Models, Inference & Algorithms (MIA)

The Models, Inference & Algorithms (MIA) Initiative at the Broad Institute supports learning and collaboration across the interface of biology and medicine with mathematics, statistics, machine learning, and computer science. Our weekly meeting features a primer, breakfast, seminar, and discussion; these are open and pedagogical, emphasizing lucid exposition of computational ideas over rapid-fire communication of results. Other MIA functions include hosting workshops, developing educational resources, advising leadership, and supporting the computational community.

 

Current co-chairs: Aleksandrina Goeva Salil Bhate (since Jan 2023) & Thouis Jones (since Jan 2022)

MIA's efforts are driven by the Steering Committee: Aleksandrina Goeva (Jan 2021 - Dec 2022) Alex Bloemendal (co-chair, Fall 2015 - Jan 2022), Elizabeth Wood, Emma Stickgold, Juan Caicedo, Lateisha Copeland-Guadarrama,  Marzieh HaghighiMehrtash BabadiMor NitzanRay Jones, and Sam Friedman, Wengong Jin, Salil Bhate, Orr Ashenberg, Eli Bingham, Matthew Amodio, David Fischer, Ashley Conard.

Jon Bloom and Alex Bloemendal founded MIA in the Fall of 2015. Jon Bloom served as a co-chair through July 2019. Past Steering Committee members: Allen GoodmanDebora MarksDavid BenjaminDylan KotliarGopal Sarma (co-chair, Jul 2019 - Jan 2021), James McFarland, Jon Bloom, Hilary FinucaneSam RiesenfeldYakir Reshef, Aviad Tsherniak, Max Shen, Brian Cleary, Mollie Morg, and Anika GuptaMartin Jankowiak, Arnav Mehta.


MIA Overview: Watch this introduction to the past, present, and future of MIA, and how you can help drive the fusion of machine learning and biomedicine. Check out the Kendall Square Codebreakers in the Harvard Crimson.


MIA Playlist: Watch and share our growing library of MIA videos.


Talking Machines: Listen to interviews with Eric LanderAviv Regev, and Nick Patterson.

Spring 2023 Schedule: 9 am Primer, 10 am Meeting, 10:50 am Discussion unless noted otherwise, in-person in Monadnock. Please refer to our MIAcast (weekly email announcement) for Zoom meeting information. Email lcopelan@broadinstitute.org with questions and mia-team@broadinstitute.org to be added to our mailing list.

MIA Talks Search

Date Speaker Title
Feb 1
  • Stanford University School of Medicine

Learning to read and write protein evolution
[Video]
Feb 8
Primer: Charting the Landscape of 3D Genome Organization with Graph Representation Learning
[Video]
Feb 8
  • Gene Regulation Observatory, Broad Institute; Society of Fellows, Harvard University
     

High-Throughput In Silico Genetic Screen for Discovering Novel 3D Genome Organization Regulation
[Video]
Feb 15
  • Bruno Correia

    Laboratory of Protein Design & Immunoengineering (LPDI), EPFL

Computational protein design
[Video]
Feb 15
  • Casper Goverde

    Laboratory of Protein Design & Immunoengineering (LPDI), EPFL

De novo design of proteins
[Video]
Mar 1
  • Haoran Zhang

    MIT

Primer: Group Fairness in Chest X-ray Diagnosis: Helpful or Harmful?
[Video]
Mar 1
Hiding in plain sight – What does AI’s ability to detect patterns not visible to radiologists mean?
[Video]
Mar 8
  • NNF Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Denmark

Variational autoencoders for analysis and integration of multi-omics and multi-modal data
[Video]
Mar 8
  • NNF Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Denmark

Deep dive into multi-omics variational autoencoding
[Video]
Mar 22
  • Massachusetts General Hospital, Harvard Medical School
    Associate Member
    Broad Institute of MIT and Harvard
     

Image2Omics: Generating Omics Data from Images
[Video]
Mar 22
  • Charles Comiter

    Massachusetts Institute of Technology
    Massachusetts General Hospital, Harvard Medical School
    Broad Institute of MIT and Harvard
     

Inference of single cell profiles from histology stains with the Single-Cell omics from Histology Analysis Framework (SCHAF)
[Video]
Apr 5
Intro to machine learning for molecules, small and large
Apr 12
Current techniques for case-control comparisons in high-throughput transcriptomics and the need for contrastive methods
Apr 12
  • University of North Carolina at Chapel Hill

Contrastive latent variable models to expose changes in case-control sequencing experiments
Apr 19 Generative AI for biomedicine
[Video]
Apr 19 How to evaluate medical AI
[Video]
Apr 26
  • Ben Deverman

    Broad Institute

ML-compatible experimental approaches to accelerate AAV engineering
Apr 26
  • Fatma Elzahraa Eid

    Broad Institute

Multi-trait protein engineering - a synergistic ML-wet lab approach to AAV engineering
May 10
A Fourier Tour of Protein Function Prediction
[Video]
May 10
Leveraging the Sparsity of Epistatic Interactions to Understand and Improve Models of Fitness Functions
[Video]