BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Sydney Precision Data Science Centre - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Sydney Precision Data Science Centre
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:20260525T130000
DTEND;TZID=Australia/Sydney:20260525T140000
DTSTAMP:20260525T164652
CREATED:20260518T023913Z
LAST-MODIFIED:20260518T023915Z
UID:5129-1779714000-1779717600@spds.sydney.edu.au
SUMMARY:Generalized cell phenotyping for spatial proteomics with language-informed vision models
DESCRIPTION:Statistical Bioinformatics SeminarSpeaker: Xuefei (Julie) Wang\, California Institute of Technology \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\nWe present DeepCell Types\, a novel approach to cell phenotyping for spatial proteomics that addresses the challenge of generalization across diverse datasets with varying marker panels collected across different platforms. Our approach utilizes a transformer with channel-wise attention to create a language-informed vision model; this model’s semantic understanding of the underlying marker panel enables it to learn from and adapt to heterogeneous datasets. Leveraging a curated\, diverse dataset named Expanded TissueNet with cell type labels spanning the literature and the NIH Human BioMolecular Atlas Program (HuBMAP) consortium\, our model demonstrates robust performance across various cell types\, tissues\, and imaging modalities. Comprehensive benchmarking shows superior accuracy and generalizability of our method compared to existing methods. This work significantly advances automated spatial proteomics analysis\, offering a generalizable and scalable solution for cell phenotyping that meets the demands of multiplexed imaging data. \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\nXuefei (Julie) Wang\n\n\n\nXuefei (Julie) Wang is a PhD student at Caltech co-advised by David Van Valen and Yisong Yue. Her research focuses on the fundamental principles of foundation models and agentic systems\, with a particular emphasis on spatial proteomics and transcriptomics. Julie’s work addresses the challenges of large-scale biological data through innovative modeling\, including the development of language-informed vision models for generalized cell phenotyping. Her goal is to build knowledge-centric agents that accelerate discovery by compounding insights from foundation tools and literature into a persistent knowledge base that grows more capable with use. In addition to her work at Caltech\, she has contributed to scientific AI efforts as a Student Researcher at Google Research with Michael P. Brenner.Connect with Xuefei:LinkedIn: xuefei-wangX: xuefei_whttps://xuefei-wang.github.io/
URL:https://spds.sydney.edu.au/event/generalized-cell-phenotyping-for-spatial-proteomics-with-language-informed-vision-models/
ATTACH;FMTTYPE=image/jpeg:https://spds.sydney.edu.au/wp-content/uploads/2025/02/Complex-systems-1-edited-scaled.jpeg
END:VEVENT
END:VCALENDAR