Past CCB Seminars

September 2023 Seminar

Speaker: Anthony-Alexander Christidis

Topic: A New Ensemble Learning Framework for Modeling High-Dimensional Data

When: Monday, September 11, 2023

Abstract: Ensemble methods have gained a lot of popularity in computational statistics and machine learning due to their flexibility and generally superior predictive performance compared to single-model methods. However, state-of-the-art ensemble methods rely on randomization and other forms of heuristics to generate diverse base learners, and are thus considered uninterpretable backbox algorithms. In this talk, we will introduce an entirely new framework for ensemble learning, free of randomization and heuristics. The models in these ensembles are learned by optimizing by a global objective function that generates diverse base learners while maintaining a degree of interpretability. Some aspects related to robustness will be discussed.

Recording: Click Here

June 2023 Seminars

Speaker: Jonathan Foster, PhD, Chief Technical Officer, Glue solutions Inc

Topic: Glue Genes: Exploratory Data Analysis for Single Cell and Spatial Omics

When: Monday, June 26, 2023

Recording: Click here

Abstract: Glue genes is a new open source tool bringing the power of the glue visualization library to analysis of single-cell and spatial omics data. The core features of glue genes are (1) flexible linking of diverse, multi-dimensional datasets, (2) automatic connections across multiple visualizations, and (3) easy extensibility and integration with other open source Python tools. I will talk about the philosophy and design of glue genes, and show examples of how it can be used to explore linked datasets in real time, showcasing the desktop application as well as the in-development “glupyter” project, which puts the power of glue inside Jupyter Lab. glue genes is developed in partnership with the Jackson Laboratory.

Software/Project Page

 

Speaker:  Graham Heimberg, PhD, Principal Scientist, Genentech

Topic: Scalable cell search of human cell atlases via deep learning reveals commonalities across disease associated macrophages

When: Monday, June 5, 2023

Recording: Click here

Single-cell RNA-seq (scRNA-seq) studies have profiled over 100 million human cells across diseases, developmental stages, and perturbations to date. A singular view of this vast and growing expression landscape could help reveal novel associations between cell states and diseases, discover cell states in unexpected tissue contexts, and relate in vivo cells to in vitro models. However, these require a common, scalable representation of expression profiles, a general measure of their similarity, and an efficient way to query these data. Here, we present SCimilarity, a metric learning framework to learn and search a unified and interpretable representation that annotates cell types and instantaneously queries for a cell state across tens of millions of profiles. We demonstrate SCimilarity on a 22.7 million cell corpus assembled across 399 published scRNA-seq studies, showing accurate integration, annotation and querying. We experimentally validated SCimilarity by querying across tissues for a macrophage subset originally identified in interstitial lung disease, and showing that cells with similar profiles are found in other fibrotic diseases, tissues, and a 3D hydrogel system, which we then leveraged to yield this cell state in vitro. SCimilarity enables researchers to query for similar cellular states across the entire human body, providing a powerful tool for generating novel biological insights from the growing Human Cell Atlas.

May 2023 Seminars

SPECIAL: The Center for Computational Biomedicine (CCB) hosted a joint seminar series with the Image Analysis Collaboratory (IAC) at Harvard Medical School with a focus on best practices and leading tools for quantitative analysis of biomedical images.

Speaker:  Talley Lambert, PhD, Associate Director of Imaging Technology @ Nikon Imaging Center, Harvard Medical School; Core Developer, Napari

Topic: Napari: A multi-dimensional data viewer for Python

When: Monday, May 1, 2023

Recording: Click here

With the advent of new multiplexed tissue imaging technologies, there is a growing need for efficient tools for browsing, annotating, and analyzing large multi-dimensional images. In this seminar, Talley will discuss Napari, an open source, interactive, multi-dimensional data viewer for Python.

Speakers: Hector Corrada Bravo, PhD; and Jayaram Kancherla

Topic: The SingleCellHub at Genentech: how to manage and query data from 130M cells

When: Monday, April 3, 3:00 – 4:00 PM Eastern Time (United States and Canada)

Recording: Click here

Speakers: Marinka Zitnik and Michelle M. Li

Topic: Foundational AI for Genomic Medicine and Therapeutic Design

When : Monday, May 22, 3:00 – 4:00 PM Eastern Time (United States and Canada)

Recording: Click here

April 2023 Seminars

Speaker:  Aaron lun, Scientist at Genentech

Topic: Code, sweat, and tears: how the OSCA sausage was made

When: Monday, April 3, 3:00 – 4:00 PM Eastern Time (United States and Canada)

Recording: Click here

Speaker: Matthew McDermott, Ph.D.

Topic: Generalizable and Performant Software for Producing Medical Record Foundation Models

When: Apr 17, 2023 09:50 AM Eastern Time (US and Canada)

Recording: Click here

March 2023 Seminars

Speaker: Isabella Grabski, PhD Candidate in Biostatistics, Department of Biostatistics, Harvard School of Public Health

 Topic: Probabilistic approaches to cell type annotation and clustering in single-cell RNA-seq data

Recording: Click here

Speaker: Sebastian Lobentanzer, Postdoc at the Institute for Computational Biomedicine, Heidelberg University Hospital

Topic: Democratising Knowledge Representation with BioCypher

Relevant links:  arXiv,  Biocypher

Recording: Click here

 

Speaker: Dr. Mine Çetinkaya-Rundel, Director of Undergraduate Studies, Professor of the Practice, Department of Statistical Science, Duke University

Topic: Hello, Quarto: A World of Possibilities (for Reproducible Publishing)

Recording: Click here

February 2023 Seminars

Speaker: Brett Beaulieu-Jones, PhD, Assistant Professor, University of Chicago

Topic:  “Limits of Machine Learning Models Tied to Clinical Intuition: Implications for AI-based Clinical Decision Support”

Relevant link: Click here

Recording: pending approval

Speaker:  Kun-Hsing Yu, MD, PhD, Assistant Professor, DBMI HMS

Topic: Artificial Intelligence-Enabled Cancer Pathology Evaluation

Recording: Not available

Speaker: Bethany Hedt-Gauthier, PhD, Associate Professor of Global Health and Social MedicineAssociate Professor in the Department of Biostatistics, Harvard T.H. Chan School of Public Health, HMS and Siona Prasad, Undergraduate Researcher at Harvard College Department of Computer Science

Topic: Image-based algorithms for remote surgical site infection diagnoses in rural Rwanda

Recording: Not available

January 2023 Seminars

Speaker: Katharina Imkeller, PhD, Group leader Computational Immunology, University Hospital Frankfurt, Germany

Topic: Unraveling Immunogenomic Diversity in Single-Cell Data

Recording: Not available

 

Speaker:  Trevor Manz, PhD Candidate & NSF Research Fellow, DBMI HMS

 Topic: Interactive, web-based visualization of high-resolution multiplexed bioimaging data

Abstract:  Although the rapid innovation of biological imaging brings significant scientific value, the proliferation of technologies without unification of interoperable standards has created challenges that limit the analysis and sharing of results. In this talk, I will discuss our work on 1.) community-driven design and adoption of open-standard next-generation file formats and 2.) the open-source Viv bioimaging visualization library which supports OME-TIFF and OME-NGFF directly in the web browser. Viv addresses a critical limitation of most web-based bioimaging viewers by removing a dependency on server-side rendering, offering a flexible toolkit for browsing multi-terabyte datasets on both mobile and desktop devices—without software installation.

Recording: Click here

December 2022 Seminars

Speaker: Nicolas Matentzoglu, PhD, Independent Contractor, Semantic Web and Knowledge Graphs expert

 Topic: Open SSSOM – Unlocking the wealth of biomedical data using shared standardized entity mappings

Recording: Click here

November 2022 Seminars

Speaker: Dr. Matthew Crowson, MD MPA MASc FRCSCAssistant Professor, Investigator, Department of Otolaryngology-Head & Neck Surgery, Massachusetts Eye & Ear

 Topic: Computer Vision for Irritable Toddlers: Improving Diagnostic Accuracy for Ear Infections

Recording: Not available

Speaker:  Faisal Mahmood, PhD, Assistant Professor, Pathology, Harvard Medical School

Affiliation: Division of Computational Pathology, Brigham and Women’s Hospital; Data Science Program, Dana-Farber/Harvard Cancer Center; Cancer Program, Broad Institute of Harvard and MIT

 Topic: Data-efficient and multimodal computational pathology

Abstract Advances in digital pathology and artificial intelligence have presented the potential to build assistive tools for objective diagnosis, prognosis and therapeutic-response and resistance prediction. In this talk we will discuss our work on: 1) Data-efficient methods for weakly-supervised whole slide classification with examples in cancer diagnosis and subtyping (Nature BME, 2021), and allograft rejection (Nature Medicine, 2022) 2) Harnessing weakly-supervised, fast and data-efficient WSI classification for identifying origins for cancers of unknown primary (Nature, 2021). 3) Discovering integrative histology-genomic prognostic markers via interpretable multimodal deep learning (IEEE TMI, 2020; ICCV, 2021; Cancer Cell, 2022). 4) Self-supervised deep learning for pathology and image retrieval (CVPR, 2022; Nature BME, 2022). 5) Deploying weakly supervised models in low resource settings without slide scanners, network connections, computational resources, and expensive microscopes. 6) Bias and fairness in computational pathology algorithms.

Relevant links: 
Lu et al. Nat BME, 2021 Data-efficient and weakly supervised computational pathology on whole-slide images

Ming et al. Nature, 2021 AI-based pathology predicts origins for cancers of unknown primary
Lipkova et al. Nature Medicine, 2022 Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies

Chen et al. Cancer Cell, 2022 Pan-cancer integrative histology-genomic analysis via multimodal deep learning

Recording: Not available

Speaker: Jeffrey Moffitt, PhD, Assistant Professor, Department of Microbiology, HMS

Topic: Building tissues atlases with MERFISH: The new opportunities and challenges of image-based single-cell transcriptomics

Recording: Not available

October 2022 Seminars

Speaker: Shila Ghazanfar, PhD, ARC Discovery Early Career Researcher, The University of Sydney, Faculty of Science, School of Mathematics and Statistics

Topic: StabMap: Mosaic single cell data integration using non-overlapping features

Recording: Click here

Speaker: Simon Norrelykke, Ph.D., Director of Image Analysis, Department of Systems Biology, HMS

Topic: Emerging Tools and Technologies in Bioimage Analysis and Processing

Recording: Not available

Speaker: Benjamin M. Gyori, Ph.D., Research Fellow, Director of Machine-assisted Modeling & Analysis, Laboratory of Systems Pharmacology, HMS

 Topic: Large-scale biomedical knowledge assembly for hypothesis generation and human-machine interaction

Recording: Not available

Speaker: Jeremy Manning, PhD, Assistant Professor of Psychological & Brain Sciences, Dartmouth College

 Topic: Geometric approaches to understanding the neural basis of human thought

Recording: Not available

September 2022 Seminars

Speaker: Antonios Lioutas, Ph.D., Research Associate in Genetics, Harvard Medical School

Topic: Super-resolution imaging of the human genome

Recording: Not available

Speaker(s): Laurent Gatto, PhD, Associate Professor of Bioinformatics, UCLouvain, Belgium and Charlotte Soneson, PhD, Research Associate, FMI, Switzerland

 Topic: The Bioconductor Education Committee and Its Initiatives

Related link: Bioconductor Education and Training

Recording: Not available

June 2022 Seminars

Speaker: Dan Triviglia, Director, DBMI IT Core, HMS

Title: Cloud Computing at HMS-DBMI

Recording: Click here

Speaker: Catia Pesquita, PhD,  Assistant Professor at LASIGE, Faculty of Sciences University of Lisbon and Vice President of BioData.pt

Title: Biomedical Semantic Similarity for Humans and Machines

Recording: Click here

Speaker: William “Gaby” Rodriguez, PhD, Computational Research Consultant & Amir Karger, PhD, Associate Director of Research Computing 

Title: The New Web Portal for HMS’ O2 Cluster: Simplifying the Experience of High Performance Computing with Open OnDemand

Recording: Click here

May 2022 Seminars

Speaker: Katy Börner, PhD, Victor H. Yngve Distinguished Professor of Intelligent Systems Engineering, Indiana University

Title: Human Reference Atlas Construction and Usage

Recording: Click here

Speaker: Robert Hoehndorf, PhD, King Abdullah University of Science and Technology

Title: Semantic Similarity and Machine Learning with Ontologies

Recording: Click here

Speaker: Jaclyn Mallard, PhD, CCB Center Administrator

Title: Filling in the Gaps: CCB’s Role in Quantitative Education at HMS

Recording: Click here

April 2022 Seminars

Speaker: Fabian Theis, PhD, Institute Director andResearch Group Leaderand Giovanni Palla, PhD Candidate at Helmholtz Munich

Title: Squidpy: A Scalable Framework for Spatial Omics Analysis

Recording: Click here

Speaker: Vincent Carey, PhD, Professor of Medicine at HMS and Associate Biostatistician at Channing Laboratory, Brigham And Women’s Hospital

Title: Open Computational eCosystems for Modern Genomics

Recording: Click here

Speaker: Artem Sokolov, PhD, HMS DBMI

Title: A Scalable, Modular Image-processing Pipeline for Multiplexed Tissue Imaging

Recording: Click here

Speaker: Constantin Ahlmann-Eltze, PhD student at the EMBL Heidelberg in the Huber group, European Molecular Biology Laboratory, Heidelberg, Germany

Title: Transformation and Preprocessing of Single-Cell RNA-Seq Data

Recording: Click here

March 2022 Seminars

Speaker: Nitesh Turaga, PhD, Scientist in the Department of Data Science, at the Dana Farber Cancer Institute of Harvard Medical School and a Core Team member at the Bioconductor Project, working at the intersection of Data Science, Computational biology, and Software Engineering

Title: Containerized and Parallel Computation in R/Bioconductor

Recording: N/A

Speaker: Paul Macklin, PhD, Associate Professor and Director of Undergraduate Studies in the Department of Intelligent Systems Engineering at Indiana University

Title: The Human Body at Cellular Resolution: the NIH Human Biomolecular Atlas Program

Recording: Click here

Speaker: Nils Eling, PhD, Postdoctoral Researcher at the Bodenmiller Laboratory at the University of Zurich

Title: Visualization and Analysis of Highly Multiplexed Imaging Data

Recording: Click here

 

February 2022 Seminars

Speaker: Sean Maden, Ph.D candidate in Computational Biology. Biomedical Engineering Dept (OHSU)

Title: Human Methylome Variation Across Infinium 450K Data on the Gene Expression Omnibus

Recording: N/A

 

Speaker: Marinka Zitnik, PhD, Assistant Professor of Biomedical Informatics, Harvard Medical School

Title: Leveraging the Cell Ontology to Classify Unseen Cell Types

Recording: Click here

 

Speaker: Levi Waldron, PhD, Associate Professor of Biostatistics at CUNY Graduate School of Public Health and Health Policy

Title: Curated Single Cell Multimodal Landmark Datasets for R/Bioconductor

Recording: Click Here

January 2022 Seminars

Speaker(s): Allon Klein, PhD, Assistant Professor of Systems Biology at HMS and Sahand Hormoz, PhD, Assistant Professor of Systems Biology at HMS

Title: Atlas of Human Population Variation in Bone Marrow Hematopoiesis

Recording: N/A

Date: January 31st, 2022

Speaker(s): Helena Crowell, PhD Candidate at University of Zurich and Dario Righelli, Assistant Researcher at Department of Statistics,University of Padua 

Title: Orchestrating Spatially Resolved Transcriptomics Analysis with Bioconductor

Recording:  Click here