Dr Fatemeh Vafaee

Professional Experience:

• 2021 - Present: Deputy Director, UNSW Data Science Hub (uDASH), UNSW 
• 2020 - Present: Theme Leader, Health Data Science, uDASH, UNSW
• 2017 - Present: Senior Lecturer, School of BABS, UNSW Sydney
• 2013 - 2017: Research Fellow, Charles Perkins Centre, School of Mathematics and Statistics, University of Sydney
• 2011 - 2013: Postdoctoral Research Associate, University of Toronto, University Health Network and Ontario Cancer Institute
• 2007 - 2011: PhD Computer Science, Artificial Intelligence (AI), the University of Illinois in Chicago

Brief Bio and Research Contribution:

Dr Vafaee is the Deputy Director of UNSW Data Science Hub (uDASH) since Feb 2021 and a Senior Lecturer in Computational Biomedicine and Bioinformatics (2017 - Present). She received her PhD in Artificial Intelligence from the School of Computer Science at the University of Illinois at Chicago, USA (2011) followed by 2 multidisciplinary postdoctoral fellowships on computational biomedicine at the University of Toronto, University Health Network (2011 – 2012), and at the University of Sydney, Charles Perkins Centre (2013 – 2017). 

Dr Vafaee has launched (2017) and leads AI-enhanced Biomedicine Laboratory at UNSW (www.VafaeeLab.com) which currently holds 10 members collaboratively working on deploying advanced AI techniques to address a variety of biomedical pressing problems. Relying on multidisciplinary expertise and cross-faculty collaborations, Dr Vafaee and her team are developing advanced machine-learning methods and deep-learning models that leverage large omics data to find hidden structures within them, account for complex interactions among the measurements, integrate heterogeneous data and make accurate predictions in different biomedical applications ranging from single-cell sequencing analysis and multi-omics biomarker discovery to disease functional genomics and drug repositioning.

Dr Vafaee has a strong track record of multidisciplinary research leadership and industrial engagement. Her research has been attracted >$10.5M for over 12 research projects and industrial partnership grants including prestigious schemes of Cooperative Research Centre Project (CRC-P, 2019), Medical Research Future Fund (MRFF, 2020, 2021), ARC Discovery (2021), and NHMRC Development (2021). She has co-authored over 40 publications (68% first/corresponding author) in prestigious venues—e.g., Briefings in Bioinformatics, Nature Methods, npj Systems Biology & Applications, Molecular Neurobiology, Precision Oncology and Nature Communications—demonstrating her research leadership and substantive contribution in methodological changes. Dr Vafaee's research has been featured in the Faculty of Science Capability Statement in Health Science and UNSW Capability Statement in Biomedical Research.

Governance and Executive memberships:

• Member of Executive Committee, School of BABS, UNSW (2018 - 2020) 
• Bioinformatics Coordinator, School of BABS, UNSW (2018 - Present) 
• Member of Executive Committee in Women in Research Network (WiRN), UNSW (2018 - 2021)
• Member of National Computational Merit Allocation Committee, NCI, Australia (2019 - 2022)

Editorial Activities:

• Associate Editor of Artificial Intelligence Review (IF: 8.139)
• Editorial Board of Cancers (IF: 6.639) 
• Advisory Board of Patterns,Cell Press
• Associate Editor of PLoS One (IF: 3.240)

Areas of Research Projects:

1) Minimally invasive biomarker discovery for personalised medicine and precision therapy: Recent advances in high-throughput technologies have provided a wealth of genomics, transcriptomics, and proteomics data to decipher disease mechanisms in a holistic and integrative manner. Such a plethora of -omics data has opened new avenues for translational medical research and has particularly facilitated the discovery of novel biomarkers for complex diseases such as cancers. My research lab – in close collaboration with experimentalists, clinicians, and oncologists – is adopting an innovative multi-disciplinary approach to tackle one of the biggest challenges of personalised cancer medicine, that is to identify robust and reproducible biomarkers in a minimally invasive way.  We are integrating multiple data sources, network and temporal information using advanced machine learning approaches to better understand the molecular complexity underpinning pathogenesis and to identify novel, precise and reproducible blood-based biomarkers for disease early detection, diagnosis, prognosis and drug responses paving the way for personalised medicine.

Examples of publications: (Ebrahimkhani et al, Molecular Neurobiology, 2020), (Colvin et al. Cancer Science, 2020), (Vafaee et al, Systems Biology and Applications, 2018),  (Ebrahimkhani et al, Precision Oncology, 2018)

2) Single-cell sequencing data analysis and integration: Cellular heterogeneity is one of the main clinical drivers of the current inefficiency in treating cancer and other complex diseases as molecular-based prescriptions or personalised medicine have often relied on bulk pro/filing of cell populations, masking intercellular variations that are functionally and clinically important. In recent years, however, there has been an increasing effort in shifting the focus from bulk to single-cell profiling. Single-cell sequencing will have a major global impact on the precision medicine through detecting rare disease-associated cells and identifying cell-type-specific biomarkers and therapeutic targets. Single cells, however, make ‘big data’, provoking substantial analytical challenges to decipher underlying biological and clinical insights. Hence, there is an emerging demand for scalable yet accurate analysis pipelines for rapidly increasing single-cell sequencing data and my research program is focused (during the last 18 months) to contribute to this significant field.

Examples of publications: (Koch et al, Briefings in Bioinformatics, 2021), (Zandavi and Vafaee, NeurIPS 2021, under-review)

3) Computational drug repositioning and network pharmacology: Repositioning existing drugs for new indications is an innovative drug development strategy offering the possibility of reduced cost, time and risk as several phases of de-novo drug discovery can be bypassed for repositioning candidates. Biopharmaceutical companies have recognised advantages of repositioning, and investment in the area is dramatically increasing. With the rapid advancement of high-throughput technologies and the explosion of various biological and medical data, computational drug repositioning has become an increasingly powerful approach to systematically identify potential repositioning candidates. My lab is the only group at UNSW, and one of the few across Australia, advancing the field of computational drug repositioning. We are developing computational tools and databases which integrate massive amounts of biological, pharmacological and biomedical information related to compounds into advanced machine learning or network-based models to predict accurate repositioning candidates.

Examples of publications: (Azad et al, Briefings in Bioinformatics, 2020), (Azad et al, Patterns, 2021)