A5029631797- Gene expression and cancer classification
- Genetic Associations and Epidemiology
- Genetic Mapping and Diversity in Plants and Animals
- Genetic and phenotypic traits in livestock
- Bioinformatics and Genomic Networks
- Influenza Virus Research Studies
- Genetics and Neurodevelopmental Disorders
- Blind Source Separation Techniques
- EEG and Brain-Computer Interfaces
- interferon and immune responses
- Genomics and Rare Diseases
- Machine Learning in Bioinformatics
- vaccines and immunoinformatics approaches
- SARS-CoV-2 and COVID-19 Research
- Neural dynamics and brain function
- Advanced Proteomics Techniques and Applications
- Congenital heart defects research
- Molecular Biology Techniques and Applications
- MicroRNA in disease regulation
- AI in cancer detection
- ECG Monitoring and Analysis
- Renal cell carcinoma treatment
- Genomic variations and chromosomal abnormalities
- COVID-19 Clinical Research Studies
- Epigenetics and DNA Methylation
Chinese University of Hong Kong
2022-2025
City University of Hong Kong, Shenzhen Research Institute
2022-2025
University of Hong Kong
2022-2025
Jilin University
2018-2020
PRG S&Tech (South Korea)
2019
Abstract Motivation Deep neural network (DNN) algorithms were utilized in predicting various biomedical phenotypes recently, and demonstrated very good prediction performances without selecting features. This study proposed a hypothesis that the DNN models may be further improved by feature selection algorithms. Results A comprehensive comparative was carried out evaluating 11 on three conventional algorithms, i.e. convolution (CNN), deep belief (DBN) recurrent (RNN), recent DNNs,...
The neurological disorder epilepsy causes substantial problems to the patients with uncontrolled seizures or even sudden deaths. Accurate detection and prediction of epileptic will significantly improve life quality patients. Various feature extraction algorithms were proposed describe EEG signals in frequency time domains. Both invasive intracranial non-invasive scalp have been screened for seizure patterns. This study extracted a comprehensive list 24 types from found 170 out 2794 features...
Influenza virus continuously evolves to escape human adaptive immunity and generates seasonal epidemics. Therefore, influenza vaccine strains need be updated annually for the upcoming flu season ensure effectiveness. We develop a computational approach, beth-1, forecast evolution select representative vaccine. The method involves modelling site-wise mutation fitness. Informed by genome population sero-positivity, we calibrate transition time of mutations project fitness landscape future...
Aim: Lung adenocarcinoma (LUAD) and lung squamous-cell carcinoma (LUSC) are two major subtypes of cancer constitute about 70% all the cases. The patient's lifespan living quality will be significantly improved if they diagnosed at an early stage adequately treated. Methods & results: This study comprehensively screened proteomic dataset both LUAD LUSC, proposed classification models for progression stages LUSC with accuracies 86.51 89.47%, respectively. Discussion conclusion: A comparative...
Aim: Breast cancer histologic grade (HG) is a well-established prognostic factor. This study aimed to select methylomic biomarkers predict breast HGs. Materials & methods: The proposed algorithm BioDog firstly used correlation bias reduction strategy eliminate redundant features. Then incremental feature selection was applied find the features with high HG prediction accuracy. sequential backward elimination employed further refine biomarkers. A comparison existing algorithms were conducted....
Aim: The two genders are different ranging from the molecular to phenotypic levels. But most studies did not use this important information. We hypothesize that integration of gender information may improve overall prediction accuracy. Materials & methods: A comprehensive comparative study was carried out test hypothesis. classification stages I + II versus III IV clear cell renal carcinoma samples formulated as an example. Results conclusion: In cases, female-specific model significantly...
Breast cancer is one of the most frequently occurring female types and represents a major cause death among women worldwide. heterogeneous in both molecular characteristics clinical outcomes for its different subtypes. High-throughput technologies facilitated fast accumulations multiple Omic data patients. These sources posed computational challenge efficient integrated multi-Omic analysis. The existing studies usually investigated differential representation or machine learning problems...
Introduction:The coronavirus disease 2019 (COVID-19) pandemic has caused extensive disruption of public health worldwide.There were reports COVID-19 patients having multiple complications.This study investigated from a genetic perspective. Methods:We conducted RNA sequencing (RNA-Seq) analysis respiratory tract samples 24 with COVID-19.Eight receiving mechanical ventilation or extracorporeal membrane oxygenation regarded as severe cases; the remaining 16 non-severe cases.After quality...
Abstract Multi-population cohorts offer unprecedented opportunities for profiling disease risk in large samples, however, heterogeneous effects underlying complex traits across populations make integrative prediction challenging. In this study, we propose a novel Bayesian probability framework, the Prism Vote (PV), to construct predictions genetic data. The PV views trait of an individual as composite from subpopulations, which stratum-specific predictors can be formed data more homogeneous...
<title>Abstract</title> In the context of Critical Assessment Genome Interpretation, 6th edition (CAGI6), Genetics Neurodevelopmental Disorders Lab in Padua proposed a new ID-challenge to give opportunity developing computational methods for predicting patient’s phenotype and causal variants. Eight research teams 30 models had access details real genetic data, based on sequences 74 genes (VCF format) 415 pediatric patients affected by (NDDs). NDDs are clinically genetically heterogeneous...
Abstract A predictive evolutionary model was developed to forecast representative influenza viral strains and select vaccine for upcoming epidemic seasons. Influenza virus continuously evolves escape human adaptive immunity generates seasonal epidemics. computational approach beth-1 that models site-wise mutation dynamics demonstrated remarkable matching of predicted the circulating viruses in subsequent seasons A(H1N1)pdm09 A(H3N2) both retrospective prospective validations. The method...
Multi-population cohorts offer unprecedented opportunities for profiling disease risk in large samples, however, heterogeneous effects underlying complex traits across populations make integrative prediction challenging. In this study, we propose a novel Bayesian probability framework, the Prism Vote (PV), to construct predictions genetic data. The PV views trait of an individual as composite from subpopulations, which stratum-specific predictors can be formed data more homogeneous...