A5082233800- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- IPv6, Mobility, Handover, Networks, Security
- Bayesian Modeling and Causal Inference
- Data Mining Algorithms and Applications
- Reinforcement Learning in Robotics
- Neural Networks and Applications
- Computational Drug Discovery Methods
- Fuzzy Logic and Control Systems
- AI-based Problem Solving and Planning
- Bioinformatics and Genomic Networks
- Distributed and Parallel Computing Systems
- RNA and protein synthesis mechanisms
- Genomics and Chromatin Dynamics
- Advanced Breast Cancer Therapies
- Mobile Agent-Based Network Management
- Advanced Multi-Objective Optimization Algorithms
- Machine Learning in Bioinformatics
- Cancer-related molecular mechanisms research
- Cloud Computing and Resource Management
- RNA Research and Splicing
- Cancer-related Molecular Pathways
- Genomics and Phylogenetic Studies
- Data Management and Algorithms
- RNA modifications and cancer
Chinese University of Hong Kong
2016-2025
Hong Kong Shue Yan University
2023-2025
Kunming Medical University
2024
University of Hong Kong
2002-2014
Applied Multilayers (United Kingdom)
2013
University of Cyprus
2013
Nokia (Finland)
2012
Wellcome Sanger Institute
2011
Prince of Wales Hospital
1988-2011
Cisco Systems (United States)
2001-2007
Crowd sourcing is evolving as a distributed problem-solving and business production model in recent years. In crowd paradigm, tasks are to networked people complete such that company's cost can be greatly reduced. 2003, Luis von Ahn his colleagues pioneered the concept of "human computation", which utilizes human abilities perform computation difficult for computers process. Later, term "crowdsourcing" was coined by Jeff Howe 2006. Since then, lot work has focused on different aspects...
Studies have shown that the accuracy of random forest (RF)-based scoring functions (SFs), such as RF-Score-v3, increases with more training samples, whereas classical SFs, X-Score, does not. Nevertheless, impact similarity between and test samples on this matter has not been studied in a systematic manner. It is therefore unclear how these SFs would perform when only trained protein-ligand complexes are highly dissimilar or similar to set. also whether based machine learning algorithms other...
Cellular neural networks (CNNs) have been successfully applied in many areas such as classification of patterns, image processing, associative memories, etc. Since they are inherently local nature, can be easily implemented very large scale integration. In the processing static images, CNNs without delay often whereas moving with found more suitable. This paper proposes a general model unbounded delay, which may potential applications motion related phenomena and studies global convergence...
The effect of low intensity pulsed ultrasound on human periosteal cells was investigated. Normal periosteum obtained to culture the cells. After characterization, cultures at Days 2 and 4 were treated with for 5, 10, 20 minutes respectively. Assessments done assess total number viable cells, cell proliferation, alkaline phosphatase activity, osteocalcin secretion, vascular endothelial growth factor expression, calcium nodule formation. With not as control, results showed that did affect It...
The authors present a comprehensive expert-system building tool, called System Z-II, that can deal with exact, fuzzy (or inexact), and combined reasoning, allowing normal terms to be freely mixed in the rules facts of an expert system. This fully implemented tool has been used build several systems fields student curriculum advisement, medical diagnosis, psychoanalysis, risk analysis. Z-II is rule-based system uses logic numbers for its inexact reasoning. It two basic concepts, fuzziness...
In crowdsourcing systems, tasks are distributed to networked people complete such that a company's production cost can be greatly reduced. Obviously, it is not efficient the amount of time for worker spent on selecting task comparable with working task, but monetary reward just small amount. The available history makes possible mine workers' preference and provide favorite recommendations. Our exploratory study survey results collected from Amazon Mechanical Turk (MTurk) shows histories...
Increasing evidence reveals that diverse non-coding RNAs (ncRNAs) play critically important roles in viral infection. Viruses can use ncRNAs to manipulate both cellular and gene expression establish a host environment conducive the completion of life cycle. Many also directly or indirectly influence replication even target virus genomes. ViRBase (http://www.rna-society.org/virbase) aims provide scientific community with resource for efficient browsing visualization virus-host...
Hepatocellular carcinoma (HCC) is one of the leading causes cancer-related deaths worldwide. Surgical resection and conventional chemotherapy radiotherapy ultimately fail due to tumor recurrence HCC's resistance. The development novel therapies against HCC thus urgently required. cyclin-dependent kinase (CDK) pathways are important well-established targets for cancer treatment. In particular, CDK2 a key factor regulating cell cycle G1 S transition hallmark cancers. this study, we utilized...
It has recently been claimed that the outstanding performance of machine-learning scoring functions (SFs) is exclusively due to presence training complexes with highly similar proteins those in test set. Here, we revisit this question using 24 similarity-based sets, a widely used set, and four SFs. Three these SFs employ machine learning instead classical linear regression approach fourth SF (X-Score which best set out 16 SFs). We have found random forest (RF)-based RF-Score-v3 outperforms...
Abstract The advances in single-cell RNA sequencing (scRNA-seq) technologies enable the characterization of transcriptomic profiles at cellular level and demonstrate great promise bulk sample analysis thereby offering opportunities to transfer gene signature from scRNA-seq data. However, expression signatures identified single cells are typically inapplicable RNA-seq data due profiling differences distinct technologies. Here, we propose pair-wise (scPAGE), a novel method develop pair...
We have developed a new approach to learning Bayesian network structures based on the minimum description length (MDL) principle and evolutionary programming. It employs MDL metric, which is founded information theory, integrates knowledge-guided genetic operator for optimization in search process.
Given the explosive growth of data collected from current business environment, mining can potentially discover new knowledge to improve managerial decision making. This paper proposes a novel approach that employs an evolutionary algorithm represented in Bayesian networks. The is applied successfully handle problem finding response models direct marketing data. Learning networks difficult problem. There are two different approaches network learning first one uses dependency analysis, while...
We aimed to investigate the characteristics of hepatitis B virus (HBV) genotype C subgroups in Hong Kong and their relationship with HBV other parts Asia.Full-genome nucleotide sequences 49 isolates from Chinese patients chronic were compared 69 12 non-genotype GenBank database. Phylogenetic analysis was performed define on basis >4% heterogeneity entire genome.HBV 80% belonged a subgroup predominantly found Southeast Asia (Vietnam, Thailand, Myanmar, southern China) designated as "Cs,"...
Visualization of protein-ligand complex plays an important role in elaborating interactions and aiding novel drug design. Most existing web visualizers either rely on slow software rendering, or lack virtual reality support. The vital feature macromolecular surface construction is also unavailable. We have developed iview, easy-to-use interactive WebGL visualizer complex. It exploits hardware acceleration rather than rendering. features three special effects settings, namely anaglyph,...
Normalization is essential to get rid of biases in microarray data for their accurate analysis. Existing normalization methods gene expression commonly assume a similar global pattern among samples being studied. However, scenarios shifts expressions are dominant cancers, making the assumption invalid. To alleviate problem, here we propose and develop novel strategy, Cross (CrossNorm), with unbalanced transcript levels samples. Conventional procedures, such as RMA LOESS, arbitrarily flatten...
Cyclin-dependent kinase 2 (CDK2) has been reported to be overexpressed in human colorectal cancer; it is responsible for the G1‑to‑S‑phase transition cell cycle and its deregulation a hallmark of cancer. The present study was first use idock, free open‑source protein‑ligand docking software developed by our group, identify potential CDK2 inhibitors from 4,311 US Food Drug Administration‑approved small molecular drugs with re‑purposing strategy. Among top compounds identified idock score,...
Extraction of meaningful information from large experimental data sets is a key element in bioinformatics research. One the challenges to identify genomic markers Hepatitis B Virus (HBV) that are associated with HCC (liver cancer) development by comparing complete sequences HBV among patients and those without HCC. In this study, mining framework, which includes molecular evolution analysis, clustering, feature selection, classifier learning, classification, introduced. Our research group...
Protein–DNA bindings between transcription factors (TFs) and factor binding sites (TFBSs) play an essential role in transcriptional regulation. Over the past decades, significant efforts have been made to study principles for protein–DNA bindings. However, it is considered that there are no simple one-to-one rules amino acids nucleotides. Many methods impose complicated features beyond sequence patterns. Protein-DNA formed from associated acid nucleotide pairs, which determine many...