Research interests:

• Plant Epigenetics
• Machine Learning to accelerate biological discovery

My research is focussed on non-coding RNA-mediated gene regulatory mechanisms and how this contributes towards physiological adaption. I use a wide variety of approaches that include in planta experiments, deep sequencing and bioinformatic tools to identify novel epigenetic components and their physiological context. See details below for epigenetic related projects that I lead or am involved in.

A parallel research focus of mine is the use of Machine Learning models to analyse complex biological data to reveal new hidden layers of information. A particular focus area is facilitating the ‘upskilling’ of biological data in accordance with the FAIR data principles, so it is analytics ready and can be used (and re-used) for answering multiple research questions.

Research projects:

1. Epitranscriptome modifications (In association with A/Prof. Iain Searle, School of Biological Sciences, UA): Molecular functions of post-transcriptional RNA modifications, 5-methylcytosine (m5C) in regulating gene expression and responses to the environment. 
2. RNA transport and signalling: Investigate the role of cell-to-cell and systemic transport of RNA transcripts in response to developmental and environmental cues using grafting techniques in combination with high-throughput RNA sequencing. Identifying molecular signatures of mobile RNA transcripts in plants using bioinformatic approaches. GitHub repository: https://github.com/CharlotteSai/DiRT
3. Machine Learning based Text Analytics: Natural Language Processing and Machine Learning models for automatic extraction of protein features from unstructured biomedical text. GitHub repository: https://github.com/RhysMenezes/find-a-protein
4. Understanding the drivers of crop yield variability: Yields of major crops in Australia are often below their water-limited potential. Genotype x Environment x Management complexity results in crop growth with spatial and temporal variability. The GRDC funded project will use Machine Learning-based methods to discover underlying relationships between climate, crop and soil variables that cause variable crop growth and yields to inform paddock management decisions.