According to this study, TP53 is a major in a number of making it a TP53 overexpression was shown to be caused by gene alteration and TCGA analysis was used to evaluate this examining the correlation between mRNA expression and survival demonstrated a significant association with many malignancies with elevated hazard study a correlation between high TP53 mRNA levels and poor OS in ACC, BRCA, KIRP, LAML, LGG, LIHC, PRAD, SARC, THCA, and free survival (RFS) has been associated with higher TP53 mRNA levels in KIRP, LIHC, and we the impact of point mutations on p53 protein misfolding using database. The of genetic alteration a role in of of P53 protein. we examined the potential role of a P53 stabilizing and its analogues in breast cancer. We screened 100 analogues to PhiKan-083 and examined them for their drug-likeliness Among those compounds were selected for their drug-likeliness and further investigated molecular docking We two novel compounds and analogues to PhiKan-083 that may be further for their therapeutic potential by P53 misfolding not only for breast cancer but for other as

breast cancerBRCA1BRCA2metastatic breast cancer
مراجعةوصول مفتوح202334استشهاد· Semantic Scholar

Implications of Early Diagnosis and Intervention in the Management of Neurodevelopmental Delay (NDD) in Children: A Systematic Review and Meta-Analysis

Cureus · مجلد 15 (5) · e38745-e38745

Neuro-developmental delay (NDD) is when a child's reflexes and nervous system are underdeveloped or immature at a given stage of child development. Neurodevelopmental delays account for delayed skill development surrounding speech, social, emotional, behavioral, motor, and cognitive delays. NDD might affect the child's psychological and physical well-being, resulting in chronic disease and disabilities throughout adulthood. This review sought to investigate the implication of early diagnosis and intervention of NDD in children. In this regard, this research opted for a systematic meta-analysis that used keywords and Boolean operators to search through main databases, including the Web of Science, JStor, PsychINFO, Science Direct, Cochrane, Scopus, and ASSIA. The result identified that telehealth interventions improved the management of NDD in children. Also, the Early Start Denver Model (ESDM) model was determined to improve the quality of life for NDD children. Another model was LEAP (Learning Experience and Alternative Program for Preschoolers and Their Parents) and Leap (Learning, engaging, and Playing), which improved behavioral, education, and social interventions in NDD children. The study identified that technology could revolutionize NDD interventions in children, possibly improving the quality of life. The parent-children relationship was shown to enhance the management of this condition; thus, it is recommended as one of the best ways to intervene in the management of NDD. Most importantly, the integration of machine learning algorithms and technology can create models; while this may not be significant in the treatment of childhood NDD but instead might be ideal in improving the quality of life for NDD children. Moreover, their social and communication skills along with academic achievements will improve. The study proposes further research in order to understand the different types of NDDs and their intervention strategies to help the researchers identify the most accurate models to improve the conditions and support the parents and guardians in the management.

neurodevelopmental delayearly diagnosisearly interventiontelehealth intervention
افتتاحيةوصول مفتوح202323استشهاد· Semantic Scholar

Future of Using Robotic and Artificial Intelligence in Implant Dentistry

Cureus · مجلد 15 (8) · e43209-e43209

The integration of robotic technology and artificial intelligence (AI) in implant dentistry has ushered in a new era of precision and efficiency. This abstract aims to understand the integration, implications, potential, and challenges of robotic technology and AI in implant dentistry. Robotic systems offer unparalleled accuracy in implant placement, reducing human error and improving treatment outcomes. AI algorithms analyze extensive patient data to assist in diagnosis, treatment planning, and implant design, optimizing the overall process. Successful case studies demonstrate improved implant survival rates and patient satisfaction. However, ethical considerations and the balance between human expertise and reliance on technology must be addressed. Ongoing research aims to enhance these technologies and integrate them with digital workflows. Collaboration and knowledge sharing among practitioners, researchers, and industry experts are essential to drive progress and ensure responsible implementation. The future of implant dentistry lies in harnessing the potential of robotics and AI while upholding the highest standards of patient care and ethical practice.

artificial intelligencedental implant surgeryimplant planningimplant design
مقالوصول مفتوح202317استشهاد· Semantic Scholar

Comparative Analysis of Supervised Machine and Deep Learning Algorithms for Kyphosis Disease Detection

Applied Sciences · مجلد 13 (8) · 5012-5012

Although Kyphosis, an excessive forward rounding of the upper back, can occur at any age, adolescence is the most common time for Kyphosis. Surgery is frequently performed on Kyphosis patients; however, the condition may persist after the operation. The tricky part is figuring out, based on the patient’s traits, if the Kyphosis condition will continue after the treatment. There have been numerous models employed in the past to predict the Kyphosis disease, including Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Deep Neural Network (DNN), and others. Unfortunately, the precision was overestimated. Based on the dataset received from Kaggle, we investigated how to predict Kyphosis disorders more accurately by using these models with Hyperparameter tuning. While the calculations were being performed, certain variables were modified. The accuracy was increased by optimizing the fit parameters based on Hyperparameter tuning. Accuracy, recall or sensitivity, specificity, precision, balanced accuracy score, F1 score, and AUC-ROC score of all models, including the Hyperparameter tuning, were compared. Overall, the Hyperparameter-tuned DNN models excelled over the other models. The DNN models’ accuracy was 87.72% with 5-fold cross-validation and 87.64% with 10-fold cross-validation. It is advised that when a patient has a clinical procedure, the DNN model be trained to detect and foresee Kyphosis disease. Medical experts can use this study’s findings to correctly predict if a patient will still have Kyphosis after surgery. We propose that deep learning should be adopted and utilized as a crucial and necessary tool throughout the broad range of resolving biological queries.

kyphosisdeep neural networkhyperparameter optimizationsupervised learning
مقالوصول مغلق202314استشهاد· Semantic Scholar

Discerning of isatin-based monoamine oxidase (MAO) inhibitors for neurodegenerative disorders by exploiting 2D, 3D-QSAR modelling and molecular dynamics simulation

Journal of Biomolecular Structure and Dynamics · مجلد 42 (5) · 2328-2340

Almost a billion people worldwide suffer from neurological disorders, which pose public health challenges. An important enzyme that is well-known for many neurodegenerative illnesses is monoamine oxidase (MAO). Although several promising drugs for the treatment of MAO inhibition have recently been examined, it is still necessary to identify the precise structural requirements for robust efficacy. Atom-based, field-based, and GA-MLR (genetic algorithm multiple linear regression) models were created for this investigation. All of the models have strong statistical (R2 and Q2) foundations because of both internal and external validation. Our dataset’s molecule has a higher docking score than safinamide, a well-known and co-crystallized MAO-B inhibitor, as we also noticed. Using the SwissSimilarity platform, we further inquired which of our docked molecules would be the best for screening. We chose ZINC000016952895 as the screen molecule with the best binding docking score (XP score = −13.3613). Finally, the 100 ns for the ZINC000016952895-MAO-B complex in our MD investigations is stable. For compounds that we hit, also anticipate ADME properties. Our research revealed that the successful compound ZINC000016952895 might pave the way for the future development of MAO inhibitors for the treatment of neurological disease.Communicated by Ramaswamy H. Sarma

isatin derivativesmonoamine oxidase inhibitorsmonoamine oxidase Bneurodegenerative diseases
مقالوصول مفتوح202311استشهاد· Semantic Scholar

RETRACTED ARTICLE: Multi-stage biomedical feature selection extraction algorithm for cancer detection

SN Applied Sciences · مجلد 5 (5)

Abstract Cancer is a significant cause of death worldwide. Early cancer detection is greatly aided by machine learning and artificial intelligence (AI) to gene microarray data sets (microarray data). Despite this, there is a significant discrepancy between the number of gene features in the microarray data set and the number of samples. Because of this, it is crucial to identify markers for gene array data. Existing feature selection algorithms, however, generally use long-standing, are limited to single-condition feature selection and rarely take feature extraction into account. This work proposes a Multi-stage algorithm for Biomedical Deep Feature Selection (MBDFS) to address this issue. In the first, three feature selection techniques are combined for thorough feature selection, and feature subsets are obtained; in the second, an unsupervised neural network is used to create the best representation of the feature subset to enhance final classification accuracy. Using a variety of metrics, including a comparison of classification results before and after feature selection and the performance of alternative feature selection methods, we evaluate MBDFS's efficacy. The experiments demonstrate that although MBDFS uses fewer features, classification accuracy is either unchanged or enhanced.

cancer detectiongene microarray datafeature selectionfeature extraction
مقالوصول مفتوح20239استشهاد· Semantic Scholar

Rectal Cancer Prediction and Performance Based on Intelligent Variational Autoencoders Machine Using Deep Learning on CDAS Dataset

Journal of Artificial Intelligence and Technology

A pathological complete response to neoadjuvant chemoradiotherapy offers patients with rectal cancer that has advanced locally the highest chance of survival. However, there isn't yet a valid prediction model available. An efficient feature extraction technique is also required to increase a prediction model's precision. CDAS (cancer data access system) program is a great place to look for cancer along with images or biospecimens. In this study, we look at data from the CDAS system, specifically Bowel cancer (colorectal cancer) datasets. This study suggested a survival prediction method for rectal cancer. In addition, determines which deep learning algorithm works best by comparing their performance in terms of prediction accuracy. The initial job that leads to correct findings is corpus cleansing. Moving forward, the data pre-processing activity will be performed, which will comprise "exploratory data analysis and pruning and normalization or experimental study of data, which is required to obtain data features to design the model for cancer detection at an early stage." Aside from that, the data corpus is separated into two sub-corpora: training data and test data, which will be utilized to assess the correctness of the constructed model. This study will compare our auto-encoder accuracy to that of other deep learning algorithms, such as ANN, CNN, and RBM, before implementing the suggested methodology and displaying the model's accuracy graphically after the suggested new methodology or algorithm for patients with rectal cancer. Various criteria, including true positive rate, ROC curve, and accuracy scores, are used in the experiments to determine the model's high accuracy. In the end, we determine the accuracy score for each model. The outcomes of the simulation demonstrated that rectal cancer patients may be estimated using prediction models. It is shown that variational deep encoders have excellent accuracy of 94% in this cancer prediction and 95% for ROC curve regions. The findings demonstrate that automated prediction algorithms are capable of properly estimating rectal cancer patients’ chances of survival. The best results, with 95% accuracy, were generated by deep autoencoders.

rectal cancersurvival predictionvariational autoencoderpathological complete response
مقالوصول مفتوح20239استشهاد

Building an Acute Ischemic Stroke Identification Model Using a Deep Learning Technique

Journal of Disability Research · مجلد 2 (1)

Acute ischemic stroke (AIS) is a leading cause of mortality and disability. Over the past several decades, researchers proposed multiple techniques to enhance the effectiveness of AIS diagnosis. Magnetic resonance imaging (MRI) and computed tomography (CT) are widely used for assessing and treating AIS. In recent years, healthcare centers have applied the deep learning–based technique to support physicians in identifying diseases at earlier stages. Recently, researchers have employed convolutional neural network (CNN)-based image classifiers to detect diseases using complex images. However, the models demand high computation resources for generating a reasonable outcome. Thus, this study intends to build a fine-tuned CNN model for identifying AIS from MRI and CT images. The proposed framework contains three phases: image enhancement, feature extraction, and fine-tuned detection model. Initially, the researcher applies an image colorization technique using generative adversarial networks. You only look once V7 is used to extract the images’ features. In the second phase, the authors employed the Aquila optimization algorithm for tuning the hyperparameters of the Residual Network with Split attention (ResNest) model. To evaluate the performance of the ResNest model, the authors utilized two benchmark datasets of brain MRI and CT images. The MRI datasets contain 1021 healthy and 955 unhealthy images, whereas the CT datasets comprise 1551 healthy and 950 unhealthy images. The findings reveal that the ResNest model outperforms the recent approaches. The model achieves an average accuracy and F 1 score of 98.25 and 97.275, and 98.65 and 98.25, for the MRI and CT datasets, respectively. In addition, the ResNest model obtained a confidence interval score of [97.84-98.13] and [97.91-98.52] for the MRI and CT datasets, respectively. The study uniquely develops a lightweight application through a compelling data preprocessing and feature extraction technique. In addition, the fine-tuned ResNest model achieves a superior outcome with limited resources. Healthcare centers can implement this lightweight model for diagnosing AIS patients.

acute ischemic strokestroke detectionbrain MRIbrain CT
مقالمفتوح (مستودع)20238استشهاد· Semantic Scholar

The prediction of sleep quality using wearable-assisted smart health monitoring systems based on statistical data

Journal of King Saud University - Science · مجلد 35 (9) · 102927-102927

The technology, which plays a significant role in our lives, has made it possible for many of the appliances and gadgets we use on a daily basis to be monitored and controlled remotely. Health and fitness data is collected by wearable devices attached to patients' bodies. A number of parties could benefit from this technology, including doctors, insurers, and health providers. This technology, including smartwatches, smart ring, smart cloth wristbands, and GPS shoes, is frequently used for fitness and wellness since it allows users to track their day-to-day health. Devices that compute the sleep characteristics by storing sleep movements fall within the category of wearables worn on the wrist. In order to lead a healthy lifestyle, sleep is crucial. Inadequate sleep can harm one's physical, mental, and emotional well-being and increase the risk of developing a number of ailments, including stress, heart disease, high blood pressure, insulin resistance, and other conditions. Deep learning (DL) models have recently been used to forecast sleep-quality based on wearables information from the awake hours. Deep learning has been demonstrated to be capable of predicting sleep efficiency based on wearable data obtained during awake periods. In this regard, this study creates a novel deep learning model for wearables-enabled smart health monitoring system (DLM-WESHMS) for the prediction of sleep quality. The wearables are initially able to collect data linked to sleep-activity using the described DLM-WESHMS approach. The data is then put through pre-processing to create a standard format. Using the DLM-WESHMS, sleep quality is predicted using the deep belief network (DBN) model. The DBN model uses the auto-encoders algorithm (AEA) to predict popularity, which improves the accuracy of its predictions of sleep quality. The experimental outcomes of the DLM-WESHMS approach are investigated using several metrics. The DLM-WESHMS model performs significantly better than other models, according to a thorough comparison analysis.

sleep quality predictionwearable devicessmart health monitoringdeep belief network
مقالوصول مفتوح20237استشهاد· Semantic Scholar

Modified Meta Heuristic BAT with ML Classifiers for Detection of Autism Spectrum Disorder

Biomolecules · مجلد 14 (1) · 48-48

ASD (autism spectrum disorder) is a complex developmental and neurological disorder that impacts the social life of the affected person by disturbing their capability for interaction and communication. As it is a behavioural disorder, early treatment will improve the quality of life of ASD patients. Traditional screening is carried out with behavioural assessment through trained physicians, which is expensive and time-consuming. To resolve the issue, several conventional methods strive to achieve an effective ASD identification system, but are limited by handling large data sets, accuracy, and speed. Therefore, the proposed identification system employed the MBA (modified bat) algorithm based on ANN (artificial neural networks), modified ANN (modified artificial neural networks), DT (decision tree), and KNN (k-nearest neighbours) for the classification of ASD in children and adolescents. A BA (bat algorithm) is utilised for the automatic zooming capability, which improves the system’s efficacy by excellently finding the solutions in the identification system. Conversely, BA is effective in the identification, it still has certain drawbacks like speed, accuracy, and falls into local extremum. Therefore, the proposed identification system modifies the BA optimisation with random perturbation of trends and optimal orientation. The dataset utilised in the respective model is the Q-chat-10 dataset. This dataset contains data of four stages of age groups such as toddlers, children, adolescents, and adults. To analyse the quality of the dataset, dataset evaluation mechanism, such as the Chi-Squared Statistic and p-value, are used in the respective research. The evaluation signifies the relation of the dataset with respect to the proposed model. Further, the performance of the proposed detection system is examined with certain performance metrics to calculate its efficiency. The outcome revealed that the modified ANN classifier model attained an accuracy of 1.00, ensuring improved performance when compared with other state-of-the-art methods. Thus, the proposed model was intended to assist physicians and researchers in enhancing the diagnosis of ASD to improve the standard of life of ASD patients.

autism spectrum disorderASD detectionmodified bat algorithmmetaheuristic optimization
مقالمفتوح (مستودع)20234استشهاد· Semantic Scholar

3D QSAR study on substituted 1, 2, 4 triazole derivatives as anticancer agents by kNN MFA approach

Saudi Pharmaceutical Journal · مجلد 31 (12) · 101836-101836

Background and objectives: Researchers have recently focused on the biological and synthetic effects of 1, 2, and 4-triazole fused heterocyclic molecules because they have tremendous medicinal value. The objective of the present study was to carry out the 3D QSAR evaluation on the substituted 1,2, and 4 triazole derivatives for anticancer potential using k-Nearest Neighbor-Molecular Field Analysis (kNN-MFA) method. Methods: Using the molecular design suite, a three-dimensional quantitative structure-activity relationship (3D-QSAR) analysis was undertaken on a series of 4-amino-5-(pyridin3yl)-4H-1, 2, and 4-triazole-3-thiol anticancer drugs (Vlife MDS). This study used a genetic algorithm and a manual selection approach on 20 substituted 1, 2, and 4-triazole derivatives. Based on the genetic algorithm (GA), the 3D-QSAR model was generated. Statistical significance and predictive capacity were evaluated using internal and external validation. Results: The most significant model has a correlation coefficient of 0.9334 (squared correlation coefficient r2 = 0.8713), showing that biological activity and descriptors have a strong relationship. The model exhibited internal predictivity of 74.45 percent (q2 = 0.2129), external predictivity of 81.09 percent (pred r2 = 0.8417), and the smallest error term for the predictive correlation coefficient (pred r2se = 0.1255). The model revealed steric (S 1047--0.0780--0.0451S 927) and electrostatic (E 1002) data points that contribute remarkably to anticancer activity. A molecular field study demonstrates a link between the structural features of substituted triazole derivatives and their activities. Conclusion: The good-to-moderate anticancer potential of compounds confirms the significant pharmacological role of 1,2,4-triazole derivatives. These results could lead to the identification of potential chemical compounds with optimal anticancer activity and minimal side effects.

1,2,4-triazole derivativesanticancer agents3D-QSARgenetic algorithm
مقالوصول مفتوح202238استشهاد· Semantic Scholar

Intelligent Deep-Learning-Enabled Decision-Making Medical System for Pancreatic Tumor Classification on CT Images

Healthcare · مجلد 10 (4) · 677-677

Decision-making medical systems (DMS) refer to the design of decision techniques in the healthcare sector. They involve a procedure of employing ideas and decisions related to certain processes such as data acquisition, processing, judgment, and conclusion. Pancreatic cancer is a lethal type of cancer, and its prediction is ineffective with current techniques. Automated detection and classification of pancreatic tumors can be provided by the computer-aided diagnosis (CAD) model using radiological images such as computed tomography (CT) and magnetic resonance imaging (MRI). The recently developed machine learning (ML) and deep learning (DL) models can be utilized for the automated and timely detection of pancreatic cancer. In light of this, this article introduces an intelligent deep-learning-enabled decision-making medical system for pancreatic tumor classification (IDLDMS-PTC) using CT images. The major intention of the IDLDMS-PTC technique is to examine the CT images for the existence of pancreatic tumors. The IDLDMS-PTC model derives an emperor penguin optimizer (EPO) with multilevel thresholding (EPO-MLT) technique for pancreatic tumor segmentation. Additionally, the MobileNet model is applied as a feature extractor with optimal auto encoder (AE) for pancreatic tumor classification. In order to optimally adjust the weight and bias values of the AE technique, the multileader optimization (MLO) technique is utilized. The design of the EPO algorithm for optimal threshold selection and the MLO algorithm for parameter tuning shows the novelty. A wide range of simulations was executed on benchmark datasets, and the outcomes reported the promising performance of the IDLDMS-PTC model on the existing methods.

CT imagescomputer-aided diagnosisEmperor Penguin Optimizermultilevel thresholding
مقالوصول مفتوح202227استشهاد· Semantic Scholar

Chaotic Sparrow Search Algorithm with Deep Transfer Learning Enabled Breast Cancer Classification on Histopathological Images

Cancers · مجلد 14 (11) · 2770-2770

Breast cancer is the major cause behind the death of women worldwide and is responsible for several deaths each year. Even though there are several means to identify breast cancer, histopathological diagnosis is now considered the gold standard in the diagnosis of cancer. However, the difficulty of histopathological image and the rapid rise in workload render this process time-consuming, and the outcomes might be subjected to pathologists' subjectivity. Hence, the development of a precise and automatic histopathological image analysis method is essential for the field. Recently, the deep learning method for breast cancer pathological image classification has made significant progress, which has become mainstream in this field. This study introduces a novel chaotic sparrow search algorithm with a deep transfer learning-enabled breast cancer classification (CSSADTL-BCC) model on histopathological images. The presented CSSADTL-BCC model mainly focused on the recognition and classification of breast cancer. To accomplish this, the CSSADTL-BCC model primarily applies the Gaussian filtering (GF) approach to eradicate the occurrence of noise. In addition, a MixNet-based feature extraction model is employed to generate a useful set of feature vectors. Moreover, a stacked gated recurrent unit (SGRU) classification approach is exploited to allot class labels. Furthermore, CSSA is applied to optimally modify the hyperparameters involved in the SGRU model. None of the earlier works have utilized the hyperparameter-tuned SGRU model for breast cancer classification on HIs. The design of the CSSA for optimal hyperparameter tuning of the SGRU model demonstrates the novelty of the work. The performance validation of the CSSADTL-BCC model is tested by a benchmark dataset, and the results reported the superior execution of the CSSADTL-BCC model over recent state-of-the-art approaches.

breast cancer classificationhistopathological imagestransfer learninghyperparameter optimization