A5035846381- MicroRNA in disease regulation
- Cancer-related molecular mechanisms research
- Bayesian Modeling and Causal Inference
- RNA Research and Splicing
- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- RNA modifications and cancer
- Advanced Causal Inference Techniques
- Explainable Artificial Intelligence (XAI)
- Statistical Methods and Inference
- Data Mining Algorithms and Applications
- Genomics and Chromatin Dynamics
- Histone Deacetylase Inhibitors Research
- Data Quality and Management
- Molecular Biology Techniques and Applications
- Gene Regulatory Network Analysis
- Advanced biosensing and bioanalysis techniques
- Pancreatic and Hepatic Oncology Research
- RNA Interference and Gene Delivery
- Genetic Associations and Epidemiology
- Retirement, Disability, and Employment
- Disability Education and Employment
- Ethics and Social Impacts of AI
- Adversarial Robustness in Machine Learning
- Single-cell and spatial transcriptomics
University of South Australia
2016-2025
Centre for Cancer Biology
2013-2025
Jeonbuk National University
2025
Chonbuk National University Hospital
2025
The University of Sydney
2025
Hanoi University of Pharmacy
2025
University of California, Los Angeles
2023
Tufts University
2009-2022
UCLA Health
2019
Great Lakes Institute of Management
2015
Abstract Summary The development of new drugs is costly, time consuming and often accompanied with safety issues. Drug repurposing can avoid the expensive lengthy process drug by finding uses for already approved drugs. In order to repurpose effectively, it useful know which proteins are targeted Computational models that estimate interaction strength drug–target pairs have potential expedite repurposing. Several been proposed this task. However, these represent as strings, not a natural way...
Many bioinformatics methods have been proposed for reducing the complexity of large gene or protein networks into relevant subnetworks modules. Yet, how such compare to each other in terms their ability identify disease-relevant modules different types network remains poorly understood. We launched 'Disease Module Identification DREAM Challenge', an open competition comprehensively assess module identification across diverse protein-protein interaction, signaling, co-expression, homology and...
Identifying molecular cancer subtypes from multi-omics data is an important step in the personalized medicine. We introduce CancerSubtypes, R package for identifying using data, including gene expression, miRNA expression and DNA methylation data. CancerSubtypes integrates four main computational methods which are highly cited subtype identification provides a standardized framework pre-processing, feature selection, result follow-up analyses, results computing, biology validation...
Discovering causal relationships from observational data is a crucial problem and it has applications in many research areas. The PC algorithm the state-of-the-art constraint based method for discovery. However, runtime of algorithm, worst-case, exponential to number nodes (variables), thus inefficient when being applied high dimensional data, e.g., gene expression datasets. On another note, advancement computer hardware last decade resulted widespread availability multi-core personal...
Causal feature selection has attracted much attention in recent years, as the causal features selected imply mechanism related to class attribute, leading more reliable prediction models built using them. Currently there is a need of developing multi-source methods, since many applications data for studying same problem been collected from various sources, such multiple gene expression datasets obtained different experiments causes disease. However, state-of-the-art methods generally tackle...
Abstract With the widespread use of learning analytics (LA), ethical concerns about fairness have been raised. Research shows that LA models may be biased against students certain demographic subgroups. Although has gained significant attention in broader machine (ML) community last decade, it is only recently paid to LA. Furthermore, decision on which unfairness mitigation algorithm or metric a particular context remains largely unknown. On this premise, we performed comparative evaluation...
Abstract Motivation: microRNAs (miRNAs) are known to play an essential role in the post-transcriptional gene regulation plants and animals. Currently, several computational approaches have been developed with a shared aim elucidate miRNA–mRNA regulatory relationships. Although these existing methods discover statistical relationships, such as correlations associations between miRNAs mRNAs at data level, relationships not necessarily real causal that would ultimately provide useful insights...
miRBase is the primary repository for published miRNA sequence and annotation data, serves as "go-to" place research. However, definition of miRNAs have been changed significantly across different versions miRBase. The changes cause inconsistency in related data between databases articles at times. Several tools developed purposes querying converting information versions, but none them individually can provide comprehensive about users will need to use a number their analyses.We introduce...
Background Identifying cancer subtypes is an important component of the personalised medicine framework. An increasing number computational methods have been developed to identify subtypes. However, existing rarely use information from gene regulatory networks facilitate subtype identification. It widely accepted that play crucial roles in understanding mechanisms diseases. Different are likely caused by different mechanisms. Therefore, there great opportunities for developing can utilise...
MicroRNAs (miRNAs) are small non-coding RNAs with the length of ∼22 nucleotides. miRNAs involved in many biological processes including cancers. Recent studies show that long (lncRNAs) emerging as miRNA sponges, playing important roles cancer physiology and development. Despite accumulating appreciation importance lncRNAs, study their complex functions is still its preliminary stage. Based on hypothesis competing endogenous (ceRNAs), several computational methods have been proposed for...
Abstract The development of new drugs is costly, time consuming, and often accompanied with safety issues. Drug repurposing can avoid the expensive lengthy process drug by finding uses for already approved drugs. In order to repurpose effectively, it useful know which proteins are targeted Computational models that estimate interaction strength drug--target pairs have potential expedite repurposing. Several been proposed this task. However, these represent as strings, not a natural way...
Discovering causal relationships is the ultimate goal of many scientific explorations. Causal can be identified with controlled experiments, but such experiments are often very expensive and sometimes impossible to conduct. On other hand, collection observational data has increased dramatically in recent decades. Therefore it desirable find from directly. Significant progress been made field discovering using Bayesian Network (CBN) theory. The applications CBNs, however, greatly limited due...
Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible conduct RCTs. Therefore observational studies based on passively observed data widely accepted as an alternative However, studies, prior knowledge required generate hypotheses about cause-effect relationships be tested, hence they can only applied problems with available domain and a handful of variables. In practice, sets high dimensionality, which leaves out...
Transcription factors (TFs) and microRNAs (miRNAs) are primary metazoan gene regulators. Regulatory mechanisms of the two main regulators great interest to biologists may provide insights into causes diseases. However, interplay between miRNAs TFs in a regulatory network still remains unearthed. Currently, it is very difficult study that involve both biological lab. Even at data level, involving miRNAs, genes will be too complicated achieve. Previous research has been mostly directed...
Uncovering causal relationships in data is a major objective of analytics. Currently, there need for scalable and automated methods relationship exploration data. Classification are fast they could be practical substitutes finding signals However, classification not designed discovery method may find false miss the true ones. In this paper, we develop decision tree (CDT) where nodes have interpretations. Our follows well-established inference framework makes use classic statistical test to...
Abstract Motivation Cancer is not a single disease and involves different subtypes characterized by sets of molecules. Patients with cancer often react heterogeneously towards the same treatment. Currently, clinical diagnoses rather than molecular profiles are used to determine most suitable A level approach will allow more precise informed way for making treatment decisions, leading better survival chance less suffering patients. Although many computational methods have been proposed...
A microRNA (miRNA) sponge is an RNA molecule with multiple tandem miRNA response elements that can sequester miRNAs from their target mRNAs. Despite growing appreciation of the importance sponges, our knowledge complex functions remains limited. Moreover, there still a lack research tools help researchers to quickly compare proposed methods other methods, apply existing new datasets, or select appropriate for assisting in subsequent experimental design.To fill gap, we present R/Bioconductor...