BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261020T133411
DTSTART;TZID=America/Detroit:20261028T160000
DTEND;TZID=America/Detroit:20261028T170000
SUMMARY:Workshop / Seminar:CCMB/DCMB Weekly Bioinformatics Seminar Series featuring Lindsey Muir\, PhD (Research Assistant Prof. of Computational Medicine & Bioinformatics)
DESCRIPTION:Development of cell reprogramming methods is hindered by low efficiency and the challenge of analyzing rare cells that have yet unknown phenotypes. While cells in a typical biosample can be identified using unbiased single-cell transcriptomics\, annotation itself relies on known gene expression signatures. Cells that begin to reprogram within a larger population remain indiscernible using this approach. Work in this area illuminates the unknowns related to our understanding of cell identity and heterogeneity. I will discuss our recent work\, including direct cell reprogramming to human hematopoietic stem cells\, future directions\, and key barriers to discovery in the field.
UID:153874-21916580@events.umich.edu
URL:https://events.umich.edu/event/153874
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Computational Science,Biosciences,biomedical research,Biomedical Engineering,Biology,Bioinformatics,Basic Science
LOCATION:Medical Science Unit I - 4B700
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260924T105845
DTSTART;TZID=America/Detroit:20261029T120000
DTEND;TZID=America/Detroit:20261029T130000
SUMMARY:Workshop / Seminar:DCMB Tools and Technology Seminar by Xiao-Su (Frank) Hu (MIDAS)
DESCRIPTION:- Tool Link:  https://auto.gluon.ai\n\n- MIDAS AI in Research Handbook:  https://midas-ai-in-research.readthedocs.io\n\nAbstract\n\nAutoGluon is an open-source AutoML framework that automates model training and selection across multiple data types\, including tabular data\, text\, and images. This talk provides a practical introduction to AutoGluon for researchers who want to incorporate machine learning into their workflows without extensive ML expertise. We will walk through hands-on examples across different data modalities and discuss common pitfalls and best practices for getting reliable results.
UID:152813-21914561@events.umich.edu
URL:https://events.umich.edu/event/152813
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Bioinformatics,Biosciences,Data Science,Machine Learning
LOCATION:Medical Science Unit I - 4B700
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20261001T102930
DTSTART;TZID=America/Detroit:20261112T120000
DTEND;TZID=America/Detroit:20261112T130000
SUMMARY:Workshop / Seminar:DCMB Tools and Technology Seminar by Sophia Luo (Biostatistics)
DESCRIPTION:Tool Link:  https://github.com/lutiffan/methylModes\n\nAbstract\nMethylModes is an R package and Shiny application to identify multimodal distributions in human DNA methylation at individual CpG sites. Multimodal distributions\, which can be the result of nearby genetic variation\, environmental exposures or assay artifacts\, are susceptible to confounding and important to identify for methylation analysis. We developed MethylModes to robustly identify multimodality in beta value distributions using an intuitive algorithm that avoids stringent modeling assumptions. MethylModes is easily incorporated into existing quality control pipelines of array-based DNA methylation data.
UID:153160-21915200@events.umich.edu
URL:https://events.umich.edu/event/153160
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Life Science,Basic Science,Bioinformatics,Biology,Biostatistics
LOCATION:Medical Science Unit I - 4B700
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20261001T103520
DTSTART;TZID=America/Detroit:20261119T120000
DTEND;TZID=America/Detroit:20261119T130000
SUMMARY:Workshop / Seminar:DCMB Tools and Technology Seminar by Junkang Wei (Computational Medicine & Bioinformatics)
DESCRIPTION:Join us for the DCMB Tools & Technology Seminar Series featuring a presentation by Junkang Wei from the Department of Computational Medicine & Bioinformatics. Enjoy a complimentary pizza lunch while learning about innovative research and cutting-edge tools.
UID:153161-21915201@events.umich.edu
URL:https://events.umich.edu/event/153161
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Basic Science,Bioinformatics
LOCATION:Medical Science Unit I - 4B700
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20261001T103923
DTSTART;TZID=America/Detroit:20261203T120000
DTEND;TZID=America/Detroit:20261203T130000
SUMMARY:Workshop / Seminar:DCMB Tools and Technology Seminar by Akhil Kondepudi (Computational Medicine & Bioinformatics)
DESCRIPTION:Join us for the DCMB Tools & Technology Seminar Series featuring a presentation by Akhil Kondepudi from the Department of Computational Medicine & Bioinformatics. Enjoy a complimentary pizza lunch while learning about innovative research and cutting-edge tools.\n\nAssociated Article:  https://www.nature.com/articles/s41591-026-04497-1\n\nAbstract\n\nFrontier artificial intelligence (AI) models have advanced rapidly through training on internet-scale public data\, yet such systems lack access to private clinical data. Neuroimaging is underrepresented in the public domain due to identifiable facial features within magnetic resonance imaging (MRI) and computed tomography (CT) scans\, restricting model performance in clinical medicine. Here we show that frontier models underperform on neuroimaging tasks and that learning directly from uncurated data generated during routine clinical care at health systems\, a paradigm we call ‘health system learning’\, yields high-performance\, generalist neuroimaging models. We introduce NeuroVFM\, a visual foundation model trained on 5.24 million clinical MRI and CT volumes using a scalable volumetric predictive architecture. NeuroVFM learns comprehensive representations of brain anatomy and pathology\, achieving state-of-the-art performance across multiple clinical tasks\, including radiologic diagnosis and report generation. The model embeds MRI and CT scans into a shared neuroanatomic latent space and grounds diagnostic findings. When paired with open-source language models\, NeuroVFM generates radiology reports that surpass frontier models in accuracy\, clinical triage and expert preference. NeuroVFM reduces hallucinated findings and critical errors\, offering safer clinical decision support. These results establish health system learning as a paradigm for building generalist medical AI and provide a scalable framework for clinical foundation models.
UID:153162-21915202@events.umich.edu
URL:https://events.umich.edu/event/153162
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Artificial Intelligence,Ai In Science And Engineering,Life Science,Basic Science,Bioinformatics,Neuroscience
LOCATION:Medical Science Unit I - 4B700
CONTACT:
END:VEVENT
END:VCALENDAR