Sydney Precision Data Science Centre

Sydney Data Science Insights

Edition 3, June 2024

Message from the Director - Professor Jean Yang

Dear Colleagues,

The first half 2024 got off to a great start with an ECR developmental workshop for our ECR members. The workshop was centred around developing strategies for deep discipline focus in the context of prevailing scientific trends and included brainstorming and skills development. The ECR committee did a great job of organising an agenda with the right balance of social activities and productive sessions.

It is a delight to announce many of our centre members have received awards and honours over the last six months. Congratulations to our students and researchers on their well-deserved achievements! All the details are in the news sections below.

We have welcomed a new research leader to our Centre, Dr Qiuzhuang Sun, who has a strong interest in bringing together operational research and data science for data-driven decision-making. I hope you enjoy learning more about our new researcher along with our featured method, MultiP, in this newsletter.

Best wishes,
Jean

Dr Qiuzhuang Sun

Researcher Spotlight: Dr Qiuzhuang Sun

In this newsletter we are spotlighting Dr Qiuzhung Sun, who joined our Centre this year.

What got you interested and excited about data science?

I began my PhD in operations research (OR) in 2015. At that time, OR and data science (DS) were largely separate fields. However, as AI technology advanced, we began to see many fascinating topics at the intersection of OR and DS. This led to me focus on data-driven decision-making, where I aimed to develop new methodologies that combine the strengths of both OR and DS.

What is keeping you busy at the moment?

I am currently working on a project that uses historical vital data of patients to make sequential decisions over time. One intriguing application is determining whether to initiate treatment for ICU patients to prevent potential sepsis based on early warning signals. I am developing a new data-driven optimisation tool to achieve this goal.

How long have you been working with the SPDS?

I have been attending SPDS group meetings since I joined the University of Sydney in January 2023. My work in OR has primarily focused on “macro” aspects, such as determining treatment plans and conducting survival analysis for patients. In contrast, lots of studies in the SPDS focus on “micro” aspects, like working with gene and protein data. I believe there are many exciting opportunities to formulate new optimisation problems within these “micro” studies.

What’s next for you at the SPDS?

I am particularly fascinated by the “multi-modalities” studies on omics data. I plan to delve deeper into these topics and collaborate with my colleagues to explore innovative data-driven optimisation problems in bioinformatics.

Discover Qiuzhuang’s research and publications via his online profile.

Feature method: MultiP

In this issue Andy Tran shares an overview of MultiP as our featured method.

In recent years, the medical field has seen rapid developments in biotechnologies, allowing the collection of biological data on a variety of “omics” platforms, at an increasingly scalable and affordable level. For example, the cost of whole exome sequencing for a single sample has dramatically declined over the last two decades from around $20 million (USD) in 2006 to around $1000 (USD) in 2018. This new access to a plethora of information is leading a revolution in precision medicine, by providing an insight into the biological mechanisms behind different diseases. Indeed, we already see modern omics data being used to help personalize cancer treatments, among other diseases. However, uptake of these technologies in clinical practice has been slow, and consistency in their implementation and interpretation remains a challenge

In our recent work, we developed a framework (MultiP) to build multi-platform precision pathways in an automated, unbiased way. The MultiP pathways mimic a clinical diagnostic pathway, where given the results of a diagnostic test, a confident decision may be made, or the patient may be referred to collect more data from a different platform. The data-driven construction of the pathways ensures a consistent implementation of evidence-based diagnostic decisions.

Furthermore, our framework provides a range of tools to interpret, visualize and compare the pathways, improving communication and enabling their evaluation on accuracy and cost, specific to different contexts. This framework will guide the development of novel diagnostic pathways for different diseases, accelerating the implementation of precision medicine into clinical practice.

Find out more in the paper, Construction and optimization of multi-platform precison pathways for precision medicine.

Spatial image highlighting the cell type and neuronal regions of cells segmented using BIDCell on mouse brain Xenium data

Schematic of the MultiP pipeline

Registrations now open!

Our annual winter data analysis challenge is on again from 22-24 July 2024. Open to all Australian undergraduate students to showcase their skills and creativity in analysis complex data. Prizes values at $500, $250 and $100. Visit the registration page for further details and to sign up.

News & updates

May 2024

Research Leader A/Prof Pengyi Yang was successful in an application for a USyd-NUS Partnership Collaboration Award with a project titled: Towards generating dopaminergic neuron containing stem cell-derived brain organoids.
Honours student Sanghyun (Sam) Kim was awarded the George Allen Scholarship in Data Science.
PhD Student Andy Tran received the Faculty of Science - Dean’s Award for Citizenship and Outreach. Andy’s received the award for his coordination and involvement in mathematical outreach activities for high school students.

April 2024

Research Leader Clara Grazian received the Rewarding Research Success grant from the University of Sydney for developing artificial intelligence tools to examine and visualise trends and factors associated with child undernutrition in Indonesia.
Our mid-year honours students gave their final presentations. Congratulations to all of them for reaching this exciting milestone!
PhD student Farhan Ameen won the BioC2024 Sticker Design Contest with a design inspired by the Grand Rapids city logo.

February 2024

Seven students completed the six-week long Science Summer Research Program by presenting their projects to the bioinformatics research group meeting.

January 2024

We are delighted to announce our PhD student Harry Robertson has been awarded a Fulbright Future Scholarship. Harry will be at Harvard University discovering contemporary biomarkers for organ transplant health through advanced imaging.
PhD student Farhan Ameen and his team finished 1st in Oceania and 2nd globally in the 2023 UN Datathon. They competed against 500+ teams from more than 100 countries around the world.
Our recent paper, "BIDCell: Biologically-informed self-supervised learning for segmentation of subcellular spatial transcriptomics data", has been selected in Nature Communications Editors' Highlights. The Editors’ Highlights pages aim to showcase the 50 best papers recently published in an area.

December 2023

Dr Garth Tarr was one of only two University academics in 2023 to receive the Vice Chancellor’s Award for Teaching and Learning Excellence. This recognises his contribution to an outstanding educational experience and outcomes for his students.
PhD student, Harry Robertson won both Best Pitch and People's Choice for Best Pitch at the 2023 Blackbird Foundry competition with his pitch for the startup, Graft AI. Harry led a team with Prof Natasha Rogers, Prof Jean Yang and Dr Ellis Patrick.
Dr Shila Ghazanfar received the ABACBS Outstanding Early Career Research Contribution Award and Hani Kim received the ABACBS Outstanding PhD Thesis Award.
PhD students Harry Robertson and Farhan Ameen both received awards at ABACBS. Harry was awarded "Best Student Oral Presentation" and Farhan won "Best Poster Award
Dr Ellis Patrick and Dr Dario Strbenac co-organised the 2023 BioC Asia Conference in Hong Kong held from October 16-17.
Three of our PhD students were successful in receiving travel grants at the COMBINE Symposium. Congratulation to Andy Tran, Lija Yu and Manoj Wagle.

Above images: Left - PhD students receive their travel grants at the COMBINE Symposiym. Middle - Harry Robertson at the US Embassy in Canberra to recieve his Fulbright Scholarship. Right - Summer students and SPDS supervisors.

Statistical Bioinformatics Seminar Series

Co-hosted with the Integrative Systems and Modelling Theme and Judith and David Coffey Life Lab in the Charles Perkins Centre. This series provides a forum for people working within the broad area of computation and statistics and their application to various aspects of biology to present their work and showcase their ongoing projects.
Held at 1pm every Monday during semester. Find out more on our events page.

ECR Update - Workshop highlights

ECR Committee member Daniel Kim shares highlights and reflections from the 2024 ECR developmental retreat held earlier this year.

This year's workshop focused on developing discipline-specific strategies for excelling as researchers amidst prevailing scientific trends, such as the use of large language models. The workshop commenced with twelve brief presentations from postdocs and senior HDR students, representing nine research leaders from the centre. The topics covered included Bayesian statistics, deep-learning models, and applications ranging from single-cell analytics to predicting graft survival for precision medicine, showcasing the diverse research interests within our centre. We also explored strategies for formulating research questions and staying ahead of the curve. The importance of understanding the broader context of one's research area to identify current gaps and limitations was particularly emphasised, which is crucial for developing relevant research questions. Additionally, there were presentations on how to become aware of and make the most of grants, fellowships, and conferences, which I found very insightful. One of the most memorable presentations was by Farhan, who shared his expertise in creating memorable figures and discussed the fundamentals of designing impacting visuals. A helpful tip was to empathise with your audience as the approaches and techniques you use will be both context and audience specific.

Although the presentations were informative, one of the most valuable aspects of these workshops was the chance to see our supervisors, colleagues, and friends in a new light. We noticed that some began their days with a quiet morning coffee, while others kicked off with a brisk 17 km run—a gentle reminder for me to exercise more. These workshops also foster a stronger sense of belonging through shared activities like cooking and cleaning together. While honing our technical skills and conducting research is essential for individual development, they highlight the equal importance of building connections and shared experiences that strengthen our community of data science enthusiasts.

Above images: Left - Go-karting as a pre-workshop social activiity. Middle - Group photo. Right - Data Scientists in the kitchen.

Keep in touch

Copyright © 2023 The University of Sydney, NSW 2006 Australia
Phone +61 2 9351 2222 ABN 15 211 513 464 CRICOS Number: 00026A

Please add university.communications@sydney.edu.au to your address book or senders safe list to make sure you continue to see our emails in the future.

Manage your preferences | Opt out from these emails
Got this as a forward? Sign up to receive our future emails.
View this email online.

Disclaimer | Privacy statement | University of Sydney