BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Dana-Farber Cancer Institute - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Dana-Farber Cancer Institute
X-ORIGINAL-URL:https://ds.dfci.harvard.edu
X-WR-CALDESC:Events for Dana-Farber Cancer Institute
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250303T160000
DTEND;TZID=America/New_York:20250303T170000
DTSTAMP:20260421T052158
CREATED:20250221T180945Z
LAST-MODIFIED:20250304T155554Z
UID:5888-1741017600-1741021200@ds.dfci.harvard.edu
SUMMARY:How Do Neural Networks Learn Features From Data?
DESCRIPTION:HSPH Biostatistics and DFCI Data Science Colloquium\nMonday March 3rd at 4:00pm\nHSPH Kresge G2 \nAdityanarayanan Radhakrishnan\nEric and Wendy Schmidt Center Postdoctoral Fellow\, Broad Institute of MIT and Harvard\, Harvard School of Engineering and Applied Sciences \nAbstract: Understanding how neural networks learn features\, or relevant patterns in data\, is key to accelerating scientific discovery. In this talk\, I will present a unifying mechanism that characterizes feature learning in neural network architectures. Namely\, features learned by neural networks are captured by a statistical operator known as the average gradient outer product (AGOP). More generally\, the AGOP enables feature learning in machine learning models that have no built-in feature learning mechanism (e.g.\, kernel methods). I will present two applications of this line of work. First\, I will show how AGOP can be used to steer LLMs and vision-language models\, guiding them towards specified concepts and shedding light on vulnerabilities in these models. I will then discuss how AGOP can be used to discover cellular programs (sets of genes whose expressions exhibit dependencies across cell subpopulations) from millions of sequenced cells. I will show how AGOP identified programs that reflect the heterogeneity found in various cell types\, subtypes\, and states in this data. Overall\, this line of work advances our fundamental understanding of how neural networks extract features from data\, leading to the development of novel\, interpretable\, and effective methods for use in scientific applications.
URL:https://ds.dfci.harvard.edu/event/how-do-neural-networks-learn-features-from-data/
LOCATION:Harvard TH Chan School of Public Health\, 677 Huntington Ave\, Boston\, MA\, 02115
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ds.dfci.harvard.edu/wp-content/uploads/2025/02/headshot-e1740161254828.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250306T160000
DTEND;TZID=America/New_York:20250306T170000
DTSTAMP:20260421T052158
CREATED:20250207T140313Z
LAST-MODIFIED:20250307T160147Z
UID:5819-1741276800-1741280400@ds.dfci.harvard.edu
SUMMARY:Universal Prediction of Cell-cycle Position Using Transfer Learning
DESCRIPTION:HSPH Biostatistics and DFCI Data Science Colloquium\nThursday\, March 6\, 2025\n4:00pm\nHarvard TH Chan School of Public Health\, FXB G13 \nKasper Hansen\, PhD\nAssociate Professor\, McKusick-Nathans Insitute of Genetic Medicine\, Department of Biostatistics\, Johns Hopkins University \nA significant barrier to progress in biomedical data science is the development of prediction models that work across contexts such as different instruments\, facilities or hospitals. This is particularly difficult for predictions based on genomics data. Here\, we present an example of a generalizable prediction model. \nThe cell cycle is a highly conserved\, continuous process which controls faithful replication and division of cells. Single-cell technologies have enabled increasingly precise measurements of the cell cycle both as a biological process of interest and as a possible confounding factor. Despite its importance and conservation\, there is no universally applicable approach to infer position in the cell cycle with high-resolution from single-cell RNA-seq data. \nHere\, we present tricycle\, an R/Bioconductor package\, which addresses this challenge by leveraging key features of the biology of the cell cycle\, the mathematical properties of principal component analysis of periodic functions\, and the use of transfer learning. We estimate a cell-cycle embedding using a fixed reference dataset and project new data into this reference embedding\, an approach that overcomes key limitations of learning a dataset-dependent embedding. Tricycle then predicts a cell-specific position in the cell cycle based on the data projection. The accuracy of tricycle compares favorably to gold-standard experimental assays\, which generally require specialized measurements in specifically constructed in vitro systems. Using internal controls which are available for any dataset\, we show that tricycle predictions generalize to datasets with multiple cell types\, across tissues\, species\, and even sequencing assays.
URL:https://ds.dfci.harvard.edu/event/universal-prediction-of-cell-cycle-position-using-transfer-learning/
LOCATION:Harvard TH Chan School of Public Health\, FXB G13\, 677 Huntington Ave\, Boston\, MA\, United States
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ds.dfci.harvard.edu/wp-content/uploads/2025/02/khansen.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250310T160000
DTEND;TZID=America/New_York:20250310T170000
DTSTAMP:20260421T052158
CREATED:20250226T134218Z
LAST-MODIFIED:20250311T161944Z
UID:5905-1741622400-1741626000@ds.dfci.harvard.edu
SUMMARY:Decoding Aging at Spatial and Single-cell Resolution with Machine Learning
DESCRIPTION:HSPH Biostatistics and DFCI Data Science Colloquium\nMonday March 10th at 4:00pm\nHSPH Kresge G2 \nEric Sun\nPhD Candidate\, Department of Biomedical Informatics\nStanford University \nAging is a highly complex process and the greatest risk factor for many chronic diseases including cardiovascular disease\, dementia\, stroke\, diabetes\, and cancer. Recent spatial and single-cell omics technologies have enabled the high-dimensional profiling of complex biology including that underlying aging. As such\, new machine learning and computational methods are needed to unlock important insights from spatial and single-cell omics datasets. First\, I present the development of high-resolution machine learning models (‘spatial aging clocks’) that can measure the aging of individual cells in the brain. Using these spatial aging clocks\, I discovered that some cell types can dramatically influence the aging of nearby cells. Next\, I present new computational and statistical methods for overcoming the gene coverage limitations of existing spatially resolved single-cell omics technologies\, which have enabled the discovery of gene pathways underlying the spatial effects of brain aging. \n 
URL:https://ds.dfci.harvard.edu/event/decoding-aging-at-spatial-and-single-cell-resolution-with-machine-learning/
LOCATION:Harvard TH Chan School of Public Health\, 677 Huntington Ave\, Boston\, MA\, 02115
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ds.dfci.harvard.edu/wp-content/uploads/2025/02/Eric_Sun-scaled-e1740577294700.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250311T160000
DTEND;TZID=America/New_York:20250311T170000
DTSTAMP:20260421T052158
CREATED:20250226T134543Z
LAST-MODIFIED:20250312T130019Z
UID:5910-1741708800-1741712400@ds.dfci.harvard.edu
SUMMARY:Dissecting Tumor Transcriptional Heterogeneity from Single-cell RNA-seq Data by Generalized Binary Covariance Decomposition
DESCRIPTION:HSPH Biostatistics and DFCI Data Science Colloquium\nTuesday March 11th at 4:00pm\nHSPH FXB G12 \nYusha Liu\, PhD\nResearch Assistant Professor\nDepartment of Biostatistics\nThe University of North Carolina at Chapel Hill \nProfiling tumors with single-cell RNA sequencing has the potential to identify recurrent patterns of transcription variation related to cancer progression\, and to produce therapeutically relevant insights. However\, strong inter-tumor heterogeneity can obscure more subtle patterns that are shared across tumors. In this talk\, I will introduce a novel statistical method\, generalized binary covariance decomposition (GBCD)\, to address this problem. GBCD can decompose transcriptional heterogeneity into interpretable components — including patient-specific\, dataset-specific and shared components relevant to disease subtypes — and that\, in the presence of strong inter-tumor heterogeneity\, it can produce more interpretable results than existing methods. Applied to data on pancreatic ductal adenocarcinoma\, GBCD produced a refined characterization of existing tumor subtypes\, and identified a gene expression program prognostic of poor survival independent of tumor stage and subtype. The gene expression program is enriched for genes involved in stress responses\, and suggests a role for the integrated stress response in pancreatic ductal adenocarcinoma.
URL:https://ds.dfci.harvard.edu/event/dissecting-tumor-transcriptional-heterogeneity-from-single-cell-rna-seq-data-by-generalized-binary-covariance-decomposition/
LOCATION:Harvard TH Chan School of Public Health\, 677 Huntington Ave\, Boston\, MA\, 02115
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/png:https://ds.dfci.harvard.edu/wp-content/uploads/2025/02/headshot-copy-e1740577495994.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250327T160000
DTEND;TZID=America/New_York:20250327T170000
DTSTAMP:20260421T052158
CREATED:20250314T163931Z
LAST-MODIFIED:20250328T121320Z
UID:5985-1743091200-1743094800@ds.dfci.harvard.edu
SUMMARY:Data Integration in Spatial and Single Cell Omics:  What is Erased\, and Can you Recover it?
DESCRIPTION:HSPH Biostatistics and DFCI Data Science Colloquium\nThursday\, March 27\, 2025\n4:00pm\nHarvard TH Chan School of Public Health\, FXB G13 \n\nNancy Zhang\, PhD\nGe Li and Ning Zhao Professor\, Professor of Statistics and Data Science\, Vice Dean of Wharton Doctoral Programs\,  The Wharton School\, University of Pennsylvania \nIn single-cell and spatial biology\, data integration refers to the alignment of cells across samples and modalities\, and is an ubiquitous challenge affecting all downstream analyses. The goal in cell integration is to find cells across data sets that share the same biological state that may be obscured by technical differences. \nIn this talk\, I will cast the cell integration problem on a continuum of weak to strong linkage\, depending on the strength of feature sharing between experiments. First\, I will examine integration across data modalities of weak linkage. This arises when there are few shared features between the data being integrated\, for example\, between single-cell RNA sequencing data and spatial proteomics data. For this\, I will present MaxFuse\, a method that leverages higher order relationships between all features\, including unshared features\, to achieve accurate integration. Next\, we consider the scenario of data alignment across the same modality in clinical scale studies. For this setting\, I will show that existing paradigms are overly aggressive\, erasing disease and treatment effects and introducing severe data distortion. I will introduce a “pool-of-controls” experimental design concept to disentangle biological variation from unwanted variation. Based on this\, I will describe CellANOVA\, a novel statistical model and scalable algorithm that recovers biological signals lost during batch integration and corrects integration related data distortion. Through these two contrasting paradigms\, I will share the key lessons learned and the remaining challenges in this field.
URL:https://ds.dfci.harvard.edu/event/data-integration-in-spatial-and-single-cell-omics-what-is-erased-and-can-you-recover-it/
LOCATION:Harvard TH Chan School of Public Health\, 677 Huntington Ave\, Boston\, MA\, 02115
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ds.dfci.harvard.edu/wp-content/uploads/2025/03/zhang-crop-e1741970356597.jpg
END:VEVENT
END:VCALENDAR