https://ir.unisa.ac.za/handle/10500/2917 Mon, 11 May 2026 17:19:52 GMT 2026-05-11T17:19:52Z https://ir.unisa.ac.za/handle/10500/32428 Deep learning for spatial multi-omics: predicting cardiomyocyte differentiation efficiency at single-cell resolution Kgabeng, Tumo Cardiovascular diseases remain the leading cause of global mortality, with limited regenerative capacity of adult cardiac tissue presenting significant therapeutic challenges. The primary cause of death worldwide is still cardiovascular diseases, and treating these conditions is extremely difficult due to the adult heart tissue's limited capacity for regeneration. Cardiomyocytes derived from human induced pluripotent stem cells (hiPSC CMs) present promising potential for cardiac regenerative medicine; however, existing differentiation protocols are highly inconsistent and do not have accurate predictive evaluation techniques. By integrating the analysis of temporal gene expression data and spatial transcriptomics, this study developed a novel hybrid deep learning architecture that combines Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) to predict the outcomes of cardiomyocyte differentiation. RNN components analysed temporal gene expression trajectories across 800 samples and 10 time points, while GNN components processed spatial transcriptomics data from 752 tissue spots to capture spatial relationships. Three fusion strategies - concatenation, attention-based, and ensemble approaches - were meticulously evaluated. With an accuracy of 96.67%, the ensemble fusion approach outperformed the state-of-the-art computational approaches by a significant margin (+13.47% compared to the top GNN approaches and +6.97% compared to specialised biological models). Keywords: Cardiomyocyte differentiation; Spatial transcriptomics, Spatial multi-omics; Single-cell biology; Deep learning; Graph Neural Networks; Recurrent Neural Networks; Stem cells; Artificial Intelligence; Cardiac biology Fri, 06 Mar 2026 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/32428 2026-03-06T00:00:00Z https://ir.unisa.ac.za/handle/10500/32332 Estimating brittleness indexes from mechanical and petrographic characteristics of Norite Molomo, Selaki Grace Norite is a coarse-grained plutonic rock that has been relatively understudied in terms of its mechanical and petrographic properties. This study investigates the brittleness of norite within the Eastern Limb of the Bushveld Igneous Complex (BIC), South Africa. However, there is a scarcity of studies that quantitatively link its petrographic characteristics to establish brittleness indices. The primary aim was to estimate brittleness indexes based on both mechanical and petrographic properties of norite, which is a significant rock type commonly found in the hanging walls of platinum mines. Given the recurring safety incidents, especially falls of ground and rock bursts in underground mining, understanding the brittleness of norite is essential for enhancing geotechnical designs and safety measures. Samples were collected from a 10-meter exposure along Mototolo Road in the Critical Zone of the Eastern Bushveld Complex, near the Anglo-American Platinum Mototolo Mine. Mechanical analysis involved laboratory testing, which includes uniaxial compressive strength (UCS), tensile strength, Young's modulus, and Poisson’s ratio, supported by numerical simulations and multivariate regression models. The results indicate that norite exhibits high compressive strength and low ductility, with brittleness indexes effectively predicted using combinations of strength parameters. Mineralogical investigations were done using thin-section petrography to evaluate grain texture, contact nature, and mineral composition. It was observed that coarse and medium grain textures significantly influence brittleness, whereas grain contact type alone lacks predictive power. The main contribution of this work is the development of integrated predictive models that use both mechanical and mineralogical data. While the use of surface samples presents a limitation, their geological equivalence to underground norite supports the relevance of the findings for subsurface application. The findings enhance the understanding of the structural performance of norite and suggest practical recommendations for underground mine design. This research further contributes to improved and safer mining operations. Fri, 13 Feb 2026 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/32332 2026-02-13T00:00:00Z https://ir.unisa.ac.za/handle/10500/32116 Topology optimization of mining vehicle tyres Müller, Peter Tyres that are used on light duty mining vehicles (LDMV’s) are for commercial vehicles that have been designed for higher speeds and used predominantly on-highway tarred road surfaces. Substitute tyres that are more sustainable and meet the criteria for mining environments are not currently attainable for this vehicle class. The objective of this research was to develop a topologically optimal tyre fit for mining conditions. As such, a computer generated topologically optimised tyre that better conforms with the design parameters of a mining vehicle was analysed and proposed using classical mechanics through a model-based systems engineering approach. A commercial tyre with all the constituent geometries and dimensions was modelled using computer aided design (CAD). The inherent vehicle data of vehicle kinematics was used as data inputs and boundary conditions to a finite element model (FEM). The model was then algorithmically analysed and optimised with the embedded software program and tools. The main purpose of topologically optimising the tyre was to reduce driveline stresses and have greater vehicle payload capacity. A proof-of-concept tyre design was developed through this research by substituting currently used pneumatic and foam filled commercial tyres with a topologically optimised tyre generated via a FEA software. The mandate was that such a tyre must conform to the vehicle design parameters of the original equipment manufacturer. The results highlighted that changing the tyre topology would better protect the driveshaft. The obtained results indicated the possibility of meeting the metric requirements of having reduced stresses of driveline components. This included reducing the tyre inertia from 6.15 to 2.28 kg/m2, reducing its mass by approximately 70% and redistributing the stress on the tyre. Furthermore, it is shown that topologically optimizing a tyre can result in a tyre with a very high stiffness and subsequent low deformation (up to 90%) characteristics. These are desirable traits in mining applications. Sun, 01 Sep 2024 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/32116 2024-09-01T00:00:00Z https://ir.unisa.ac.za/handle/10500/32110 A system dynamics model to enhance on-time delivery of infrastructure projects within a power utility in South Africa Mashamba, Takalani Energy plays a fundamental role in sustainable development and poverty alleviation efforts. The energy sector is critical, looking at the economic growth perspective as it contributes about 3.2% of South Africa’s Gross Domestic Product. Due to economic growth in South Africa, the state-owned firm has witnessed increasing demand for power supply over the last 20 years. To alleviate the existing supply restriction, the electricity sector started implementing capital expansion build projects. The completion of capital expansion build projects has been delayed due to quality problems and cost overruns, which results in frequent power outages that limit overall economic activity and erode investor trust in the area. The primary motivation of this research was to develop a System Dynamics Model to enhance on-time delivery of infrastructure projects within the power utility in South Africa. The proposed study is aimed at developing a System Dynamics Model to inform policy and decision-makers in the energy sector in Mon, 01 Jan 2024 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/32110 2024-01-01T00:00:00Z