Abstract: Development of new biomaterials with improved surface physicochemical properties and functionalities are at the forefront of tissue engineering research and material science. The applications of the so called materiomics span not only for health industries but also energy field. Biomolecules such as peptides and proteins are continuously under research and development to create new nanomaterials that enhance the efficiency of photovoltaic (such as solar cells) and other electronic devices. Similarly, biomaterials tailored towards a particular biological response, such as resistance to bacterial attachment, biofilm formation or encouragement of stem cell differentiation to a particular lineage are actively being studied. The challenge remains on the ability to create high-throughput and automated platform that is validated to screen and assay hundreds to thousands of materials (usually polymers – synthetic or naturally-derived) simultaneously to produce large amount of data for regressional analysis. The resulting model should have a good reproducibility (acceptable level of errors / variance) to ‘predict’ the performance of other materials (not used for ‘training’ the model) whether it is existing materials, to-be-synthesized materials or virtual materials (i.e. only encoded with numerical descriptors). The model produced using a machine learning algorithm with training dataset derived from only a handful (tens to up to a hundred) of selected materials to produce new materials in situ / in silico using the principle of combinatorial chemistry (polymer microarray). With improved computational power of computer to analyze large amount of numerical data (that describe physical, biological and chemical properties of materials) and the advancement in the field of artificial intelligence (particularly machine learning, robotics technology and 2D/3D image vision analysis), combined with our cumulative knowledge of the materials that are safe-to-use and cost-effective, researchers and scientists now have a toolkit for potentially discovering new biomaterials with desired properties and functionalities.
Bio: Dr Yusvana studied Biotechnology at University of Nottingham (UK) and University of New South Wales (Australia) for his B.Sc and M.Sc respectively. He then worked in Bioengineering field for his PhD research studies in Edinburgh (UK) for the construction of artificial skin tissue using electric field (dielectrophoresis). During his studies, he developed a program using LabVIEW Vision Development module that simultaneously analyze image of 2D/3D cells aggregate microarray for high throughput cells analysis platform. After nearly 2 years of postdoctoral works experience involving microfluidic in nanofabrication facility, University of Glasgow (UK), he continued his career teaching Biotechnology and Biologics Manufacturing at a university in Malaysia including Analytical Method Validation (for ISO 17025 Certification). With more than 5 years of teaching experience, he received Google Certified Educator Level 2 certification for using Google tools in classroom. Dr. Yusvana continued building his technical skills with knowledge in Internet of Things (IoT) technology and Machine Learning using Microsoft Azure ML Studio platform for potential applications in health care and agriculture industries.