A new collaborative research program has been established between the Centre for Drug Discovery Innovation (DDI) and Sydney Precision Data Science Centre to advance decision-making in drug discovery enabled by data science. With established strengths in both data science and drug discovery the collaboration is ideally placed to explore how these new context-specific questions from drug discovery will inform methodological developments in data science. Four supplementary scholarships have been made available to support this program with funding from the Faculty of Science and the DDI.
Supplementary scholarships are available for eligible HDR students to work on the projects listed below. Details of the scholarship criteria, terms and conditions, and application form is available on the scholarship’s website.
Project 1
Identifying novel cell-specific drug targets for Alzheimer’s disease
Chief investigator: Associate Professor Eleanor Drummond
This project aims to accelerate the identification of new drug targets for Alzheimer’s disease by capitalising on recent high-powered single cell transcriptomics datasets of human Alzheimer’s disease brain tissue. We will perform a combined analysis of these high-powered datasets to identify the most important changes in Alzheimer’s disease brain tissue and use these data to develop a new online tool that defines which brain cell types express these changes. We believe our results will enhance understanding of Alzheimer’s disease biology in human brain tissue, identify new drug targets, and accelerate interpretation of independent omics data.
Data challenge
The challenge is integrating and analysing multiple single-cell RNA-seq studies associated with Alzheimer’s disease (AD), which involve high-dimensional data with high sparsity. This project will focus on developing AD-specific cell type annotation strategies using data science models.
Project 2
Unmask the mYXtery of sex bias in disease and therapy
Chief Investigator: Duan Ni
Female and male differ in disease development and treatment response. For example, females are more prone to develop multiple sclerosis while males have higher incidence of tuberculosis. The underlying causes for such biases seem to be multifaceted, involving differences in lifestyles, hormones and X chromosome. Surprisingly, the role of Y chromosome and its genes, another common difference between female and male, remains elusive.
Here, leveraging unprecedented global health and single cell multi-omic data, we aim to systematically profile the sex bias landscapes in diseases and treatments and delineate the underlying mechanistic roles of Y chromosome in physiology, pathology and therapy.
Data challenge
The challenge is to integrate and analyze global health and single-cell RNA-seq studies which involve high-dimensional data with high sparsity. This project will have a specific focus in understanding the association between sex bias and ChrY status in different immune cell
Project 3
Identifying the key drivers of motor neuron disease
Chief Investigator: Associate Professor Rachel Tan
Amyotrophic lateral sclerosis is an aggressive neurodegenerative disease that occurs sporadically in over 90% of patients. The last few years has seen a growing body of evidence demonstrating the involvement of multiple divergent pathways that converge to a clinically indistinguishable presentation, underscoring the need to identify key drivers of disease and develop accessible biomarkers that can reliably detect these disease-specific changes in the brain. The present study addresses this by studying biospecimens collected from a large cohort of patients with ALS to identify novel therapeutic targets and biomarkers that can improve targeted intervention in ALS.
Data challenge
The challenge is to independently analyse and integrate large detailed datasets, which include multi-omics, histopathological and clinical data that have been collected
from deeply phenotyped patient samples to identify patterns and clinically impactful measures.
Project 4
Developing an ALT-cancer targeted therapy: Transforming peptides into small molecules using generative diffusion models
Chief Investigator: Associate Professor Yu Heng Lau
This project aims to discover a small-molecule inhibitor of the RMI1/2-FANCM protein-protein interaction with future ambitions to develop the first ALT-cancer targeted therapeutic. A robust pipeline for discovering small-molecule inhibitors of protein-protein interactions is needed. This project targets ALT-positive cancers by transforming cyclic peptides that block the FANCM-RMI1/2 interaction into small molecules using a structure-based stepwise transformation, integrating generative geometric deep-learning, similarity screening, and molecular dynamics. This generalisable data-driven pipeline streamlines the synthesis and testing of candidates, accelerating the speed and efficiency of small molecule drug discovery.
Data challenge
Developing a systematic GenAI-enabled approach to transform peptides into small molecules would represent a significant and generalisable innovation, advancing drug discovery. A key data analysis challenge lies in filtering the most ‘drug-like’ small molecule inhibitors from a pool of AI-generated small molecules. The multidisciplinary nature of the project demands robust integration of computational and experimental methods to ensure reproducible and biologically-relevant outcomes.