2005 - 2009 Doctor of Philosophy, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore
2001 - 2005 Bachelor of Mechanical Engineering, Faculty of Mechanical Engineering, Universiti Teknologi Malaysia
RESEARCH, TEACHING, or OTHER INTERESTS
Mechanical Engineering, Multidisciplinary, Modeling and Simulation, Numerical Analysis
Amogel: a multi-omics classification framework using associative graph neural networks with prior knowledge for biomarker identification Chia Yan Tan, Huey Fang Ong, Chern Hong Lim, Mei Sze Tan, Ean Hin Ooi, et al. BMC Bioinformatics, 2025 The advent of high-throughput sequencing technologies, such as DNA microarray and DNA sequencing, has enabled effective analysis of cancer subtypes and targeted treatment. Furthermore, numerous studies have highlighted the capability of graph neural networks (GNN) to model complex biological systems and capture non-linear interactions in high-throughput data. GNN has proven to be useful in leveraging multiple types of omics data, including prior biological knowledge from various sources, such as transcriptomics, genomics, proteomics, and metabolomics, to improve cancer classification. However, current works do not fully utilize the non-linear learning potential of GNN and lack of the integration ability to analyse high-throughput multi-omics data simultaneously with prior biological knowledge. Nevertheless, relying on limited prior knowledge in generating gene graphs might lead to less accurate classification due to undiscovered significant gene-gene interactions, which may require expert intervention and can be time-consuming. Hence, this study proposes a graph classification model called associative multi-omics graph embedding learning (AMOGEL) to effectively integrate multi-omics datasets and prior knowledge through GNN coupled with association rule mining (ARM). AMOGEL employs an early fusion technique using ARM to mine intra-omics and inter-omics relationships, forming a multi-omics synthetic information graph before the model training. Moreover, AMOGEL introduces multi-dimensional edges, with multi-omics gene associations or edges as the main contributors and prior knowledge edges as auxiliary contributors. Additionally, it uses a gene ranking technique based on attention scores, considering the relationships between neighbouring genes. Several experiments were performed on BRCA and KIPAN cancer subtypes to demonstrate the integration of multi-omics datasets (miRNA, mRNA, and DNA methylation) with prior biological knowledge of protein-protein interactions, KEGG pathways and Gene Ontology. The experimental results showed that the AMOGEL outperformed the current state-of-the-art models in terms of classification accuracy, F1 score and AUC score. The findings of this study represent a crucial step forward in advancing the effective integration of multi-omics data and prior knowledge to improve cancer subtype classification.
Lattice Boltzmann-based microchannel concentration mixing with surface roughness-mediated flow dynamics Lit Kean Chai, Chin Vern Yeoh, Ean Hin Ooi, Ji Jinn Foo Physics of Fluids, 2025 Efficient mixing at the microscales is essential for optimizing mass transfer and reaction rates in various microfluidic applications, underscoring the significance of comprehending and manipulating surface roughness to improve mixing performance. Surface morphology in microchannels is inherently influenced by fabrication and post-treatment. This study investigates the effects of three-dimensional (3D) Gaussian-generated random roughness on species homogenization. Nine roughness profiles, varying in (a) relative roughness (ε = 0.4%, 0.7%, 1.0%) and (b) correlation length (k = 10%, 20%, 30%), form the channel base at ReDh = 100. Using the lattice Boltzmann method, we examine the mixing efficiency (MI), velocity statistics, and spatial frequency. Higher ε enhances near-wall mixing, with a 5.7% MI increase for ε = 1.0% compared to 0.4%. Conversely, shorter correlation lengths create more rugged surfaces, increasing interfacial area for diffusion and thereby elevating the near-wall MI by 8.4% when k decreases from 30% to 10%. Spatial frequency analysis confirms that higher spatial frequencies (shorter spatial wavelengths, lower k) improve near-surface mixing. However, smoother surfaces (higher k) reduce global flow resistance, enhance central advective effects, and improve overall outlet mixing. Thus, for practical applications emphasizing outlet performance, lower ε and higher k yield superior results. This study not only advances our understanding of surface roughness parameters for fluid mixing in rough-walled microchannels and highlights the significance of spatial frequency characteristics but also offers valuable insights into optimizing mixing processes in diverse applications.
Augmentation of piezoelectric thin-film flapping velocimetry turbulence strength detection via machine learning Ted Sian Lee, Ean Hin Ooi, Wei Sea Chang, Ji Jinn Foo Physics of Fluids, 2025 Qualitatively evaluating the fundamental mechanical characteristics of square-fractal-grid (SFG)-generated turbulent flow using piezoelectric thin-film flapping velocimetry (PTFV) is rather time-consuming. More importantly, its sensitivity in detecting high-frequency, fine-scale turbulent fluctuations is constrained by high-speed camera specifications. To reduce dependency on high-speed imaging in future PTFV implementations, regression models are trained with supervised machine learning to determine the correlation between piezoelectric-generated voltage V and the corresponding local equivalent flow velocity fluctuation. Using V and thin-film tip deflection δ data as predictors and responses, respectively, Trilayered Neural Network (TNN) emerges as the best-performing model compared to linear regression, regression trees, support vector machines, Gaussian process regression, and ensembles of trees. TNN models trained on data from the (i) lower quarter, (ii) bottom left corner, and (iii) central opening of the SFG-grid provide accurate predictions of insert-induced centerline streamwise and cross-sectional equivalent lateral turbulence intensity and root mean square-δ, with average errors not exceeding 5%. The output predicted from the V response, which considers small-scale turbulence fluctuations across the entire thin-film surface, better expresses the equivalent lateral integral length scale (38% smaller) and turbulence forcing (270% greater), particularly at the bottom left corner of SFG where small-scale eddies are significant. Furthermore, the TNN model effectively captures the occasional extensive excitation forces from large-scale turbulent eddies, resulting in a more balanced force distribution. In short, this study paves the path for comprehensive and expedited flow dynamics characterization and turbulence forcing detection via PTFV, with potential deployment in high Reynolds number flows generated by various grid configurations.
Anisotropic Heat Transfer in a Fibrous Membrane with Hierarchically Assembled 2D Materials Yu Du, Fangzheng Zhen, Siyuan Ding, Yueni Zhong, Peixuan Li, et al. ACS Applied Materials and Interfaces, 2024 Effective heat redistribution in specific directions is vital for advanced thermal management, significantly enhancing device performance by optimizing spatial heat configurations. We have designed and fabricated a hierarchical fibrous membrane that enables precise heat directing. By integrating hierarchical structure design with the anisotropic thermal conductivity of two-dimensional (2D) materials, we developed a fibrous membrane for anisotropic heat transfer. Such a structure is fabricated by aligning a 1D structured fiber in the 2D plane to achieve anisotropy at each scale level. The fiber units, where 2D nanosheets circumferentially and axially aligned, achieved a high axial thermal conductivity of 16.8 W·m-1·K-1 and advanced heat directing ability, confirmed by characterizations and simulations. The assembled membrane demonstrated an exceptional tensile strength (365 MPa) and high thermal conductivity (10.5 W·m-1·K-1) along the fiber axis. Our membranes are seen as a refined model for thermal management materials, combining the benefits of heat spreaders and thermal interface materials, thus being proficient in directing heat along programmed pathways. A practical wireless charging cooling demonstration illustrated this. Our methodology also proved versatile with different 2D fillers and various geometries. This research presents a method to achieve precise heat directing at the material's level, facilitating the systematic design of thermal management in electronics.
