BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Sydney Precision Data Science Centre - ECPv6.15.18//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:20240406T160000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:20241005T160000
END:DAYLIGHT
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Australia/Sydney:20250901T130000
DTEND;TZID=Australia/Sydney:20250901T140000
DTSTAMP:20260407T004403
CREATED:20250825T055007Z
LAST-MODIFIED:20250922T065653Z
UID:4142-1756731600-1756735200@spds.sydney.edu.au
SUMMARY:A Systematic Comparison of Single-Cell Perturbation Response Prediction Models
DESCRIPTION:Statistical Bioinformatics SeminarDr Yue You\, Guangzhou National Laboratory\n\n\n\nThis was an online event held via Zoom. \n\n\n\n\n\n\n\n\n\n\n\nPredicting single-cell transcriptional responses to perturbations is central to dissecting gene regulation and accelerating therapeutic design\, yet the field lacks a rigorous\, task-spanning assessment of model behavior. We present a large-scale benchmark of 12 representative methods and 3 baselines across 25 datasets spanning diverse perturbation modalities and species\, including two new primary immune-cell drug-response resources. We evaluated three core tasks—generalization to unseen single-gene perturbations\, prediction of combinatorial interactions\, and transfer across cell types—using 24 metrics covering expression-level accuracy\, relative changes\, differential expression recovery\, and distributional similarity. \n\n\n\nAcross tasks\, performance depended strongly on perturbation effect size and evaluation perspective: expression-level agreement was highest for small-effect perturbations resembling controls\, whereas delta- and DE-based metrics improved with larger effects\, providing clearer signals. Models shared a conservative bias\, with fine-tuned foundation models compressing variance and underestimating synergistic effects in combinations. PerturbNet showed superior recovery of DE signatures in Tasks 1 and 2\, while no method consistently generalized across cell types in Task 3\, where dataset heterogeneity dominated outcomes. \n\n\n\nThis benchmark establishes current methodological limits\, clarifies when metrics diverge\, and provides a foundation for developing virtual-cell models that more faithfully capture heterogeneous perturbation responses. \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 Yue You\n\n\n\nDr Yue You is a postdoctoral researcher at the Guangzhou National Laboratory. Her research centers on developing single-cell multi-omics algorithms and spatial-omics data analysis to decode cellular dynamics under genetic and pharmacological perturbations.
URL:https://spds.sydney.edu.au/event/a-systematic-comparison-of-single-cell-perturbation-response-prediction-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