top of page
Ginkgo Biloba brain as a herbal medicine
Screen Shot 2019-11-11 at 11.32.06 AM.pn

What: Virtual lecture series on topics across machine learning in medicine, featuring extensive Q & A and panel discussions

Why: To reduce academia’s carbon footprint, accommodate the schedules of the world’s top scientists and maintain social distancing

Who: All are welcome!

Where: Zoom Webinar

​

Recordings of previous talks can be found here

We are currently inviting speakers for Fall 2024! If you are interested or would like to nominate a speaker, please fill out this nomination form

9cb6c101-1ece-42c8-bb76-eafd96a10f48 (2).jpeg
David van Dijk, PhD, MSc 
​When: Friday, November 8th, 2024, 10am-11am EDT
​
Title: Learning the Language of Biology: Transforming Biomedical Discovery with Foundation Models and Causal Inference
​

AbstractIn this talk, I will showcase the work of my lab in revolutionizing biomedical data analysis through foundation models and large language models (LLMs). First, we introduce CINEMA-OT, a causal-inference-based approach using optimal transport for single-cell perturbation analysis. CINEMA-OT allows individual treatment-effect analysis, response clustering, and synergy analysis, revealing potential mechanisms in airway antiviral response and immune cell recruitment. Next, we present CaLMFlow, combining flow matching with integral equations and causal language models. By fine-tuning LLMs on flow matching and conditioning on natural language prompts, CaLMFlow predicts single-cell perturbation responses and performs protein backbone generation. We then explore "Cell2Sentence" (C2S), a technique translating single-cell transcriptomics into a language for LLMs. C2S automates the generation of natural language insights directly from biological data and generates cells based on textual prompts, enhancing data interpretation and synthesis. Additionally, I will discuss "BrainLM," the first fMRI foundation model to decode brain activity, predict clinical variables, and improve our understanding of brain function and disease. Finally, I will present some of our efforts to integrate foundation models with graphs with the aim to leverage pre-trained textual and non-textual foundation models for graph-based tasks.

​

Bio: Dr. David van Dijk is an Assistant Professor in the departments of Computer Science and Internal Medicine at Yale University, where he leads a research group focused on developing cutting-edge machine learning (ML) and artificial intelligence (AI) algorithms for large-scale biomedical datasets. His research interests span the application of foundation models, large language models (LLMs), graph representation learning, and neural operator learning to model spatiotemporal systems in biology and medicine. Dr. van Dijk completed his PhD in Computer Science at the University of Amsterdam and the Weizmann Institute of Science, where he utilized ML techniques to decipher the complex links between DNA sequence and gene activity. He then pursued postdoctoral fellow positions at Columbia University and Yale University, where he developed advanced manifold learning and machine learning algorithms specifically tailored for single-cell genomic data. Currently, Dr. van Dijk's research focuses on developing innovative algorithms to model and analyze a wide range of biomedical data, including single-cell RNA sequencing, electronic health records, medical imaging, and brain activity recordings. His lab is at the forefront of applying foundation models and LLMs to extract meaningful insights from these diverse and complex datasets. By leveraging the power of advanced AI techniques, Dr. van Dijk aims to uncover novel patterns, predict clinical outcomes, and drive groundbreaking discoveries in biomedical research. Dr. van Dijk's contributions to the field have been recognized by awards such as the Dutch Research Council Rubicon fellowship and the NIH R35 MIRA award.

Bratislav Misic, PhD 
​
When: Friday, November 22nd, 2024, 10am-11am EST
​
Title:  TBD
​

Abstract: TBD

​

Bio: TBD

image.png
Anant Madabhushi, PhD
​
When: Friday, December 6th, 2024, 10am-11am EST
​
Title:  Sequence-based deep learning models for understanding gene regulation and disease genetics
​

Abstract: 

Traditional biology generally looks at only a few aspects of an organism at a time and

attempts to molecularly dissect diseases and study them part by part with the hope that the sum of knowledge of parts would help explain the operation of the whole. Rarely has this been a successful strategy to understand the causes and cures for complex diseases. The motivation

for a systems based approach to disease understanding aims to understand how large numbers of interrelated health variables, gene expression profiling, its cellular architecture and

microenvironment, as seen in its histological image features, its 3 dimensional tissue

architecture and vascularization, as seen in dynamic contrast enhanced (DCE) MRI, and its

metabolic features, as seen by Magnetic Resonance Spectroscopy (MRS) or Positron Emission

Tomography (PET), result in emergence of definable phenotypes. Within our group has been

developing novel computerized knowledge alignment, representation, and fusion tools for

integrating and correlating heterogeneous biological data spanning different spatial and

temporal scales, modalities, and functionalities. These tools include computerized feature

analysis methods for extracting subvisual attributes for characterizing disease appearance and

behavior on radiographic (radiomics) and digitized pathology images (pathomics). In this talk I

will discuss the development work in our group on new radiomic and pathomic approaches for

capturing intra-tumoral heterogeneity and modeling tumor appearance. I will also focus my talk on how these radiomic and pathomic approaches can be applied to predicting disease outcome, recurrence, progression and response to therapy in the context of prostate, brain, rectal, oropharyngeal, and lung cancers. Additionally I will also discuss some recent work on looking at use of pathomics in the context of racial health disparity and creation of more precise and tailored prognostic and response prediction models.

​

Bio:

Dr. Anant Madabhushi is the Robert W Woodruff Professor of Biomedical Engineering; and on the faculty in the Departments of Pathology, Biomedical Informatics, and Radiology and Imaging Sciences at Emory University. He is also a Research Health Scientist at the Atlanta Veterans Administration Medical Center. Dr. Madabhushi has authored more than 475 peer-reviewed publications and more than 100 patents issued or pending. He is a, Fellow of the American Institute of Medical and Biological Engineering (AIMBE), and the Institute for Electrical and Electronic Engineers (IEEE) and the National Academy of Inventors (NAI). His work on "Smart Imaging Computers for Identifying lung cancer patients who need chemotherapy" was called out by Prevention Magazine as one of the top 10 medical breakthroughs of 2018. In 2019, Nature Magazine hailed him as one of 5 scientists developing "offbeat and innovative approaches for cancer research". Dr. Madabhushi was named to The Pathologist’s Power List in 2019, 2020, 2021 and 2022.

Derek Beaton, PhD 
​
When: Friday, December 13th, 2024, 10am-11am EST
​
Title:  TBD
​

Abstract: TBD

​

Bio: TBD

bottom of page