Construction and Validation of a Reliable Disulfidptosis-Related LncRNAs Signature of the Subtype, Prognostic, and Immune Landscape in Colon Cancer

International Journal of Molecular Sciences, Journal Year: 2023, Volume and Issue: 24(16), P. 12915 - 12915

Published: Aug. 18, 2023

Disulfidptosis, a novel form of regulated cell death (RCD) associated with metabolism, represents promising intervention target in cancer therapy. While abnormal lncRNA expression is colon development, the prognostic potential and biological characteristics disulfidptosis-related lncRNAs (DRLs) remain unclear. Consequently, research aimed to discover indication DRLs significant implications, investigate their possible molecular role advancement cancer. Here, we acquired RNA-seq data, pertinent clinical genomic mutations adenocarcinoma (COAD) from TCGA database, then were determined through Pearson correlation analysis. A total 434 COAD patients divided three subgroups clustering analysis based on DRLs. By utilizing univariate Cox regression, least absolute shrinkage selection operator (LASSO) algorithm, multivariate regression analysis, ultimately created model consisting four (AC007728.3, AP003555.1, ATP2B1.AS1, NSMCE1.DT), an external database was used validate features risk model. According Kaplan-Meier curve low-risk group exhibited considerably superior survival time comparison those high-risk group. Enrichment revealed association between metabolic processes genes that differentially expressed high- groups. Additionally, differences tumor immune microenvironment landscape observed, specifically pertaining cells, function, checkpoints. High-risk low likelihood evasion, as indicated by Tumor Immune Dysfunction Exclusion (TIDE) Patients who exhibit both high Mutational Burden (TMB) experience amount for survival, whereas belonging low-TMB category demonstrate most favorable prognosis. In addition, groups 4-DRLs signature displayed distinct drug sensitivities. Finally, confirmed levels rt-qPCR tissue samples lines. Taken together, first 4-DRLs-based proposed may serve hopeful instrument forecasting prognosis, landscape, therapeutic responses patients, thereby facilitating optimal decision-making.

Language: Английский

---

A SYSTEMATIC LITERATURE REVIEW: RECURSIVE FEATURE ELIMINATION ALGORITHMS

JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), Journal Year: 2024, Volume and Issue: 9(2), P. 196 - 207

Published: Feb. 1, 2024

Recursive feature elimination (RFE) is a selection algorithm that works by gradually eliminating unimportant features. RFE has become popular method for in various machine learning applications, such as classification and prediction. However, there no systematic literature review (SLR) discusses recursive algorithms. This article conducts SLR on The goal to provide an overview of the current state algorithm. uses IEEE Xplore, ScienceDirect, Springer, Scopus (publish publish) databases from 2018 2023. received 76 relevant papers with 49% standard RFEs, 43% strategy 8% modified RFEs. Research using continues increase every year, used simultaneously or comparison based filter approach, namely Pearson correlation, embedded random forest. most widely algorithms are support vector machines forests, 19.5% 16.7%, respectively. Strategy can be referred hybrid Based papers, it found broadly divided into two categories: after other methods methods. Modification done modifying flow RFE. modification process before calculating smallest weight criteria criteria. Calculating this still challenge at time obtain optimal results.

Language: Английский

---

Refining breast cancer biomarker discovery and drug targeting through an advanced data-driven approach

BMC Bioinformatics, Journal Year: 2024, Volume and Issue: 25(1)

Published: Jan. 22, 2024

Abstract Breast cancer remains a major public health challenge worldwide. The identification of accurate biomarkers is critical for the early detection and effective treatment breast cancer. This study utilizes an integrative machine learning approach to analyze gene expression data superior biomarker drug target discovery. Gene datasets, obtained from GEO database, were merged post-preprocessing. From dataset, differential analysis between normal samples revealed 164 differentially expressed genes. Meanwhile, separate dataset 350 Additionally, BGWO_SA_Ens algorithm, integrating binary grey wolf optimization simulated annealing with ensemble classifier, was employed on datasets identify predictive genes including TOP2A, AKR1C3, EZH2, MMP1, EDNRB, S100B, SPP1. over 10,000 genes, identified 1404 in (F1 score: 0.981, PR-AUC: 0.998, ROC-AUC: 0.995) 1710 GSE45827 0.965, 0.986, 0.972). intersection DEGs selected 35 that consistently significant across methods. Enrichment analyses uncovered involvement these key pathways such as AMPK, Adipocytokine, PPAR signaling. Protein-protein interaction network highlighted subnetworks central nodes. Finally, drug-gene investigation connections anticancer drugs. Collectively, workflow robust signature cancer, illuminated their biological roles, interactions therapeutic associations, underscored potential computational approaches discovery precision oncology.

Language: Английский

---

Hybrid XGBoost model with hyperparameter tuning for prediction of liver disease with better accuracy

World Journal of Gastroenterology, Journal Year: 2022, Volume and Issue: 28(46), P. 6551 - 6563

Published: Dec. 6, 2022

Liver disease indicates any pathology that can harm or destroy the liver prevent it from normal functioning. The global community has recently witnessed an increase in mortality rate due to disease. This could be attributed many factors, among which are human habits, awareness issues, poor healthcare, and late detection. To curb growing threats disease, early detection is critical help reduce risks improve treatment outcome. Emerging technologies such as machine learning, shown this study, deployed assist enhancing its prediction treatment.To present a more efficient system for timely of using hybrid eXtreme Gradient Boosting model with hyperparameter tuning view detection, diagnosis, reduction associated disease.The dataset used study consisted 416 people problems 167 no history. data were collected state Andhra Pradesh, India, through https://www.kaggle.com/datasets/uciml/indian-liver-patient-records. population was divided into two sets depending on patient. binary information recorded attribute "is_patient".The results indicated chi-square automated interaction classification regression trees models achieved accuracy level 71.36% 73.24%, respectively, much better than conventional method. proposed solution would patients physicians tackling problem ensuring cases detected developing cirrhosis (scarring) enhance survival patients. showed potential learning health care, especially concerns monitoring.This contributed knowledge application efforts toward combating However, relevant authorities have invest research other maximize their potential.

Language: Английский

---

Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer

British Journal of Cancer, Journal Year: 2023, Volume and Issue: 128(12), P. 2141 - 2149

Published: March 4, 2023

Language: Английский

---

Identification of Novel Diagnostic and Prognostic Gene Signature Biomarkers for Breast Cancer Using Artificial Intelligence and Machine Learning Assisted Transcriptomics Analysis

Cancers, Journal Year: 2023, Volume and Issue: 15(12), P. 3237 - 3237

Published: June 18, 2023

Background: Breast cancer (BC) is one of the most common female cancers. Clinical and histopathological information collectively used for diagnosis, but often not precise. We applied machine learning (ML) methods to identify valuable gene signature model based on differentially expressed genes (DEGs) BC diagnosis prognosis. Methods: A cohort 701 samples from 11 GEO microarray datasets was identification significant DEGs. Seven ML methods, including RFECV-LR, RFECV-SVM, LR-L1, SVC-L1, RF, Extra-Trees were reduction construction a diagnostic classification. Kaplan–Meier survival analysis performed prognostic construction. The potential biomarkers confirmed via qRT-PCR validated by another set GBDT, XGBoost, AdaBoost, KNN, MLP. Results: identified 355 DEGs predicted BC-associated pathways, kinetochore metaphase signaling, PTEN, senescence, phagosome-formation pathways. hub 28 novel nine-gene (COL10A, S100P, ADAMTS5, WISP1, COMP, CXCL10, LYVE1, COL11A1, INHBA) using stringent filter conditions. Similarly, consisting eight-gene signatures (CCNE2, NUSAP1, TPX2, ITM2A, LIFR, TNXA, ZBTB16) also disease-free overall analysis. Gene methods. Finally, results expression in BC. Conclusion: approach helped construct models profiling showed excellent prognosis, respectively.

Language: Английский

---

Multiparametric MRI model to predict molecular subtypes of breast cancer using Shapley additive explanations interpretability analysis

Diagnostic and Interventional Imaging, Journal Year: 2024, Volume and Issue: 105(5), P. 191 - 205

Published: Jan. 24, 2024

Language: Английский

---

Unraveling Biomarker Signatures in Triple-Negative Breast Cancer: A Systematic Review for Targeted Approaches

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(5), P. 2559 - 2559

Published: Feb. 22, 2024

Triple-negative breast cancer (TNBC) is one of the most aggressive subtypes cancer, marked by poor outcomes and dismal prognosis. Due to absence targetable receptors, chemotherapy still represents main therapeutic option. Therefore, current research now focusing on understanding specific molecular pathways implicated in TNBC, order identify novel biomarker signatures develop targeted therapies able improve its clinical management. With aim identifying features characterizing elucidating mechanisms which these biomarkers are tumor development progression, assessing impact cancerous cells following their inhibition or modulation, we conducted a literature search from earliest works December 2023 PubMed, Scopus, Web Of Science. A total 146 studies were selected. The results obtained demonstrated that TNBC characterized heterogeneous profile. Several have proven not only be characteristic but also serve as potential effective targets, holding promise new era personalized treatments pre-clinical findings emerged our systematic review set stage for further investigation forthcoming trials.

Language: Английский

---

MiVitals– xed Reality Interface for Monitoring: A HoloLens based prototype for healthcare practices

Computational and Structural Biotechnology Journal, Journal Year: 2024, Volume and Issue: 24, P. 160 - 175

Published: March 1, 2024

In this paper, we introduce MiVitals—a Mixed Reality (MR) system designed for healthcare professionals to monitor patients in wards or clinics. We detail the design, development, and evaluation of MiVitals, which integrates real-time vital signs from a biosensor-equipped wearable, VitalitiTM. The generates holographic visualizations, allowing interact with medical charts information panels holographically. These visualizations display signs, trends, other significant physiological signals, early warning scores comprehensive manner. conducted User Interface/User Experience (UI/UX) study focusing on novel interfaces that intuitively present information. This approach brings traditional bedside life real environment through non-contact 3D images, supporting rapid decision-making, pattern anomaly detection, enhancing clinicians' performance wards. Additionally, findings usability involving doctors practitioners assess MiVitals' efficacy. System Usability Scale yielded score 84, indicating MiVitals has high usability.

Language: Английский

---

Machine learning analysis of lung squamous cell carcinoma gene expression datasets reveals novel prognostic signatures

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 165, P. 107430 - 107430

Published: Aug. 30, 2023

Language: Английский

---