In this paper, a new approach based on Binary Black Hole Algorithm (BBHA) and Adaptive Boosting version Ml (AdaboostM1) is proposed for finding genes that can classify the group of cancers correctly. In this approach, BBHA is used to perform gene selection and AdaboostM1 with 10-fold cross validation is adopted as the classifier. Also, to find the relation between the biomarkers for biological point of view, decision tree algorithm (C4.5) is utilized. The proposed approach is tested on three benchmark microarrays. The experimental results show that our proposed method can select the most informative gene subsets by reducing the dimension of the data set and improve classification accuracy as compared to several recent studies.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2016.7591380 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Dual-Enzyme-Instructed Peptide Self-Assembly to Boost Immunogenic Cell Death by Coordinating Intracellular Calcium Overload and Chemotherapy.
ACS Nano
January 2025
Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation, The First Affiliated Hospital, Wenzhou Medical University, Wenzhou 325035, Zhejiang, P. R. China.
The concept of immunogenic cell death (ICD) induced by chemotherapy as a potential synergistic modality for cancer immunotherapy has been widely discussed. Unfortunately, most chemotherapeutic agents failed to dictate effective ICD responses due to their defects in inducing potent ICD signaling. Here, we report a dual-enzyme-instructed peptide self-assembly platform of (CPT-GFFpY-PLGVRK-Caps) that cooperatively utilizes camptothecin (CPT) and capsaicin (Caps) to promote ICD and engage systemic adaptive immunity for tumor rejection.
View Article and Find Full Text PDFAssociations between structural brain changes and blood neurofilament light chain protein in treatment-resistant schizophrenia.
Aust N Z J Psychiatry
January 2025
Melbourne Neuropsychiatry Centre, Department of Psychiatry, The University of Melbourne, Parkville, VIC, Australia.
Objective: Around 30% of people with schizophrenia are refractory to antipsychotic treatment (treatment-resistant schizophrenia). Abnormal structural neuroimaging findings, in particular volume and thickness reductions, are often described in schizophrenia. Novel biomarkers of active brain pathology such as neurofilament light chain protein are now expected to improve current understanding of psychiatric disorders, including schizophrenia.
View Article and Find Full Text PDFLiquid biopsy in organ damage: introduction of an innovative tool for assessing the complexity of blunt splenic injury.
Eur J Med Res
January 2025
Department of General, Visceral and Thoracic Surgery, German Armed Forces Central Hospital, Koblenz, Germany.
Liquid biomarkers are essential in trauma cases and critical care and offer valuable insights into the extent of injury, prognostic predictions, and treatment guidance. They can help assess the severity of organ damage (OD), assist in treatment decisions and forecast patient outcomes. Notably, small extracellular vesicles, particularly those involved in splenic trauma, have been overlooked.
View Article and Find Full Text PDFEvaluating the weight-adjusted waist index as a predictive tool for sarcopenia and mortality risk.
Eat Weight Disord
January 2025
Department of Gastrointestinal Surgery, The First Affiliated Hospital, Wenzhou Medical University, Nanbaixiang Street, Wenzhou, 325035, Zhejiang, China.
Purpose: The weight-adjusted waist index (WWI) is a novel anthropometric measure. WWI is linked to reduced muscle mass and strength; however, its efficacy for assessing sarcopenia and predicting adverse outcomes has yet to be validated. This study compared and examined the relationship between sarcopenia and WWI across different diagnostic criteria and aimed to evaluate its potential as a predictor of sarcopenia and all-cause mortality.
View Article and Find Full Text PDFClassification of non-TCGA cancer samples to TCGA molecular subtypes using compact feature sets.
Cancer Cell
December 2024
Department of Epigenetics, Van Andel Institute, Grand Rapids, MI 49503, USA. Electronic address:
Molecular subtypes, such as defined by The Cancer Genome Atlas (TCGA), delineate a cancer's underlying biology, bringing hope to inform a patient's prognosis and treatment plan. However, most approaches used in the discovery of subtypes are not suitable for assigning subtype labels to new cancer specimens from other studies or clinical trials. Here, we address this barrier by applying five different machine learning approaches to multi-omic data from 8,791 TCGA tumor samples comprising 106 subtypes from 26 different cancer cohorts to build models based upon small numbers of features that can classify new samples into previously defined TCGA molecular subtypes-a step toward molecular subtype application in the clinic.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!