BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Sydney Precision Data Science Centre - ECPv6.18.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://spds.sydney.edu.au
X-WR-CALDESC:Events for Sydney Precision Data Science Centre
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Australia/Sydney
BEGIN:STANDARD
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
DTSTART:20250405T160000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:20251004T160000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
DTSTART:20260404T160000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:20261003T160000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
DTSTART:20270403T160000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:20271002T160000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Australia/Sydney:20261012T130000
DTEND;TZID=Australia/Sydney:20261012T140000
DTSTAMP:20260930T003457Z
CREATED:20260914T032605Z
LAST-MODIFIED:20260930T003457Z
UID:5507-1791810000-1791813600@spds.sydney.edu.au
SUMMARY:Predicting Cellular Perturbations: Biological Benchmarks and AI-Assisted Model Discovery
DESCRIPTION:Statistical Bioinformatics SeminarSpeaker: Dr Yiqun Chen\, Johns Hopkins University \n\n\n\nThis is an online event held via Zoom: https://uni-sydney.zoom.us/j/85114748391 \n\n\n\n\n\n\n\n\n\nLarge-scale genetic perturbation screens have enabled researchers to probe gene function and regulatory networks\, but measuring changes in gene expression for every perturbation in a new cellular context remains experimentally costly\, if not infeasible. This limitation has motivated substantial interest in machine learning (ML) and artificial intelligence (AI) models that predict transcriptional responses to unmeasured perturbations and cellular contexts. \n\n\n\nIn this talk\, I will give an overview of a simplified framing of the problem and present some recent work addressing these questions through statistical modeling\, biological benchmarking\, and AI-assisted model development. We begin with a prediction benchmarking study that compares popular deep learning methods versus simplified statistical models built on top of pretrained embeddings (vectors summarizing biological information) for classifying whether perturbation–gene pairs lead to up\, down\, or no changes in differential expression (DE). We find that models with strong expression-level accuracy do not necessarily identify the genes that respond to a perturbation. In particular\, discrepancies between predicted and observed expression distributions can produce substantial disagreement in differential expression calls. \n\n\n\nI will also discuss our preliminary experiments using AI agents to develop perturbation-prediction methods. Some agent-developed models outperform established baselines on expression prediction\, and inspection of their analysis workflows reveals recurring uses of biological knowledge and statistical adjustments that are conceptually simple\, yet elaborate and informative. These results highlight opportunities for agents to help discover useful modeling strategies\, while raising questions about reproducibility\, evaluation\, and the translation and generalization of predictive gains to other related problems. Our work explores how biological knowledge\, statistical structure\, and increasingly automated model development can improve the prediction and interpretation of cellular perturbations. \n\n\n\n\n\n\nSubscribe to our seminar mailing list\n\n\n\n\n→\n\n\n\n\n\n\n\nFind out more about the Statistical Bioinformatics seminar series\n\n\n\n\n\n→\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nDr Yiqun Chen\n\n\n\nYiqun Chen (he/him) is an Assistant Professor of Biostatistics with a courtesy appointment in Computer Science at Johns Hopkins University. He was previously a data science postdoctoral fellow at Stanford and received his PhD from the University of Washington\, Seattle. His research focuses on statistical inference and evaluation frameworks for modern AI agents and biomedical data science practice\, with recent work exploring creative ways to leverage large language models for scientific data analysis and discovery.  \n\n\n\nConnect with Yiqun:X: @yc_yc_yc_yc
URL:https://spds.sydney.edu.au/event/powerful-and-accurate-case-control-analysis-of-spatial-molecular-data/
ATTACH;FMTTYPE=image/jpeg:https://spds.sydney.edu.au/wp-content/uploads/2025/01/Complex-systems-1-scaled.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Australia/Sydney:20261015T110000
DTEND;TZID=Australia/Sydney:20261015T120000
DTSTAMP:20260923T010945Z
CREATED:20260909T015737Z
LAST-MODIFIED:20260923T010945Z
UID:5483-1792062000-1792065600@spds.sydney.edu.au
SUMMARY:Charles Perkins Centre Data Science Hub - Introduction and Showcase
DESCRIPTION:This event is in-person only and requires registration. \n\n\n\n\n\n\n\nJoin us as we introduce the Charles Perkins Centre Data Science Hub and showcase our first projects.Discover how the Data Science Hub’s collaborative platform advances data-intensive research\, builds capacity and shares knowledge. The event will highlight key achievements from projects of varying scale and share our vision to support EMCRs and accelerate research translation.We invite you to meet our data scientists\, explore opportunities for collaboration\, and discover how to engage with us.  Refreshments will be provided. \n\n\n\nFor more information\, please visit this page.\n\n\n\n\n\n\n\nThe Data Science Hub is a collaborative partnership with the Charles Perkins Centre and Sydney Precision Data Science Centre\, co-funded by the Charles Perkins Centre’s Jennie Mackenzie Research Fund\, the Faculty of Medicine and Health and Faculty of Science.  The Data Science Hub advances data-intensive research with a direct translational impact in biomedical\, metabolomics health\, epidemiological research\, and beyond. We specialise in context-specific data analysis for high-throughput biomedical data generated by scientists.
URL:https://spds.sydney.edu.au/event/charles-perkins-centre-data-science-hub-introduction-and-showcase/
LOCATION:Jennie Mackenzie Room\, Level 6\, Charles Perkins Centre\, Johns Hopkins Drive\, University of Sydney\, Camperdown NSW 2006\, Sydney\, 2006\, Australia
ATTACH;FMTTYPE=image/jpeg:https://spds.sydney.edu.au/wp-content/uploads/2026/09/DASH-Event-banner_resized-scaled.jpg
END:VEVENT
END:VCALENDAR